commit 43f3a0d0b435c5c9a67fa0393a87d6767598fd0a Author: Felix Zösch Date: Tue Dec 16 10:17:11 2025 +0100 Initial commit: Add Home Assistant skill - Add homeassistant.skill (packaged version) - Add skills/homeassistant source directory - Include scripts for API interaction and validation - Add comprehensive reference documentation - Include automation templates - Add README and .gitignore diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..7f5f2a3 --- /dev/null +++ b/.gitignore @@ -0,0 +1,17 @@ +# macOS +.DS_Store +.AppleDouble +.LSOverride + +# Python +__pycache__/ +*.py[cod] +*$py.class +*.so +.Python +env/ +venv/ +*.egg-info/ + +# Claude +.claude/ diff --git a/README.md b/README.md new file mode 100644 index 0000000..508a05e --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +# Claude Skills Collection + +This repository contains custom Claude Code skills for various use cases. + +## Available Skills + +### Home Assistant Skill + +**Location:** `homeassistant.skill` (packaged) or `skills/homeassistant/` (source) + +Comprehensive Home Assistant smart home automation toolkit that helps with: +- Creating and editing automations in YAML +- Controlling and querying devices via the Home Assistant API +- Writing and validating configuration files +- Troubleshooting automation and configuration issues +- Understanding Home Assistant concepts (triggers, conditions, actions) + +**Features:** +- Python scripts for API interaction +- YAML validation tools +- Pre-built automation templates +- Comprehensive reference documentation +- Troubleshooting guides + +## Installation + +### As Personal Skill (recommended) + +```bash +# Extract and install to personal skills directory +mkdir -p ~/.claude/skills/homeassistant +unzip homeassistant.skill -d ~/.claude/skills/ +mv ~/.claude/skills/homeassistant/homeassistant/* ~/.claude/skills/homeassistant/ +rmdir ~/.claude/skills/homeassistant/homeassistant +``` + +### As Project Skill + +```bash +# Extract and install to project skills directory +mkdir -p .claude/skills/homeassistant +unzip homeassistant.skill -d .claude/skills/ +mv .claude/skills/homeassistant/homeassistant/* .claude/skills/homeassistant/ +rmdir .claude/skills/homeassistant/homeassistant +``` + +## Skill Structure + +Skills in this repository include: +- `SKILL.md` - Main skill documentation with YAML frontmatter +- `scripts/` - Executable Python/Bash scripts +- `references/` - Detailed documentation loaded as needed +- `assets/` - Templates and resources for output + +## Usage + +Skills are automatically activated by Claude Code when relevant to your request. No manual invocation needed. + +## Contributing + +This is a personal skill collection. Feel free to fork and adapt for your own use. + +## License + +See individual skill directories for licensing information. diff --git a/homeassistant.skill b/homeassistant.skill new file mode 100644 index 0000000..7416706 Binary files /dev/null and b/homeassistant.skill differ diff --git a/skills/algorithmic-art/LICENSE.txt b/skills/algorithmic-art/LICENSE.txt new file mode 100644 index 0000000..7a4a3ea --- /dev/null +++ b/skills/algorithmic-art/LICENSE.txt @@ -0,0 +1,202 @@ + + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [yyyy] [name of copyright owner] + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. \ No newline at end of file diff --git a/skills/algorithmic-art/SKILL.md b/skills/algorithmic-art/SKILL.md new file mode 100644 index 0000000..634f6fa --- /dev/null +++ b/skills/algorithmic-art/SKILL.md @@ -0,0 +1,405 @@ +--- +name: algorithmic-art +description: Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations. +license: Complete terms in LICENSE.txt +--- + +Algorithmic philosophies are computational aesthetic movements that are then expressed through code. Output .md files (philosophy), .html files (interactive viewer), and .js files (generative algorithms). + +This happens in two steps: +1. Algorithmic Philosophy Creation (.md file) +2. Express by creating p5.js generative art (.html + .js files) + +First, undertake this task: + +## ALGORITHMIC PHILOSOPHY CREATION + +To begin, create an ALGORITHMIC PHILOSOPHY (not static images or templates) that will be interpreted through: +- Computational processes, emergent behavior, mathematical beauty +- Seeded randomness, noise fields, organic systems +- Particles, flows, fields, forces +- Parametric variation and controlled chaos + +### THE CRITICAL UNDERSTANDING +- What is received: Some subtle input or instructions by the user to take into account, but use as a foundation; it should not constrain creative freedom. +- What is created: An algorithmic philosophy/generative aesthetic movement. +- What happens next: The same version receives the philosophy and EXPRESSES IT IN CODE - creating p5.js sketches that are 90% algorithmic generation, 10% essential parameters. + +Consider this approach: +- Write a manifesto for a generative art movement +- The next phase involves writing the algorithm that brings it to life + +The philosophy must emphasize: Algorithmic expression. Emergent behavior. Computational beauty. Seeded variation. + +### HOW TO GENERATE AN ALGORITHMIC PHILOSOPHY + +**Name the movement** (1-2 words): "Organic Turbulence" / "Quantum Harmonics" / "Emergent Stillness" + +**Articulate the philosophy** (4-6 paragraphs - concise but complete): + +To capture the ALGORITHMIC essence, express how this philosophy manifests through: +- Computational processes and mathematical relationships? +- Noise functions and randomness patterns? +- Particle behaviors and field dynamics? +- Temporal evolution and system states? +- Parametric variation and emergent complexity? + +**CRITICAL GUIDELINES:** +- **Avoid redundancy**: Each algorithmic aspect should be mentioned once. Avoid repeating concepts about noise theory, particle dynamics, or mathematical principles unless adding new depth. +- **Emphasize craftsmanship REPEATEDLY**: The philosophy MUST stress multiple times that the final algorithm should appear as though it took countless hours to develop, was refined with care, and comes from someone at the absolute top of their field. This framing is essential - repeat phrases like "meticulously crafted algorithm," "the product of deep computational expertise," "painstaking optimization," "master-level implementation." +- **Leave creative space**: Be specific about the algorithmic direction, but concise enough that the next Claude has room to make interpretive implementation choices at an extremely high level of craftsmanship. + +The philosophy must guide the next version to express ideas ALGORITHMICALLY, not through static images. Beauty lives in the process, not the final frame. + +### PHILOSOPHY EXAMPLES + +**"Organic Turbulence"** +Philosophy: Chaos constrained by natural law, order emerging from disorder. +Algorithmic expression: Flow fields driven by layered Perlin noise. Thousands of particles following vector forces, their trails accumulating into organic density maps. Multiple noise octaves create turbulent regions and calm zones. Color emerges from velocity and density - fast particles burn bright, slow ones fade to shadow. The algorithm runs until equilibrium - a meticulously tuned balance where every parameter was refined through countless iterations by a master of computational aesthetics. + +**"Quantum Harmonics"** +Philosophy: Discrete entities exhibiting wave-like interference patterns. +Algorithmic expression: Particles initialized on a grid, each carrying a phase value that evolves through sine waves. When particles are near, their phases interfere - constructive interference creates bright nodes, destructive creates voids. Simple harmonic motion generates complex emergent mandalas. The result of painstaking frequency calibration where every ratio was carefully chosen to produce resonant beauty. + +**"Recursive Whispers"** +Philosophy: Self-similarity across scales, infinite depth in finite space. +Algorithmic expression: Branching structures that subdivide recursively. Each branch slightly randomized but constrained by golden ratios. L-systems or recursive subdivision generate tree-like forms that feel both mathematical and organic. Subtle noise perturbations break perfect symmetry. Line weights diminish with each recursion level. Every branching angle the product of deep mathematical exploration. + +**"Field Dynamics"** +Philosophy: Invisible forces made visible through their effects on matter. +Algorithmic expression: Vector fields constructed from mathematical functions or noise. Particles born at edges, flowing along field lines, dying when they reach equilibrium or boundaries. Multiple fields can attract, repel, or rotate particles. The visualization shows only the traces - ghost-like evidence of invisible forces. A computational dance meticulously choreographed through force balance. + +**"Stochastic Crystallization"** +Philosophy: Random processes crystallizing into ordered structures. +Algorithmic expression: Randomized circle packing or Voronoi tessellation. Start with random points, let them evolve through relaxation algorithms. Cells push apart until equilibrium. Color based on cell size, neighbor count, or distance from center. The organic tiling that emerges feels both random and inevitable. Every seed produces unique crystalline beauty - the mark of a master-level generative algorithm. + +*These are condensed examples. The actual algorithmic philosophy should be 4-6 substantial paragraphs.* + +### ESSENTIAL PRINCIPLES +- **ALGORITHMIC PHILOSOPHY**: Creating a computational worldview to be expressed through code +- **PROCESS OVER PRODUCT**: Always emphasize that beauty emerges from the algorithm's execution - each run is unique +- **PARAMETRIC EXPRESSION**: Ideas communicate through mathematical relationships, forces, behaviors - not static composition +- **ARTISTIC FREEDOM**: The next Claude interprets the philosophy algorithmically - provide creative implementation room +- **PURE GENERATIVE ART**: This is about making LIVING ALGORITHMS, not static images with randomness +- **EXPERT CRAFTSMANSHIP**: Repeatedly emphasize the final algorithm must feel meticulously crafted, refined through countless iterations, the product of deep expertise by someone at the absolute top of their field in computational aesthetics + +**The algorithmic philosophy should be 4-6 paragraphs long.** Fill it with poetic computational philosophy that brings together the intended vision. Avoid repeating the same points. Output this algorithmic philosophy as a .md file. + +--- + +## DEDUCING THE CONCEPTUAL SEED + +**CRITICAL STEP**: Before implementing the algorithm, identify the subtle conceptual thread from the original request. + +**THE ESSENTIAL PRINCIPLE**: +The concept is a **subtle, niche reference embedded within the algorithm itself** - not always literal, always sophisticated. Someone familiar with the subject should feel it intuitively, while others simply experience a masterful generative composition. The algorithmic philosophy provides the computational language. The deduced concept provides the soul - the quiet conceptual DNA woven invisibly into parameters, behaviors, and emergence patterns. + +This is **VERY IMPORTANT**: The reference must be so refined that it enhances the work's depth without announcing itself. Think like a jazz musician quoting another song through algorithmic harmony - only those who know will catch it, but everyone appreciates the generative beauty. + +--- + +## P5.JS IMPLEMENTATION + +With the philosophy AND conceptual framework established, express it through code. Pause to gather thoughts before proceeding. Use only the algorithmic philosophy created and the instructions below. + +### ⚠️ STEP 0: READ THE TEMPLATE FIRST ⚠️ + +**CRITICAL: BEFORE writing any HTML:** + +1. **Read** `templates/viewer.html` using the Read tool +2. **Study** the exact structure, styling, and Anthropic branding +3. **Use that file as the LITERAL STARTING POINT** - not just inspiration +4. **Keep all FIXED sections exactly as shown** (header, sidebar structure, Anthropic colors/fonts, seed controls, action buttons) +5. **Replace only the VARIABLE sections** marked in the file's comments (algorithm, parameters, UI controls for parameters) + +**Avoid:** +- ❌ Creating HTML from scratch +- ❌ Inventing custom styling or color schemes +- ❌ Using system fonts or dark themes +- ❌ Changing the sidebar structure + +**Follow these practices:** +- ✅ Copy the template's exact HTML structure +- ✅ Keep Anthropic branding (Poppins/Lora fonts, light colors, gradient backdrop) +- ✅ Maintain the sidebar layout (Seed → Parameters → Colors? → Actions) +- ✅ Replace only the p5.js algorithm and parameter controls + +The template is the foundation. Build on it, don't rebuild it. + +--- + +To create gallery-quality computational art that lives and breathes, use the algorithmic philosophy as the foundation. + +### TECHNICAL REQUIREMENTS + +**Seeded Randomness (Art Blocks Pattern)**: +```javascript +// ALWAYS use a seed for reproducibility +let seed = 12345; // or hash from user input +randomSeed(seed); +noiseSeed(seed); +``` + +**Parameter Structure - FOLLOW THE PHILOSOPHY**: + +To establish parameters that emerge naturally from the algorithmic philosophy, consider: "What qualities of this system can be adjusted?" + +```javascript +let params = { + seed: 12345, // Always include seed for reproducibility + // colors + // Add parameters that control YOUR algorithm: + // - Quantities (how many?) + // - Scales (how big? how fast?) + // - Probabilities (how likely?) + // - Ratios (what proportions?) + // - Angles (what direction?) + // - Thresholds (when does behavior change?) +}; +``` + +**To design effective parameters, focus on the properties the system needs to be tunable rather than thinking in terms of "pattern types".** + +**Core Algorithm - EXPRESS THE PHILOSOPHY**: + +**CRITICAL**: The algorithmic philosophy should dictate what to build. + +To express the philosophy through code, avoid thinking "which pattern should I use?" and instead think "how to express this philosophy through code?" + +If the philosophy is about **organic emergence**, consider using: +- Elements that accumulate or grow over time +- Random processes constrained by natural rules +- Feedback loops and interactions + +If the philosophy is about **mathematical beauty**, consider using: +- Geometric relationships and ratios +- Trigonometric functions and harmonics +- Precise calculations creating unexpected patterns + +If the philosophy is about **controlled chaos**, consider using: +- Random variation within strict boundaries +- Bifurcation and phase transitions +- Order emerging from disorder + +**The algorithm flows from the philosophy, not from a menu of options.** + +To guide the implementation, let the conceptual essence inform creative and original choices. Build something that expresses the vision for this particular request. + +**Canvas Setup**: Standard p5.js structure: +```javascript +function setup() { + createCanvas(1200, 1200); + // Initialize your system +} + +function draw() { + // Your generative algorithm + // Can be static (noLoop) or animated +} +``` + +### CRAFTSMANSHIP REQUIREMENTS + +**CRITICAL**: To achieve mastery, create algorithms that feel like they emerged through countless iterations by a master generative artist. Tune every parameter carefully. Ensure every pattern emerges with purpose. This is NOT random noise - this is CONTROLLED CHAOS refined through deep expertise. + +- **Balance**: Complexity without visual noise, order without rigidity +- **Color Harmony**: Thoughtful palettes, not random RGB values +- **Composition**: Even in randomness, maintain visual hierarchy and flow +- **Performance**: Smooth execution, optimized for real-time if animated +- **Reproducibility**: Same seed ALWAYS produces identical output + +### OUTPUT FORMAT + +Output: +1. **Algorithmic Philosophy** - As markdown or text explaining the generative aesthetic +2. **Single HTML Artifact** - Self-contained interactive generative art built from `templates/viewer.html` (see STEP 0 and next section) + +The HTML artifact contains everything: p5.js (from CDN), the algorithm, parameter controls, and UI - all in one file that works immediately in claude.ai artifacts or any browser. Start from the template file, not from scratch. + +--- + +## INTERACTIVE ARTIFACT CREATION + +**REMINDER: `templates/viewer.html` should have already been read (see STEP 0). Use that file as the starting point.** + +To allow exploration of the generative art, create a single, self-contained HTML artifact. Ensure this artifact works immediately in claude.ai or any browser - no setup required. Embed everything inline. + +### CRITICAL: WHAT'S FIXED VS VARIABLE + +The `templates/viewer.html` file is the foundation. It contains the exact structure and styling needed. + +**FIXED (always include exactly as shown):** +- Layout structure (header, sidebar, main canvas area) +- Anthropic branding (UI colors, fonts, gradients) +- Seed section in sidebar: + - Seed display + - Previous/Next buttons + - Random button + - Jump to seed input + Go button +- Actions section in sidebar: + - Regenerate button + - Reset button + +**VARIABLE (customize for each artwork):** +- The entire p5.js algorithm (setup/draw/classes) +- The parameters object (define what the art needs) +- The Parameters section in sidebar: + - Number of parameter controls + - Parameter names + - Min/max/step values for sliders + - Control types (sliders, inputs, etc.) +- Colors section (optional): + - Some art needs color pickers + - Some art might use fixed colors + - Some art might be monochrome (no color controls needed) + - Decide based on the art's needs + +**Every artwork should have unique parameters and algorithm!** The fixed parts provide consistent UX - everything else expresses the unique vision. + +### REQUIRED FEATURES + +**1. Parameter Controls** +- Sliders for numeric parameters (particle count, noise scale, speed, etc.) +- Color pickers for palette colors +- Real-time updates when parameters change +- Reset button to restore defaults + +**2. Seed Navigation** +- Display current seed number +- "Previous" and "Next" buttons to cycle through seeds +- "Random" button for random seed +- Input field to jump to specific seed +- Generate 100 variations when requested (seeds 1-100) + +**3. Single Artifact Structure** +```html + + + + + + + + +
+
+ +
+ + + +``` + +**CRITICAL**: This is a single artifact. No external files, no imports (except p5.js CDN). Everything inline. + +**4. Implementation Details - BUILD THE SIDEBAR** + +The sidebar structure: + +**1. Seed (FIXED)** - Always include exactly as shown: +- Seed display +- Prev/Next/Random/Jump buttons + +**2. Parameters (VARIABLE)** - Create controls for the art: +```html +
+ + + ... +
+``` +Add as many control-group divs as there are parameters. + +**3. Colors (OPTIONAL/VARIABLE)** - Include if the art needs adjustable colors: +- Add color pickers if users should control palette +- Skip this section if the art uses fixed colors +- Skip if the art is monochrome + +**4. Actions (FIXED)** - Always include exactly as shown: +- Regenerate button +- Reset button +- Download PNG button + +**Requirements**: +- Seed controls must work (prev/next/random/jump/display) +- All parameters must have UI controls +- Regenerate, Reset, Download buttons must work +- Keep Anthropic branding (UI styling, not art colors) + +### USING THE ARTIFACT + +The HTML artifact works immediately: +1. **In claude.ai**: Displayed as an interactive artifact - runs instantly +2. **As a file**: Save and open in any browser - no server needed +3. **Sharing**: Send the HTML file - it's completely self-contained + +--- + +## VARIATIONS & EXPLORATION + +The artifact includes seed navigation by default (prev/next/random buttons), allowing users to explore variations without creating multiple files. If the user wants specific variations highlighted: + +- Include seed presets (buttons for "Variation 1: Seed 42", "Variation 2: Seed 127", etc.) +- Add a "Gallery Mode" that shows thumbnails of multiple seeds side-by-side +- All within the same single artifact + +This is like creating a series of prints from the same plate - the algorithm is consistent, but each seed reveals different facets of its potential. The interactive nature means users discover their own favorites by exploring the seed space. + +--- + +## THE CREATIVE PROCESS + +**User request** → **Algorithmic philosophy** → **Implementation** + +Each request is unique. The process involves: + +1. **Interpret the user's intent** - What aesthetic is being sought? +2. **Create an algorithmic philosophy** (4-6 paragraphs) describing the computational approach +3. **Implement it in code** - Build the algorithm that expresses this philosophy +4. **Design appropriate parameters** - What should be tunable? +5. **Build matching UI controls** - Sliders/inputs for those parameters + +**The constants**: +- Anthropic branding (colors, fonts, layout) +- Seed navigation (always present) +- Self-contained HTML artifact + +**Everything else is variable**: +- The algorithm itself +- The parameters +- The UI controls +- The visual outcome + +To achieve the best results, trust creativity and let the philosophy guide the implementation. + +--- + +## RESOURCES + +This skill includes helpful templates and documentation: + +- **templates/viewer.html**: REQUIRED STARTING POINT for all HTML artifacts. + - This is the foundation - contains the exact structure and Anthropic branding + - **Keep unchanged**: Layout structure, sidebar organization, Anthropic colors/fonts, seed controls, action buttons + - **Replace**: The p5.js algorithm, parameter definitions, and UI controls in Parameters section + - The extensive comments in the file mark exactly what to keep vs replace + +- **templates/generator_template.js**: Reference for p5.js best practices and code structure principles. + - Shows how to organize parameters, use seeded randomness, structure classes + - NOT a pattern menu - use these principles to build unique algorithms + - Embed algorithms inline in the HTML artifact (don't create separate .js files) + +**Critical reminder**: +- The **template is the STARTING POINT**, not inspiration +- The **algorithm is where to create** something unique +- Don't copy the flow field example - build what the philosophy demands +- But DO keep the exact UI structure and Anthropic branding from the template \ No newline at end of file diff --git a/skills/algorithmic-art/templates/generator_template.js b/skills/algorithmic-art/templates/generator_template.js new file mode 100644 index 0000000..e263fbd --- /dev/null +++ b/skills/algorithmic-art/templates/generator_template.js @@ -0,0 +1,223 @@ +/** + * ═══════════════════════════════════════════════════════════════════════════ + * P5.JS GENERATIVE ART - BEST PRACTICES + * ═══════════════════════════════════════════════════════════════════════════ + * + * This file shows STRUCTURE and PRINCIPLES for p5.js generative art. + * It does NOT prescribe what art you should create. + * + * Your algorithmic philosophy should guide what you build. + * These are just best practices for how to structure your code. + * + * ═══════════════════════════════════════════════════════════════════════════ + */ + +// ============================================================================ +// 1. PARAMETER ORGANIZATION +// ============================================================================ +// Keep all tunable parameters in one object +// This makes it easy to: +// - Connect to UI controls +// - Reset to defaults +// - Serialize/save configurations + +let params = { + // Define parameters that match YOUR algorithm + // Examples (customize for your art): + // - Counts: how many elements (particles, circles, branches, etc.) + // - Scales: size, speed, spacing + // - Probabilities: likelihood of events + // - Angles: rotation, direction + // - Colors: palette arrays + + seed: 12345, + // define colorPalette as an array -- choose whatever colors you'd like ['#d97757', '#6a9bcc', '#788c5d', '#b0aea5'] + // Add YOUR parameters here based on your algorithm +}; + +// ============================================================================ +// 2. SEEDED RANDOMNESS (Critical for reproducibility) +// ============================================================================ +// ALWAYS use seeded random for Art Blocks-style reproducible output + +function initializeSeed(seed) { + randomSeed(seed); + noiseSeed(seed); + // Now all random() and noise() calls will be deterministic +} + +// ============================================================================ +// 3. P5.JS LIFECYCLE +// ============================================================================ + +function setup() { + createCanvas(800, 800); + + // Initialize seed first + initializeSeed(params.seed); + + // Set up your generative system + // This is where you initialize: + // - Arrays of objects + // - Grid structures + // - Initial positions + // - Starting states + + // For static art: call noLoop() at the end of setup + // For animated art: let draw() keep running +} + +function draw() { + // Option 1: Static generation (runs once, then stops) + // - Generate everything in setup() + // - Call noLoop() in setup() + // - draw() doesn't do much or can be empty + + // Option 2: Animated generation (continuous) + // - Update your system each frame + // - Common patterns: particle movement, growth, evolution + // - Can optionally call noLoop() after N frames + + // Option 3: User-triggered regeneration + // - Use noLoop() by default + // - Call redraw() when parameters change +} + +// ============================================================================ +// 4. CLASS STRUCTURE (When you need objects) +// ============================================================================ +// Use classes when your algorithm involves multiple entities +// Examples: particles, agents, cells, nodes, etc. + +class Entity { + constructor() { + // Initialize entity properties + // Use random() here - it will be seeded + } + + update() { + // Update entity state + // This might involve: + // - Physics calculations + // - Behavioral rules + // - Interactions with neighbors + } + + display() { + // Render the entity + // Keep rendering logic separate from update logic + } +} + +// ============================================================================ +// 5. PERFORMANCE CONSIDERATIONS +// ============================================================================ + +// For large numbers of elements: +// - Pre-calculate what you can +// - Use simple collision detection (spatial hashing if needed) +// - Limit expensive operations (sqrt, trig) when possible +// - Consider using p5 vectors efficiently + +// For smooth animation: +// - Aim for 60fps +// - Profile if things are slow +// - Consider reducing particle counts or simplifying calculations + +// ============================================================================ +// 6. UTILITY FUNCTIONS +// ============================================================================ + +// Color utilities +function hexToRgb(hex) { + const result = /^#?([a-f\d]{2})([a-f\d]{2})([a-f\d]{2})$/i.exec(hex); + return result ? { + r: parseInt(result[1], 16), + g: parseInt(result[2], 16), + b: parseInt(result[3], 16) + } : null; +} + +function colorFromPalette(index) { + return params.colorPalette[index % params.colorPalette.length]; +} + +// Mapping and easing +function mapRange(value, inMin, inMax, outMin, outMax) { + return outMin + (outMax - outMin) * ((value - inMin) / (inMax - inMin)); +} + +function easeInOutCubic(t) { + return t < 0.5 ? 4 * t * t * t : 1 - Math.pow(-2 * t + 2, 3) / 2; +} + +// Constrain to bounds +function wrapAround(value, max) { + if (value < 0) return max; + if (value > max) return 0; + return value; +} + +// ============================================================================ +// 7. PARAMETER UPDATES (Connect to UI) +// ============================================================================ + +function updateParameter(paramName, value) { + params[paramName] = value; + // Decide if you need to regenerate or just update + // Some params can update in real-time, others need full regeneration +} + +function regenerate() { + // Reinitialize your generative system + // Useful when parameters change significantly + initializeSeed(params.seed); + // Then regenerate your system +} + +// ============================================================================ +// 8. COMMON P5.JS PATTERNS +// ============================================================================ + +// Drawing with transparency for trails/fading +function fadeBackground(opacity) { + fill(250, 249, 245, opacity); // Anthropic light with alpha + noStroke(); + rect(0, 0, width, height); +} + +// Using noise for organic variation +function getNoiseValue(x, y, scale = 0.01) { + return noise(x * scale, y * scale); +} + +// Creating vectors from angles +function vectorFromAngle(angle, magnitude = 1) { + return createVector(cos(angle), sin(angle)).mult(magnitude); +} + +// ============================================================================ +// 9. EXPORT FUNCTIONS +// ============================================================================ + +function exportImage() { + saveCanvas('generative-art-' + params.seed, 'png'); +} + +// ============================================================================ +// REMEMBER +// ============================================================================ +// +// These are TOOLS and PRINCIPLES, not a recipe. +// Your algorithmic philosophy should guide WHAT you create. +// This structure helps you create it WELL. +// +// Focus on: +// - Clean, readable code +// - Parameterized for exploration +// - Seeded for reproducibility +// - Performant execution +// +// The art itself is entirely up to you! +// +// ============================================================================ \ No newline at end of file diff --git a/skills/algorithmic-art/templates/viewer.html b/skills/algorithmic-art/templates/viewer.html new file mode 100644 index 0000000..630cc1f --- /dev/null +++ b/skills/algorithmic-art/templates/viewer.html @@ -0,0 +1,599 @@ + + + + + + + Generative Art Viewer + + + + + + + +
+ +
+ +

TITLE - EDIT

+
SUBHEADER - EDIT
+ + +
+

Seed

+ +
+ + +
+ +
+ + +
+

Parameters

+ + +
+ +
+ + 5000 +
+
+ + +
+ +
+ + 0.5 +
+
+ + +
+ +
+ + 0.005 +
+
+ + +
+ +
+ + 8 +
+
+
+ + +
+

Colors

+ + +
+ +
+ + #d97757 +
+
+ + +
+ +
+ + #6a9bcc +
+
+ + +
+ +
+ + #788c5d +
+
+
+ + +
+

Actions

+
+ +
+
+
+ + +
+
+
Initializing generative art...
+
+
+
+ + + + \ No newline at end of file diff --git a/skills/brand-guidelines/LICENSE.txt b/skills/brand-guidelines/LICENSE.txt new file mode 100644 index 0000000..7a4a3ea --- /dev/null +++ b/skills/brand-guidelines/LICENSE.txt @@ -0,0 +1,202 @@ + + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [yyyy] [name of copyright owner] + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. \ No newline at end of file diff --git a/skills/brand-guidelines/SKILL.md b/skills/brand-guidelines/SKILL.md new file mode 100644 index 0000000..47c72c6 --- /dev/null +++ b/skills/brand-guidelines/SKILL.md @@ -0,0 +1,73 @@ +--- +name: brand-guidelines +description: Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. +license: Complete terms in LICENSE.txt +--- + +# Anthropic Brand Styling + +## Overview + +To access Anthropic's official brand identity and style resources, use this skill. + +**Keywords**: branding, corporate identity, visual identity, post-processing, styling, brand colors, typography, Anthropic brand, visual formatting, visual design + +## Brand Guidelines + +### Colors + +**Main Colors:** + +- Dark: `#141413` - Primary text and dark backgrounds +- Light: `#faf9f5` - Light backgrounds and text on dark +- Mid Gray: `#b0aea5` - Secondary elements +- Light Gray: `#e8e6dc` - Subtle backgrounds + +**Accent Colors:** + +- Orange: `#d97757` - Primary accent +- Blue: `#6a9bcc` - Secondary accent +- Green: `#788c5d` - Tertiary accent + +### Typography + +- **Headings**: Poppins (with Arial fallback) +- **Body Text**: Lora (with Georgia fallback) +- **Note**: Fonts should be pre-installed in your environment for best results + +## Features + +### Smart Font Application + +- Applies Poppins font to headings (24pt and larger) +- Applies Lora font to body text +- Automatically falls back to Arial/Georgia if custom fonts unavailable +- Preserves readability across all systems + +### Text Styling + +- Headings (24pt+): Poppins font +- Body text: Lora font +- Smart color selection based on background +- Preserves text hierarchy and formatting + +### Shape and Accent Colors + +- Non-text shapes use accent colors +- Cycles through orange, blue, and green accents +- Maintains visual interest while staying on-brand + +## Technical Details + +### Font Management + +- Uses system-installed Poppins and Lora fonts when available +- Provides automatic fallback to Arial (headings) and Georgia (body) +- No font installation required - works with existing system fonts +- For best results, pre-install Poppins and Lora fonts in your environment + +### Color Application + +- Uses RGB color values for precise brand matching +- Applied via python-pptx's RGBColor class +- Maintains color fidelity across different systems diff --git a/skills/canvas-design/LICENSE.txt b/skills/canvas-design/LICENSE.txt new file mode 100644 index 0000000..7a4a3ea --- /dev/null +++ b/skills/canvas-design/LICENSE.txt @@ -0,0 +1,202 @@ + + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [yyyy] [name of copyright owner] + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. \ No newline at end of file diff --git a/skills/canvas-design/SKILL.md b/skills/canvas-design/SKILL.md new file mode 100644 index 0000000..9f63fee --- /dev/null +++ b/skills/canvas-design/SKILL.md @@ -0,0 +1,130 @@ +--- +name: canvas-design +description: Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations. +license: Complete terms in LICENSE.txt +--- + +These are instructions for creating design philosophies - aesthetic movements that are then EXPRESSED VISUALLY. Output only .md files, .pdf files, and .png files. + +Complete this in two steps: +1. Design Philosophy Creation (.md file) +2. Express by creating it on a canvas (.pdf file or .png file) + +First, undertake this task: + +## DESIGN PHILOSOPHY CREATION + +To begin, create a VISUAL PHILOSOPHY (not layouts or templates) that will be interpreted through: +- Form, space, color, composition +- Images, graphics, shapes, patterns +- Minimal text as visual accent + +### THE CRITICAL UNDERSTANDING +- What is received: Some subtle input or instructions by the user that should be taken into account, but used as a foundation; it should not constrain creative freedom. +- What is created: A design philosophy/aesthetic movement. +- What happens next: Then, the same version receives the philosophy and EXPRESSES IT VISUALLY - creating artifacts that are 90% visual design, 10% essential text. + +Consider this approach: +- Write a manifesto for an art movement +- The next phase involves making the artwork + +The philosophy must emphasize: Visual expression. Spatial communication. Artistic interpretation. Minimal words. + +### HOW TO GENERATE A VISUAL PHILOSOPHY + +**Name the movement** (1-2 words): "Brutalist Joy" / "Chromatic Silence" / "Metabolist Dreams" + +**Articulate the philosophy** (4-6 paragraphs - concise but complete): + +To capture the VISUAL essence, express how the philosophy manifests through: +- Space and form +- Color and material +- Scale and rhythm +- Composition and balance +- Visual hierarchy + +**CRITICAL GUIDELINES:** +- **Avoid redundancy**: Each design aspect should be mentioned once. Avoid repeating points about color theory, spatial relationships, or typographic principles unless adding new depth. +- **Emphasize craftsmanship REPEATEDLY**: The philosophy MUST stress multiple times that the final work should appear as though it took countless hours to create, was labored over with care, and comes from someone at the absolute top of their field. This framing is essential - repeat phrases like "meticulously crafted," "the product of deep expertise," "painstaking attention," "master-level execution." +- **Leave creative space**: Remain specific about the aesthetic direction, but concise enough that the next Claude has room to make interpretive choices also at a extremely high level of craftmanship. + +The philosophy must guide the next version to express ideas VISUALLY, not through text. Information lives in design, not paragraphs. + +### PHILOSOPHY EXAMPLES + +**"Concrete Poetry"** +Philosophy: Communication through monumental form and bold geometry. +Visual expression: Massive color blocks, sculptural typography (huge single words, tiny labels), Brutalist spatial divisions, Polish poster energy meets Le Corbusier. Ideas expressed through visual weight and spatial tension, not explanation. Text as rare, powerful gesture - never paragraphs, only essential words integrated into the visual architecture. Every element placed with the precision of a master craftsman. + +**"Chromatic Language"** +Philosophy: Color as the primary information system. +Visual expression: Geometric precision where color zones create meaning. Typography minimal - small sans-serif labels letting chromatic fields communicate. Think Josef Albers' interaction meets data visualization. Information encoded spatially and chromatically. Words only to anchor what color already shows. The result of painstaking chromatic calibration. + +**"Analog Meditation"** +Philosophy: Quiet visual contemplation through texture and breathing room. +Visual expression: Paper grain, ink bleeds, vast negative space. Photography and illustration dominate. Typography whispered (small, restrained, serving the visual). Japanese photobook aesthetic. Images breathe across pages. Text appears sparingly - short phrases, never explanatory blocks. Each composition balanced with the care of a meditation practice. + +**"Organic Systems"** +Philosophy: Natural clustering and modular growth patterns. +Visual expression: Rounded forms, organic arrangements, color from nature through architecture. Information shown through visual diagrams, spatial relationships, iconography. Text only for key labels floating in space. The composition tells the story through expert spatial orchestration. + +**"Geometric Silence"** +Philosophy: Pure order and restraint. +Visual expression: Grid-based precision, bold photography or stark graphics, dramatic negative space. Typography precise but minimal - small essential text, large quiet zones. Swiss formalism meets Brutalist material honesty. Structure communicates, not words. Every alignment the work of countless refinements. + +*These are condensed examples. The actual design philosophy should be 4-6 substantial paragraphs.* + +### ESSENTIAL PRINCIPLES +- **VISUAL PHILOSOPHY**: Create an aesthetic worldview to be expressed through design +- **MINIMAL TEXT**: Always emphasize that text is sparse, essential-only, integrated as visual element - never lengthy +- **SPATIAL EXPRESSION**: Ideas communicate through space, form, color, composition - not paragraphs +- **ARTISTIC FREEDOM**: The next Claude interprets the philosophy visually - provide creative room +- **PURE DESIGN**: This is about making ART OBJECTS, not documents with decoration +- **EXPERT CRAFTSMANSHIP**: Repeatedly emphasize the final work must look meticulously crafted, labored over with care, the product of countless hours by someone at the top of their field + +**The design philosophy should be 4-6 paragraphs long.** Fill it with poetic design philosophy that brings together the core vision. Avoid repeating the same points. Keep the design philosophy generic without mentioning the intention of the art, as if it can be used wherever. Output the design philosophy as a .md file. + +--- + +## DEDUCING THE SUBTLE REFERENCE + +**CRITICAL STEP**: Before creating the canvas, identify the subtle conceptual thread from the original request. + +**THE ESSENTIAL PRINCIPLE**: +The topic is a **subtle, niche reference embedded within the art itself** - not always literal, always sophisticated. Someone familiar with the subject should feel it intuitively, while others simply experience a masterful abstract composition. The design philosophy provides the aesthetic language. The deduced topic provides the soul - the quiet conceptual DNA woven invisibly into form, color, and composition. + +This is **VERY IMPORTANT**: The reference must be refined so it enhances the work's depth without announcing itself. Think like a jazz musician quoting another song - only those who know will catch it, but everyone appreciates the music. + +--- + +## CANVAS CREATION + +With both the philosophy and the conceptual framework established, express it on a canvas. Take a moment to gather thoughts and clear the mind. Use the design philosophy created and the instructions below to craft a masterpiece, embodying all aspects of the philosophy with expert craftsmanship. + +**IMPORTANT**: For any type of content, even if the user requests something for a movie/game/book, the approach should still be sophisticated. Never lose sight of the idea that this should be art, not something that's cartoony or amateur. + +To create museum or magazine quality work, use the design philosophy as the foundation. Create one single page, highly visual, design-forward PDF or PNG output (unless asked for more pages). Generally use repeating patterns and perfect shapes. Treat the abstract philosophical design as if it were a scientific bible, borrowing the visual language of systematic observation—dense accumulation of marks, repeated elements, or layered patterns that build meaning through patient repetition and reward sustained viewing. Add sparse, clinical typography and systematic reference markers that suggest this could be a diagram from an imaginary discipline, treating the invisible subject with the same reverence typically reserved for documenting observable phenomena. Anchor the piece with simple phrase(s) or details positioned subtly, using a limited color palette that feels intentional and cohesive. Embrace the paradox of using analytical visual language to express ideas about human experience: the result should feel like an artifact that proves something ephemeral can be studied, mapped, and understood through careful attention. This is true art. + +**Text as a contextual element**: Text is always minimal and visual-first, but let context guide whether that means whisper-quiet labels or bold typographic gestures. A punk venue poster might have larger, more aggressive type than a minimalist ceramics studio identity. Most of the time, font should be thin. All use of fonts must be design-forward and prioritize visual communication. Regardless of text scale, nothing falls off the page and nothing overlaps. Every element must be contained within the canvas boundaries with proper margins. Check carefully that all text, graphics, and visual elements have breathing room and clear separation. This is non-negotiable for professional execution. **IMPORTANT: Use different fonts if writing text. Search the `./canvas-fonts` directory. Regardless of approach, sophistication is non-negotiable.** + +Download and use whatever fonts are needed to make this a reality. Get creative by making the typography actually part of the art itself -- if the art is abstract, bring the font onto the canvas, not typeset digitally. + +To push boundaries, follow design instinct/intuition while using the philosophy as a guiding principle. Embrace ultimate design freedom and choice. Push aesthetics and design to the frontier. + +**CRITICAL**: To achieve human-crafted quality (not AI-generated), create work that looks like it took countless hours. Make it appear as though someone at the absolute top of their field labored over every detail with painstaking care. Ensure the composition, spacing, color choices, typography - everything screams expert-level craftsmanship. Double-check that nothing overlaps, formatting is flawless, every detail perfect. Create something that could be shown to people to prove expertise and rank as undeniably impressive. + +Output the final result as a single, downloadable .pdf or .png file, alongside the design philosophy used as a .md file. + +--- + +## FINAL STEP + +**IMPORTANT**: The user ALREADY said "It isn't perfect enough. It must be pristine, a masterpiece if craftsmanship, as if it were about to be displayed in a museum." + +**CRITICAL**: To refine the work, avoid adding more graphics; instead refine what has been created and make it extremely crisp, respecting the design philosophy and the principles of minimalism entirely. Rather than adding a fun filter or refactoring a font, consider how to make the existing composition more cohesive with the art. If the instinct is to call a new function or draw a new shape, STOP and instead ask: "How can I make what's already here more of a piece of art?" + +Take a second pass. Go back to the code and refine/polish further to make this a philosophically designed masterpiece. + +## MULTI-PAGE OPTION + +To create additional pages when requested, create more creative pages along the same lines as the design philosophy but distinctly different as well. Bundle those pages in the same .pdf or many .pngs. Treat the first page as just a single page in a whole coffee table book waiting to be filled. Make the next pages unique twists and memories of the original. Have them almost tell a story in a very tasteful way. Exercise full creative freedom. \ No newline at end of file diff --git a/skills/canvas-design/canvas-fonts/ArsenalSC-OFL.txt b/skills/canvas-design/canvas-fonts/ArsenalSC-OFL.txt new file mode 100644 index 0000000..1dad6ca --- /dev/null +++ b/skills/canvas-design/canvas-fonts/ArsenalSC-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2012 The Arsenal Project Authors (andrij.design@gmail.com) + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/ArsenalSC-Regular.ttf b/skills/canvas-design/canvas-fonts/ArsenalSC-Regular.ttf new file mode 100644 index 0000000..fe5409b Binary files /dev/null and b/skills/canvas-design/canvas-fonts/ArsenalSC-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/BigShoulders-Bold.ttf b/skills/canvas-design/canvas-fonts/BigShoulders-Bold.ttf new file mode 100644 index 0000000..fc5f8fd Binary files /dev/null and b/skills/canvas-design/canvas-fonts/BigShoulders-Bold.ttf differ diff --git a/skills/canvas-design/canvas-fonts/BigShoulders-OFL.txt b/skills/canvas-design/canvas-fonts/BigShoulders-OFL.txt new file mode 100644 index 0000000..b220280 --- /dev/null +++ b/skills/canvas-design/canvas-fonts/BigShoulders-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2019 The Big Shoulders Project Authors (https://github.com/xotypeco/big_shoulders) + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/BigShoulders-Regular.ttf b/skills/canvas-design/canvas-fonts/BigShoulders-Regular.ttf new file mode 100644 index 0000000..de8308c Binary files /dev/null and b/skills/canvas-design/canvas-fonts/BigShoulders-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/Boldonse-OFL.txt b/skills/canvas-design/canvas-fonts/Boldonse-OFL.txt new file mode 100644 index 0000000..1890cb1 --- /dev/null +++ b/skills/canvas-design/canvas-fonts/Boldonse-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2024 The Boldonse Project Authors (https://github.com/googlefonts/boldonse) + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/Boldonse-Regular.ttf b/skills/canvas-design/canvas-fonts/Boldonse-Regular.ttf new file mode 100644 index 0000000..43fa30a Binary files /dev/null and b/skills/canvas-design/canvas-fonts/Boldonse-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/BricolageGrotesque-Bold.ttf b/skills/canvas-design/canvas-fonts/BricolageGrotesque-Bold.ttf new file mode 100644 index 0000000..f3b1ded Binary files /dev/null and b/skills/canvas-design/canvas-fonts/BricolageGrotesque-Bold.ttf differ diff --git a/skills/canvas-design/canvas-fonts/BricolageGrotesque-OFL.txt b/skills/canvas-design/canvas-fonts/BricolageGrotesque-OFL.txt new file mode 100644 index 0000000..fc2b216 --- /dev/null +++ b/skills/canvas-design/canvas-fonts/BricolageGrotesque-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2022 The Bricolage Grotesque Project Authors (https://github.com/ateliertriay/bricolage) + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/BricolageGrotesque-Regular.ttf b/skills/canvas-design/canvas-fonts/BricolageGrotesque-Regular.ttf new file mode 100644 index 0000000..0674ae3 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/BricolageGrotesque-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/CrimsonPro-Bold.ttf b/skills/canvas-design/canvas-fonts/CrimsonPro-Bold.ttf new file mode 100644 index 0000000..58730fb Binary files /dev/null and b/skills/canvas-design/canvas-fonts/CrimsonPro-Bold.ttf differ diff --git a/skills/canvas-design/canvas-fonts/CrimsonPro-Italic.ttf b/skills/canvas-design/canvas-fonts/CrimsonPro-Italic.ttf new file mode 100644 index 0000000..786a1bd Binary files /dev/null and b/skills/canvas-design/canvas-fonts/CrimsonPro-Italic.ttf differ diff --git a/skills/canvas-design/canvas-fonts/CrimsonPro-OFL.txt b/skills/canvas-design/canvas-fonts/CrimsonPro-OFL.txt new file mode 100644 index 0000000..f976fdc --- /dev/null +++ b/skills/canvas-design/canvas-fonts/CrimsonPro-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2018 The Crimson Pro Project Authors (https://github.com/Fonthausen/CrimsonPro) + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/CrimsonPro-Regular.ttf b/skills/canvas-design/canvas-fonts/CrimsonPro-Regular.ttf new file mode 100644 index 0000000..f5666b9 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/CrimsonPro-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/DMMono-OFL.txt b/skills/canvas-design/canvas-fonts/DMMono-OFL.txt new file mode 100644 index 0000000..5b17f0c --- /dev/null +++ b/skills/canvas-design/canvas-fonts/DMMono-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2020 The DM Mono Project Authors (https://www.github.com/googlefonts/dm-mono) + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/DMMono-Regular.ttf b/skills/canvas-design/canvas-fonts/DMMono-Regular.ttf new file mode 100644 index 0000000..7efe813 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/DMMono-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/EricaOne-OFL.txt b/skills/canvas-design/canvas-fonts/EricaOne-OFL.txt new file mode 100644 index 0000000..490d012 --- /dev/null +++ b/skills/canvas-design/canvas-fonts/EricaOne-OFL.txt @@ -0,0 +1,94 @@ +Copyright (c) 2011 by LatinoType Limitada (luciano@latinotype.com), +with Reserved Font Names "Erica One" + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/EricaOne-Regular.ttf b/skills/canvas-design/canvas-fonts/EricaOne-Regular.ttf new file mode 100644 index 0000000..8bd91d1 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/EricaOne-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/GeistMono-Bold.ttf b/skills/canvas-design/canvas-fonts/GeistMono-Bold.ttf new file mode 100644 index 0000000..736ff7c Binary files /dev/null and b/skills/canvas-design/canvas-fonts/GeistMono-Bold.ttf differ diff --git a/skills/canvas-design/canvas-fonts/GeistMono-OFL.txt b/skills/canvas-design/canvas-fonts/GeistMono-OFL.txt new file mode 100644 index 0000000..679a685 --- /dev/null +++ b/skills/canvas-design/canvas-fonts/GeistMono-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2024 The Geist Project Authors (https://github.com/vercel/geist-font.git) + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/GeistMono-Regular.ttf b/skills/canvas-design/canvas-fonts/GeistMono-Regular.ttf new file mode 100644 index 0000000..1a30262 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/GeistMono-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/Gloock-OFL.txt b/skills/canvas-design/canvas-fonts/Gloock-OFL.txt new file mode 100644 index 0000000..363acd3 --- /dev/null +++ b/skills/canvas-design/canvas-fonts/Gloock-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2022 The Gloock Project Authors (https://github.com/duartp/gloock) + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/Gloock-Regular.ttf b/skills/canvas-design/canvas-fonts/Gloock-Regular.ttf new file mode 100644 index 0000000..3e58c4e Binary files /dev/null and b/skills/canvas-design/canvas-fonts/Gloock-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/IBMPlexMono-Bold.ttf b/skills/canvas-design/canvas-fonts/IBMPlexMono-Bold.ttf new file mode 100644 index 0000000..247979c Binary files /dev/null and b/skills/canvas-design/canvas-fonts/IBMPlexMono-Bold.ttf differ diff --git a/skills/canvas-design/canvas-fonts/IBMPlexMono-OFL.txt b/skills/canvas-design/canvas-fonts/IBMPlexMono-OFL.txt new file mode 100644 index 0000000..e423b74 --- /dev/null +++ b/skills/canvas-design/canvas-fonts/IBMPlexMono-OFL.txt @@ -0,0 +1,93 @@ +Copyright © 2017 IBM Corp. with Reserved Font Name "Plex" + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/IBMPlexMono-Regular.ttf b/skills/canvas-design/canvas-fonts/IBMPlexMono-Regular.ttf new file mode 100644 index 0000000..601ae94 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/IBMPlexMono-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/IBMPlexSerif-Bold.ttf b/skills/canvas-design/canvas-fonts/IBMPlexSerif-Bold.ttf new file mode 100644 index 0000000..78f6e50 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/IBMPlexSerif-Bold.ttf differ diff --git a/skills/canvas-design/canvas-fonts/IBMPlexSerif-BoldItalic.ttf b/skills/canvas-design/canvas-fonts/IBMPlexSerif-BoldItalic.ttf new file mode 100644 index 0000000..369b89d Binary files /dev/null and b/skills/canvas-design/canvas-fonts/IBMPlexSerif-BoldItalic.ttf differ diff --git a/skills/canvas-design/canvas-fonts/IBMPlexSerif-Italic.ttf b/skills/canvas-design/canvas-fonts/IBMPlexSerif-Italic.ttf new file mode 100644 index 0000000..a4d859a Binary files /dev/null and b/skills/canvas-design/canvas-fonts/IBMPlexSerif-Italic.ttf differ diff --git a/skills/canvas-design/canvas-fonts/IBMPlexSerif-Regular.ttf b/skills/canvas-design/canvas-fonts/IBMPlexSerif-Regular.ttf new file mode 100644 index 0000000..35f454c Binary files /dev/null and b/skills/canvas-design/canvas-fonts/IBMPlexSerif-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/InstrumentSans-Bold.ttf b/skills/canvas-design/canvas-fonts/InstrumentSans-Bold.ttf new file mode 100644 index 0000000..f602dce Binary files /dev/null and b/skills/canvas-design/canvas-fonts/InstrumentSans-Bold.ttf differ diff --git a/skills/canvas-design/canvas-fonts/InstrumentSans-BoldItalic.ttf b/skills/canvas-design/canvas-fonts/InstrumentSans-BoldItalic.ttf new file mode 100644 index 0000000..122b273 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/InstrumentSans-BoldItalic.ttf differ diff --git a/skills/canvas-design/canvas-fonts/InstrumentSans-Italic.ttf b/skills/canvas-design/canvas-fonts/InstrumentSans-Italic.ttf new file mode 100644 index 0000000..4b98fb8 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/InstrumentSans-Italic.ttf differ diff --git a/skills/canvas-design/canvas-fonts/InstrumentSans-OFL.txt b/skills/canvas-design/canvas-fonts/InstrumentSans-OFL.txt new file mode 100644 index 0000000..4bb9914 --- /dev/null +++ b/skills/canvas-design/canvas-fonts/InstrumentSans-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2022 The Instrument Sans Project Authors (https://github.com/Instrument/instrument-sans) + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/InstrumentSans-Regular.ttf b/skills/canvas-design/canvas-fonts/InstrumentSans-Regular.ttf new file mode 100644 index 0000000..14c6113 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/InstrumentSans-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/InstrumentSerif-Italic.ttf b/skills/canvas-design/canvas-fonts/InstrumentSerif-Italic.ttf new file mode 100644 index 0000000..8fa958d Binary files /dev/null and b/skills/canvas-design/canvas-fonts/InstrumentSerif-Italic.ttf differ diff --git a/skills/canvas-design/canvas-fonts/InstrumentSerif-Regular.ttf b/skills/canvas-design/canvas-fonts/InstrumentSerif-Regular.ttf new file mode 100644 index 0000000..9763031 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/InstrumentSerif-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/Italiana-OFL.txt b/skills/canvas-design/canvas-fonts/Italiana-OFL.txt new file mode 100644 index 0000000..ba8af21 --- /dev/null +++ b/skills/canvas-design/canvas-fonts/Italiana-OFL.txt @@ -0,0 +1,93 @@ +Copyright (c) 2011, Santiago Orozco (hi@typemade.mx), with Reserved Font Name "Italiana". + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/Italiana-Regular.ttf b/skills/canvas-design/canvas-fonts/Italiana-Regular.ttf new file mode 100644 index 0000000..a9b828c Binary files /dev/null and b/skills/canvas-design/canvas-fonts/Italiana-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/JetBrainsMono-Bold.ttf b/skills/canvas-design/canvas-fonts/JetBrainsMono-Bold.ttf new file mode 100644 index 0000000..1926c80 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/JetBrainsMono-Bold.ttf differ diff --git a/skills/canvas-design/canvas-fonts/JetBrainsMono-OFL.txt b/skills/canvas-design/canvas-fonts/JetBrainsMono-OFL.txt new file mode 100644 index 0000000..5ceee00 --- /dev/null +++ b/skills/canvas-design/canvas-fonts/JetBrainsMono-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2020 The JetBrains Mono Project Authors (https://github.com/JetBrains/JetBrainsMono) + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/JetBrainsMono-Regular.ttf b/skills/canvas-design/canvas-fonts/JetBrainsMono-Regular.ttf new file mode 100644 index 0000000..436c982 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/JetBrainsMono-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/Jura-Light.ttf b/skills/canvas-design/canvas-fonts/Jura-Light.ttf new file mode 100644 index 0000000..dffbb33 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/Jura-Light.ttf differ diff --git a/skills/canvas-design/canvas-fonts/Jura-Medium.ttf b/skills/canvas-design/canvas-fonts/Jura-Medium.ttf new file mode 100644 index 0000000..4bf91a3 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/Jura-Medium.ttf differ diff --git a/skills/canvas-design/canvas-fonts/Jura-OFL.txt b/skills/canvas-design/canvas-fonts/Jura-OFL.txt new file mode 100644 index 0000000..64ad4c6 --- /dev/null +++ b/skills/canvas-design/canvas-fonts/Jura-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2019 The Jura Project Authors (https://github.com/ossobuffo/jura) + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/LibreBaskerville-OFL.txt b/skills/canvas-design/canvas-fonts/LibreBaskerville-OFL.txt new file mode 100644 index 0000000..8c531fa --- /dev/null +++ b/skills/canvas-design/canvas-fonts/LibreBaskerville-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2012 The Libre Baskerville Project Authors (https://github.com/impallari/Libre-Baskerville) with Reserved Font Name Libre Baskerville. + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/LibreBaskerville-Regular.ttf b/skills/canvas-design/canvas-fonts/LibreBaskerville-Regular.ttf new file mode 100644 index 0000000..c1abc26 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/LibreBaskerville-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/Lora-Bold.ttf b/skills/canvas-design/canvas-fonts/Lora-Bold.ttf new file mode 100644 index 0000000..edae21e Binary files /dev/null and b/skills/canvas-design/canvas-fonts/Lora-Bold.ttf differ diff --git a/skills/canvas-design/canvas-fonts/Lora-BoldItalic.ttf b/skills/canvas-design/canvas-fonts/Lora-BoldItalic.ttf new file mode 100644 index 0000000..12dea8c Binary files /dev/null and b/skills/canvas-design/canvas-fonts/Lora-BoldItalic.ttf differ diff --git a/skills/canvas-design/canvas-fonts/Lora-Italic.ttf b/skills/canvas-design/canvas-fonts/Lora-Italic.ttf new file mode 100644 index 0000000..e24b69b Binary files /dev/null and b/skills/canvas-design/canvas-fonts/Lora-Italic.ttf differ diff --git a/skills/canvas-design/canvas-fonts/Lora-OFL.txt b/skills/canvas-design/canvas-fonts/Lora-OFL.txt new file mode 100644 index 0000000..4cf1b95 --- /dev/null +++ b/skills/canvas-design/canvas-fonts/Lora-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2011 The Lora Project Authors (https://github.com/cyrealtype/Lora-Cyrillic), with Reserved Font Name "Lora". + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/Lora-Regular.ttf b/skills/canvas-design/canvas-fonts/Lora-Regular.ttf new file mode 100644 index 0000000..dc751db Binary files /dev/null and b/skills/canvas-design/canvas-fonts/Lora-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/NationalPark-Bold.ttf b/skills/canvas-design/canvas-fonts/NationalPark-Bold.ttf new file mode 100644 index 0000000..f4d7c02 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/NationalPark-Bold.ttf differ diff --git a/skills/canvas-design/canvas-fonts/NationalPark-OFL.txt b/skills/canvas-design/canvas-fonts/NationalPark-OFL.txt new file mode 100644 index 0000000..f4ec3fb --- /dev/null +++ b/skills/canvas-design/canvas-fonts/NationalPark-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2025 The National Park Project Authors (https://github.com/benhoepner/National-Park) + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/NationalPark-Regular.ttf b/skills/canvas-design/canvas-fonts/NationalPark-Regular.ttf new file mode 100644 index 0000000..e4cbfbf Binary files /dev/null and b/skills/canvas-design/canvas-fonts/NationalPark-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/NothingYouCouldDo-OFL.txt b/skills/canvas-design/canvas-fonts/NothingYouCouldDo-OFL.txt new file mode 100644 index 0000000..c81eccd --- /dev/null +++ b/skills/canvas-design/canvas-fonts/NothingYouCouldDo-OFL.txt @@ -0,0 +1,93 @@ +Copyright (c) 2010, Kimberly Geswein (kimberlygeswein.com) + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/NothingYouCouldDo-Regular.ttf b/skills/canvas-design/canvas-fonts/NothingYouCouldDo-Regular.ttf new file mode 100644 index 0000000..b086bce Binary files /dev/null and b/skills/canvas-design/canvas-fonts/NothingYouCouldDo-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/Outfit-Bold.ttf b/skills/canvas-design/canvas-fonts/Outfit-Bold.ttf new file mode 100644 index 0000000..f9f2f72 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/Outfit-Bold.ttf differ diff --git a/skills/canvas-design/canvas-fonts/Outfit-OFL.txt b/skills/canvas-design/canvas-fonts/Outfit-OFL.txt new file mode 100644 index 0000000..fd0cb99 --- /dev/null +++ b/skills/canvas-design/canvas-fonts/Outfit-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2021 The Outfit Project Authors (https://github.com/Outfitio/Outfit-Fonts) + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/Outfit-Regular.ttf b/skills/canvas-design/canvas-fonts/Outfit-Regular.ttf new file mode 100644 index 0000000..3939ab2 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/Outfit-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/PixelifySans-Medium.ttf b/skills/canvas-design/canvas-fonts/PixelifySans-Medium.ttf new file mode 100644 index 0000000..95cd372 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/PixelifySans-Medium.ttf differ diff --git a/skills/canvas-design/canvas-fonts/PixelifySans-OFL.txt b/skills/canvas-design/canvas-fonts/PixelifySans-OFL.txt new file mode 100644 index 0000000..b02d1b6 --- /dev/null +++ b/skills/canvas-design/canvas-fonts/PixelifySans-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2021 The Pixelify Sans Project Authors (https://github.com/eifetx/Pixelify-Sans) + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/PoiretOne-OFL.txt b/skills/canvas-design/canvas-fonts/PoiretOne-OFL.txt new file mode 100644 index 0000000..607bdad --- /dev/null +++ b/skills/canvas-design/canvas-fonts/PoiretOne-OFL.txt @@ -0,0 +1,93 @@ +Copyright (c) 2011, Denis Masharov (denis.masharov@gmail.com) + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/PoiretOne-Regular.ttf b/skills/canvas-design/canvas-fonts/PoiretOne-Regular.ttf new file mode 100644 index 0000000..b339511 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/PoiretOne-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/RedHatMono-Bold.ttf b/skills/canvas-design/canvas-fonts/RedHatMono-Bold.ttf new file mode 100644 index 0000000..a6e3cf1 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/RedHatMono-Bold.ttf differ diff --git a/skills/canvas-design/canvas-fonts/RedHatMono-OFL.txt b/skills/canvas-design/canvas-fonts/RedHatMono-OFL.txt new file mode 100644 index 0000000..16cf394 --- /dev/null +++ b/skills/canvas-design/canvas-fonts/RedHatMono-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2024 The Red Hat Project Authors (https://github.com/RedHatOfficial/RedHatFont) + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/RedHatMono-Regular.ttf b/skills/canvas-design/canvas-fonts/RedHatMono-Regular.ttf new file mode 100644 index 0000000..3bf6a69 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/RedHatMono-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/Silkscreen-OFL.txt b/skills/canvas-design/canvas-fonts/Silkscreen-OFL.txt new file mode 100644 index 0000000..a1fe7d5 --- /dev/null +++ b/skills/canvas-design/canvas-fonts/Silkscreen-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2001 The Silkscreen Project Authors (https://github.com/googlefonts/silkscreen) + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/Silkscreen-Regular.ttf b/skills/canvas-design/canvas-fonts/Silkscreen-Regular.ttf new file mode 100644 index 0000000..8abaa7c Binary files /dev/null and b/skills/canvas-design/canvas-fonts/Silkscreen-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/SmoochSans-Medium.ttf b/skills/canvas-design/canvas-fonts/SmoochSans-Medium.ttf new file mode 100644 index 0000000..0af9ead Binary files /dev/null and b/skills/canvas-design/canvas-fonts/SmoochSans-Medium.ttf differ diff --git a/skills/canvas-design/canvas-fonts/SmoochSans-OFL.txt b/skills/canvas-design/canvas-fonts/SmoochSans-OFL.txt new file mode 100644 index 0000000..4c2f033 --- /dev/null +++ b/skills/canvas-design/canvas-fonts/SmoochSans-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2016 The Smooch Sans Project Authors (https://github.com/googlefonts/smooch-sans) + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/Tektur-Medium.ttf b/skills/canvas-design/canvas-fonts/Tektur-Medium.ttf new file mode 100644 index 0000000..34fc797 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/Tektur-Medium.ttf differ diff --git a/skills/canvas-design/canvas-fonts/Tektur-OFL.txt b/skills/canvas-design/canvas-fonts/Tektur-OFL.txt new file mode 100644 index 0000000..2cad55f --- /dev/null +++ b/skills/canvas-design/canvas-fonts/Tektur-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2023 The Tektur Project Authors (https://www.github.com/hyvyys/Tektur) + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/Tektur-Regular.ttf b/skills/canvas-design/canvas-fonts/Tektur-Regular.ttf new file mode 100644 index 0000000..f280fba Binary files /dev/null and b/skills/canvas-design/canvas-fonts/Tektur-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/WorkSans-Bold.ttf b/skills/canvas-design/canvas-fonts/WorkSans-Bold.ttf new file mode 100644 index 0000000..5c97989 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/WorkSans-Bold.ttf differ diff --git a/skills/canvas-design/canvas-fonts/WorkSans-BoldItalic.ttf b/skills/canvas-design/canvas-fonts/WorkSans-BoldItalic.ttf new file mode 100644 index 0000000..54418b8 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/WorkSans-BoldItalic.ttf differ diff --git a/skills/canvas-design/canvas-fonts/WorkSans-Italic.ttf b/skills/canvas-design/canvas-fonts/WorkSans-Italic.ttf new file mode 100644 index 0000000..40529b6 Binary files /dev/null and b/skills/canvas-design/canvas-fonts/WorkSans-Italic.ttf differ diff --git a/skills/canvas-design/canvas-fonts/WorkSans-OFL.txt b/skills/canvas-design/canvas-fonts/WorkSans-OFL.txt new file mode 100644 index 0000000..070f341 --- /dev/null +++ b/skills/canvas-design/canvas-fonts/WorkSans-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2019 The Work Sans Project Authors (https://github.com/weiweihuanghuang/Work-Sans) + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/WorkSans-Regular.ttf b/skills/canvas-design/canvas-fonts/WorkSans-Regular.ttf new file mode 100644 index 0000000..d24586c Binary files /dev/null and b/skills/canvas-design/canvas-fonts/WorkSans-Regular.ttf differ diff --git a/skills/canvas-design/canvas-fonts/YoungSerif-OFL.txt b/skills/canvas-design/canvas-fonts/YoungSerif-OFL.txt new file mode 100644 index 0000000..f09443c --- /dev/null +++ b/skills/canvas-design/canvas-fonts/YoungSerif-OFL.txt @@ -0,0 +1,93 @@ +Copyright 2023 The Young Serif Project Authors (https://github.com/noirblancrouge/YoungSerif) + +This Font Software is licensed under the SIL Open Font License, Version 1.1. +This license is copied below, and is also available with a FAQ at: +https://openfontlicense.org + + +----------------------------------------------------------- +SIL OPEN FONT LICENSE Version 1.1 - 26 February 2007 +----------------------------------------------------------- + +PREAMBLE +The goals of the Open Font License (OFL) are to stimulate worldwide +development of collaborative font projects, to support the font creation +efforts of academic and linguistic communities, and to provide a free and +open framework in which fonts may be shared and improved in partnership +with others. + +The OFL allows the licensed fonts to be used, studied, modified and +redistributed freely as long as they are not sold by themselves. The +fonts, including any derivative works, can be bundled, embedded, +redistributed and/or sold with any software provided that any reserved +names are not used by derivative works. The fonts and derivatives, +however, cannot be released under any other type of license. The +requirement for fonts to remain under this license does not apply +to any document created using the fonts or their derivatives. + +DEFINITIONS +"Font Software" refers to the set of files released by the Copyright +Holder(s) under this license and clearly marked as such. This may +include source files, build scripts and documentation. + +"Reserved Font Name" refers to any names specified as such after the +copyright statement(s). + +"Original Version" refers to the collection of Font Software components as +distributed by the Copyright Holder(s). + +"Modified Version" refers to any derivative made by adding to, deleting, +or substituting -- in part or in whole -- any of the components of the +Original Version, by changing formats or by porting the Font Software to a +new environment. + +"Author" refers to any designer, engineer, programmer, technical +writer or other person who contributed to the Font Software. + +PERMISSION & CONDITIONS +Permission is hereby granted, free of charge, to any person obtaining +a copy of the Font Software, to use, study, copy, merge, embed, modify, +redistribute, and sell modified and unmodified copies of the Font +Software, subject to the following conditions: + +1) Neither the Font Software nor any of its individual components, +in Original or Modified Versions, may be sold by itself. + +2) Original or Modified Versions of the Font Software may be bundled, +redistributed and/or sold with any software, provided that each copy +contains the above copyright notice and this license. These can be +included either as stand-alone text files, human-readable headers or +in the appropriate machine-readable metadata fields within text or +binary files as long as those fields can be easily viewed by the user. + +3) No Modified Version of the Font Software may use the Reserved Font +Name(s) unless explicit written permission is granted by the corresponding +Copyright Holder. This restriction only applies to the primary font name as +presented to the users. + +4) The name(s) of the Copyright Holder(s) or the Author(s) of the Font +Software shall not be used to promote, endorse or advertise any +Modified Version, except to acknowledge the contribution(s) of the +Copyright Holder(s) and the Author(s) or with their explicit written +permission. + +5) The Font Software, modified or unmodified, in part or in whole, +must be distributed entirely under this license, and must not be +distributed under any other license. The requirement for fonts to +remain under this license does not apply to any document created +using the Font Software. + +TERMINATION +This license becomes null and void if any of the above conditions are +not met. + +DISCLAIMER +THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT +OF COPYRIGHT, PATENT, TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL THE +COPYRIGHT HOLDER BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, +INCLUDING ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL +DAMAGES, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING +FROM, OUT OF THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM +OTHER DEALINGS IN THE FONT SOFTWARE. diff --git a/skills/canvas-design/canvas-fonts/YoungSerif-Regular.ttf b/skills/canvas-design/canvas-fonts/YoungSerif-Regular.ttf new file mode 100644 index 0000000..f454fbe Binary files /dev/null and b/skills/canvas-design/canvas-fonts/YoungSerif-Regular.ttf differ diff --git a/skills/doc-coauthoring/SKILL.md b/skills/doc-coauthoring/SKILL.md new file mode 100644 index 0000000..a5a6983 --- /dev/null +++ b/skills/doc-coauthoring/SKILL.md @@ -0,0 +1,375 @@ +--- +name: doc-coauthoring +description: Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. +--- + +# Doc Co-Authoring Workflow + +This skill provides a structured workflow for guiding users through collaborative document creation. Act as an active guide, walking users through three stages: Context Gathering, Refinement & Structure, and Reader Testing. + +## When to Offer This Workflow + +**Trigger conditions:** +- User mentions writing documentation: "write a doc", "draft a proposal", "create a spec", "write up" +- User mentions specific doc types: "PRD", "design doc", "decision doc", "RFC" +- User seems to be starting a substantial writing task + +**Initial offer:** +Offer the user a structured workflow for co-authoring the document. Explain the three stages: + +1. **Context Gathering**: User provides all relevant context while Claude asks clarifying questions +2. **Refinement & Structure**: Iteratively build each section through brainstorming and editing +3. **Reader Testing**: Test the doc with a fresh Claude (no context) to catch blind spots before others read it + +Explain that this approach helps ensure the doc works well when others read it (including when they paste it into Claude). Ask if they want to try this workflow or prefer to work freeform. + +If user declines, work freeform. If user accepts, proceed to Stage 1. + +## Stage 1: Context Gathering + +**Goal:** Close the gap between what the user knows and what Claude knows, enabling smart guidance later. + +### Initial Questions + +Start by asking the user for meta-context about the document: + +1. What type of document is this? (e.g., technical spec, decision doc, proposal) +2. Who's the primary audience? +3. What's the desired impact when someone reads this? +4. Is there a template or specific format to follow? +5. Any other constraints or context to know? + +Inform them they can answer in shorthand or dump information however works best for them. + +**If user provides a template or mentions a doc type:** +- Ask if they have a template document to share +- If they provide a link to a shared document, use the appropriate integration to fetch it +- If they provide a file, read it + +**If user mentions editing an existing shared document:** +- Use the appropriate integration to read the current state +- Check for images without alt-text +- If images exist without alt-text, explain that when others use Claude to understand the doc, Claude won't be able to see them. Ask if they want alt-text generated. If so, request they paste each image into chat for descriptive alt-text generation. + +### Info Dumping + +Once initial questions are answered, encourage the user to dump all the context they have. Request information such as: +- Background on the project/problem +- Related team discussions or shared documents +- Why alternative solutions aren't being used +- Organizational context (team dynamics, past incidents, politics) +- Timeline pressures or constraints +- Technical architecture or dependencies +- Stakeholder concerns + +Advise them not to worry about organizing it - just get it all out. Offer multiple ways to provide context: +- Info dump stream-of-consciousness +- Point to team channels or threads to read +- Link to shared documents + +**If integrations are available** (e.g., Slack, Teams, Google Drive, SharePoint, or other MCP servers), mention that these can be used to pull in context directly. + +**If no integrations are detected and in Claude.ai or Claude app:** Suggest they can enable connectors in their Claude settings to allow pulling context from messaging apps and document storage directly. + +Inform them clarifying questions will be asked once they've done their initial dump. + +**During context gathering:** + +- If user mentions team channels or shared documents: + - If integrations available: Inform them the content will be read now, then use the appropriate integration + - If integrations not available: Explain lack of access. Suggest they enable connectors in Claude settings, or paste the relevant content directly. + +- If user mentions entities/projects that are unknown: + - Ask if connected tools should be searched to learn more + - Wait for user confirmation before searching + +- As user provides context, track what's being learned and what's still unclear + +**Asking clarifying questions:** + +When user signals they've done their initial dump (or after substantial context provided), ask clarifying questions to ensure understanding: + +Generate 5-10 numbered questions based on gaps in the context. + +Inform them they can use shorthand to answer (e.g., "1: yes, 2: see #channel, 3: no because backwards compat"), link to more docs, point to channels to read, or just keep info-dumping. Whatever's most efficient for them. + +**Exit condition:** +Sufficient context has been gathered when questions show understanding - when edge cases and trade-offs can be asked about without needing basics explained. + +**Transition:** +Ask if there's any more context they want to provide at this stage, or if it's time to move on to drafting the document. + +If user wants to add more, let them. When ready, proceed to Stage 2. + +## Stage 2: Refinement & Structure + +**Goal:** Build the document section by section through brainstorming, curation, and iterative refinement. + +**Instructions to user:** +Explain that the document will be built section by section. For each section: +1. Clarifying questions will be asked about what to include +2. 5-20 options will be brainstormed +3. User will indicate what to keep/remove/combine +4. The section will be drafted +5. It will be refined through surgical edits + +Start with whichever section has the most unknowns (usually the core decision/proposal), then work through the rest. + +**Section ordering:** + +If the document structure is clear: +Ask which section they'd like to start with. + +Suggest starting with whichever section has the most unknowns. For decision docs, that's usually the core proposal. For specs, it's typically the technical approach. Summary sections are best left for last. + +If user doesn't know what sections they need: +Based on the type of document and template, suggest 3-5 sections appropriate for the doc type. + +Ask if this structure works, or if they want to adjust it. + +**Once structure is agreed:** + +Create the initial document structure with placeholder text for all sections. + +**If access to artifacts is available:** +Use `create_file` to create an artifact. This gives both Claude and the user a scaffold to work from. + +Inform them that the initial structure with placeholders for all sections will be created. + +Create artifact with all section headers and brief placeholder text like "[To be written]" or "[Content here]". + +Provide the scaffold link and indicate it's time to fill in each section. + +**If no access to artifacts:** +Create a markdown file in the working directory. Name it appropriately (e.g., `decision-doc.md`, `technical-spec.md`). + +Inform them that the initial structure with placeholders for all sections will be created. + +Create file with all section headers and placeholder text. + +Confirm the filename has been created and indicate it's time to fill in each section. + +**For each section:** + +### Step 1: Clarifying Questions + +Announce work will begin on the [SECTION NAME] section. Ask 5-10 clarifying questions about what should be included: + +Generate 5-10 specific questions based on context and section purpose. + +Inform them they can answer in shorthand or just indicate what's important to cover. + +### Step 2: Brainstorming + +For the [SECTION NAME] section, brainstorm [5-20] things that might be included, depending on the section's complexity. Look for: +- Context shared that might have been forgotten +- Angles or considerations not yet mentioned + +Generate 5-20 numbered options based on section complexity. At the end, offer to brainstorm more if they want additional options. + +### Step 3: Curation + +Ask which points should be kept, removed, or combined. Request brief justifications to help learn priorities for the next sections. + +Provide examples: +- "Keep 1,4,7,9" +- "Remove 3 (duplicates 1)" +- "Remove 6 (audience already knows this)" +- "Combine 11 and 12" + +**If user gives freeform feedback** (e.g., "looks good" or "I like most of it but...") instead of numbered selections, extract their preferences and proceed. Parse what they want kept/removed/changed and apply it. + +### Step 4: Gap Check + +Based on what they've selected, ask if there's anything important missing for the [SECTION NAME] section. + +### Step 5: Drafting + +Use `str_replace` to replace the placeholder text for this section with the actual drafted content. + +Announce the [SECTION NAME] section will be drafted now based on what they've selected. + +**If using artifacts:** +After drafting, provide a link to the artifact. + +Ask them to read through it and indicate what to change. Note that being specific helps learning for the next sections. + +**If using a file (no artifacts):** +After drafting, confirm completion. + +Inform them the [SECTION NAME] section has been drafted in [filename]. Ask them to read through it and indicate what to change. Note that being specific helps learning for the next sections. + +**Key instruction for user (include when drafting the first section):** +Provide a note: Instead of editing the doc directly, ask them to indicate what to change. This helps learning of their style for future sections. For example: "Remove the X bullet - already covered by Y" or "Make the third paragraph more concise". + +### Step 6: Iterative Refinement + +As user provides feedback: +- Use `str_replace` to make edits (never reprint the whole doc) +- **If using artifacts:** Provide link to artifact after each edit +- **If using files:** Just confirm edits are complete +- If user edits doc directly and asks to read it: mentally note the changes they made and keep them in mind for future sections (this shows their preferences) + +**Continue iterating** until user is satisfied with the section. + +### Quality Checking + +After 3 consecutive iterations with no substantial changes, ask if anything can be removed without losing important information. + +When section is done, confirm [SECTION NAME] is complete. Ask if ready to move to the next section. + +**Repeat for all sections.** + +### Near Completion + +As approaching completion (80%+ of sections done), announce intention to re-read the entire document and check for: +- Flow and consistency across sections +- Redundancy or contradictions +- Anything that feels like "slop" or generic filler +- Whether every sentence carries weight + +Read entire document and provide feedback. + +**When all sections are drafted and refined:** +Announce all sections are drafted. Indicate intention to review the complete document one more time. + +Review for overall coherence, flow, completeness. + +Provide any final suggestions. + +Ask if ready to move to Reader Testing, or if they want to refine anything else. + +## Stage 3: Reader Testing + +**Goal:** Test the document with a fresh Claude (no context bleed) to verify it works for readers. + +**Instructions to user:** +Explain that testing will now occur to see if the document actually works for readers. This catches blind spots - things that make sense to the authors but might confuse others. + +### Testing Approach + +**If access to sub-agents is available (e.g., in Claude Code):** + +Perform the testing directly without user involvement. + +### Step 1: Predict Reader Questions + +Announce intention to predict what questions readers might ask when trying to discover this document. + +Generate 5-10 questions that readers would realistically ask. + +### Step 2: Test with Sub-Agent + +Announce that these questions will be tested with a fresh Claude instance (no context from this conversation). + +For each question, invoke a sub-agent with just the document content and the question. + +Summarize what Reader Claude got right/wrong for each question. + +### Step 3: Run Additional Checks + +Announce additional checks will be performed. + +Invoke sub-agent to check for ambiguity, false assumptions, contradictions. + +Summarize any issues found. + +### Step 4: Report and Fix + +If issues found: +Report that Reader Claude struggled with specific issues. + +List the specific issues. + +Indicate intention to fix these gaps. + +Loop back to refinement for problematic sections. + +--- + +**If no access to sub-agents (e.g., claude.ai web interface):** + +The user will need to do the testing manually. + +### Step 1: Predict Reader Questions + +Ask what questions people might ask when trying to discover this document. What would they type into Claude.ai? + +Generate 5-10 questions that readers would realistically ask. + +### Step 2: Setup Testing + +Provide testing instructions: +1. Open a fresh Claude conversation: https://claude.ai +2. Paste or share the document content (if using a shared doc platform with connectors enabled, provide the link) +3. Ask Reader Claude the generated questions + +For each question, instruct Reader Claude to provide: +- The answer +- Whether anything was ambiguous or unclear +- What knowledge/context the doc assumes is already known + +Check if Reader Claude gives correct answers or misinterprets anything. + +### Step 3: Additional Checks + +Also ask Reader Claude: +- "What in this doc might be ambiguous or unclear to readers?" +- "What knowledge or context does this doc assume readers already have?" +- "Are there any internal contradictions or inconsistencies?" + +### Step 4: Iterate Based on Results + +Ask what Reader Claude got wrong or struggled with. Indicate intention to fix those gaps. + +Loop back to refinement for any problematic sections. + +--- + +### Exit Condition (Both Approaches) + +When Reader Claude consistently answers questions correctly and doesn't surface new gaps or ambiguities, the doc is ready. + +## Final Review + +When Reader Testing passes: +Announce the doc has passed Reader Claude testing. Before completion: + +1. Recommend they do a final read-through themselves - they own this document and are responsible for its quality +2. Suggest double-checking any facts, links, or technical details +3. Ask them to verify it achieves the impact they wanted + +Ask if they want one more review, or if the work is done. + +**If user wants final review, provide it. Otherwise:** +Announce document completion. Provide a few final tips: +- Consider linking this conversation in an appendix so readers can see how the doc was developed +- Use appendices to provide depth without bloating the main doc +- Update the doc as feedback is received from real readers + +## Tips for Effective Guidance + +**Tone:** +- Be direct and procedural +- Explain rationale briefly when it affects user behavior +- Don't try to "sell" the approach - just execute it + +**Handling Deviations:** +- If user wants to skip a stage: Ask if they want to skip this and write freeform +- If user seems frustrated: Acknowledge this is taking longer than expected. Suggest ways to move faster +- Always give user agency to adjust the process + +**Context Management:** +- Throughout, if context is missing on something mentioned, proactively ask +- Don't let gaps accumulate - address them as they come up + +**Artifact Management:** +- Use `create_file` for drafting full sections +- Use `str_replace` for all edits +- Provide artifact link after every change +- Never use artifacts for brainstorming lists - that's just conversation + +**Quality over Speed:** +- Don't rush through stages +- Each iteration should make meaningful improvements +- The goal is a document that actually works for readers diff --git a/skills/docx/LICENSE.txt b/skills/docx/LICENSE.txt new file mode 100644 index 0000000..c55ab42 --- /dev/null +++ b/skills/docx/LICENSE.txt @@ -0,0 +1,30 @@ +© 2025 Anthropic, PBC. All rights reserved. + +LICENSE: Use of these materials (including all code, prompts, assets, files, +and other components of this Skill) is governed by your agreement with +Anthropic regarding use of Anthropic's services. If no separate agreement +exists, use is governed by Anthropic's Consumer Terms of Service or +Commercial Terms of Service, as applicable: +https://www.anthropic.com/legal/consumer-terms +https://www.anthropic.com/legal/commercial-terms +Your applicable agreement is referred to as the "Agreement." "Services" are +as defined in the Agreement. + +ADDITIONAL RESTRICTIONS: Notwithstanding anything in the Agreement to the +contrary, users may not: + +- Extract these materials from the Services or retain copies of these + materials outside the Services +- Reproduce or copy these materials, except for temporary copies created + automatically during authorized use of the Services +- Create derivative works based on these materials +- Distribute, sublicense, or transfer these materials to any third party +- Make, offer to sell, sell, or import any inventions embodied in these + materials +- Reverse engineer, decompile, or disassemble these materials + +The receipt, viewing, or possession of these materials does not convey or +imply any license or right beyond those expressly granted above. + +Anthropic retains all right, title, and interest in these materials, +including all copyrights, patents, and other intellectual property rights. diff --git a/skills/docx/SKILL.md b/skills/docx/SKILL.md new file mode 100644 index 0000000..6646638 --- /dev/null +++ b/skills/docx/SKILL.md @@ -0,0 +1,197 @@ +--- +name: docx +description: "Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks" +license: Proprietary. LICENSE.txt has complete terms +--- + +# DOCX creation, editing, and analysis + +## Overview + +A user may ask you to create, edit, or analyze the contents of a .docx file. A .docx file is essentially a ZIP archive containing XML files and other resources that you can read or edit. You have different tools and workflows available for different tasks. + +## Workflow Decision Tree + +### Reading/Analyzing Content +Use "Text extraction" or "Raw XML access" sections below + +### Creating New Document +Use "Creating a new Word document" workflow + +### Editing Existing Document +- **Your own document + simple changes** + Use "Basic OOXML editing" workflow + +- **Someone else's document** + Use **"Redlining workflow"** (recommended default) + +- **Legal, academic, business, or government docs** + Use **"Redlining workflow"** (required) + +## Reading and analyzing content + +### Text extraction +If you just need to read the text contents of a document, you should convert the document to markdown using pandoc. Pandoc provides excellent support for preserving document structure and can show tracked changes: + +```bash +# Convert document to markdown with tracked changes +pandoc --track-changes=all path-to-file.docx -o output.md +# Options: --track-changes=accept/reject/all +``` + +### Raw XML access +You need raw XML access for: comments, complex formatting, document structure, embedded media, and metadata. For any of these features, you'll need to unpack a document and read its raw XML contents. + +#### Unpacking a file +`python ooxml/scripts/unpack.py ` + +#### Key file structures +* `word/document.xml` - Main document contents +* `word/comments.xml` - Comments referenced in document.xml +* `word/media/` - Embedded images and media files +* Tracked changes use `` (insertions) and `` (deletions) tags + +## Creating a new Word document + +When creating a new Word document from scratch, use **docx-js**, which allows you to create Word documents using JavaScript/TypeScript. + +### Workflow +1. **MANDATORY - READ ENTIRE FILE**: Read [`docx-js.md`](docx-js.md) (~500 lines) completely from start to finish. **NEVER set any range limits when reading this file.** Read the full file content for detailed syntax, critical formatting rules, and best practices before proceeding with document creation. +2. Create a JavaScript/TypeScript file using Document, Paragraph, TextRun components (You can assume all dependencies are installed, but if not, refer to the dependencies section below) +3. Export as .docx using Packer.toBuffer() + +## Editing an existing Word document + +When editing an existing Word document, use the **Document library** (a Python library for OOXML manipulation). The library automatically handles infrastructure setup and provides methods for document manipulation. For complex scenarios, you can access the underlying DOM directly through the library. + +### Workflow +1. **MANDATORY - READ ENTIRE FILE**: Read [`ooxml.md`](ooxml.md) (~600 lines) completely from start to finish. **NEVER set any range limits when reading this file.** Read the full file content for the Document library API and XML patterns for directly editing document files. +2. Unpack the document: `python ooxml/scripts/unpack.py ` +3. Create and run a Python script using the Document library (see "Document Library" section in ooxml.md) +4. Pack the final document: `python ooxml/scripts/pack.py ` + +The Document library provides both high-level methods for common operations and direct DOM access for complex scenarios. + +## Redlining workflow for document review + +This workflow allows you to plan comprehensive tracked changes using markdown before implementing them in OOXML. **CRITICAL**: For complete tracked changes, you must implement ALL changes systematically. + +**Batching Strategy**: Group related changes into batches of 3-10 changes. This makes debugging manageable while maintaining efficiency. Test each batch before moving to the next. + +**Principle: Minimal, Precise Edits** +When implementing tracked changes, only mark text that actually changes. Repeating unchanged text makes edits harder to review and appears unprofessional. Break replacements into: [unchanged text] + [deletion] + [insertion] + [unchanged text]. Preserve the original run's RSID for unchanged text by extracting the `` element from the original and reusing it. + +Example - Changing "30 days" to "60 days" in a sentence: +```python +# BAD - Replaces entire sentence +'The term is 30 days.The term is 60 days.' + +# GOOD - Only marks what changed, preserves original for unchanged text +'The term is 3060 days.' +``` + +### Tracked changes workflow + +1. **Get markdown representation**: Convert document to markdown with tracked changes preserved: + ```bash + pandoc --track-changes=all path-to-file.docx -o current.md + ``` + +2. **Identify and group changes**: Review the document and identify ALL changes needed, organizing them into logical batches: + + **Location methods** (for finding changes in XML): + - Section/heading numbers (e.g., "Section 3.2", "Article IV") + - Paragraph identifiers if numbered + - Grep patterns with unique surrounding text + - Document structure (e.g., "first paragraph", "signature block") + - **DO NOT use markdown line numbers** - they don't map to XML structure + + **Batch organization** (group 3-10 related changes per batch): + - By section: "Batch 1: Section 2 amendments", "Batch 2: Section 5 updates" + - By type: "Batch 1: Date corrections", "Batch 2: Party name changes" + - By complexity: Start with simple text replacements, then tackle complex structural changes + - Sequential: "Batch 1: Pages 1-3", "Batch 2: Pages 4-6" + +3. **Read documentation and unpack**: + - **MANDATORY - READ ENTIRE FILE**: Read [`ooxml.md`](ooxml.md) (~600 lines) completely from start to finish. **NEVER set any range limits when reading this file.** Pay special attention to the "Document Library" and "Tracked Change Patterns" sections. + - **Unpack the document**: `python ooxml/scripts/unpack.py ` + - **Note the suggested RSID**: The unpack script will suggest an RSID to use for your tracked changes. Copy this RSID for use in step 4b. + +4. **Implement changes in batches**: Group changes logically (by section, by type, or by proximity) and implement them together in a single script. This approach: + - Makes debugging easier (smaller batch = easier to isolate errors) + - Allows incremental progress + - Maintains efficiency (batch size of 3-10 changes works well) + + **Suggested batch groupings:** + - By document section (e.g., "Section 3 changes", "Definitions", "Termination clause") + - By change type (e.g., "Date changes", "Party name updates", "Legal term replacements") + - By proximity (e.g., "Changes on pages 1-3", "Changes in first half of document") + + For each batch of related changes: + + **a. Map text to XML**: Grep for text in `word/document.xml` to verify how text is split across `` elements. + + **b. Create and run script**: Use `get_node` to find nodes, implement changes, then `doc.save()`. See **"Document Library"** section in ooxml.md for patterns. + + **Note**: Always grep `word/document.xml` immediately before writing a script to get current line numbers and verify text content. Line numbers change after each script run. + +5. **Pack the document**: After all batches are complete, convert the unpacked directory back to .docx: + ```bash + python ooxml/scripts/pack.py unpacked reviewed-document.docx + ``` + +6. **Final verification**: Do a comprehensive check of the complete document: + - Convert final document to markdown: + ```bash + pandoc --track-changes=all reviewed-document.docx -o verification.md + ``` + - Verify ALL changes were applied correctly: + ```bash + grep "original phrase" verification.md # Should NOT find it + grep "replacement phrase" verification.md # Should find it + ``` + - Check that no unintended changes were introduced + + +## Converting Documents to Images + +To visually analyze Word documents, convert them to images using a two-step process: + +1. **Convert DOCX to PDF**: + ```bash + soffice --headless --convert-to pdf document.docx + ``` + +2. **Convert PDF pages to JPEG images**: + ```bash + pdftoppm -jpeg -r 150 document.pdf page + ``` + This creates files like `page-1.jpg`, `page-2.jpg`, etc. + +Options: +- `-r 150`: Sets resolution to 150 DPI (adjust for quality/size balance) +- `-jpeg`: Output JPEG format (use `-png` for PNG if preferred) +- `-f N`: First page to convert (e.g., `-f 2` starts from page 2) +- `-l N`: Last page to convert (e.g., `-l 5` stops at page 5) +- `page`: Prefix for output files + +Example for specific range: +```bash +pdftoppm -jpeg -r 150 -f 2 -l 5 document.pdf page # Converts only pages 2-5 +``` + +## Code Style Guidelines +**IMPORTANT**: When generating code for DOCX operations: +- Write concise code +- Avoid verbose variable names and redundant operations +- Avoid unnecessary print statements + +## Dependencies + +Required dependencies (install if not available): + +- **pandoc**: `sudo apt-get install pandoc` (for text extraction) +- **docx**: `npm install -g docx` (for creating new documents) +- **LibreOffice**: `sudo apt-get install libreoffice` (for PDF conversion) +- **Poppler**: `sudo apt-get install poppler-utils` (for pdftoppm to convert PDF to images) +- **defusedxml**: `pip install defusedxml` (for secure XML parsing) \ No newline at end of file diff --git a/skills/docx/docx-js.md b/skills/docx/docx-js.md new file mode 100644 index 0000000..c6d7b2d --- /dev/null +++ b/skills/docx/docx-js.md @@ -0,0 +1,350 @@ +# DOCX Library Tutorial + +Generate .docx files with JavaScript/TypeScript. + +**Important: Read this entire document before starting.** Critical formatting rules and common pitfalls are covered throughout - skipping sections may result in corrupted files or rendering issues. + +## Setup +Assumes docx is already installed globally +If not installed: `npm install -g docx` + +```javascript +const { Document, Packer, Paragraph, TextRun, Table, TableRow, TableCell, ImageRun, Media, + Header, Footer, AlignmentType, PageOrientation, LevelFormat, ExternalHyperlink, + InternalHyperlink, TableOfContents, HeadingLevel, BorderStyle, WidthType, TabStopType, + TabStopPosition, UnderlineType, ShadingType, VerticalAlign, SymbolRun, PageNumber, + FootnoteReferenceRun, Footnote, PageBreak } = require('docx'); + +// Create & Save +const doc = new Document({ sections: [{ children: [/* content */] }] }); +Packer.toBuffer(doc).then(buffer => fs.writeFileSync("doc.docx", buffer)); // Node.js +Packer.toBlob(doc).then(blob => { /* download logic */ }); // Browser +``` + +## Text & Formatting +```javascript +// IMPORTANT: Never use \n for line breaks - always use separate Paragraph elements +// ❌ WRONG: new TextRun("Line 1\nLine 2") +// ✅ CORRECT: new Paragraph({ children: [new TextRun("Line 1")] }), new Paragraph({ children: [new TextRun("Line 2")] }) + +// Basic text with all formatting options +new Paragraph({ + alignment: AlignmentType.CENTER, + spacing: { before: 200, after: 200 }, + indent: { left: 720, right: 720 }, + children: [ + new TextRun({ text: "Bold", bold: true }), + new TextRun({ text: "Italic", italics: true }), + new TextRun({ text: "Underlined", underline: { type: UnderlineType.DOUBLE, color: "FF0000" } }), + new TextRun({ text: "Colored", color: "FF0000", size: 28, font: "Arial" }), // Arial default + new TextRun({ text: "Highlighted", highlight: "yellow" }), + new TextRun({ text: "Strikethrough", strike: true }), + new TextRun({ text: "x2", superScript: true }), + new TextRun({ text: "H2O", subScript: true }), + new TextRun({ text: "SMALL CAPS", smallCaps: true }), + new SymbolRun({ char: "2022", font: "Symbol" }), // Bullet • + new SymbolRun({ char: "00A9", font: "Arial" }) // Copyright © - Arial for symbols + ] +}) +``` + +## Styles & Professional Formatting + +```javascript +const doc = new Document({ + styles: { + default: { document: { run: { font: "Arial", size: 24 } } }, // 12pt default + paragraphStyles: [ + // Document title style - override built-in Title style + { id: "Title", name: "Title", basedOn: "Normal", + run: { size: 56, bold: true, color: "000000", font: "Arial" }, + paragraph: { spacing: { before: 240, after: 120 }, alignment: AlignmentType.CENTER } }, + // IMPORTANT: Override built-in heading styles by using their exact IDs + { id: "Heading1", name: "Heading 1", basedOn: "Normal", next: "Normal", quickFormat: true, + run: { size: 32, bold: true, color: "000000", font: "Arial" }, // 16pt + paragraph: { spacing: { before: 240, after: 240 }, outlineLevel: 0 } }, // Required for TOC + { id: "Heading2", name: "Heading 2", basedOn: "Normal", next: "Normal", quickFormat: true, + run: { size: 28, bold: true, color: "000000", font: "Arial" }, // 14pt + paragraph: { spacing: { before: 180, after: 180 }, outlineLevel: 1 } }, + // Custom styles use your own IDs + { id: "myStyle", name: "My Style", basedOn: "Normal", + run: { size: 28, bold: true, color: "000000" }, + paragraph: { spacing: { after: 120 }, alignment: AlignmentType.CENTER } } + ], + characterStyles: [{ id: "myCharStyle", name: "My Char Style", + run: { color: "FF0000", bold: true, underline: { type: UnderlineType.SINGLE } } }] + }, + sections: [{ + properties: { page: { margin: { top: 1440, right: 1440, bottom: 1440, left: 1440 } } }, + children: [ + new Paragraph({ heading: HeadingLevel.TITLE, children: [new TextRun("Document Title")] }), // Uses overridden Title style + new Paragraph({ heading: HeadingLevel.HEADING_1, children: [new TextRun("Heading 1")] }), // Uses overridden Heading1 style + new Paragraph({ style: "myStyle", children: [new TextRun("Custom paragraph style")] }), + new Paragraph({ children: [ + new TextRun("Normal with "), + new TextRun({ text: "custom char style", style: "myCharStyle" }) + ]}) + ] + }] +}); +``` + +**Professional Font Combinations:** +- **Arial (Headers) + Arial (Body)** - Most universally supported, clean and professional +- **Times New Roman (Headers) + Arial (Body)** - Classic serif headers with modern sans-serif body +- **Georgia (Headers) + Verdana (Body)** - Optimized for screen reading, elegant contrast + +**Key Styling Principles:** +- **Override built-in styles**: Use exact IDs like "Heading1", "Heading2", "Heading3" to override Word's built-in heading styles +- **HeadingLevel constants**: `HeadingLevel.HEADING_1` uses "Heading1" style, `HeadingLevel.HEADING_2` uses "Heading2" style, etc. +- **Include outlineLevel**: Set `outlineLevel: 0` for H1, `outlineLevel: 1` for H2, etc. to ensure TOC works correctly +- **Use custom styles** instead of inline formatting for consistency +- **Set a default font** using `styles.default.document.run.font` - Arial is universally supported +- **Establish visual hierarchy** with different font sizes (titles > headers > body) +- **Add proper spacing** with `before` and `after` paragraph spacing +- **Use colors sparingly**: Default to black (000000) and shades of gray for titles and headings (heading 1, heading 2, etc.) +- **Set consistent margins** (1440 = 1 inch is standard) + + +## Lists (ALWAYS USE PROPER LISTS - NEVER USE UNICODE BULLETS) +```javascript +// Bullets - ALWAYS use the numbering config, NOT unicode symbols +// CRITICAL: Use LevelFormat.BULLET constant, NOT the string "bullet" +const doc = new Document({ + numbering: { + config: [ + { reference: "bullet-list", + levels: [{ level: 0, format: LevelFormat.BULLET, text: "•", alignment: AlignmentType.LEFT, + style: { paragraph: { indent: { left: 720, hanging: 360 } } } }] }, + { reference: "first-numbered-list", + levels: [{ level: 0, format: LevelFormat.DECIMAL, text: "%1.", alignment: AlignmentType.LEFT, + style: { paragraph: { indent: { left: 720, hanging: 360 } } } }] }, + { reference: "second-numbered-list", // Different reference = restarts at 1 + levels: [{ level: 0, format: LevelFormat.DECIMAL, text: "%1.", alignment: AlignmentType.LEFT, + style: { paragraph: { indent: { left: 720, hanging: 360 } } } }] } + ] + }, + sections: [{ + children: [ + // Bullet list items + new Paragraph({ numbering: { reference: "bullet-list", level: 0 }, + children: [new TextRun("First bullet point")] }), + new Paragraph({ numbering: { reference: "bullet-list", level: 0 }, + children: [new TextRun("Second bullet point")] }), + // Numbered list items + new Paragraph({ numbering: { reference: "first-numbered-list", level: 0 }, + children: [new TextRun("First numbered item")] }), + new Paragraph({ numbering: { reference: "first-numbered-list", level: 0 }, + children: [new TextRun("Second numbered item")] }), + // ⚠️ CRITICAL: Different reference = INDEPENDENT list that restarts at 1 + // Same reference = CONTINUES previous numbering + new Paragraph({ numbering: { reference: "second-numbered-list", level: 0 }, + children: [new TextRun("Starts at 1 again (because different reference)")] }) + ] + }] +}); + +// ⚠️ CRITICAL NUMBERING RULE: Each reference creates an INDEPENDENT numbered list +// - Same reference = continues numbering (1, 2, 3... then 4, 5, 6...) +// - Different reference = restarts at 1 (1, 2, 3... then 1, 2, 3...) +// Use unique reference names for each separate numbered section! + +// ⚠️ CRITICAL: NEVER use unicode bullets - they create fake lists that don't work properly +// new TextRun("• Item") // WRONG +// new SymbolRun({ char: "2022" }) // WRONG +// ✅ ALWAYS use numbering config with LevelFormat.BULLET for real Word lists +``` + +## Tables +```javascript +// Complete table with margins, borders, headers, and bullet points +const tableBorder = { style: BorderStyle.SINGLE, size: 1, color: "CCCCCC" }; +const cellBorders = { top: tableBorder, bottom: tableBorder, left: tableBorder, right: tableBorder }; + +new Table({ + columnWidths: [4680, 4680], // ⚠️ CRITICAL: Set column widths at table level - values in DXA (twentieths of a point) + margins: { top: 100, bottom: 100, left: 180, right: 180 }, // Set once for all cells + rows: [ + new TableRow({ + tableHeader: true, + children: [ + new TableCell({ + borders: cellBorders, + width: { size: 4680, type: WidthType.DXA }, // ALSO set width on each cell + // ⚠️ CRITICAL: Always use ShadingType.CLEAR to prevent black backgrounds in Word. + shading: { fill: "D5E8F0", type: ShadingType.CLEAR }, + verticalAlign: VerticalAlign.CENTER, + children: [new Paragraph({ + alignment: AlignmentType.CENTER, + children: [new TextRun({ text: "Header", bold: true, size: 22 })] + })] + }), + new TableCell({ + borders: cellBorders, + width: { size: 4680, type: WidthType.DXA }, // ALSO set width on each cell + shading: { fill: "D5E8F0", type: ShadingType.CLEAR }, + children: [new Paragraph({ + alignment: AlignmentType.CENTER, + children: [new TextRun({ text: "Bullet Points", bold: true, size: 22 })] + })] + }) + ] + }), + new TableRow({ + children: [ + new TableCell({ + borders: cellBorders, + width: { size: 4680, type: WidthType.DXA }, // ALSO set width on each cell + children: [new Paragraph({ children: [new TextRun("Regular data")] })] + }), + new TableCell({ + borders: cellBorders, + width: { size: 4680, type: WidthType.DXA }, // ALSO set width on each cell + children: [ + new Paragraph({ + numbering: { reference: "bullet-list", level: 0 }, + children: [new TextRun("First bullet point")] + }), + new Paragraph({ + numbering: { reference: "bullet-list", level: 0 }, + children: [new TextRun("Second bullet point")] + }) + ] + }) + ] + }) + ] +}) +``` + +**IMPORTANT: Table Width & Borders** +- Use BOTH `columnWidths: [width1, width2, ...]` array AND `width: { size: X, type: WidthType.DXA }` on each cell +- Values in DXA (twentieths of a point): 1440 = 1 inch, Letter usable width = 9360 DXA (with 1" margins) +- Apply borders to individual `TableCell` elements, NOT the `Table` itself + +**Precomputed Column Widths (Letter size with 1" margins = 9360 DXA total):** +- **2 columns:** `columnWidths: [4680, 4680]` (equal width) +- **3 columns:** `columnWidths: [3120, 3120, 3120]` (equal width) + +## Links & Navigation +```javascript +// TOC (requires headings) - CRITICAL: Use HeadingLevel only, NOT custom styles +// ❌ WRONG: new Paragraph({ heading: HeadingLevel.HEADING_1, style: "customHeader", children: [new TextRun("Title")] }) +// ✅ CORRECT: new Paragraph({ heading: HeadingLevel.HEADING_1, children: [new TextRun("Title")] }) +new TableOfContents("Table of Contents", { hyperlink: true, headingStyleRange: "1-3" }), + +// External link +new Paragraph({ + children: [new ExternalHyperlink({ + children: [new TextRun({ text: "Google", style: "Hyperlink" })], + link: "https://www.google.com" + })] +}), + +// Internal link & bookmark +new Paragraph({ + children: [new InternalHyperlink({ + children: [new TextRun({ text: "Go to Section", style: "Hyperlink" })], + anchor: "section1" + })] +}), +new Paragraph({ + children: [new TextRun("Section Content")], + bookmark: { id: "section1", name: "section1" } +}), +``` + +## Images & Media +```javascript +// Basic image with sizing & positioning +// CRITICAL: Always specify 'type' parameter - it's REQUIRED for ImageRun +new Paragraph({ + alignment: AlignmentType.CENTER, + children: [new ImageRun({ + type: "png", // NEW REQUIREMENT: Must specify image type (png, jpg, jpeg, gif, bmp, svg) + data: fs.readFileSync("image.png"), + transformation: { width: 200, height: 150, rotation: 0 }, // rotation in degrees + altText: { title: "Logo", description: "Company logo", name: "Name" } // IMPORTANT: All three fields are required + })] +}) +``` + +## Page Breaks +```javascript +// Manual page break +new Paragraph({ children: [new PageBreak()] }), + +// Page break before paragraph +new Paragraph({ + pageBreakBefore: true, + children: [new TextRun("This starts on a new page")] +}) + +// ⚠️ CRITICAL: NEVER use PageBreak standalone - it will create invalid XML that Word cannot open +// ❌ WRONG: new PageBreak() +// ✅ CORRECT: new Paragraph({ children: [new PageBreak()] }) +``` + +## Headers/Footers & Page Setup +```javascript +const doc = new Document({ + sections: [{ + properties: { + page: { + margin: { top: 1440, right: 1440, bottom: 1440, left: 1440 }, // 1440 = 1 inch + size: { orientation: PageOrientation.LANDSCAPE }, + pageNumbers: { start: 1, formatType: "decimal" } // "upperRoman", "lowerRoman", "upperLetter", "lowerLetter" + } + }, + headers: { + default: new Header({ children: [new Paragraph({ + alignment: AlignmentType.RIGHT, + children: [new TextRun("Header Text")] + })] }) + }, + footers: { + default: new Footer({ children: [new Paragraph({ + alignment: AlignmentType.CENTER, + children: [new TextRun("Page "), new TextRun({ children: [PageNumber.CURRENT] }), new TextRun(" of "), new TextRun({ children: [PageNumber.TOTAL_PAGES] })] + })] }) + }, + children: [/* content */] + }] +}); +``` + +## Tabs +```javascript +new Paragraph({ + tabStops: [ + { type: TabStopType.LEFT, position: TabStopPosition.MAX / 4 }, + { type: TabStopType.CENTER, position: TabStopPosition.MAX / 2 }, + { type: TabStopType.RIGHT, position: TabStopPosition.MAX * 3 / 4 } + ], + children: [new TextRun("Left\tCenter\tRight")] +}) +``` + +## Constants & Quick Reference +- **Underlines:** `SINGLE`, `DOUBLE`, `WAVY`, `DASH` +- **Borders:** `SINGLE`, `DOUBLE`, `DASHED`, `DOTTED` +- **Numbering:** `DECIMAL` (1,2,3), `UPPER_ROMAN` (I,II,III), `LOWER_LETTER` (a,b,c) +- **Tabs:** `LEFT`, `CENTER`, `RIGHT`, `DECIMAL` +- **Symbols:** `"2022"` (•), `"00A9"` (©), `"00AE"` (®), `"2122"` (™), `"00B0"` (°), `"F070"` (✓), `"F0FC"` (✗) + +## Critical Issues & Common Mistakes +- **CRITICAL: PageBreak must ALWAYS be inside a Paragraph** - standalone PageBreak creates invalid XML that Word cannot open +- **ALWAYS use ShadingType.CLEAR for table cell shading** - Never use ShadingType.SOLID (causes black background). +- Measurements in DXA (1440 = 1 inch) | Each table cell needs ≥1 Paragraph | TOC requires HeadingLevel styles only +- **ALWAYS use custom styles** with Arial font for professional appearance and proper visual hierarchy +- **ALWAYS set a default font** using `styles.default.document.run.font` - Arial recommended +- **ALWAYS use columnWidths array for tables** + individual cell widths for compatibility +- **NEVER use unicode symbols for bullets** - always use proper numbering configuration with `LevelFormat.BULLET` constant (NOT the string "bullet") +- **NEVER use \n for line breaks anywhere** - always use separate Paragraph elements for each line +- **ALWAYS use TextRun objects within Paragraph children** - never use text property directly on Paragraph +- **CRITICAL for images**: ImageRun REQUIRES `type` parameter - always specify "png", "jpg", "jpeg", "gif", "bmp", or "svg" +- **CRITICAL for bullets**: Must use `LevelFormat.BULLET` constant, not string "bullet", and include `text: "•"` for the bullet character +- **CRITICAL for numbering**: Each numbering reference creates an INDEPENDENT list. Same reference = continues numbering (1,2,3 then 4,5,6). Different reference = restarts at 1 (1,2,3 then 1,2,3). Use unique reference names for each separate numbered section! +- **CRITICAL for TOC**: When using TableOfContents, headings must use HeadingLevel ONLY - do NOT add custom styles to heading paragraphs or TOC will break +- **Tables**: Set `columnWidths` array + individual cell widths, apply borders to cells not table +- **Set table margins at TABLE level** for consistent cell padding (avoids repetition per cell) \ No newline at end of file diff --git a/skills/docx/ooxml.md b/skills/docx/ooxml.md new file mode 100644 index 0000000..7677e7b --- /dev/null +++ b/skills/docx/ooxml.md @@ -0,0 +1,610 @@ +# Office Open XML Technical Reference + +**Important: Read this entire document before starting.** This document covers: +- [Technical Guidelines](#technical-guidelines) - Schema compliance rules and validation requirements +- [Document Content Patterns](#document-content-patterns) - XML patterns for headings, lists, tables, formatting, etc. +- [Document Library (Python)](#document-library-python) - Recommended approach for OOXML manipulation with automatic infrastructure setup +- [Tracked Changes (Redlining)](#tracked-changes-redlining) - XML patterns for implementing tracked changes + +## Technical Guidelines + +### Schema Compliance +- **Element ordering in ``**: ``, ``, ``, ``, `` +- **Whitespace**: Add `xml:space='preserve'` to `` elements with leading/trailing spaces +- **Unicode**: Escape characters in ASCII content: `"` becomes `“` + - **Character encoding reference**: Curly quotes `""` become `“”`, apostrophe `'` becomes `’`, em-dash `—` becomes `—` +- **Tracked changes**: Use `` and `` tags with `w:author="Claude"` outside `` elements + - **Critical**: `` closes with ``, `` closes with `` - never mix + - **RSIDs must be 8-digit hex**: Use values like `00AB1234` (only 0-9, A-F characters) + - **trackRevisions placement**: Add `` after `` in settings.xml +- **Images**: Add to `word/media/`, reference in `document.xml`, set dimensions to prevent overflow + +## Document Content Patterns + +### Basic Structure +```xml + + Text content + +``` + +### Headings and Styles +```xml + + + + + + Document Title + + + + + Section Heading + +``` + +### Text Formatting +```xml + +Bold + +Italic + +Underlined + +Highlighted +``` + +### Lists +```xml + + + + + + + + First item + + + + + + + + + + New list item 1 + + + + + + + + + + + Bullet item + +``` + +### Tables +```xml + + + + + + + + + + + + Cell 1 + + + + Cell 2 + + + +``` + +### Layout +```xml + + + + + + + + + + + + New Section Title + + + + + + + + + + Centered text + + + + + + + + Monospace text + + + + + + + This text is Courier New + + and this text uses default font + +``` + +## File Updates + +When adding content, update these files: + +**`word/_rels/document.xml.rels`:** +```xml + + +``` + +**`[Content_Types].xml`:** +```xml + + +``` + +### Images +**CRITICAL**: Calculate dimensions to prevent page overflow and maintain aspect ratio. + +```xml + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +``` + +### Links (Hyperlinks) + +**IMPORTANT**: All hyperlinks (both internal and external) require the Hyperlink style to be defined in styles.xml. Without this style, links will look like regular text instead of blue underlined clickable links. + +**External Links:** +```xml + + + + + Link Text + + + + + +``` + +**Internal Links:** + +```xml + + + + + Link Text + + + + + +Target content + +``` + +**Hyperlink Style (required in styles.xml):** +```xml + + + + + + + + + + +``` + +## Document Library (Python) + +Use the Document class from `scripts/document.py` for all tracked changes and comments. It automatically handles infrastructure setup (people.xml, RSIDs, settings.xml, comment files, relationships, content types). Only use direct XML manipulation for complex scenarios not supported by the library. + +**Working with Unicode and Entities:** +- **Searching**: Both entity notation and Unicode characters work - `contains="“Company"` and `contains="\u201cCompany"` find the same text +- **Replacing**: Use either entities (`“`) or Unicode (`\u201c`) - both work and will be converted appropriately based on the file's encoding (ascii → entities, utf-8 → Unicode) + +### Initialization + +**Find the docx skill root** (directory containing `scripts/` and `ooxml/`): +```bash +# Search for document.py to locate the skill root +# Note: /mnt/skills is used here as an example; check your context for the actual location +find /mnt/skills -name "document.py" -path "*/docx/scripts/*" 2>/dev/null | head -1 +# Example output: /mnt/skills/docx/scripts/document.py +# Skill root is: /mnt/skills/docx +``` + +**Run your script with PYTHONPATH** set to the docx skill root: +```bash +PYTHONPATH=/mnt/skills/docx python your_script.py +``` + +**In your script**, import from the skill root: +```python +from scripts.document import Document, DocxXMLEditor + +# Basic initialization (automatically creates temp copy and sets up infrastructure) +doc = Document('unpacked') + +# Customize author and initials +doc = Document('unpacked', author="John Doe", initials="JD") + +# Enable track revisions mode +doc = Document('unpacked', track_revisions=True) + +# Specify custom RSID (auto-generated if not provided) +doc = Document('unpacked', rsid="07DC5ECB") +``` + +### Creating Tracked Changes + +**CRITICAL**: Only mark text that actually changes. Keep ALL unchanged text outside ``/`` tags. Marking unchanged text makes edits unprofessional and harder to review. + +**Attribute Handling**: The Document class auto-injects attributes (w:id, w:date, w:rsidR, w:rsidDel, w16du:dateUtc, xml:space) into new elements. When preserving unchanged text from the original document, copy the original `` element with its existing attributes to maintain document integrity. + +**Method Selection Guide**: +- **Adding your own changes to regular text**: Use `replace_node()` with ``/`` tags, or `suggest_deletion()` for removing entire `` or `` elements +- **Partially modifying another author's tracked change**: Use `replace_node()` to nest your changes inside their ``/`` +- **Completely rejecting another author's insertion**: Use `revert_insertion()` on the `` element (NOT `suggest_deletion()`) +- **Completely rejecting another author's deletion**: Use `revert_deletion()` on the `` element to restore deleted content using tracked changes + +```python +# Minimal edit - change one word: "The report is monthly" → "The report is quarterly" +# Original: The report is monthly +node = doc["word/document.xml"].get_node(tag="w:r", contains="The report is monthly") +rpr = tags[0].toxml() if (tags := node.getElementsByTagName("w:rPr")) else "" +replacement = f'{rpr}The report is {rpr}monthly{rpr}quarterly' +doc["word/document.xml"].replace_node(node, replacement) + +# Minimal edit - change number: "within 30 days" → "within 45 days" +# Original: within 30 days +node = doc["word/document.xml"].get_node(tag="w:r", contains="within 30 days") +rpr = tags[0].toxml() if (tags := node.getElementsByTagName("w:rPr")) else "" +replacement = f'{rpr}within {rpr}30{rpr}45{rpr} days' +doc["word/document.xml"].replace_node(node, replacement) + +# Complete replacement - preserve formatting even when replacing all text +node = doc["word/document.xml"].get_node(tag="w:r", contains="apple") +rpr = tags[0].toxml() if (tags := node.getElementsByTagName("w:rPr")) else "" +replacement = f'{rpr}apple{rpr}banana orange' +doc["word/document.xml"].replace_node(node, replacement) + +# Insert new content (no attributes needed - auto-injected) +node = doc["word/document.xml"].get_node(tag="w:r", contains="existing text") +doc["word/document.xml"].insert_after(node, 'new text') + +# Partially delete another author's insertion +# Original: quarterly financial report +# Goal: Delete only "financial" to make it "quarterly report" +node = doc["word/document.xml"].get_node(tag="w:ins", attrs={"w:id": "5"}) +# IMPORTANT: Preserve w:author="Jane Smith" on the outer to maintain authorship +replacement = ''' + quarterly + financial + report +''' +doc["word/document.xml"].replace_node(node, replacement) + +# Change part of another author's insertion +# Original: in silence, safe and sound +# Goal: Change "safe and sound" to "soft and unbound" +node = doc["word/document.xml"].get_node(tag="w:ins", attrs={"w:id": "8"}) +replacement = f''' + in silence, + + + soft and unbound + + + safe and sound +''' +doc["word/document.xml"].replace_node(node, replacement) + +# Delete entire run (use only when deleting all content; use replace_node for partial deletions) +node = doc["word/document.xml"].get_node(tag="w:r", contains="text to delete") +doc["word/document.xml"].suggest_deletion(node) + +# Delete entire paragraph (in-place, handles both regular and numbered list paragraphs) +para = doc["word/document.xml"].get_node(tag="w:p", contains="paragraph to delete") +doc["word/document.xml"].suggest_deletion(para) + +# Add new numbered list item +target_para = doc["word/document.xml"].get_node(tag="w:p", contains="existing list item") +pPr = tags[0].toxml() if (tags := target_para.getElementsByTagName("w:pPr")) else "" +new_item = f'{pPr}New item' +tracked_para = DocxXMLEditor.suggest_paragraph(new_item) +doc["word/document.xml"].insert_after(target_para, tracked_para) +# Optional: add spacing paragraph before content for better visual separation +# spacing = DocxXMLEditor.suggest_paragraph('') +# doc["word/document.xml"].insert_after(target_para, spacing + tracked_para) +``` + +### Adding Comments + +```python +# Add comment spanning two existing tracked changes +# Note: w:id is auto-generated. Only search by w:id if you know it from XML inspection +start_node = doc["word/document.xml"].get_node(tag="w:del", attrs={"w:id": "1"}) +end_node = doc["word/document.xml"].get_node(tag="w:ins", attrs={"w:id": "2"}) +doc.add_comment(start=start_node, end=end_node, text="Explanation of this change") + +# Add comment on a paragraph +para = doc["word/document.xml"].get_node(tag="w:p", contains="paragraph text") +doc.add_comment(start=para, end=para, text="Comment on this paragraph") + +# Add comment on newly created tracked change +# First create the tracked change +node = doc["word/document.xml"].get_node(tag="w:r", contains="old") +new_nodes = doc["word/document.xml"].replace_node( + node, + 'oldnew' +) +# Then add comment on the newly created elements +# new_nodes[0] is the , new_nodes[1] is the +doc.add_comment(start=new_nodes[0], end=new_nodes[1], text="Changed old to new per requirements") + +# Reply to existing comment +doc.reply_to_comment(parent_comment_id=0, text="I agree with this change") +``` + +### Rejecting Tracked Changes + +**IMPORTANT**: Use `revert_insertion()` to reject insertions and `revert_deletion()` to restore deletions using tracked changes. Use `suggest_deletion()` only for regular unmarked content. + +```python +# Reject insertion (wraps it in deletion) +# Use this when another author inserted text that you want to delete +ins = doc["word/document.xml"].get_node(tag="w:ins", attrs={"w:id": "5"}) +nodes = doc["word/document.xml"].revert_insertion(ins) # Returns [ins] + +# Reject deletion (creates insertion to restore deleted content) +# Use this when another author deleted text that you want to restore +del_elem = doc["word/document.xml"].get_node(tag="w:del", attrs={"w:id": "3"}) +nodes = doc["word/document.xml"].revert_deletion(del_elem) # Returns [del_elem, new_ins] + +# Reject all insertions in a paragraph +para = doc["word/document.xml"].get_node(tag="w:p", contains="paragraph text") +nodes = doc["word/document.xml"].revert_insertion(para) # Returns [para] + +# Reject all deletions in a paragraph +para = doc["word/document.xml"].get_node(tag="w:p", contains="paragraph text") +nodes = doc["word/document.xml"].revert_deletion(para) # Returns [para] +``` + +### Inserting Images + +**CRITICAL**: The Document class works with a temporary copy at `doc.unpacked_path`. Always copy images to this temp directory, not the original unpacked folder. + +```python +from PIL import Image +import shutil, os + +# Initialize document first +doc = Document('unpacked') + +# Copy image and calculate full-width dimensions with aspect ratio +media_dir = os.path.join(doc.unpacked_path, 'word/media') +os.makedirs(media_dir, exist_ok=True) +shutil.copy('image.png', os.path.join(media_dir, 'image1.png')) +img = Image.open(os.path.join(media_dir, 'image1.png')) +width_emus = int(6.5 * 914400) # 6.5" usable width, 914400 EMUs/inch +height_emus = int(width_emus * img.size[1] / img.size[0]) + +# Add relationship and content type +rels_editor = doc['word/_rels/document.xml.rels'] +next_rid = rels_editor.get_next_rid() +rels_editor.append_to(rels_editor.dom.documentElement, + f'') +doc['[Content_Types].xml'].append_to(doc['[Content_Types].xml'].dom.documentElement, + '') + +# Insert image +node = doc["word/document.xml"].get_node(tag="w:p", line_number=100) +doc["word/document.xml"].insert_after(node, f''' + + + + + + + + + + + + + + + + + +''') +``` + +### Getting Nodes + +```python +# By text content +node = doc["word/document.xml"].get_node(tag="w:p", contains="specific text") + +# By line range +para = doc["word/document.xml"].get_node(tag="w:p", line_number=range(100, 150)) + +# By attributes +node = doc["word/document.xml"].get_node(tag="w:del", attrs={"w:id": "1"}) + +# By exact line number (must be line number where tag opens) +para = doc["word/document.xml"].get_node(tag="w:p", line_number=42) + +# Combine filters +node = doc["word/document.xml"].get_node(tag="w:r", line_number=range(40, 60), contains="text") + +# Disambiguate when text appears multiple times - add line_number range +node = doc["word/document.xml"].get_node(tag="w:r", contains="Section", line_number=range(2400, 2500)) +``` + +### Saving + +```python +# Save with automatic validation (copies back to original directory) +doc.save() # Validates by default, raises error if validation fails + +# Save to different location +doc.save('modified-unpacked') + +# Skip validation (debugging only - needing this in production indicates XML issues) +doc.save(validate=False) +``` + +### Direct DOM Manipulation + +For complex scenarios not covered by the library: + +```python +# Access any XML file +editor = doc["word/document.xml"] +editor = doc["word/comments.xml"] + +# Direct DOM access (defusedxml.minidom.Document) +node = doc["word/document.xml"].get_node(tag="w:p", line_number=5) +parent = node.parentNode +parent.removeChild(node) +parent.appendChild(node) # Move to end + +# General document manipulation (without tracked changes) +old_node = doc["word/document.xml"].get_node(tag="w:p", contains="original text") +doc["word/document.xml"].replace_node(old_node, "replacement text") + +# Multiple insertions - use return value to maintain order +node = doc["word/document.xml"].get_node(tag="w:r", line_number=100) +nodes = doc["word/document.xml"].insert_after(node, "A") +nodes = doc["word/document.xml"].insert_after(nodes[-1], "B") +nodes = doc["word/document.xml"].insert_after(nodes[-1], "C") +# Results in: original_node, A, B, C +``` + +## Tracked Changes (Redlining) + +**Use the Document class above for all tracked changes.** The patterns below are for reference when constructing replacement XML strings. + +### Validation Rules +The validator checks that the document text matches the original after reverting Claude's changes. This means: +- **NEVER modify text inside another author's `` or `` tags** +- **ALWAYS use nested deletions** to remove another author's insertions +- **Every edit must be properly tracked** with `` or `` tags + +### Tracked Change Patterns + +**CRITICAL RULES**: +1. Never modify the content inside another author's tracked changes. Always use nested deletions. +2. **XML Structure**: Always place `` and `` at paragraph level containing complete `` elements. Never nest inside `` elements - this creates invalid XML that breaks document processing. + +**Text Insertion:** +```xml + + + inserted text + + +``` + +**Text Deletion:** +```xml + + + deleted text + + +``` + +**Deleting Another Author's Insertion (MUST use nested structure):** +```xml + + + + monthly + + + + weekly + +``` + +**Restoring Another Author's Deletion:** +```xml + + + within 30 days + + + within 30 days + +``` \ No newline at end of file diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-chart.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-chart.xsd new file mode 100644 index 0000000..6454ef9 --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-chart.xsd @@ -0,0 +1,1499 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd new file mode 100644 index 0000000..afa4f46 --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd @@ -0,0 +1,146 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd new file mode 100644 index 0000000..64e66b8 --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd @@ -0,0 +1,1085 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd new file mode 100644 index 0000000..687eea8 --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd @@ -0,0 +1,11 @@ + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-main.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-main.xsd new file mode 100644 index 0000000..6ac81b0 --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-main.xsd @@ -0,0 +1,3081 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-picture.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-picture.xsd new file mode 100644 index 0000000..1dbf051 --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-picture.xsd @@ -0,0 +1,23 @@ + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd new file mode 100644 index 0000000..f1af17d --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd @@ -0,0 +1,185 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd new file mode 100644 index 0000000..0a185ab --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd @@ -0,0 +1,287 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/pml.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/pml.xsd new file mode 100644 index 0000000..14ef488 --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/pml.xsd @@ -0,0 +1,1676 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd new file mode 100644 index 0000000..c20f3bf --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd @@ -0,0 +1,28 @@ + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd new file mode 100644 index 0000000..ac60252 --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd @@ -0,0 +1,144 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd new file mode 100644 index 0000000..424b8ba --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd @@ -0,0 +1,174 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd new file mode 100644 index 0000000..2bddce2 --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd @@ -0,0 +1,25 @@ + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd new file mode 100644 index 0000000..8a8c18b --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd @@ -0,0 +1,18 @@ + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd new file mode 100644 index 0000000..5c42706 --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd @@ -0,0 +1,59 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd new file mode 100644 index 0000000..853c341 --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd @@ -0,0 +1,56 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd new file mode 100644 index 0000000..da835ee --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd @@ -0,0 +1,195 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-math.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-math.xsd new file mode 100644 index 0000000..87ad265 --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-math.xsd @@ -0,0 +1,582 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd new file mode 100644 index 0000000..9e86f1b --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd @@ -0,0 +1,25 @@ + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/sml.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/sml.xsd new file mode 100644 index 0000000..d0be42e --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/sml.xsd @@ -0,0 +1,4439 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-main.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-main.xsd new file mode 100644 index 0000000..8821dd1 --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-main.xsd @@ -0,0 +1,570 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd new file mode 100644 index 0000000..ca2575c --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd @@ -0,0 +1,509 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd new file mode 100644 index 0000000..dd079e6 --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd @@ -0,0 +1,12 @@ + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd new file mode 100644 index 0000000..3dd6cf6 --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd @@ -0,0 +1,108 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd new file mode 100644 index 0000000..f1041e3 --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd @@ -0,0 +1,96 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/wml.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/wml.xsd new file mode 100644 index 0000000..9c5b7a6 --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/wml.xsd @@ -0,0 +1,3646 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/xml.xsd b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/xml.xsd new file mode 100644 index 0000000..0f13678 --- /dev/null +++ b/skills/docx/ooxml/schemas/ISO-IEC29500-4_2016/xml.xsd @@ -0,0 +1,116 @@ + + + + + + See http://www.w3.org/XML/1998/namespace.html and + http://www.w3.org/TR/REC-xml for information about this namespace. + + This schema document describes the XML namespace, in a form + suitable for import by other schema documents. + + Note that local names in this namespace are intended to be defined + only by the World Wide Web Consortium or its subgroups. The + following names are currently defined in this namespace and should + not be used with conflicting semantics by any Working Group, + specification, or document instance: + + base (as an attribute name): denotes an attribute whose value + provides a URI to be used as the base for interpreting any + relative URIs in the scope of the element on which it + appears; its value is inherited. This name is reserved + by virtue of its definition in the XML Base specification. + + lang (as an attribute name): denotes an attribute whose value + is a language code for the natural language of the content of + any element; its value is inherited. This name is reserved + by virtue of its definition in the XML specification. + + space (as an attribute name): denotes an attribute whose + value is a keyword indicating what whitespace processing + discipline is intended for the content of the element; its + value is inherited. This name is reserved by virtue of its + definition in the XML specification. + + Father (in any context at all): denotes Jon Bosak, the chair of + the original XML Working Group. This name is reserved by + the following decision of the W3C XML Plenary and + XML Coordination groups: + + In appreciation for his vision, leadership and dedication + the W3C XML Plenary on this 10th day of February, 2000 + reserves for Jon Bosak in perpetuity the XML name + xml:Father + + + + + This schema defines attributes and an attribute group + suitable for use by + schemas wishing to allow xml:base, xml:lang or xml:space attributes + on elements they define. + + To enable this, such a schema must import this schema + for the XML namespace, e.g. as follows: + <schema . . .> + . . . + <import namespace="http://www.w3.org/XML/1998/namespace" + schemaLocation="http://www.w3.org/2001/03/xml.xsd"/> + + Subsequently, qualified reference to any of the attributes + or the group defined below will have the desired effect, e.g. + + <type . . .> + . . . + <attributeGroup ref="xml:specialAttrs"/> + + will define a type which will schema-validate an instance + element with any of those attributes + + + + In keeping with the XML Schema WG's standard versioning + policy, this schema document will persist at + http://www.w3.org/2001/03/xml.xsd. + At the date of issue it can also be found at + http://www.w3.org/2001/xml.xsd. + The schema document at that URI may however change in the future, + in order to remain compatible with the latest version of XML Schema + itself. In other words, if the XML Schema namespace changes, the version + of this document at + http://www.w3.org/2001/xml.xsd will change + accordingly; the version at + http://www.w3.org/2001/03/xml.xsd will not change. + + + + + + In due course, we should install the relevant ISO 2- and 3-letter + codes as the enumerated possible values . . . + + + + + + + + + + + + + + + See http://www.w3.org/TR/xmlbase/ for + information about this attribute. + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ecma/fouth-edition/opc-contentTypes.xsd b/skills/docx/ooxml/schemas/ecma/fouth-edition/opc-contentTypes.xsd new file mode 100644 index 0000000..a6de9d2 --- /dev/null +++ b/skills/docx/ooxml/schemas/ecma/fouth-edition/opc-contentTypes.xsd @@ -0,0 +1,42 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ecma/fouth-edition/opc-coreProperties.xsd b/skills/docx/ooxml/schemas/ecma/fouth-edition/opc-coreProperties.xsd new file mode 100644 index 0000000..10e978b --- /dev/null +++ b/skills/docx/ooxml/schemas/ecma/fouth-edition/opc-coreProperties.xsd @@ -0,0 +1,50 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ecma/fouth-edition/opc-digSig.xsd b/skills/docx/ooxml/schemas/ecma/fouth-edition/opc-digSig.xsd new file mode 100644 index 0000000..4248bf7 --- /dev/null +++ b/skills/docx/ooxml/schemas/ecma/fouth-edition/opc-digSig.xsd @@ -0,0 +1,49 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/ecma/fouth-edition/opc-relationships.xsd b/skills/docx/ooxml/schemas/ecma/fouth-edition/opc-relationships.xsd new file mode 100644 index 0000000..5649746 --- /dev/null +++ b/skills/docx/ooxml/schemas/ecma/fouth-edition/opc-relationships.xsd @@ -0,0 +1,33 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/mce/mc.xsd b/skills/docx/ooxml/schemas/mce/mc.xsd new file mode 100644 index 0000000..ef72545 --- /dev/null +++ b/skills/docx/ooxml/schemas/mce/mc.xsd @@ -0,0 +1,75 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/microsoft/wml-2010.xsd b/skills/docx/ooxml/schemas/microsoft/wml-2010.xsd new file mode 100644 index 0000000..f65f777 --- /dev/null +++ b/skills/docx/ooxml/schemas/microsoft/wml-2010.xsd @@ -0,0 +1,560 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/microsoft/wml-2012.xsd b/skills/docx/ooxml/schemas/microsoft/wml-2012.xsd new file mode 100644 index 0000000..6b00755 --- /dev/null +++ b/skills/docx/ooxml/schemas/microsoft/wml-2012.xsd @@ -0,0 +1,67 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/microsoft/wml-2018.xsd b/skills/docx/ooxml/schemas/microsoft/wml-2018.xsd new file mode 100644 index 0000000..f321d33 --- /dev/null +++ b/skills/docx/ooxml/schemas/microsoft/wml-2018.xsd @@ -0,0 +1,14 @@ + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/microsoft/wml-cex-2018.xsd b/skills/docx/ooxml/schemas/microsoft/wml-cex-2018.xsd new file mode 100644 index 0000000..364c6a9 --- /dev/null +++ b/skills/docx/ooxml/schemas/microsoft/wml-cex-2018.xsd @@ -0,0 +1,20 @@ + + + + + + + + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/microsoft/wml-cid-2016.xsd b/skills/docx/ooxml/schemas/microsoft/wml-cid-2016.xsd new file mode 100644 index 0000000..fed9d15 --- /dev/null +++ b/skills/docx/ooxml/schemas/microsoft/wml-cid-2016.xsd @@ -0,0 +1,13 @@ + + + + + + + + + + + + + diff --git a/skills/docx/ooxml/schemas/microsoft/wml-sdtdatahash-2020.xsd b/skills/docx/ooxml/schemas/microsoft/wml-sdtdatahash-2020.xsd new file mode 100644 index 0000000..680cf15 --- /dev/null +++ b/skills/docx/ooxml/schemas/microsoft/wml-sdtdatahash-2020.xsd @@ -0,0 +1,4 @@ + + + + diff --git a/skills/docx/ooxml/schemas/microsoft/wml-symex-2015.xsd b/skills/docx/ooxml/schemas/microsoft/wml-symex-2015.xsd new file mode 100644 index 0000000..89ada90 --- /dev/null +++ b/skills/docx/ooxml/schemas/microsoft/wml-symex-2015.xsd @@ -0,0 +1,8 @@ + + + + + + + + diff --git a/skills/docx/ooxml/scripts/pack.py b/skills/docx/ooxml/scripts/pack.py new file mode 100755 index 0000000..68bc088 --- /dev/null +++ b/skills/docx/ooxml/scripts/pack.py @@ -0,0 +1,159 @@ +#!/usr/bin/env python3 +""" +Tool to pack a directory into a .docx, .pptx, or .xlsx file with XML formatting undone. + +Example usage: + python pack.py [--force] +""" + +import argparse +import shutil +import subprocess +import sys +import tempfile +import defusedxml.minidom +import zipfile +from pathlib import Path + + +def main(): + parser = argparse.ArgumentParser(description="Pack a directory into an Office file") + parser.add_argument("input_directory", help="Unpacked Office document directory") + parser.add_argument("output_file", help="Output Office file (.docx/.pptx/.xlsx)") + parser.add_argument("--force", action="store_true", help="Skip validation") + args = parser.parse_args() + + try: + success = pack_document( + args.input_directory, args.output_file, validate=not args.force + ) + + # Show warning if validation was skipped + if args.force: + print("Warning: Skipped validation, file may be corrupt", file=sys.stderr) + # Exit with error if validation failed + elif not success: + print("Contents would produce a corrupt file.", file=sys.stderr) + print("Please validate XML before repacking.", file=sys.stderr) + print("Use --force to skip validation and pack anyway.", file=sys.stderr) + sys.exit(1) + + except ValueError as e: + sys.exit(f"Error: {e}") + + +def pack_document(input_dir, output_file, validate=False): + """Pack a directory into an Office file (.docx/.pptx/.xlsx). + + Args: + input_dir: Path to unpacked Office document directory + output_file: Path to output Office file + validate: If True, validates with soffice (default: False) + + Returns: + bool: True if successful, False if validation failed + """ + input_dir = Path(input_dir) + output_file = Path(output_file) + + if not input_dir.is_dir(): + raise ValueError(f"{input_dir} is not a directory") + if output_file.suffix.lower() not in {".docx", ".pptx", ".xlsx"}: + raise ValueError(f"{output_file} must be a .docx, .pptx, or .xlsx file") + + # Work in temporary directory to avoid modifying original + with tempfile.TemporaryDirectory() as temp_dir: + temp_content_dir = Path(temp_dir) / "content" + shutil.copytree(input_dir, temp_content_dir) + + # Process XML files to remove pretty-printing whitespace + for pattern in ["*.xml", "*.rels"]: + for xml_file in temp_content_dir.rglob(pattern): + condense_xml(xml_file) + + # Create final Office file as zip archive + output_file.parent.mkdir(parents=True, exist_ok=True) + with zipfile.ZipFile(output_file, "w", zipfile.ZIP_DEFLATED) as zf: + for f in temp_content_dir.rglob("*"): + if f.is_file(): + zf.write(f, f.relative_to(temp_content_dir)) + + # Validate if requested + if validate: + if not validate_document(output_file): + output_file.unlink() # Delete the corrupt file + return False + + return True + + +def validate_document(doc_path): + """Validate document by converting to HTML with soffice.""" + # Determine the correct filter based on file extension + match doc_path.suffix.lower(): + case ".docx": + filter_name = "html:HTML" + case ".pptx": + filter_name = "html:impress_html_Export" + case ".xlsx": + filter_name = "html:HTML (StarCalc)" + + with tempfile.TemporaryDirectory() as temp_dir: + try: + result = subprocess.run( + [ + "soffice", + "--headless", + "--convert-to", + filter_name, + "--outdir", + temp_dir, + str(doc_path), + ], + capture_output=True, + timeout=10, + text=True, + ) + if not (Path(temp_dir) / f"{doc_path.stem}.html").exists(): + error_msg = result.stderr.strip() or "Document validation failed" + print(f"Validation error: {error_msg}", file=sys.stderr) + return False + return True + except FileNotFoundError: + print("Warning: soffice not found. Skipping validation.", file=sys.stderr) + return True + except subprocess.TimeoutExpired: + print("Validation error: Timeout during conversion", file=sys.stderr) + return False + except Exception as e: + print(f"Validation error: {e}", file=sys.stderr) + return False + + +def condense_xml(xml_file): + """Strip unnecessary whitespace and remove comments.""" + with open(xml_file, "r", encoding="utf-8") as f: + dom = defusedxml.minidom.parse(f) + + # Process each element to remove whitespace and comments + for element in dom.getElementsByTagName("*"): + # Skip w:t elements and their processing + if element.tagName.endswith(":t"): + continue + + # Remove whitespace-only text nodes and comment nodes + for child in list(element.childNodes): + if ( + child.nodeType == child.TEXT_NODE + and child.nodeValue + and child.nodeValue.strip() == "" + ) or child.nodeType == child.COMMENT_NODE: + element.removeChild(child) + + # Write back the condensed XML + with open(xml_file, "wb") as f: + f.write(dom.toxml(encoding="UTF-8")) + + +if __name__ == "__main__": + main() diff --git a/skills/docx/ooxml/scripts/unpack.py b/skills/docx/ooxml/scripts/unpack.py new file mode 100755 index 0000000..4938798 --- /dev/null +++ b/skills/docx/ooxml/scripts/unpack.py @@ -0,0 +1,29 @@ +#!/usr/bin/env python3 +"""Unpack and format XML contents of Office files (.docx, .pptx, .xlsx)""" + +import random +import sys +import defusedxml.minidom +import zipfile +from pathlib import Path + +# Get command line arguments +assert len(sys.argv) == 3, "Usage: python unpack.py " +input_file, output_dir = sys.argv[1], sys.argv[2] + +# Extract and format +output_path = Path(output_dir) +output_path.mkdir(parents=True, exist_ok=True) +zipfile.ZipFile(input_file).extractall(output_path) + +# Pretty print all XML files +xml_files = list(output_path.rglob("*.xml")) + list(output_path.rglob("*.rels")) +for xml_file in xml_files: + content = xml_file.read_text(encoding="utf-8") + dom = defusedxml.minidom.parseString(content) + xml_file.write_bytes(dom.toprettyxml(indent=" ", encoding="ascii")) + +# For .docx files, suggest an RSID for tracked changes +if input_file.endswith(".docx"): + suggested_rsid = "".join(random.choices("0123456789ABCDEF", k=8)) + print(f"Suggested RSID for edit session: {suggested_rsid}") diff --git a/skills/docx/ooxml/scripts/validate.py b/skills/docx/ooxml/scripts/validate.py new file mode 100755 index 0000000..508c589 --- /dev/null +++ b/skills/docx/ooxml/scripts/validate.py @@ -0,0 +1,69 @@ +#!/usr/bin/env python3 +""" +Command line tool to validate Office document XML files against XSD schemas and tracked changes. + +Usage: + python validate.py --original +""" + +import argparse +import sys +from pathlib import Path + +from validation import DOCXSchemaValidator, PPTXSchemaValidator, RedliningValidator + + +def main(): + parser = argparse.ArgumentParser(description="Validate Office document XML files") + parser.add_argument( + "unpacked_dir", + help="Path to unpacked Office document directory", + ) + parser.add_argument( + "--original", + required=True, + help="Path to original file (.docx/.pptx/.xlsx)", + ) + parser.add_argument( + "-v", + "--verbose", + action="store_true", + help="Enable verbose output", + ) + args = parser.parse_args() + + # Validate paths + unpacked_dir = Path(args.unpacked_dir) + original_file = Path(args.original) + file_extension = original_file.suffix.lower() + assert unpacked_dir.is_dir(), f"Error: {unpacked_dir} is not a directory" + assert original_file.is_file(), f"Error: {original_file} is not a file" + assert file_extension in [".docx", ".pptx", ".xlsx"], ( + f"Error: {original_file} must be a .docx, .pptx, or .xlsx file" + ) + + # Run validations + match file_extension: + case ".docx": + validators = [DOCXSchemaValidator, RedliningValidator] + case ".pptx": + validators = [PPTXSchemaValidator] + case _: + print(f"Error: Validation not supported for file type {file_extension}") + sys.exit(1) + + # Run validators + success = True + for V in validators: + validator = V(unpacked_dir, original_file, verbose=args.verbose) + if not validator.validate(): + success = False + + if success: + print("All validations PASSED!") + + sys.exit(0 if success else 1) + + +if __name__ == "__main__": + main() diff --git a/skills/docx/ooxml/scripts/validation/__init__.py b/skills/docx/ooxml/scripts/validation/__init__.py new file mode 100644 index 0000000..db092ec --- /dev/null +++ b/skills/docx/ooxml/scripts/validation/__init__.py @@ -0,0 +1,15 @@ +""" +Validation modules for Word document processing. +""" + +from .base import BaseSchemaValidator +from .docx import DOCXSchemaValidator +from .pptx import PPTXSchemaValidator +from .redlining import RedliningValidator + +__all__ = [ + "BaseSchemaValidator", + "DOCXSchemaValidator", + "PPTXSchemaValidator", + "RedliningValidator", +] diff --git a/skills/docx/ooxml/scripts/validation/base.py b/skills/docx/ooxml/scripts/validation/base.py new file mode 100644 index 0000000..0681b19 --- /dev/null +++ b/skills/docx/ooxml/scripts/validation/base.py @@ -0,0 +1,951 @@ +""" +Base validator with common validation logic for document files. +""" + +import re +from pathlib import Path + +import lxml.etree + + +class BaseSchemaValidator: + """Base validator with common validation logic for document files.""" + + # Elements whose 'id' attributes must be unique within their file + # Format: element_name -> (attribute_name, scope) + # scope can be 'file' (unique within file) or 'global' (unique across all files) + UNIQUE_ID_REQUIREMENTS = { + # Word elements + "comment": ("id", "file"), # Comment IDs in comments.xml + "commentrangestart": ("id", "file"), # Must match comment IDs + "commentrangeend": ("id", "file"), # Must match comment IDs + "bookmarkstart": ("id", "file"), # Bookmark start IDs + "bookmarkend": ("id", "file"), # Bookmark end IDs + # Note: ins and del (track changes) can share IDs when part of same revision + # PowerPoint elements + "sldid": ("id", "file"), # Slide IDs in presentation.xml + "sldmasterid": ("id", "global"), # Slide master IDs must be globally unique + "sldlayoutid": ("id", "global"), # Slide layout IDs must be globally unique + "cm": ("authorid", "file"), # Comment author IDs + # Excel elements + "sheet": ("sheetid", "file"), # Sheet IDs in workbook.xml + "definedname": ("id", "file"), # Named range IDs + # Drawing/Shape elements (all formats) + "cxnsp": ("id", "file"), # Connection shape IDs + "sp": ("id", "file"), # Shape IDs + "pic": ("id", "file"), # Picture IDs + "grpsp": ("id", "file"), # Group shape IDs + } + + # Mapping of element names to expected relationship types + # Subclasses should override this with format-specific mappings + ELEMENT_RELATIONSHIP_TYPES = {} + + # Unified schema mappings for all Office document types + SCHEMA_MAPPINGS = { + # Document type specific schemas + "word": "ISO-IEC29500-4_2016/wml.xsd", # Word documents + "ppt": "ISO-IEC29500-4_2016/pml.xsd", # PowerPoint presentations + "xl": "ISO-IEC29500-4_2016/sml.xsd", # Excel spreadsheets + # Common file types + "[Content_Types].xml": "ecma/fouth-edition/opc-contentTypes.xsd", + "app.xml": "ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd", + "core.xml": "ecma/fouth-edition/opc-coreProperties.xsd", + "custom.xml": "ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd", + ".rels": "ecma/fouth-edition/opc-relationships.xsd", + # Word-specific files + "people.xml": "microsoft/wml-2012.xsd", + "commentsIds.xml": "microsoft/wml-cid-2016.xsd", + "commentsExtensible.xml": "microsoft/wml-cex-2018.xsd", + "commentsExtended.xml": "microsoft/wml-2012.xsd", + # Chart files (common across document types) + "chart": "ISO-IEC29500-4_2016/dml-chart.xsd", + # Theme files (common across document types) + "theme": "ISO-IEC29500-4_2016/dml-main.xsd", + # Drawing and media files + "drawing": "ISO-IEC29500-4_2016/dml-main.xsd", + } + + # Unified namespace constants + MC_NAMESPACE = "http://schemas.openxmlformats.org/markup-compatibility/2006" + XML_NAMESPACE = "http://www.w3.org/XML/1998/namespace" + + # Common OOXML namespaces used across validators + PACKAGE_RELATIONSHIPS_NAMESPACE = ( + "http://schemas.openxmlformats.org/package/2006/relationships" + ) + OFFICE_RELATIONSHIPS_NAMESPACE = ( + "http://schemas.openxmlformats.org/officeDocument/2006/relationships" + ) + CONTENT_TYPES_NAMESPACE = ( + "http://schemas.openxmlformats.org/package/2006/content-types" + ) + + # Folders where we should clean ignorable namespaces + MAIN_CONTENT_FOLDERS = {"word", "ppt", "xl"} + + # All allowed OOXML namespaces (superset of all document types) + OOXML_NAMESPACES = { + "http://schemas.openxmlformats.org/officeDocument/2006/math", + "http://schemas.openxmlformats.org/officeDocument/2006/relationships", + "http://schemas.openxmlformats.org/schemaLibrary/2006/main", + "http://schemas.openxmlformats.org/drawingml/2006/main", + "http://schemas.openxmlformats.org/drawingml/2006/chart", + "http://schemas.openxmlformats.org/drawingml/2006/chartDrawing", + "http://schemas.openxmlformats.org/drawingml/2006/diagram", + "http://schemas.openxmlformats.org/drawingml/2006/picture", + "http://schemas.openxmlformats.org/drawingml/2006/spreadsheetDrawing", + "http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing", + "http://schemas.openxmlformats.org/wordprocessingml/2006/main", + "http://schemas.openxmlformats.org/presentationml/2006/main", + "http://schemas.openxmlformats.org/spreadsheetml/2006/main", + "http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes", + "http://www.w3.org/XML/1998/namespace", + } + + def __init__(self, unpacked_dir, original_file, verbose=False): + self.unpacked_dir = Path(unpacked_dir).resolve() + self.original_file = Path(original_file) + self.verbose = verbose + + # Set schemas directory + self.schemas_dir = Path(__file__).parent.parent.parent / "schemas" + + # Get all XML and .rels files + patterns = ["*.xml", "*.rels"] + self.xml_files = [ + f for pattern in patterns for f in self.unpacked_dir.rglob(pattern) + ] + + if not self.xml_files: + print(f"Warning: No XML files found in {self.unpacked_dir}") + + def validate(self): + """Run all validation checks and return True if all pass.""" + raise NotImplementedError("Subclasses must implement the validate method") + + def validate_xml(self): + """Validate that all XML files are well-formed.""" + errors = [] + + for xml_file in self.xml_files: + try: + # Try to parse the XML file + lxml.etree.parse(str(xml_file)) + except lxml.etree.XMLSyntaxError as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {e.lineno}: {e.msg}" + ) + except Exception as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Unexpected error: {str(e)}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} XML violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All XML files are well-formed") + return True + + def validate_namespaces(self): + """Validate that namespace prefixes in Ignorable attributes are declared.""" + errors = [] + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + declared = set(root.nsmap.keys()) - {None} # Exclude default namespace + + for attr_val in [ + v for k, v in root.attrib.items() if k.endswith("Ignorable") + ]: + undeclared = set(attr_val.split()) - declared + errors.extend( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Namespace '{ns}' in Ignorable but not declared" + for ns in undeclared + ) + except lxml.etree.XMLSyntaxError: + continue + + if errors: + print(f"FAILED - {len(errors)} namespace issues:") + for error in errors: + print(error) + return False + if self.verbose: + print("PASSED - All namespace prefixes properly declared") + return True + + def validate_unique_ids(self): + """Validate that specific IDs are unique according to OOXML requirements.""" + errors = [] + global_ids = {} # Track globally unique IDs across all files + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + file_ids = {} # Track IDs that must be unique within this file + + # Remove all mc:AlternateContent elements from the tree + mc_elements = root.xpath( + ".//mc:AlternateContent", namespaces={"mc": self.MC_NAMESPACE} + ) + for elem in mc_elements: + elem.getparent().remove(elem) + + # Now check IDs in the cleaned tree + for elem in root.iter(): + # Get the element name without namespace + tag = ( + elem.tag.split("}")[-1].lower() + if "}" in elem.tag + else elem.tag.lower() + ) + + # Check if this element type has ID uniqueness requirements + if tag in self.UNIQUE_ID_REQUIREMENTS: + attr_name, scope = self.UNIQUE_ID_REQUIREMENTS[tag] + + # Look for the specified attribute + id_value = None + for attr, value in elem.attrib.items(): + attr_local = ( + attr.split("}")[-1].lower() + if "}" in attr + else attr.lower() + ) + if attr_local == attr_name: + id_value = value + break + + if id_value is not None: + if scope == "global": + # Check global uniqueness + if id_value in global_ids: + prev_file, prev_line, prev_tag = global_ids[ + id_value + ] + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: Global ID '{id_value}' in <{tag}> " + f"already used in {prev_file} at line {prev_line} in <{prev_tag}>" + ) + else: + global_ids[id_value] = ( + xml_file.relative_to(self.unpacked_dir), + elem.sourceline, + tag, + ) + elif scope == "file": + # Check file-level uniqueness + key = (tag, attr_name) + if key not in file_ids: + file_ids[key] = {} + + if id_value in file_ids[key]: + prev_line = file_ids[key][id_value] + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: Duplicate {attr_name}='{id_value}' in <{tag}> " + f"(first occurrence at line {prev_line})" + ) + else: + file_ids[key][id_value] = elem.sourceline + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} ID uniqueness violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All required IDs are unique") + return True + + def validate_file_references(self): + """ + Validate that all .rels files properly reference files and that all files are referenced. + """ + errors = [] + + # Find all .rels files + rels_files = list(self.unpacked_dir.rglob("*.rels")) + + if not rels_files: + if self.verbose: + print("PASSED - No .rels files found") + return True + + # Get all files in the unpacked directory (excluding reference files) + all_files = [] + for file_path in self.unpacked_dir.rglob("*"): + if ( + file_path.is_file() + and file_path.name != "[Content_Types].xml" + and not file_path.name.endswith(".rels") + ): # This file is not referenced by .rels + all_files.append(file_path.resolve()) + + # Track all files that are referenced by any .rels file + all_referenced_files = set() + + if self.verbose: + print( + f"Found {len(rels_files)} .rels files and {len(all_files)} target files" + ) + + # Check each .rels file + for rels_file in rels_files: + try: + # Parse relationships file + rels_root = lxml.etree.parse(str(rels_file)).getroot() + + # Get the directory where this .rels file is located + rels_dir = rels_file.parent + + # Find all relationships and their targets + referenced_files = set() + broken_refs = [] + + for rel in rels_root.findall( + ".//ns:Relationship", + namespaces={"ns": self.PACKAGE_RELATIONSHIPS_NAMESPACE}, + ): + target = rel.get("Target") + if target and not target.startswith( + ("http", "mailto:") + ): # Skip external URLs + # Resolve the target path relative to the .rels file location + if rels_file.name == ".rels": + # Root .rels file - targets are relative to unpacked_dir + target_path = self.unpacked_dir / target + else: + # Other .rels files - targets are relative to their parent's parent + # e.g., word/_rels/document.xml.rels -> targets relative to word/ + base_dir = rels_dir.parent + target_path = base_dir / target + + # Normalize the path and check if it exists + try: + target_path = target_path.resolve() + if target_path.exists() and target_path.is_file(): + referenced_files.add(target_path) + all_referenced_files.add(target_path) + else: + broken_refs.append((target, rel.sourceline)) + except (OSError, ValueError): + broken_refs.append((target, rel.sourceline)) + + # Report broken references + if broken_refs: + rel_path = rels_file.relative_to(self.unpacked_dir) + for broken_ref, line_num in broken_refs: + errors.append( + f" {rel_path}: Line {line_num}: Broken reference to {broken_ref}" + ) + + except Exception as e: + rel_path = rels_file.relative_to(self.unpacked_dir) + errors.append(f" Error parsing {rel_path}: {e}") + + # Check for unreferenced files (files that exist but are not referenced anywhere) + unreferenced_files = set(all_files) - all_referenced_files + + if unreferenced_files: + for unref_file in sorted(unreferenced_files): + unref_rel_path = unref_file.relative_to(self.unpacked_dir) + errors.append(f" Unreferenced file: {unref_rel_path}") + + if errors: + print(f"FAILED - Found {len(errors)} relationship validation errors:") + for error in errors: + print(error) + print( + "CRITICAL: These errors will cause the document to appear corrupt. " + + "Broken references MUST be fixed, " + + "and unreferenced files MUST be referenced or removed." + ) + return False + else: + if self.verbose: + print( + "PASSED - All references are valid and all files are properly referenced" + ) + return True + + def validate_all_relationship_ids(self): + """ + Validate that all r:id attributes in XML files reference existing IDs + in their corresponding .rels files, and optionally validate relationship types. + """ + import lxml.etree + + errors = [] + + # Process each XML file that might contain r:id references + for xml_file in self.xml_files: + # Skip .rels files themselves + if xml_file.suffix == ".rels": + continue + + # Determine the corresponding .rels file + # For dir/file.xml, it's dir/_rels/file.xml.rels + rels_dir = xml_file.parent / "_rels" + rels_file = rels_dir / f"{xml_file.name}.rels" + + # Skip if there's no corresponding .rels file (that's okay) + if not rels_file.exists(): + continue + + try: + # Parse the .rels file to get valid relationship IDs and their types + rels_root = lxml.etree.parse(str(rels_file)).getroot() + rid_to_type = {} + + for rel in rels_root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rid = rel.get("Id") + rel_type = rel.get("Type", "") + if rid: + # Check for duplicate rIds + if rid in rid_to_type: + rels_rel_path = rels_file.relative_to(self.unpacked_dir) + errors.append( + f" {rels_rel_path}: Line {rel.sourceline}: " + f"Duplicate relationship ID '{rid}' (IDs must be unique)" + ) + # Extract just the type name from the full URL + type_name = ( + rel_type.split("/")[-1] if "/" in rel_type else rel_type + ) + rid_to_type[rid] = type_name + + # Parse the XML file to find all r:id references + xml_root = lxml.etree.parse(str(xml_file)).getroot() + + # Find all elements with r:id attributes + for elem in xml_root.iter(): + # Check for r:id attribute (relationship ID) + rid_attr = elem.get(f"{{{self.OFFICE_RELATIONSHIPS_NAMESPACE}}}id") + if rid_attr: + xml_rel_path = xml_file.relative_to(self.unpacked_dir) + elem_name = ( + elem.tag.split("}")[-1] if "}" in elem.tag else elem.tag + ) + + # Check if the ID exists + if rid_attr not in rid_to_type: + errors.append( + f" {xml_rel_path}: Line {elem.sourceline}: " + f"<{elem_name}> references non-existent relationship '{rid_attr}' " + f"(valid IDs: {', '.join(sorted(rid_to_type.keys())[:5])}{'...' if len(rid_to_type) > 5 else ''})" + ) + # Check if we have type expectations for this element + elif self.ELEMENT_RELATIONSHIP_TYPES: + expected_type = self._get_expected_relationship_type( + elem_name + ) + if expected_type: + actual_type = rid_to_type[rid_attr] + # Check if the actual type matches or contains the expected type + if expected_type not in actual_type.lower(): + errors.append( + f" {xml_rel_path}: Line {elem.sourceline}: " + f"<{elem_name}> references '{rid_attr}' which points to '{actual_type}' " + f"but should point to a '{expected_type}' relationship" + ) + + except Exception as e: + xml_rel_path = xml_file.relative_to(self.unpacked_dir) + errors.append(f" Error processing {xml_rel_path}: {e}") + + if errors: + print(f"FAILED - Found {len(errors)} relationship ID reference errors:") + for error in errors: + print(error) + print("\nThese ID mismatches will cause the document to appear corrupt!") + return False + else: + if self.verbose: + print("PASSED - All relationship ID references are valid") + return True + + def _get_expected_relationship_type(self, element_name): + """ + Get the expected relationship type for an element. + First checks the explicit mapping, then tries pattern detection. + """ + # Normalize element name to lowercase + elem_lower = element_name.lower() + + # Check explicit mapping first + if elem_lower in self.ELEMENT_RELATIONSHIP_TYPES: + return self.ELEMENT_RELATIONSHIP_TYPES[elem_lower] + + # Try pattern detection for common patterns + # Pattern 1: Elements ending in "Id" often expect a relationship of the prefix type + if elem_lower.endswith("id") and len(elem_lower) > 2: + # e.g., "sldId" -> "sld", "sldMasterId" -> "sldMaster" + prefix = elem_lower[:-2] # Remove "id" + # Check if this might be a compound like "sldMasterId" + if prefix.endswith("master"): + return prefix.lower() + elif prefix.endswith("layout"): + return prefix.lower() + else: + # Simple case like "sldId" -> "slide" + # Common transformations + if prefix == "sld": + return "slide" + return prefix.lower() + + # Pattern 2: Elements ending in "Reference" expect a relationship of the prefix type + if elem_lower.endswith("reference") and len(elem_lower) > 9: + prefix = elem_lower[:-9] # Remove "reference" + return prefix.lower() + + return None + + def validate_content_types(self): + """Validate that all content files are properly declared in [Content_Types].xml.""" + errors = [] + + # Find [Content_Types].xml file + content_types_file = self.unpacked_dir / "[Content_Types].xml" + if not content_types_file.exists(): + print("FAILED - [Content_Types].xml file not found") + return False + + try: + # Parse and get all declared parts and extensions + root = lxml.etree.parse(str(content_types_file)).getroot() + declared_parts = set() + declared_extensions = set() + + # Get Override declarations (specific files) + for override in root.findall( + f".//{{{self.CONTENT_TYPES_NAMESPACE}}}Override" + ): + part_name = override.get("PartName") + if part_name is not None: + declared_parts.add(part_name.lstrip("/")) + + # Get Default declarations (by extension) + for default in root.findall( + f".//{{{self.CONTENT_TYPES_NAMESPACE}}}Default" + ): + extension = default.get("Extension") + if extension is not None: + declared_extensions.add(extension.lower()) + + # Root elements that require content type declaration + declarable_roots = { + "sld", + "sldLayout", + "sldMaster", + "presentation", # PowerPoint + "document", # Word + "workbook", + "worksheet", # Excel + "theme", # Common + } + + # Common media file extensions that should be declared + media_extensions = { + "png": "image/png", + "jpg": "image/jpeg", + "jpeg": "image/jpeg", + "gif": "image/gif", + "bmp": "image/bmp", + "tiff": "image/tiff", + "wmf": "image/x-wmf", + "emf": "image/x-emf", + } + + # Get all files in the unpacked directory + all_files = list(self.unpacked_dir.rglob("*")) + all_files = [f for f in all_files if f.is_file()] + + # Check all XML files for Override declarations + for xml_file in self.xml_files: + path_str = str(xml_file.relative_to(self.unpacked_dir)).replace( + "\\", "/" + ) + + # Skip non-content files + if any( + skip in path_str + for skip in [".rels", "[Content_Types]", "docProps/", "_rels/"] + ): + continue + + try: + root_tag = lxml.etree.parse(str(xml_file)).getroot().tag + root_name = root_tag.split("}")[-1] if "}" in root_tag else root_tag + + if root_name in declarable_roots and path_str not in declared_parts: + errors.append( + f" {path_str}: File with <{root_name}> root not declared in [Content_Types].xml" + ) + + except Exception: + continue # Skip unparseable files + + # Check all non-XML files for Default extension declarations + for file_path in all_files: + # Skip XML files and metadata files (already checked above) + if file_path.suffix.lower() in {".xml", ".rels"}: + continue + if file_path.name == "[Content_Types].xml": + continue + if "_rels" in file_path.parts or "docProps" in file_path.parts: + continue + + extension = file_path.suffix.lstrip(".").lower() + if extension and extension not in declared_extensions: + # Check if it's a known media extension that should be declared + if extension in media_extensions: + relative_path = file_path.relative_to(self.unpacked_dir) + errors.append( + f' {relative_path}: File with extension \'{extension}\' not declared in [Content_Types].xml - should add: ' + ) + + except Exception as e: + errors.append(f" Error parsing [Content_Types].xml: {e}") + + if errors: + print(f"FAILED - Found {len(errors)} content type declaration errors:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print( + "PASSED - All content files are properly declared in [Content_Types].xml" + ) + return True + + def validate_file_against_xsd(self, xml_file, verbose=False): + """Validate a single XML file against XSD schema, comparing with original. + + Args: + xml_file: Path to XML file to validate + verbose: Enable verbose output + + Returns: + tuple: (is_valid, new_errors_set) where is_valid is True/False/None (skipped) + """ + # Resolve both paths to handle symlinks + xml_file = Path(xml_file).resolve() + unpacked_dir = self.unpacked_dir.resolve() + + # Validate current file + is_valid, current_errors = self._validate_single_file_xsd( + xml_file, unpacked_dir + ) + + if is_valid is None: + return None, set() # Skipped + elif is_valid: + return True, set() # Valid, no errors + + # Get errors from original file for this specific file + original_errors = self._get_original_file_errors(xml_file) + + # Compare with original (both are guaranteed to be sets here) + assert current_errors is not None + new_errors = current_errors - original_errors + + if new_errors: + if verbose: + relative_path = xml_file.relative_to(unpacked_dir) + print(f"FAILED - {relative_path}: {len(new_errors)} new error(s)") + for error in list(new_errors)[:3]: + truncated = error[:250] + "..." if len(error) > 250 else error + print(f" - {truncated}") + return False, new_errors + else: + # All errors existed in original + if verbose: + print( + f"PASSED - No new errors (original had {len(current_errors)} errors)" + ) + return True, set() + + def validate_against_xsd(self): + """Validate XML files against XSD schemas, showing only new errors compared to original.""" + new_errors = [] + original_error_count = 0 + valid_count = 0 + skipped_count = 0 + + for xml_file in self.xml_files: + relative_path = str(xml_file.relative_to(self.unpacked_dir)) + is_valid, new_file_errors = self.validate_file_against_xsd( + xml_file, verbose=False + ) + + if is_valid is None: + skipped_count += 1 + continue + elif is_valid and not new_file_errors: + valid_count += 1 + continue + elif is_valid: + # Had errors but all existed in original + original_error_count += 1 + valid_count += 1 + continue + + # Has new errors + new_errors.append(f" {relative_path}: {len(new_file_errors)} new error(s)") + for error in list(new_file_errors)[:3]: # Show first 3 errors + new_errors.append( + f" - {error[:250]}..." if len(error) > 250 else f" - {error}" + ) + + # Print summary + if self.verbose: + print(f"Validated {len(self.xml_files)} files:") + print(f" - Valid: {valid_count}") + print(f" - Skipped (no schema): {skipped_count}") + if original_error_count: + print(f" - With original errors (ignored): {original_error_count}") + print( + f" - With NEW errors: {len(new_errors) > 0 and len([e for e in new_errors if not e.startswith(' ')]) or 0}" + ) + + if new_errors: + print("\nFAILED - Found NEW validation errors:") + for error in new_errors: + print(error) + return False + else: + if self.verbose: + print("\nPASSED - No new XSD validation errors introduced") + return True + + def _get_schema_path(self, xml_file): + """Determine the appropriate schema path for an XML file.""" + # Check exact filename match + if xml_file.name in self.SCHEMA_MAPPINGS: + return self.schemas_dir / self.SCHEMA_MAPPINGS[xml_file.name] + + # Check .rels files + if xml_file.suffix == ".rels": + return self.schemas_dir / self.SCHEMA_MAPPINGS[".rels"] + + # Check chart files + if "charts/" in str(xml_file) and xml_file.name.startswith("chart"): + return self.schemas_dir / self.SCHEMA_MAPPINGS["chart"] + + # Check theme files + if "theme/" in str(xml_file) and xml_file.name.startswith("theme"): + return self.schemas_dir / self.SCHEMA_MAPPINGS["theme"] + + # Check if file is in a main content folder and use appropriate schema + if xml_file.parent.name in self.MAIN_CONTENT_FOLDERS: + return self.schemas_dir / self.SCHEMA_MAPPINGS[xml_file.parent.name] + + return None + + def _clean_ignorable_namespaces(self, xml_doc): + """Remove attributes and elements not in allowed namespaces.""" + # Create a clean copy + xml_string = lxml.etree.tostring(xml_doc, encoding="unicode") + xml_copy = lxml.etree.fromstring(xml_string) + + # Remove attributes not in allowed namespaces + for elem in xml_copy.iter(): + attrs_to_remove = [] + + for attr in elem.attrib: + # Check if attribute is from a namespace other than allowed ones + if "{" in attr: + ns = attr.split("}")[0][1:] + if ns not in self.OOXML_NAMESPACES: + attrs_to_remove.append(attr) + + # Remove collected attributes + for attr in attrs_to_remove: + del elem.attrib[attr] + + # Remove elements not in allowed namespaces + self._remove_ignorable_elements(xml_copy) + + return lxml.etree.ElementTree(xml_copy) + + def _remove_ignorable_elements(self, root): + """Recursively remove all elements not in allowed namespaces.""" + elements_to_remove = [] + + # Find elements to remove + for elem in list(root): + # Skip non-element nodes (comments, processing instructions, etc.) + if not hasattr(elem, "tag") or callable(elem.tag): + continue + + tag_str = str(elem.tag) + if tag_str.startswith("{"): + ns = tag_str.split("}")[0][1:] + if ns not in self.OOXML_NAMESPACES: + elements_to_remove.append(elem) + continue + + # Recursively clean child elements + self._remove_ignorable_elements(elem) + + # Remove collected elements + for elem in elements_to_remove: + root.remove(elem) + + def _preprocess_for_mc_ignorable(self, xml_doc): + """Preprocess XML to handle mc:Ignorable attribute properly.""" + # Remove mc:Ignorable attributes before validation + root = xml_doc.getroot() + + # Remove mc:Ignorable attribute from root + if f"{{{self.MC_NAMESPACE}}}Ignorable" in root.attrib: + del root.attrib[f"{{{self.MC_NAMESPACE}}}Ignorable"] + + return xml_doc + + def _validate_single_file_xsd(self, xml_file, base_path): + """Validate a single XML file against XSD schema. Returns (is_valid, errors_set).""" + schema_path = self._get_schema_path(xml_file) + if not schema_path: + return None, None # Skip file + + try: + # Load schema + with open(schema_path, "rb") as xsd_file: + parser = lxml.etree.XMLParser() + xsd_doc = lxml.etree.parse( + xsd_file, parser=parser, base_url=str(schema_path) + ) + schema = lxml.etree.XMLSchema(xsd_doc) + + # Load and preprocess XML + with open(xml_file, "r") as f: + xml_doc = lxml.etree.parse(f) + + xml_doc, _ = self._remove_template_tags_from_text_nodes(xml_doc) + xml_doc = self._preprocess_for_mc_ignorable(xml_doc) + + # Clean ignorable namespaces if needed + relative_path = xml_file.relative_to(base_path) + if ( + relative_path.parts + and relative_path.parts[0] in self.MAIN_CONTENT_FOLDERS + ): + xml_doc = self._clean_ignorable_namespaces(xml_doc) + + # Validate + if schema.validate(xml_doc): + return True, set() + else: + errors = set() + for error in schema.error_log: + # Store normalized error message (without line numbers for comparison) + errors.add(error.message) + return False, errors + + except Exception as e: + return False, {str(e)} + + def _get_original_file_errors(self, xml_file): + """Get XSD validation errors from a single file in the original document. + + Args: + xml_file: Path to the XML file in unpacked_dir to check + + Returns: + set: Set of error messages from the original file + """ + import tempfile + import zipfile + + # Resolve both paths to handle symlinks (e.g., /var vs /private/var on macOS) + xml_file = Path(xml_file).resolve() + unpacked_dir = self.unpacked_dir.resolve() + relative_path = xml_file.relative_to(unpacked_dir) + + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + # Extract original file + with zipfile.ZipFile(self.original_file, "r") as zip_ref: + zip_ref.extractall(temp_path) + + # Find corresponding file in original + original_xml_file = temp_path / relative_path + + if not original_xml_file.exists(): + # File didn't exist in original, so no original errors + return set() + + # Validate the specific file in original + is_valid, errors = self._validate_single_file_xsd( + original_xml_file, temp_path + ) + return errors if errors else set() + + def _remove_template_tags_from_text_nodes(self, xml_doc): + """Remove template tags from XML text nodes and collect warnings. + + Template tags follow the pattern {{ ... }} and are used as placeholders + for content replacement. They should be removed from text content before + XSD validation while preserving XML structure. + + Returns: + tuple: (cleaned_xml_doc, warnings_list) + """ + warnings = [] + template_pattern = re.compile(r"\{\{[^}]*\}\}") + + # Create a copy of the document to avoid modifying the original + xml_string = lxml.etree.tostring(xml_doc, encoding="unicode") + xml_copy = lxml.etree.fromstring(xml_string) + + def process_text_content(text, content_type): + if not text: + return text + matches = list(template_pattern.finditer(text)) + if matches: + for match in matches: + warnings.append( + f"Found template tag in {content_type}: {match.group()}" + ) + return template_pattern.sub("", text) + return text + + # Process all text nodes in the document + for elem in xml_copy.iter(): + # Skip processing if this is a w:t element + if not hasattr(elem, "tag") or callable(elem.tag): + continue + tag_str = str(elem.tag) + if tag_str.endswith("}t") or tag_str == "t": + continue + + elem.text = process_text_content(elem.text, "text content") + elem.tail = process_text_content(elem.tail, "tail content") + + return lxml.etree.ElementTree(xml_copy), warnings + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/skills/docx/ooxml/scripts/validation/docx.py b/skills/docx/ooxml/scripts/validation/docx.py new file mode 100644 index 0000000..602c470 --- /dev/null +++ b/skills/docx/ooxml/scripts/validation/docx.py @@ -0,0 +1,274 @@ +""" +Validator for Word document XML files against XSD schemas. +""" + +import re +import tempfile +import zipfile + +import lxml.etree + +from .base import BaseSchemaValidator + + +class DOCXSchemaValidator(BaseSchemaValidator): + """Validator for Word document XML files against XSD schemas.""" + + # Word-specific namespace + WORD_2006_NAMESPACE = "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + + # Word-specific element to relationship type mappings + # Start with empty mapping - add specific cases as we discover them + ELEMENT_RELATIONSHIP_TYPES = {} + + def validate(self): + """Run all validation checks and return True if all pass.""" + # Test 0: XML well-formedness + if not self.validate_xml(): + return False + + # Test 1: Namespace declarations + all_valid = True + if not self.validate_namespaces(): + all_valid = False + + # Test 2: Unique IDs + if not self.validate_unique_ids(): + all_valid = False + + # Test 3: Relationship and file reference validation + if not self.validate_file_references(): + all_valid = False + + # Test 4: Content type declarations + if not self.validate_content_types(): + all_valid = False + + # Test 5: XSD schema validation + if not self.validate_against_xsd(): + all_valid = False + + # Test 6: Whitespace preservation + if not self.validate_whitespace_preservation(): + all_valid = False + + # Test 7: Deletion validation + if not self.validate_deletions(): + all_valid = False + + # Test 8: Insertion validation + if not self.validate_insertions(): + all_valid = False + + # Test 9: Relationship ID reference validation + if not self.validate_all_relationship_ids(): + all_valid = False + + # Count and compare paragraphs + self.compare_paragraph_counts() + + return all_valid + + def validate_whitespace_preservation(self): + """ + Validate that w:t elements with whitespace have xml:space='preserve'. + """ + errors = [] + + for xml_file in self.xml_files: + # Only check document.xml files + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + + # Find all w:t elements + for elem in root.iter(f"{{{self.WORD_2006_NAMESPACE}}}t"): + if elem.text: + text = elem.text + # Check if text starts or ends with whitespace + if re.match(r"^\s.*", text) or re.match(r".*\s$", text): + # Check if xml:space="preserve" attribute exists + xml_space_attr = f"{{{self.XML_NAMESPACE}}}space" + if ( + xml_space_attr not in elem.attrib + or elem.attrib[xml_space_attr] != "preserve" + ): + # Show a preview of the text + text_preview = ( + repr(text)[:50] + "..." + if len(repr(text)) > 50 + else repr(text) + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: w:t element with whitespace missing xml:space='preserve': {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} whitespace preservation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All whitespace is properly preserved") + return True + + def validate_deletions(self): + """ + Validate that w:t elements are not within w:del elements. + For some reason, XSD validation does not catch this, so we do it manually. + """ + errors = [] + + for xml_file in self.xml_files: + # Only check document.xml files + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + + # Find all w:t elements that are descendants of w:del elements + namespaces = {"w": self.WORD_2006_NAMESPACE} + xpath_expression = ".//w:del//w:t" + problematic_t_elements = root.xpath( + xpath_expression, namespaces=namespaces + ) + for t_elem in problematic_t_elements: + if t_elem.text: + # Show a preview of the text + text_preview = ( + repr(t_elem.text)[:50] + "..." + if len(repr(t_elem.text)) > 50 + else repr(t_elem.text) + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {t_elem.sourceline}: found within : {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} deletion validation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - No w:t elements found within w:del elements") + return True + + def count_paragraphs_in_unpacked(self): + """Count the number of paragraphs in the unpacked document.""" + count = 0 + + for xml_file in self.xml_files: + # Only check document.xml files + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + # Count all w:p elements + paragraphs = root.findall(f".//{{{self.WORD_2006_NAMESPACE}}}p") + count = len(paragraphs) + except Exception as e: + print(f"Error counting paragraphs in unpacked document: {e}") + + return count + + def count_paragraphs_in_original(self): + """Count the number of paragraphs in the original docx file.""" + count = 0 + + try: + # Create temporary directory to unpack original + with tempfile.TemporaryDirectory() as temp_dir: + # Unpack original docx + with zipfile.ZipFile(self.original_file, "r") as zip_ref: + zip_ref.extractall(temp_dir) + + # Parse document.xml + doc_xml_path = temp_dir + "/word/document.xml" + root = lxml.etree.parse(doc_xml_path).getroot() + + # Count all w:p elements + paragraphs = root.findall(f".//{{{self.WORD_2006_NAMESPACE}}}p") + count = len(paragraphs) + + except Exception as e: + print(f"Error counting paragraphs in original document: {e}") + + return count + + def validate_insertions(self): + """ + Validate that w:delText elements are not within w:ins elements. + w:delText is only allowed in w:ins if nested within a w:del. + """ + errors = [] + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + namespaces = {"w": self.WORD_2006_NAMESPACE} + + # Find w:delText in w:ins that are NOT within w:del + invalid_elements = root.xpath( + ".//w:ins//w:delText[not(ancestor::w:del)]", + namespaces=namespaces + ) + + for elem in invalid_elements: + text_preview = ( + repr(elem.text or "")[:50] + "..." + if len(repr(elem.text or "")) > 50 + else repr(elem.text or "") + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: within : {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} insertion validation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - No w:delText elements within w:ins elements") + return True + + def compare_paragraph_counts(self): + """Compare paragraph counts between original and new document.""" + original_count = self.count_paragraphs_in_original() + new_count = self.count_paragraphs_in_unpacked() + + diff = new_count - original_count + diff_str = f"+{diff}" if diff > 0 else str(diff) + print(f"\nParagraphs: {original_count} → {new_count} ({diff_str})") + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/skills/docx/ooxml/scripts/validation/pptx.py b/skills/docx/ooxml/scripts/validation/pptx.py new file mode 100644 index 0000000..66d5b1e --- /dev/null +++ b/skills/docx/ooxml/scripts/validation/pptx.py @@ -0,0 +1,315 @@ +""" +Validator for PowerPoint presentation XML files against XSD schemas. +""" + +import re + +from .base import BaseSchemaValidator + + +class PPTXSchemaValidator(BaseSchemaValidator): + """Validator for PowerPoint presentation XML files against XSD schemas.""" + + # PowerPoint presentation namespace + PRESENTATIONML_NAMESPACE = ( + "http://schemas.openxmlformats.org/presentationml/2006/main" + ) + + # PowerPoint-specific element to relationship type mappings + ELEMENT_RELATIONSHIP_TYPES = { + "sldid": "slide", + "sldmasterid": "slidemaster", + "notesmasterid": "notesmaster", + "sldlayoutid": "slidelayout", + "themeid": "theme", + "tablestyleid": "tablestyles", + } + + def validate(self): + """Run all validation checks and return True if all pass.""" + # Test 0: XML well-formedness + if not self.validate_xml(): + return False + + # Test 1: Namespace declarations + all_valid = True + if not self.validate_namespaces(): + all_valid = False + + # Test 2: Unique IDs + if not self.validate_unique_ids(): + all_valid = False + + # Test 3: UUID ID validation + if not self.validate_uuid_ids(): + all_valid = False + + # Test 4: Relationship and file reference validation + if not self.validate_file_references(): + all_valid = False + + # Test 5: Slide layout ID validation + if not self.validate_slide_layout_ids(): + all_valid = False + + # Test 6: Content type declarations + if not self.validate_content_types(): + all_valid = False + + # Test 7: XSD schema validation + if not self.validate_against_xsd(): + all_valid = False + + # Test 8: Notes slide reference validation + if not self.validate_notes_slide_references(): + all_valid = False + + # Test 9: Relationship ID reference validation + if not self.validate_all_relationship_ids(): + all_valid = False + + # Test 10: Duplicate slide layout references validation + if not self.validate_no_duplicate_slide_layouts(): + all_valid = False + + return all_valid + + def validate_uuid_ids(self): + """Validate that ID attributes that look like UUIDs contain only hex values.""" + import lxml.etree + + errors = [] + # UUID pattern: 8-4-4-4-12 hex digits with optional braces/hyphens + uuid_pattern = re.compile( + r"^[\{\(]?[0-9A-Fa-f]{8}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{12}[\}\)]?$" + ) + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + + # Check all elements for ID attributes + for elem in root.iter(): + for attr, value in elem.attrib.items(): + # Check if this is an ID attribute + attr_name = attr.split("}")[-1].lower() + if attr_name == "id" or attr_name.endswith("id"): + # Check if value looks like a UUID (has the right length and pattern structure) + if self._looks_like_uuid(value): + # Validate that it contains only hex characters in the right positions + if not uuid_pattern.match(value): + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: ID '{value}' appears to be a UUID but contains invalid hex characters" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} UUID ID validation errors:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All UUID-like IDs contain valid hex values") + return True + + def _looks_like_uuid(self, value): + """Check if a value has the general structure of a UUID.""" + # Remove common UUID delimiters + clean_value = value.strip("{}()").replace("-", "") + # Check if it's 32 hex-like characters (could include invalid hex chars) + return len(clean_value) == 32 and all(c.isalnum() for c in clean_value) + + def validate_slide_layout_ids(self): + """Validate that sldLayoutId elements in slide masters reference valid slide layouts.""" + import lxml.etree + + errors = [] + + # Find all slide master files + slide_masters = list(self.unpacked_dir.glob("ppt/slideMasters/*.xml")) + + if not slide_masters: + if self.verbose: + print("PASSED - No slide masters found") + return True + + for slide_master in slide_masters: + try: + # Parse the slide master file + root = lxml.etree.parse(str(slide_master)).getroot() + + # Find the corresponding _rels file for this slide master + rels_file = slide_master.parent / "_rels" / f"{slide_master.name}.rels" + + if not rels_file.exists(): + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: " + f"Missing relationships file: {rels_file.relative_to(self.unpacked_dir)}" + ) + continue + + # Parse the relationships file + rels_root = lxml.etree.parse(str(rels_file)).getroot() + + # Build a set of valid relationship IDs that point to slide layouts + valid_layout_rids = set() + for rel in rels_root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rel_type = rel.get("Type", "") + if "slideLayout" in rel_type: + valid_layout_rids.add(rel.get("Id")) + + # Find all sldLayoutId elements in the slide master + for sld_layout_id in root.findall( + f".//{{{self.PRESENTATIONML_NAMESPACE}}}sldLayoutId" + ): + r_id = sld_layout_id.get( + f"{{{self.OFFICE_RELATIONSHIPS_NAMESPACE}}}id" + ) + layout_id = sld_layout_id.get("id") + + if r_id and r_id not in valid_layout_rids: + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: " + f"Line {sld_layout_id.sourceline}: sldLayoutId with id='{layout_id}' " + f"references r:id='{r_id}' which is not found in slide layout relationships" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} slide layout ID validation errors:") + for error in errors: + print(error) + print( + "Remove invalid references or add missing slide layouts to the relationships file." + ) + return False + else: + if self.verbose: + print("PASSED - All slide layout IDs reference valid slide layouts") + return True + + def validate_no_duplicate_slide_layouts(self): + """Validate that each slide has exactly one slideLayout reference.""" + import lxml.etree + + errors = [] + slide_rels_files = list(self.unpacked_dir.glob("ppt/slides/_rels/*.xml.rels")) + + for rels_file in slide_rels_files: + try: + root = lxml.etree.parse(str(rels_file)).getroot() + + # Find all slideLayout relationships + layout_rels = [ + rel + for rel in root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ) + if "slideLayout" in rel.get("Type", "") + ] + + if len(layout_rels) > 1: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: has {len(layout_rels)} slideLayout references" + ) + + except Exception as e: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print("FAILED - Found slides with duplicate slideLayout references:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All slides have exactly one slideLayout reference") + return True + + def validate_notes_slide_references(self): + """Validate that each notesSlide file is referenced by only one slide.""" + import lxml.etree + + errors = [] + notes_slide_references = {} # Track which slides reference each notesSlide + + # Find all slide relationship files + slide_rels_files = list(self.unpacked_dir.glob("ppt/slides/_rels/*.xml.rels")) + + if not slide_rels_files: + if self.verbose: + print("PASSED - No slide relationship files found") + return True + + for rels_file in slide_rels_files: + try: + # Parse the relationships file + root = lxml.etree.parse(str(rels_file)).getroot() + + # Find all notesSlide relationships + for rel in root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rel_type = rel.get("Type", "") + if "notesSlide" in rel_type: + target = rel.get("Target", "") + if target: + # Normalize the target path to handle relative paths + normalized_target = target.replace("../", "") + + # Track which slide references this notesSlide + slide_name = rels_file.stem.replace( + ".xml", "" + ) # e.g., "slide1" + + if normalized_target not in notes_slide_references: + notes_slide_references[normalized_target] = [] + notes_slide_references[normalized_target].append( + (slide_name, rels_file) + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + # Check for duplicate references + for target, references in notes_slide_references.items(): + if len(references) > 1: + slide_names = [ref[0] for ref in references] + errors.append( + f" Notes slide '{target}' is referenced by multiple slides: {', '.join(slide_names)}" + ) + for slide_name, rels_file in references: + errors.append(f" - {rels_file.relative_to(self.unpacked_dir)}") + + if errors: + print( + f"FAILED - Found {len([e for e in errors if not e.startswith(' ')])} notes slide reference validation errors:" + ) + for error in errors: + print(error) + print("Each slide may optionally have its own slide file.") + return False + else: + if self.verbose: + print("PASSED - All notes slide references are unique") + return True + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/skills/docx/ooxml/scripts/validation/redlining.py b/skills/docx/ooxml/scripts/validation/redlining.py new file mode 100644 index 0000000..7ed425e --- /dev/null +++ b/skills/docx/ooxml/scripts/validation/redlining.py @@ -0,0 +1,279 @@ +""" +Validator for tracked changes in Word documents. +""" + +import subprocess +import tempfile +import zipfile +from pathlib import Path + + +class RedliningValidator: + """Validator for tracked changes in Word documents.""" + + def __init__(self, unpacked_dir, original_docx, verbose=False): + self.unpacked_dir = Path(unpacked_dir) + self.original_docx = Path(original_docx) + self.verbose = verbose + self.namespaces = { + "w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + } + + def validate(self): + """Main validation method that returns True if valid, False otherwise.""" + # Verify unpacked directory exists and has correct structure + modified_file = self.unpacked_dir / "word" / "document.xml" + if not modified_file.exists(): + print(f"FAILED - Modified document.xml not found at {modified_file}") + return False + + # First, check if there are any tracked changes by Claude to validate + try: + import xml.etree.ElementTree as ET + + tree = ET.parse(modified_file) + root = tree.getroot() + + # Check for w:del or w:ins tags authored by Claude + del_elements = root.findall(".//w:del", self.namespaces) + ins_elements = root.findall(".//w:ins", self.namespaces) + + # Filter to only include changes by Claude + claude_del_elements = [ + elem + for elem in del_elements + if elem.get(f"{{{self.namespaces['w']}}}author") == "Claude" + ] + claude_ins_elements = [ + elem + for elem in ins_elements + if elem.get(f"{{{self.namespaces['w']}}}author") == "Claude" + ] + + # Redlining validation is only needed if tracked changes by Claude have been used. + if not claude_del_elements and not claude_ins_elements: + if self.verbose: + print("PASSED - No tracked changes by Claude found.") + return True + + except Exception: + # If we can't parse the XML, continue with full validation + pass + + # Create temporary directory for unpacking original docx + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + # Unpack original docx + try: + with zipfile.ZipFile(self.original_docx, "r") as zip_ref: + zip_ref.extractall(temp_path) + except Exception as e: + print(f"FAILED - Error unpacking original docx: {e}") + return False + + original_file = temp_path / "word" / "document.xml" + if not original_file.exists(): + print( + f"FAILED - Original document.xml not found in {self.original_docx}" + ) + return False + + # Parse both XML files using xml.etree.ElementTree for redlining validation + try: + import xml.etree.ElementTree as ET + + modified_tree = ET.parse(modified_file) + modified_root = modified_tree.getroot() + original_tree = ET.parse(original_file) + original_root = original_tree.getroot() + except ET.ParseError as e: + print(f"FAILED - Error parsing XML files: {e}") + return False + + # Remove Claude's tracked changes from both documents + self._remove_claude_tracked_changes(original_root) + self._remove_claude_tracked_changes(modified_root) + + # Extract and compare text content + modified_text = self._extract_text_content(modified_root) + original_text = self._extract_text_content(original_root) + + if modified_text != original_text: + # Show detailed character-level differences for each paragraph + error_message = self._generate_detailed_diff( + original_text, modified_text + ) + print(error_message) + return False + + if self.verbose: + print("PASSED - All changes by Claude are properly tracked") + return True + + def _generate_detailed_diff(self, original_text, modified_text): + """Generate detailed word-level differences using git word diff.""" + error_parts = [ + "FAILED - Document text doesn't match after removing Claude's tracked changes", + "", + "Likely causes:", + " 1. Modified text inside another author's or tags", + " 2. Made edits without proper tracked changes", + " 3. Didn't nest inside when deleting another's insertion", + "", + "For pre-redlined documents, use correct patterns:", + " - To reject another's INSERTION: Nest inside their ", + " - To restore another's DELETION: Add new AFTER their ", + "", + ] + + # Show git word diff + git_diff = self._get_git_word_diff(original_text, modified_text) + if git_diff: + error_parts.extend(["Differences:", "============", git_diff]) + else: + error_parts.append("Unable to generate word diff (git not available)") + + return "\n".join(error_parts) + + def _get_git_word_diff(self, original_text, modified_text): + """Generate word diff using git with character-level precision.""" + try: + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + # Create two files + original_file = temp_path / "original.txt" + modified_file = temp_path / "modified.txt" + + original_file.write_text(original_text, encoding="utf-8") + modified_file.write_text(modified_text, encoding="utf-8") + + # Try character-level diff first for precise differences + result = subprocess.run( + [ + "git", + "diff", + "--word-diff=plain", + "--word-diff-regex=.", # Character-by-character diff + "-U0", # Zero lines of context - show only changed lines + "--no-index", + str(original_file), + str(modified_file), + ], + capture_output=True, + text=True, + ) + + if result.stdout.strip(): + # Clean up the output - remove git diff header lines + lines = result.stdout.split("\n") + # Skip the header lines (diff --git, index, +++, ---, @@) + content_lines = [] + in_content = False + for line in lines: + if line.startswith("@@"): + in_content = True + continue + if in_content and line.strip(): + content_lines.append(line) + + if content_lines: + return "\n".join(content_lines) + + # Fallback to word-level diff if character-level is too verbose + result = subprocess.run( + [ + "git", + "diff", + "--word-diff=plain", + "-U0", # Zero lines of context + "--no-index", + str(original_file), + str(modified_file), + ], + capture_output=True, + text=True, + ) + + if result.stdout.strip(): + lines = result.stdout.split("\n") + content_lines = [] + in_content = False + for line in lines: + if line.startswith("@@"): + in_content = True + continue + if in_content and line.strip(): + content_lines.append(line) + return "\n".join(content_lines) + + except (subprocess.CalledProcessError, FileNotFoundError, Exception): + # Git not available or other error, return None to use fallback + pass + + return None + + def _remove_claude_tracked_changes(self, root): + """Remove tracked changes authored by Claude from the XML root.""" + ins_tag = f"{{{self.namespaces['w']}}}ins" + del_tag = f"{{{self.namespaces['w']}}}del" + author_attr = f"{{{self.namespaces['w']}}}author" + + # Remove w:ins elements + for parent in root.iter(): + to_remove = [] + for child in parent: + if child.tag == ins_tag and child.get(author_attr) == "Claude": + to_remove.append(child) + for elem in to_remove: + parent.remove(elem) + + # Unwrap content in w:del elements where author is "Claude" + deltext_tag = f"{{{self.namespaces['w']}}}delText" + t_tag = f"{{{self.namespaces['w']}}}t" + + for parent in root.iter(): + to_process = [] + for child in parent: + if child.tag == del_tag and child.get(author_attr) == "Claude": + to_process.append((child, list(parent).index(child))) + + # Process in reverse order to maintain indices + for del_elem, del_index in reversed(to_process): + # Convert w:delText to w:t before moving + for elem in del_elem.iter(): + if elem.tag == deltext_tag: + elem.tag = t_tag + + # Move all children of w:del to its parent before removing w:del + for child in reversed(list(del_elem)): + parent.insert(del_index, child) + parent.remove(del_elem) + + def _extract_text_content(self, root): + """Extract text content from Word XML, preserving paragraph structure. + + Empty paragraphs are skipped to avoid false positives when tracked + insertions add only structural elements without text content. + """ + p_tag = f"{{{self.namespaces['w']}}}p" + t_tag = f"{{{self.namespaces['w']}}}t" + + paragraphs = [] + for p_elem in root.findall(f".//{p_tag}"): + # Get all text elements within this paragraph + text_parts = [] + for t_elem in p_elem.findall(f".//{t_tag}"): + if t_elem.text: + text_parts.append(t_elem.text) + paragraph_text = "".join(text_parts) + # Skip empty paragraphs - they don't affect content validation + if paragraph_text: + paragraphs.append(paragraph_text) + + return "\n".join(paragraphs) + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/skills/docx/scripts/__init__.py b/skills/docx/scripts/__init__.py new file mode 100755 index 0000000..bf9c562 --- /dev/null +++ b/skills/docx/scripts/__init__.py @@ -0,0 +1 @@ +# Make scripts directory a package for relative imports in tests diff --git a/skills/docx/scripts/document.py b/skills/docx/scripts/document.py new file mode 100755 index 0000000..ae9328d --- /dev/null +++ b/skills/docx/scripts/document.py @@ -0,0 +1,1276 @@ +#!/usr/bin/env python3 +""" +Library for working with Word documents: comments, tracked changes, and editing. + +Usage: + from skills.docx.scripts.document import Document + + # Initialize + doc = Document('workspace/unpacked') + doc = Document('workspace/unpacked', author="John Doe", initials="JD") + + # Find nodes + node = doc["word/document.xml"].get_node(tag="w:del", attrs={"w:id": "1"}) + node = doc["word/document.xml"].get_node(tag="w:p", line_number=10) + + # Add comments + doc.add_comment(start=node, end=node, text="Comment text") + doc.reply_to_comment(parent_comment_id=0, text="Reply text") + + # Suggest tracked changes + doc["word/document.xml"].suggest_deletion(node) # Delete content + doc["word/document.xml"].revert_insertion(ins_node) # Reject insertion + doc["word/document.xml"].revert_deletion(del_node) # Reject deletion + + # Save + doc.save() +""" + +import html +import random +import shutil +import tempfile +from datetime import datetime, timezone +from pathlib import Path + +from defusedxml import minidom +from ooxml.scripts.pack import pack_document +from ooxml.scripts.validation.docx import DOCXSchemaValidator +from ooxml.scripts.validation.redlining import RedliningValidator + +from .utilities import XMLEditor + +# Path to template files +TEMPLATE_DIR = Path(__file__).parent / "templates" + + +class DocxXMLEditor(XMLEditor): + """XMLEditor that automatically applies RSID, author, and date to new elements. + + Automatically adds attributes to elements that support them when inserting new content: + - w:rsidR, w:rsidRDefault, w:rsidP (for w:p and w:r elements) + - w:author and w:date (for w:ins, w:del, w:comment elements) + - w:id (for w:ins and w:del elements) + + Attributes: + dom (defusedxml.minidom.Document): The DOM document for direct manipulation + """ + + def __init__( + self, xml_path, rsid: str, author: str = "Claude", initials: str = "C" + ): + """Initialize with required RSID and optional author. + + Args: + xml_path: Path to XML file to edit + rsid: RSID to automatically apply to new elements + author: Author name for tracked changes and comments (default: "Claude") + initials: Author initials (default: "C") + """ + super().__init__(xml_path) + self.rsid = rsid + self.author = author + self.initials = initials + + def _get_next_change_id(self): + """Get the next available change ID by checking all tracked change elements.""" + max_id = -1 + for tag in ("w:ins", "w:del"): + elements = self.dom.getElementsByTagName(tag) + for elem in elements: + change_id = elem.getAttribute("w:id") + if change_id: + try: + max_id = max(max_id, int(change_id)) + except ValueError: + pass + return max_id + 1 + + def _ensure_w16du_namespace(self): + """Ensure w16du namespace is declared on the root element.""" + root = self.dom.documentElement + if not root.hasAttribute("xmlns:w16du"): # type: ignore + root.setAttribute( # type: ignore + "xmlns:w16du", + "http://schemas.microsoft.com/office/word/2023/wordml/word16du", + ) + + def _ensure_w16cex_namespace(self): + """Ensure w16cex namespace is declared on the root element.""" + root = self.dom.documentElement + if not root.hasAttribute("xmlns:w16cex"): # type: ignore + root.setAttribute( # type: ignore + "xmlns:w16cex", + "http://schemas.microsoft.com/office/word/2018/wordml/cex", + ) + + def _ensure_w14_namespace(self): + """Ensure w14 namespace is declared on the root element.""" + root = self.dom.documentElement + if not root.hasAttribute("xmlns:w14"): # type: ignore + root.setAttribute( # type: ignore + "xmlns:w14", + "http://schemas.microsoft.com/office/word/2010/wordml", + ) + + def _inject_attributes_to_nodes(self, nodes): + """Inject RSID, author, and date attributes into DOM nodes where applicable. + + Adds attributes to elements that support them: + - w:r: gets w:rsidR (or w:rsidDel if inside w:del) + - w:p: gets w:rsidR, w:rsidRDefault, w:rsidP, w14:paraId, w14:textId + - w:t: gets xml:space="preserve" if text has leading/trailing whitespace + - w:ins, w:del: get w:id, w:author, w:date, w16du:dateUtc + - w:comment: gets w:author, w:date, w:initials + - w16cex:commentExtensible: gets w16cex:dateUtc + + Args: + nodes: List of DOM nodes to process + """ + from datetime import datetime, timezone + + timestamp = datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ") + + def is_inside_deletion(elem): + """Check if element is inside a w:del element.""" + parent = elem.parentNode + while parent: + if parent.nodeType == parent.ELEMENT_NODE and parent.tagName == "w:del": + return True + parent = parent.parentNode + return False + + def add_rsid_to_p(elem): + if not elem.hasAttribute("w:rsidR"): + elem.setAttribute("w:rsidR", self.rsid) + if not elem.hasAttribute("w:rsidRDefault"): + elem.setAttribute("w:rsidRDefault", self.rsid) + if not elem.hasAttribute("w:rsidP"): + elem.setAttribute("w:rsidP", self.rsid) + # Add w14:paraId and w14:textId if not present + if not elem.hasAttribute("w14:paraId"): + self._ensure_w14_namespace() + elem.setAttribute("w14:paraId", _generate_hex_id()) + if not elem.hasAttribute("w14:textId"): + self._ensure_w14_namespace() + elem.setAttribute("w14:textId", _generate_hex_id()) + + def add_rsid_to_r(elem): + # Use w:rsidDel for inside , otherwise w:rsidR + if is_inside_deletion(elem): + if not elem.hasAttribute("w:rsidDel"): + elem.setAttribute("w:rsidDel", self.rsid) + else: + if not elem.hasAttribute("w:rsidR"): + elem.setAttribute("w:rsidR", self.rsid) + + def add_tracked_change_attrs(elem): + # Auto-assign w:id if not present + if not elem.hasAttribute("w:id"): + elem.setAttribute("w:id", str(self._get_next_change_id())) + if not elem.hasAttribute("w:author"): + elem.setAttribute("w:author", self.author) + if not elem.hasAttribute("w:date"): + elem.setAttribute("w:date", timestamp) + # Add w16du:dateUtc for tracked changes (same as w:date since we generate UTC timestamps) + if elem.tagName in ("w:ins", "w:del") and not elem.hasAttribute( + "w16du:dateUtc" + ): + self._ensure_w16du_namespace() + elem.setAttribute("w16du:dateUtc", timestamp) + + def add_comment_attrs(elem): + if not elem.hasAttribute("w:author"): + elem.setAttribute("w:author", self.author) + if not elem.hasAttribute("w:date"): + elem.setAttribute("w:date", timestamp) + if not elem.hasAttribute("w:initials"): + elem.setAttribute("w:initials", self.initials) + + def add_comment_extensible_date(elem): + # Add w16cex:dateUtc for comment extensible elements + if not elem.hasAttribute("w16cex:dateUtc"): + self._ensure_w16cex_namespace() + elem.setAttribute("w16cex:dateUtc", timestamp) + + def add_xml_space_to_t(elem): + # Add xml:space="preserve" to w:t if text has leading/trailing whitespace + if ( + elem.firstChild + and elem.firstChild.nodeType == elem.firstChild.TEXT_NODE + ): + text = elem.firstChild.data + if text and (text[0].isspace() or text[-1].isspace()): + if not elem.hasAttribute("xml:space"): + elem.setAttribute("xml:space", "preserve") + + for node in nodes: + if node.nodeType != node.ELEMENT_NODE: + continue + + # Handle the node itself + if node.tagName == "w:p": + add_rsid_to_p(node) + elif node.tagName == "w:r": + add_rsid_to_r(node) + elif node.tagName == "w:t": + add_xml_space_to_t(node) + elif node.tagName in ("w:ins", "w:del"): + add_tracked_change_attrs(node) + elif node.tagName == "w:comment": + add_comment_attrs(node) + elif node.tagName == "w16cex:commentExtensible": + add_comment_extensible_date(node) + + # Process descendants (getElementsByTagName doesn't return the element itself) + for elem in node.getElementsByTagName("w:p"): + add_rsid_to_p(elem) + for elem in node.getElementsByTagName("w:r"): + add_rsid_to_r(elem) + for elem in node.getElementsByTagName("w:t"): + add_xml_space_to_t(elem) + for tag in ("w:ins", "w:del"): + for elem in node.getElementsByTagName(tag): + add_tracked_change_attrs(elem) + for elem in node.getElementsByTagName("w:comment"): + add_comment_attrs(elem) + for elem in node.getElementsByTagName("w16cex:commentExtensible"): + add_comment_extensible_date(elem) + + def replace_node(self, elem, new_content): + """Replace node with automatic attribute injection.""" + nodes = super().replace_node(elem, new_content) + self._inject_attributes_to_nodes(nodes) + return nodes + + def insert_after(self, elem, xml_content): + """Insert after with automatic attribute injection.""" + nodes = super().insert_after(elem, xml_content) + self._inject_attributes_to_nodes(nodes) + return nodes + + def insert_before(self, elem, xml_content): + """Insert before with automatic attribute injection.""" + nodes = super().insert_before(elem, xml_content) + self._inject_attributes_to_nodes(nodes) + return nodes + + def append_to(self, elem, xml_content): + """Append to with automatic attribute injection.""" + nodes = super().append_to(elem, xml_content) + self._inject_attributes_to_nodes(nodes) + return nodes + + def revert_insertion(self, elem): + """Reject an insertion by wrapping its content in a deletion. + + Wraps all runs inside w:ins in w:del, converting w:t to w:delText. + Can process a single w:ins element or a container element with multiple w:ins. + + Args: + elem: Element to process (w:ins, w:p, w:body, etc.) + + Returns: + list: List containing the processed element(s) + + Raises: + ValueError: If the element contains no w:ins elements + + Example: + # Reject a single insertion + ins = doc["word/document.xml"].get_node(tag="w:ins", attrs={"w:id": "5"}) + doc["word/document.xml"].revert_insertion(ins) + + # Reject all insertions in a paragraph + para = doc["word/document.xml"].get_node(tag="w:p", line_number=42) + doc["word/document.xml"].revert_insertion(para) + """ + # Collect insertions + ins_elements = [] + if elem.tagName == "w:ins": + ins_elements.append(elem) + else: + ins_elements.extend(elem.getElementsByTagName("w:ins")) + + # Validate that there are insertions to reject + if not ins_elements: + raise ValueError( + f"revert_insertion requires w:ins elements. " + f"The provided element <{elem.tagName}> contains no insertions. " + ) + + # Process all insertions - wrap all children in w:del + for ins_elem in ins_elements: + runs = list(ins_elem.getElementsByTagName("w:r")) + if not runs: + continue + + # Create deletion wrapper + del_wrapper = self.dom.createElement("w:del") + + # Process each run + for run in runs: + # Convert w:t → w:delText and w:rsidR → w:rsidDel + if run.hasAttribute("w:rsidR"): + run.setAttribute("w:rsidDel", run.getAttribute("w:rsidR")) + run.removeAttribute("w:rsidR") + elif not run.hasAttribute("w:rsidDel"): + run.setAttribute("w:rsidDel", self.rsid) + + for t_elem in list(run.getElementsByTagName("w:t")): + del_text = self.dom.createElement("w:delText") + # Copy ALL child nodes (not just firstChild) to handle entities + while t_elem.firstChild: + del_text.appendChild(t_elem.firstChild) + for i in range(t_elem.attributes.length): + attr = t_elem.attributes.item(i) + del_text.setAttribute(attr.name, attr.value) + t_elem.parentNode.replaceChild(del_text, t_elem) + + # Move all children from ins to del wrapper + while ins_elem.firstChild: + del_wrapper.appendChild(ins_elem.firstChild) + + # Add del wrapper back to ins + ins_elem.appendChild(del_wrapper) + + # Inject attributes to the deletion wrapper + self._inject_attributes_to_nodes([del_wrapper]) + + return [elem] + + def revert_deletion(self, elem): + """Reject a deletion by re-inserting the deleted content. + + Creates w:ins elements after each w:del, copying deleted content and + converting w:delText back to w:t. + Can process a single w:del element or a container element with multiple w:del. + + Args: + elem: Element to process (w:del, w:p, w:body, etc.) + + Returns: + list: If elem is w:del, returns [elem, new_ins]. Otherwise returns [elem]. + + Raises: + ValueError: If the element contains no w:del elements + + Example: + # Reject a single deletion - returns [w:del, w:ins] + del_elem = doc["word/document.xml"].get_node(tag="w:del", attrs={"w:id": "3"}) + nodes = doc["word/document.xml"].revert_deletion(del_elem) + + # Reject all deletions in a paragraph - returns [para] + para = doc["word/document.xml"].get_node(tag="w:p", line_number=42) + nodes = doc["word/document.xml"].revert_deletion(para) + """ + # Collect deletions FIRST - before we modify the DOM + del_elements = [] + is_single_del = elem.tagName == "w:del" + + if is_single_del: + del_elements.append(elem) + else: + del_elements.extend(elem.getElementsByTagName("w:del")) + + # Validate that there are deletions to reject + if not del_elements: + raise ValueError( + f"revert_deletion requires w:del elements. " + f"The provided element <{elem.tagName}> contains no deletions. " + ) + + # Track created insertion (only relevant if elem is a single w:del) + created_insertion = None + + # Process all deletions - create insertions that copy the deleted content + for del_elem in del_elements: + # Clone the deleted runs and convert them to insertions + runs = list(del_elem.getElementsByTagName("w:r")) + if not runs: + continue + + # Create insertion wrapper + ins_elem = self.dom.createElement("w:ins") + + for run in runs: + # Clone the run + new_run = run.cloneNode(True) + + # Convert w:delText → w:t + for del_text in list(new_run.getElementsByTagName("w:delText")): + t_elem = self.dom.createElement("w:t") + # Copy ALL child nodes (not just firstChild) to handle entities + while del_text.firstChild: + t_elem.appendChild(del_text.firstChild) + for i in range(del_text.attributes.length): + attr = del_text.attributes.item(i) + t_elem.setAttribute(attr.name, attr.value) + del_text.parentNode.replaceChild(t_elem, del_text) + + # Update run attributes: w:rsidDel → w:rsidR + if new_run.hasAttribute("w:rsidDel"): + new_run.setAttribute("w:rsidR", new_run.getAttribute("w:rsidDel")) + new_run.removeAttribute("w:rsidDel") + elif not new_run.hasAttribute("w:rsidR"): + new_run.setAttribute("w:rsidR", self.rsid) + + ins_elem.appendChild(new_run) + + # Insert the new insertion after the deletion + nodes = self.insert_after(del_elem, ins_elem.toxml()) + + # If processing a single w:del, track the created insertion + if is_single_del and nodes: + created_insertion = nodes[0] + + # Return based on input type + if is_single_del and created_insertion: + return [elem, created_insertion] + else: + return [elem] + + @staticmethod + def suggest_paragraph(xml_content: str) -> str: + """Transform paragraph XML to add tracked change wrapping for insertion. + + Wraps runs in and adds to w:rPr in w:pPr for numbered lists. + + Args: + xml_content: XML string containing a element + + Returns: + str: Transformed XML with tracked change wrapping + """ + wrapper = f'{xml_content}' + doc = minidom.parseString(wrapper) + para = doc.getElementsByTagName("w:p")[0] + + # Ensure w:pPr exists + pPr_list = para.getElementsByTagName("w:pPr") + if not pPr_list: + pPr = doc.createElement("w:pPr") + para.insertBefore( + pPr, para.firstChild + ) if para.firstChild else para.appendChild(pPr) + else: + pPr = pPr_list[0] + + # Ensure w:rPr exists in w:pPr + rPr_list = pPr.getElementsByTagName("w:rPr") + if not rPr_list: + rPr = doc.createElement("w:rPr") + pPr.appendChild(rPr) + else: + rPr = rPr_list[0] + + # Add to w:rPr + ins_marker = doc.createElement("w:ins") + rPr.insertBefore( + ins_marker, rPr.firstChild + ) if rPr.firstChild else rPr.appendChild(ins_marker) + + # Wrap all non-pPr children in + ins_wrapper = doc.createElement("w:ins") + for child in [c for c in para.childNodes if c.nodeName != "w:pPr"]: + para.removeChild(child) + ins_wrapper.appendChild(child) + para.appendChild(ins_wrapper) + + return para.toxml() + + def suggest_deletion(self, elem): + """Mark a w:r or w:p element as deleted with tracked changes (in-place DOM manipulation). + + For w:r: wraps in , converts to , preserves w:rPr + For w:p (regular): wraps content in , converts to + For w:p (numbered list): adds to w:rPr in w:pPr, wraps content in + + Args: + elem: A w:r or w:p DOM element without existing tracked changes + + Returns: + Element: The modified element + + Raises: + ValueError: If element has existing tracked changes or invalid structure + """ + if elem.nodeName == "w:r": + # Check for existing w:delText + if elem.getElementsByTagName("w:delText"): + raise ValueError("w:r element already contains w:delText") + + # Convert w:t → w:delText + for t_elem in list(elem.getElementsByTagName("w:t")): + del_text = self.dom.createElement("w:delText") + # Copy ALL child nodes (not just firstChild) to handle entities + while t_elem.firstChild: + del_text.appendChild(t_elem.firstChild) + # Preserve attributes like xml:space + for i in range(t_elem.attributes.length): + attr = t_elem.attributes.item(i) + del_text.setAttribute(attr.name, attr.value) + t_elem.parentNode.replaceChild(del_text, t_elem) + + # Update run attributes: w:rsidR → w:rsidDel + if elem.hasAttribute("w:rsidR"): + elem.setAttribute("w:rsidDel", elem.getAttribute("w:rsidR")) + elem.removeAttribute("w:rsidR") + elif not elem.hasAttribute("w:rsidDel"): + elem.setAttribute("w:rsidDel", self.rsid) + + # Wrap in w:del + del_wrapper = self.dom.createElement("w:del") + parent = elem.parentNode + parent.insertBefore(del_wrapper, elem) + parent.removeChild(elem) + del_wrapper.appendChild(elem) + + # Inject attributes to the deletion wrapper + self._inject_attributes_to_nodes([del_wrapper]) + + return del_wrapper + + elif elem.nodeName == "w:p": + # Check for existing tracked changes + if elem.getElementsByTagName("w:ins") or elem.getElementsByTagName("w:del"): + raise ValueError("w:p element already contains tracked changes") + + # Check if it's a numbered list item + pPr_list = elem.getElementsByTagName("w:pPr") + is_numbered = pPr_list and pPr_list[0].getElementsByTagName("w:numPr") + + if is_numbered: + # Add to w:rPr in w:pPr + pPr = pPr_list[0] + rPr_list = pPr.getElementsByTagName("w:rPr") + + if not rPr_list: + rPr = self.dom.createElement("w:rPr") + pPr.appendChild(rPr) + else: + rPr = rPr_list[0] + + # Add marker + del_marker = self.dom.createElement("w:del") + rPr.insertBefore( + del_marker, rPr.firstChild + ) if rPr.firstChild else rPr.appendChild(del_marker) + + # Convert w:t → w:delText in all runs + for t_elem in list(elem.getElementsByTagName("w:t")): + del_text = self.dom.createElement("w:delText") + # Copy ALL child nodes (not just firstChild) to handle entities + while t_elem.firstChild: + del_text.appendChild(t_elem.firstChild) + # Preserve attributes like xml:space + for i in range(t_elem.attributes.length): + attr = t_elem.attributes.item(i) + del_text.setAttribute(attr.name, attr.value) + t_elem.parentNode.replaceChild(del_text, t_elem) + + # Update run attributes: w:rsidR → w:rsidDel + for run in elem.getElementsByTagName("w:r"): + if run.hasAttribute("w:rsidR"): + run.setAttribute("w:rsidDel", run.getAttribute("w:rsidR")) + run.removeAttribute("w:rsidR") + elif not run.hasAttribute("w:rsidDel"): + run.setAttribute("w:rsidDel", self.rsid) + + # Wrap all non-pPr children in + del_wrapper = self.dom.createElement("w:del") + for child in [c for c in elem.childNodes if c.nodeName != "w:pPr"]: + elem.removeChild(child) + del_wrapper.appendChild(child) + elem.appendChild(del_wrapper) + + # Inject attributes to the deletion wrapper + self._inject_attributes_to_nodes([del_wrapper]) + + return elem + + else: + raise ValueError(f"Element must be w:r or w:p, got {elem.nodeName}") + + +def _generate_hex_id() -> str: + """Generate random 8-character hex ID for para/durable IDs. + + Values are constrained to be less than 0x7FFFFFFF per OOXML spec: + - paraId must be < 0x80000000 + - durableId must be < 0x7FFFFFFF + We use the stricter constraint (0x7FFFFFFF) for both. + """ + return f"{random.randint(1, 0x7FFFFFFE):08X}" + + +def _generate_rsid() -> str: + """Generate random 8-character hex RSID.""" + return "".join(random.choices("0123456789ABCDEF", k=8)) + + +class Document: + """Manages comments in unpacked Word documents.""" + + def __init__( + self, + unpacked_dir, + rsid=None, + track_revisions=False, + author="Claude", + initials="C", + ): + """ + Initialize with path to unpacked Word document directory. + Automatically sets up comment infrastructure (people.xml, RSIDs). + + Args: + unpacked_dir: Path to unpacked DOCX directory (must contain word/ subdirectory) + rsid: Optional RSID to use for all comment elements. If not provided, one will be generated. + track_revisions: If True, enables track revisions in settings.xml (default: False) + author: Default author name for comments (default: "Claude") + initials: Default author initials for comments (default: "C") + """ + self.original_path = Path(unpacked_dir) + + if not self.original_path.exists() or not self.original_path.is_dir(): + raise ValueError(f"Directory not found: {unpacked_dir}") + + # Create temporary directory with subdirectories for unpacked content and baseline + self.temp_dir = tempfile.mkdtemp(prefix="docx_") + self.unpacked_path = Path(self.temp_dir) / "unpacked" + shutil.copytree(self.original_path, self.unpacked_path) + + # Pack original directory into temporary .docx for validation baseline (outside unpacked dir) + self.original_docx = Path(self.temp_dir) / "original.docx" + pack_document(self.original_path, self.original_docx, validate=False) + + self.word_path = self.unpacked_path / "word" + + # Generate RSID if not provided + self.rsid = rsid if rsid else _generate_rsid() + print(f"Using RSID: {self.rsid}") + + # Set default author and initials + self.author = author + self.initials = initials + + # Cache for lazy-loaded editors + self._editors = {} + + # Comment file paths + self.comments_path = self.word_path / "comments.xml" + self.comments_extended_path = self.word_path / "commentsExtended.xml" + self.comments_ids_path = self.word_path / "commentsIds.xml" + self.comments_extensible_path = self.word_path / "commentsExtensible.xml" + + # Load existing comments and determine next ID (before setup modifies files) + self.existing_comments = self._load_existing_comments() + self.next_comment_id = self._get_next_comment_id() + + # Convenient access to document.xml editor (semi-private) + self._document = self["word/document.xml"] + + # Setup tracked changes infrastructure + self._setup_tracking(track_revisions=track_revisions) + + # Add author to people.xml + self._add_author_to_people(author) + + def __getitem__(self, xml_path: str) -> DocxXMLEditor: + """ + Get or create a DocxXMLEditor for the specified XML file. + + Enables lazy-loaded editors with bracket notation: + node = doc["word/document.xml"].get_node(tag="w:p", line_number=42) + + Args: + xml_path: Relative path to XML file (e.g., "word/document.xml", "word/comments.xml") + + Returns: + DocxXMLEditor instance for the specified file + + Raises: + ValueError: If the file does not exist + + Example: + # Get node from document.xml + node = doc["word/document.xml"].get_node(tag="w:del", attrs={"w:id": "1"}) + + # Get node from comments.xml + comment = doc["word/comments.xml"].get_node(tag="w:comment", attrs={"w:id": "0"}) + """ + if xml_path not in self._editors: + file_path = self.unpacked_path / xml_path + if not file_path.exists(): + raise ValueError(f"XML file not found: {xml_path}") + # Use DocxXMLEditor with RSID, author, and initials for all editors + self._editors[xml_path] = DocxXMLEditor( + file_path, rsid=self.rsid, author=self.author, initials=self.initials + ) + return self._editors[xml_path] + + def add_comment(self, start, end, text: str) -> int: + """ + Add a comment spanning from one element to another. + + Args: + start: DOM element for the starting point + end: DOM element for the ending point + text: Comment content + + Returns: + The comment ID that was created + + Example: + start_node = cm.get_document_node(tag="w:del", id="1") + end_node = cm.get_document_node(tag="w:ins", id="2") + cm.add_comment(start=start_node, end=end_node, text="Explanation") + """ + comment_id = self.next_comment_id + para_id = _generate_hex_id() + durable_id = _generate_hex_id() + timestamp = datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ") + + # Add comment ranges to document.xml immediately + self._document.insert_before(start, self._comment_range_start_xml(comment_id)) + + # If end node is a paragraph, append comment markup inside it + # Otherwise insert after it (for run-level anchors) + if end.tagName == "w:p": + self._document.append_to(end, self._comment_range_end_xml(comment_id)) + else: + self._document.insert_after(end, self._comment_range_end_xml(comment_id)) + + # Add to comments.xml immediately + self._add_to_comments_xml( + comment_id, para_id, text, self.author, self.initials, timestamp + ) + + # Add to commentsExtended.xml immediately + self._add_to_comments_extended_xml(para_id, parent_para_id=None) + + # Add to commentsIds.xml immediately + self._add_to_comments_ids_xml(para_id, durable_id) + + # Add to commentsExtensible.xml immediately + self._add_to_comments_extensible_xml(durable_id) + + # Update existing_comments so replies work + self.existing_comments[comment_id] = {"para_id": para_id} + + self.next_comment_id += 1 + return comment_id + + def reply_to_comment( + self, + parent_comment_id: int, + text: str, + ) -> int: + """ + Add a reply to an existing comment. + + Args: + parent_comment_id: The w:id of the parent comment to reply to + text: Reply text + + Returns: + The comment ID that was created for the reply + + Example: + cm.reply_to_comment(parent_comment_id=0, text="I agree with this change") + """ + if parent_comment_id not in self.existing_comments: + raise ValueError(f"Parent comment with id={parent_comment_id} not found") + + parent_info = self.existing_comments[parent_comment_id] + comment_id = self.next_comment_id + para_id = _generate_hex_id() + durable_id = _generate_hex_id() + timestamp = datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ") + + # Add comment ranges to document.xml immediately + parent_start_elem = self._document.get_node( + tag="w:commentRangeStart", attrs={"w:id": str(parent_comment_id)} + ) + parent_ref_elem = self._document.get_node( + tag="w:commentReference", attrs={"w:id": str(parent_comment_id)} + ) + + self._document.insert_after( + parent_start_elem, self._comment_range_start_xml(comment_id) + ) + parent_ref_run = parent_ref_elem.parentNode + self._document.insert_after( + parent_ref_run, f'' + ) + self._document.insert_after( + parent_ref_run, self._comment_ref_run_xml(comment_id) + ) + + # Add to comments.xml immediately + self._add_to_comments_xml( + comment_id, para_id, text, self.author, self.initials, timestamp + ) + + # Add to commentsExtended.xml immediately (with parent) + self._add_to_comments_extended_xml( + para_id, parent_para_id=parent_info["para_id"] + ) + + # Add to commentsIds.xml immediately + self._add_to_comments_ids_xml(para_id, durable_id) + + # Add to commentsExtensible.xml immediately + self._add_to_comments_extensible_xml(durable_id) + + # Update existing_comments so replies work + self.existing_comments[comment_id] = {"para_id": para_id} + + self.next_comment_id += 1 + return comment_id + + def __del__(self): + """Clean up temporary directory on deletion.""" + if hasattr(self, "temp_dir") and Path(self.temp_dir).exists(): + shutil.rmtree(self.temp_dir) + + def validate(self) -> None: + """ + Validate the document against XSD schema and redlining rules. + + Raises: + ValueError: If validation fails. + """ + # Create validators with current state + schema_validator = DOCXSchemaValidator( + self.unpacked_path, self.original_docx, verbose=False + ) + redlining_validator = RedliningValidator( + self.unpacked_path, self.original_docx, verbose=False + ) + + # Run validations + if not schema_validator.validate(): + raise ValueError("Schema validation failed") + if not redlining_validator.validate(): + raise ValueError("Redlining validation failed") + + def save(self, destination=None, validate=True) -> None: + """ + Save all modified XML files to disk and copy to destination directory. + + This persists all changes made via add_comment() and reply_to_comment(). + + Args: + destination: Optional path to save to. If None, saves back to original directory. + validate: If True, validates document before saving (default: True). + """ + # Only ensure comment relationships and content types if comment files exist + if self.comments_path.exists(): + self._ensure_comment_relationships() + self._ensure_comment_content_types() + + # Save all modified XML files in temp directory + for editor in self._editors.values(): + editor.save() + + # Validate by default + if validate: + self.validate() + + # Copy contents from temp directory to destination (or original directory) + target_path = Path(destination) if destination else self.original_path + shutil.copytree(self.unpacked_path, target_path, dirs_exist_ok=True) + + # ==================== Private: Initialization ==================== + + def _get_next_comment_id(self): + """Get the next available comment ID.""" + if not self.comments_path.exists(): + return 0 + + editor = self["word/comments.xml"] + max_id = -1 + for comment_elem in editor.dom.getElementsByTagName("w:comment"): + comment_id = comment_elem.getAttribute("w:id") + if comment_id: + try: + max_id = max(max_id, int(comment_id)) + except ValueError: + pass + return max_id + 1 + + def _load_existing_comments(self): + """Load existing comments from files to enable replies.""" + if not self.comments_path.exists(): + return {} + + editor = self["word/comments.xml"] + existing = {} + + for comment_elem in editor.dom.getElementsByTagName("w:comment"): + comment_id = comment_elem.getAttribute("w:id") + if not comment_id: + continue + + # Find para_id from the w:p element within the comment + para_id = None + for p_elem in comment_elem.getElementsByTagName("w:p"): + para_id = p_elem.getAttribute("w14:paraId") + if para_id: + break + + if not para_id: + continue + + existing[int(comment_id)] = {"para_id": para_id} + + return existing + + # ==================== Private: Setup Methods ==================== + + def _setup_tracking(self, track_revisions=False): + """Set up comment infrastructure in unpacked directory. + + Args: + track_revisions: If True, enables track revisions in settings.xml + """ + # Create or update word/people.xml + people_file = self.word_path / "people.xml" + self._update_people_xml(people_file) + + # Update XML files + self._add_content_type_for_people(self.unpacked_path / "[Content_Types].xml") + self._add_relationship_for_people( + self.word_path / "_rels" / "document.xml.rels" + ) + + # Always add RSID to settings.xml, optionally enable trackRevisions + self._update_settings( + self.word_path / "settings.xml", track_revisions=track_revisions + ) + + def _update_people_xml(self, path): + """Create people.xml if it doesn't exist.""" + if not path.exists(): + # Copy from template + shutil.copy(TEMPLATE_DIR / "people.xml", path) + + def _add_content_type_for_people(self, path): + """Add people.xml content type to [Content_Types].xml if not already present.""" + editor = self["[Content_Types].xml"] + + if self._has_override(editor, "/word/people.xml"): + return + + # Add Override element + root = editor.dom.documentElement + override_xml = '' + editor.append_to(root, override_xml) + + def _add_relationship_for_people(self, path): + """Add people.xml relationship to document.xml.rels if not already present.""" + editor = self["word/_rels/document.xml.rels"] + + if self._has_relationship(editor, "people.xml"): + return + + root = editor.dom.documentElement + root_tag = root.tagName # type: ignore + prefix = root_tag.split(":")[0] + ":" if ":" in root_tag else "" + next_rid = editor.get_next_rid() + + # Create the relationship entry + rel_xml = f'<{prefix}Relationship Id="{next_rid}" Type="http://schemas.microsoft.com/office/2011/relationships/people" Target="people.xml"/>' + editor.append_to(root, rel_xml) + + def _update_settings(self, path, track_revisions=False): + """Add RSID and optionally enable track revisions in settings.xml. + + Args: + path: Path to settings.xml + track_revisions: If True, adds trackRevisions element + + Places elements per OOXML schema order: + - trackRevisions: early (before defaultTabStop) + - rsids: late (after compat) + """ + editor = self["word/settings.xml"] + root = editor.get_node(tag="w:settings") + prefix = root.tagName.split(":")[0] if ":" in root.tagName else "w" + + # Conditionally add trackRevisions if requested + if track_revisions: + track_revisions_exists = any( + elem.tagName == f"{prefix}:trackRevisions" + for elem in editor.dom.getElementsByTagName(f"{prefix}:trackRevisions") + ) + + if not track_revisions_exists: + track_rev_xml = f"<{prefix}:trackRevisions/>" + # Try to insert before documentProtection, defaultTabStop, or at start + inserted = False + for tag in [f"{prefix}:documentProtection", f"{prefix}:defaultTabStop"]: + elements = editor.dom.getElementsByTagName(tag) + if elements: + editor.insert_before(elements[0], track_rev_xml) + inserted = True + break + if not inserted: + # Insert as first child of settings + if root.firstChild: + editor.insert_before(root.firstChild, track_rev_xml) + else: + editor.append_to(root, track_rev_xml) + + # Always check if rsids section exists + rsids_elements = editor.dom.getElementsByTagName(f"{prefix}:rsids") + + if not rsids_elements: + # Add new rsids section + rsids_xml = f'''<{prefix}:rsids> + <{prefix}:rsidRoot {prefix}:val="{self.rsid}"/> + <{prefix}:rsid {prefix}:val="{self.rsid}"/> +''' + + # Try to insert after compat, before clrSchemeMapping, or before closing tag + inserted = False + compat_elements = editor.dom.getElementsByTagName(f"{prefix}:compat") + if compat_elements: + editor.insert_after(compat_elements[0], rsids_xml) + inserted = True + + if not inserted: + clr_elements = editor.dom.getElementsByTagName( + f"{prefix}:clrSchemeMapping" + ) + if clr_elements: + editor.insert_before(clr_elements[0], rsids_xml) + inserted = True + + if not inserted: + editor.append_to(root, rsids_xml) + else: + # Check if this rsid already exists + rsids_elem = rsids_elements[0] + rsid_exists = any( + elem.getAttribute(f"{prefix}:val") == self.rsid + for elem in rsids_elem.getElementsByTagName(f"{prefix}:rsid") + ) + + if not rsid_exists: + rsid_xml = f'<{prefix}:rsid {prefix}:val="{self.rsid}"/>' + editor.append_to(rsids_elem, rsid_xml) + + # ==================== Private: XML File Creation ==================== + + def _add_to_comments_xml( + self, comment_id, para_id, text, author, initials, timestamp + ): + """Add a single comment to comments.xml.""" + if not self.comments_path.exists(): + shutil.copy(TEMPLATE_DIR / "comments.xml", self.comments_path) + + editor = self["word/comments.xml"] + root = editor.get_node(tag="w:comments") + + escaped_text = ( + text.replace("&", "&").replace("<", "<").replace(">", ">") + ) + # Note: w:rsidR, w:rsidRDefault, w:rsidP on w:p, w:rsidR on w:r, + # and w:author, w:date, w:initials on w:comment are automatically added by DocxXMLEditor + comment_xml = f''' + + + {escaped_text} + +''' + editor.append_to(root, comment_xml) + + def _add_to_comments_extended_xml(self, para_id, parent_para_id): + """Add a single comment to commentsExtended.xml.""" + if not self.comments_extended_path.exists(): + shutil.copy( + TEMPLATE_DIR / "commentsExtended.xml", self.comments_extended_path + ) + + editor = self["word/commentsExtended.xml"] + root = editor.get_node(tag="w15:commentsEx") + + if parent_para_id: + xml = f'' + else: + xml = f'' + editor.append_to(root, xml) + + def _add_to_comments_ids_xml(self, para_id, durable_id): + """Add a single comment to commentsIds.xml.""" + if not self.comments_ids_path.exists(): + shutil.copy(TEMPLATE_DIR / "commentsIds.xml", self.comments_ids_path) + + editor = self["word/commentsIds.xml"] + root = editor.get_node(tag="w16cid:commentsIds") + + xml = f'' + editor.append_to(root, xml) + + def _add_to_comments_extensible_xml(self, durable_id): + """Add a single comment to commentsExtensible.xml.""" + if not self.comments_extensible_path.exists(): + shutil.copy( + TEMPLATE_DIR / "commentsExtensible.xml", self.comments_extensible_path + ) + + editor = self["word/commentsExtensible.xml"] + root = editor.get_node(tag="w16cex:commentsExtensible") + + xml = f'' + editor.append_to(root, xml) + + # ==================== Private: XML Fragments ==================== + + def _comment_range_start_xml(self, comment_id): + """Generate XML for comment range start.""" + return f'' + + def _comment_range_end_xml(self, comment_id): + """Generate XML for comment range end with reference run. + + Note: w:rsidR is automatically added by DocxXMLEditor. + """ + return f''' + + + +''' + + def _comment_ref_run_xml(self, comment_id): + """Generate XML for comment reference run. + + Note: w:rsidR is automatically added by DocxXMLEditor. + """ + return f''' + + +''' + + # ==================== Private: Metadata Updates ==================== + + def _has_relationship(self, editor, target): + """Check if a relationship with given target exists.""" + for rel_elem in editor.dom.getElementsByTagName("Relationship"): + if rel_elem.getAttribute("Target") == target: + return True + return False + + def _has_override(self, editor, part_name): + """Check if an override with given part name exists.""" + for override_elem in editor.dom.getElementsByTagName("Override"): + if override_elem.getAttribute("PartName") == part_name: + return True + return False + + def _has_author(self, editor, author): + """Check if an author already exists in people.xml.""" + for person_elem in editor.dom.getElementsByTagName("w15:person"): + if person_elem.getAttribute("w15:author") == author: + return True + return False + + def _add_author_to_people(self, author): + """Add author to people.xml (called during initialization).""" + people_path = self.word_path / "people.xml" + + # people.xml should already exist from _setup_tracking + if not people_path.exists(): + raise ValueError("people.xml should exist after _setup_tracking") + + editor = self["word/people.xml"] + root = editor.get_node(tag="w15:people") + + # Check if author already exists + if self._has_author(editor, author): + return + + # Add author with proper XML escaping to prevent injection + escaped_author = html.escape(author, quote=True) + person_xml = f''' + +''' + editor.append_to(root, person_xml) + + def _ensure_comment_relationships(self): + """Ensure word/_rels/document.xml.rels has comment relationships.""" + editor = self["word/_rels/document.xml.rels"] + + if self._has_relationship(editor, "comments.xml"): + return + + root = editor.dom.documentElement + root_tag = root.tagName # type: ignore + prefix = root_tag.split(":")[0] + ":" if ":" in root_tag else "" + next_rid_num = int(editor.get_next_rid()[3:]) + + # Add relationship elements + rels = [ + ( + next_rid_num, + "http://schemas.openxmlformats.org/officeDocument/2006/relationships/comments", + "comments.xml", + ), + ( + next_rid_num + 1, + "http://schemas.microsoft.com/office/2011/relationships/commentsExtended", + "commentsExtended.xml", + ), + ( + next_rid_num + 2, + "http://schemas.microsoft.com/office/2016/09/relationships/commentsIds", + "commentsIds.xml", + ), + ( + next_rid_num + 3, + "http://schemas.microsoft.com/office/2018/08/relationships/commentsExtensible", + "commentsExtensible.xml", + ), + ] + + for rel_id, rel_type, target in rels: + rel_xml = f'<{prefix}Relationship Id="rId{rel_id}" Type="{rel_type}" Target="{target}"/>' + editor.append_to(root, rel_xml) + + def _ensure_comment_content_types(self): + """Ensure [Content_Types].xml has comment content types.""" + editor = self["[Content_Types].xml"] + + if self._has_override(editor, "/word/comments.xml"): + return + + root = editor.dom.documentElement + + # Add Override elements + overrides = [ + ( + "/word/comments.xml", + "application/vnd.openxmlformats-officedocument.wordprocessingml.comments+xml", + ), + ( + "/word/commentsExtended.xml", + "application/vnd.openxmlformats-officedocument.wordprocessingml.commentsExtended+xml", + ), + ( + "/word/commentsIds.xml", + "application/vnd.openxmlformats-officedocument.wordprocessingml.commentsIds+xml", + ), + ( + "/word/commentsExtensible.xml", + "application/vnd.openxmlformats-officedocument.wordprocessingml.commentsExtensible+xml", + ), + ] + + for part_name, content_type in overrides: + override_xml = ( + f'' + ) + editor.append_to(root, override_xml) diff --git a/skills/docx/scripts/templates/comments.xml b/skills/docx/scripts/templates/comments.xml new file mode 100644 index 0000000..b5dace0 --- /dev/null +++ b/skills/docx/scripts/templates/comments.xml @@ -0,0 +1,3 @@ + + + \ No newline at end of file diff --git a/skills/docx/scripts/templates/commentsExtended.xml b/skills/docx/scripts/templates/commentsExtended.xml new file mode 100644 index 0000000..b4cf23e --- /dev/null +++ b/skills/docx/scripts/templates/commentsExtended.xml @@ -0,0 +1,3 @@ + + + \ No newline at end of file diff --git a/skills/docx/scripts/templates/commentsExtensible.xml b/skills/docx/scripts/templates/commentsExtensible.xml new file mode 100644 index 0000000..e32a05e --- /dev/null +++ b/skills/docx/scripts/templates/commentsExtensible.xml @@ -0,0 +1,3 @@ + + + \ No newline at end of file diff --git a/skills/docx/scripts/templates/commentsIds.xml b/skills/docx/scripts/templates/commentsIds.xml new file mode 100644 index 0000000..d04bc8e --- /dev/null +++ b/skills/docx/scripts/templates/commentsIds.xml @@ -0,0 +1,3 @@ + + + \ No newline at end of file diff --git a/skills/docx/scripts/templates/people.xml b/skills/docx/scripts/templates/people.xml new file mode 100644 index 0000000..a839caf --- /dev/null +++ b/skills/docx/scripts/templates/people.xml @@ -0,0 +1,3 @@ + + + \ No newline at end of file diff --git a/skills/docx/scripts/utilities.py b/skills/docx/scripts/utilities.py new file mode 100755 index 0000000..d92dae6 --- /dev/null +++ b/skills/docx/scripts/utilities.py @@ -0,0 +1,374 @@ +#!/usr/bin/env python3 +""" +Utilities for editing OOXML documents. + +This module provides XMLEditor, a tool for manipulating XML files with support for +line-number-based node finding and DOM manipulation. Each element is automatically +annotated with its original line and column position during parsing. + +Example usage: + editor = XMLEditor("document.xml") + + # Find node by line number or range + elem = editor.get_node(tag="w:r", line_number=519) + elem = editor.get_node(tag="w:p", line_number=range(100, 200)) + + # Find node by text content + elem = editor.get_node(tag="w:p", contains="specific text") + + # Find node by attributes + elem = editor.get_node(tag="w:r", attrs={"w:id": "target"}) + + # Combine filters + elem = editor.get_node(tag="w:p", line_number=range(1, 50), contains="text") + + # Replace, insert, or manipulate + new_elem = editor.replace_node(elem, "new text") + editor.insert_after(new_elem, "more") + + # Save changes + editor.save() +""" + +import html +from pathlib import Path +from typing import Optional, Union + +import defusedxml.minidom +import defusedxml.sax + + +class XMLEditor: + """ + Editor for manipulating OOXML XML files with line-number-based node finding. + + This class parses XML files and tracks the original line and column position + of each element. This enables finding nodes by their line number in the original + file, which is useful when working with Read tool output. + + Attributes: + xml_path: Path to the XML file being edited + encoding: Detected encoding of the XML file ('ascii' or 'utf-8') + dom: Parsed DOM tree with parse_position attributes on elements + """ + + def __init__(self, xml_path): + """ + Initialize with path to XML file and parse with line number tracking. + + Args: + xml_path: Path to XML file to edit (str or Path) + + Raises: + ValueError: If the XML file does not exist + """ + self.xml_path = Path(xml_path) + if not self.xml_path.exists(): + raise ValueError(f"XML file not found: {xml_path}") + + with open(self.xml_path, "rb") as f: + header = f.read(200).decode("utf-8", errors="ignore") + self.encoding = "ascii" if 'encoding="ascii"' in header else "utf-8" + + parser = _create_line_tracking_parser() + self.dom = defusedxml.minidom.parse(str(self.xml_path), parser) + + def get_node( + self, + tag: str, + attrs: Optional[dict[str, str]] = None, + line_number: Optional[Union[int, range]] = None, + contains: Optional[str] = None, + ): + """ + Get a DOM element by tag and identifier. + + Finds an element by either its line number in the original file or by + matching attribute values. Exactly one match must be found. + + Args: + tag: The XML tag name (e.g., "w:del", "w:ins", "w:r") + attrs: Dictionary of attribute name-value pairs to match (e.g., {"w:id": "1"}) + line_number: Line number (int) or line range (range) in original XML file (1-indexed) + contains: Text string that must appear in any text node within the element. + Supports both entity notation (“) and Unicode characters (\u201c). + + Returns: + defusedxml.minidom.Element: The matching DOM element + + Raises: + ValueError: If node not found or multiple matches found + + Example: + elem = editor.get_node(tag="w:r", line_number=519) + elem = editor.get_node(tag="w:r", line_number=range(100, 200)) + elem = editor.get_node(tag="w:del", attrs={"w:id": "1"}) + elem = editor.get_node(tag="w:p", attrs={"w14:paraId": "12345678"}) + elem = editor.get_node(tag="w:commentRangeStart", attrs={"w:id": "0"}) + elem = editor.get_node(tag="w:p", contains="specific text") + elem = editor.get_node(tag="w:t", contains="“Agreement") # Entity notation + elem = editor.get_node(tag="w:t", contains="\u201cAgreement") # Unicode character + """ + matches = [] + for elem in self.dom.getElementsByTagName(tag): + # Check line_number filter + if line_number is not None: + parse_pos = getattr(elem, "parse_position", (None,)) + elem_line = parse_pos[0] + + # Handle both single line number and range + if isinstance(line_number, range): + if elem_line not in line_number: + continue + else: + if elem_line != line_number: + continue + + # Check attrs filter + if attrs is not None: + if not all( + elem.getAttribute(attr_name) == attr_value + for attr_name, attr_value in attrs.items() + ): + continue + + # Check contains filter + if contains is not None: + elem_text = self._get_element_text(elem) + # Normalize the search string: convert HTML entities to Unicode characters + # This allows searching for both "“Rowan" and ""Rowan" + normalized_contains = html.unescape(contains) + if normalized_contains not in elem_text: + continue + + # If all applicable filters passed, this is a match + matches.append(elem) + + if not matches: + # Build descriptive error message + filters = [] + if line_number is not None: + line_str = ( + f"lines {line_number.start}-{line_number.stop - 1}" + if isinstance(line_number, range) + else f"line {line_number}" + ) + filters.append(f"at {line_str}") + if attrs is not None: + filters.append(f"with attributes {attrs}") + if contains is not None: + filters.append(f"containing '{contains}'") + + filter_desc = " ".join(filters) if filters else "" + base_msg = f"Node not found: <{tag}> {filter_desc}".strip() + + # Add helpful hint based on filters used + if contains: + hint = "Text may be split across elements or use different wording." + elif line_number: + hint = "Line numbers may have changed if document was modified." + elif attrs: + hint = "Verify attribute values are correct." + else: + hint = "Try adding filters (attrs, line_number, or contains)." + + raise ValueError(f"{base_msg}. {hint}") + if len(matches) > 1: + raise ValueError( + f"Multiple nodes found: <{tag}>. " + f"Add more filters (attrs, line_number, or contains) to narrow the search." + ) + return matches[0] + + def _get_element_text(self, elem): + """ + Recursively extract all text content from an element. + + Skips text nodes that contain only whitespace (spaces, tabs, newlines), + which typically represent XML formatting rather than document content. + + Args: + elem: defusedxml.minidom.Element to extract text from + + Returns: + str: Concatenated text from all non-whitespace text nodes within the element + """ + text_parts = [] + for node in elem.childNodes: + if node.nodeType == node.TEXT_NODE: + # Skip whitespace-only text nodes (XML formatting) + if node.data.strip(): + text_parts.append(node.data) + elif node.nodeType == node.ELEMENT_NODE: + text_parts.append(self._get_element_text(node)) + return "".join(text_parts) + + def replace_node(self, elem, new_content): + """ + Replace a DOM element with new XML content. + + Args: + elem: defusedxml.minidom.Element to replace + new_content: String containing XML to replace the node with + + Returns: + List[defusedxml.minidom.Node]: All inserted nodes + + Example: + new_nodes = editor.replace_node(old_elem, "text") + """ + parent = elem.parentNode + nodes = self._parse_fragment(new_content) + for node in nodes: + parent.insertBefore(node, elem) + parent.removeChild(elem) + return nodes + + def insert_after(self, elem, xml_content): + """ + Insert XML content after a DOM element. + + Args: + elem: defusedxml.minidom.Element to insert after + xml_content: String containing XML to insert + + Returns: + List[defusedxml.minidom.Node]: All inserted nodes + + Example: + new_nodes = editor.insert_after(elem, "text") + """ + parent = elem.parentNode + next_sibling = elem.nextSibling + nodes = self._parse_fragment(xml_content) + for node in nodes: + if next_sibling: + parent.insertBefore(node, next_sibling) + else: + parent.appendChild(node) + return nodes + + def insert_before(self, elem, xml_content): + """ + Insert XML content before a DOM element. + + Args: + elem: defusedxml.minidom.Element to insert before + xml_content: String containing XML to insert + + Returns: + List[defusedxml.minidom.Node]: All inserted nodes + + Example: + new_nodes = editor.insert_before(elem, "text") + """ + parent = elem.parentNode + nodes = self._parse_fragment(xml_content) + for node in nodes: + parent.insertBefore(node, elem) + return nodes + + def append_to(self, elem, xml_content): + """ + Append XML content as a child of a DOM element. + + Args: + elem: defusedxml.minidom.Element to append to + xml_content: String containing XML to append + + Returns: + List[defusedxml.minidom.Node]: All inserted nodes + + Example: + new_nodes = editor.append_to(elem, "text") + """ + nodes = self._parse_fragment(xml_content) + for node in nodes: + elem.appendChild(node) + return nodes + + def get_next_rid(self): + """Get the next available rId for relationships files.""" + max_id = 0 + for rel_elem in self.dom.getElementsByTagName("Relationship"): + rel_id = rel_elem.getAttribute("Id") + if rel_id.startswith("rId"): + try: + max_id = max(max_id, int(rel_id[3:])) + except ValueError: + pass + return f"rId{max_id + 1}" + + def save(self): + """ + Save the edited XML back to the file. + + Serializes the DOM tree and writes it back to the original file path, + preserving the original encoding (ascii or utf-8). + """ + content = self.dom.toxml(encoding=self.encoding) + self.xml_path.write_bytes(content) + + def _parse_fragment(self, xml_content): + """ + Parse XML fragment and return list of imported nodes. + + Args: + xml_content: String containing XML fragment + + Returns: + List of defusedxml.minidom.Node objects imported into this document + + Raises: + AssertionError: If fragment contains no element nodes + """ + # Extract namespace declarations from the root document element + root_elem = self.dom.documentElement + namespaces = [] + if root_elem and root_elem.attributes: + for i in range(root_elem.attributes.length): + attr = root_elem.attributes.item(i) + if attr.name.startswith("xmlns"): # type: ignore + namespaces.append(f'{attr.name}="{attr.value}"') # type: ignore + + ns_decl = " ".join(namespaces) + wrapper = f"{xml_content}" + fragment_doc = defusedxml.minidom.parseString(wrapper) + nodes = [ + self.dom.importNode(child, deep=True) + for child in fragment_doc.documentElement.childNodes # type: ignore + ] + elements = [n for n in nodes if n.nodeType == n.ELEMENT_NODE] + assert elements, "Fragment must contain at least one element" + return nodes + + +def _create_line_tracking_parser(): + """ + Create a SAX parser that tracks line and column numbers for each element. + + Monkey patches the SAX content handler to store the current line and column + position from the underlying expat parser onto each element as a parse_position + attribute (line, column) tuple. + + Returns: + defusedxml.sax.xmlreader.XMLReader: Configured SAX parser + """ + + def set_content_handler(dom_handler): + def startElementNS(name, tagName, attrs): + orig_start_cb(name, tagName, attrs) + cur_elem = dom_handler.elementStack[-1] + cur_elem.parse_position = ( + parser._parser.CurrentLineNumber, # type: ignore + parser._parser.CurrentColumnNumber, # type: ignore + ) + + orig_start_cb = dom_handler.startElementNS + dom_handler.startElementNS = startElementNS + orig_set_content_handler(dom_handler) + + parser = defusedxml.sax.make_parser() + orig_set_content_handler = parser.setContentHandler + parser.setContentHandler = set_content_handler # type: ignore + return parser diff --git a/skills/frontend-design/LICENSE.txt b/skills/frontend-design/LICENSE.txt new file mode 100644 index 0000000..f433b1a --- /dev/null +++ b/skills/frontend-design/LICENSE.txt @@ -0,0 +1,177 @@ + + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS diff --git a/skills/frontend-design/SKILL.md b/skills/frontend-design/SKILL.md new file mode 100644 index 0000000..5be498e --- /dev/null +++ b/skills/frontend-design/SKILL.md @@ -0,0 +1,42 @@ +--- +name: frontend-design +description: Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics. +license: Complete terms in LICENSE.txt +--- + +This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices. + +The user provides frontend requirements: a component, page, application, or interface to build. They may include context about the purpose, audience, or technical constraints. + +## Design Thinking + +Before coding, understand the context and commit to a BOLD aesthetic direction: +- **Purpose**: What problem does this interface solve? Who uses it? +- **Tone**: Pick an extreme: brutally minimal, maximalist chaos, retro-futuristic, organic/natural, luxury/refined, playful/toy-like, editorial/magazine, brutalist/raw, art deco/geometric, soft/pastel, industrial/utilitarian, etc. There are so many flavors to choose from. Use these for inspiration but design one that is true to the aesthetic direction. +- **Constraints**: Technical requirements (framework, performance, accessibility). +- **Differentiation**: What makes this UNFORGETTABLE? What's the one thing someone will remember? + +**CRITICAL**: Choose a clear conceptual direction and execute it with precision. Bold maximalism and refined minimalism both work - the key is intentionality, not intensity. + +Then implement working code (HTML/CSS/JS, React, Vue, etc.) that is: +- Production-grade and functional +- Visually striking and memorable +- Cohesive with a clear aesthetic point-of-view +- Meticulously refined in every detail + +## Frontend Aesthetics Guidelines + +Focus on: +- **Typography**: Choose fonts that are beautiful, unique, and interesting. Avoid generic fonts like Arial and Inter; opt instead for distinctive choices that elevate the frontend's aesthetics; unexpected, characterful font choices. Pair a distinctive display font with a refined body font. +- **Color & Theme**: Commit to a cohesive aesthetic. Use CSS variables for consistency. Dominant colors with sharp accents outperform timid, evenly-distributed palettes. +- **Motion**: Use animations for effects and micro-interactions. Prioritize CSS-only solutions for HTML. Use Motion library for React when available. Focus on high-impact moments: one well-orchestrated page load with staggered reveals (animation-delay) creates more delight than scattered micro-interactions. Use scroll-triggering and hover states that surprise. +- **Spatial Composition**: Unexpected layouts. Asymmetry. Overlap. Diagonal flow. Grid-breaking elements. Generous negative space OR controlled density. +- **Backgrounds & Visual Details**: Create atmosphere and depth rather than defaulting to solid colors. Add contextual effects and textures that match the overall aesthetic. Apply creative forms like gradient meshes, noise textures, geometric patterns, layered transparencies, dramatic shadows, decorative borders, custom cursors, and grain overlays. + +NEVER use generic AI-generated aesthetics like overused font families (Inter, Roboto, Arial, system fonts), cliched color schemes (particularly purple gradients on white backgrounds), predictable layouts and component patterns, and cookie-cutter design that lacks context-specific character. + +Interpret creatively and make unexpected choices that feel genuinely designed for the context. No design should be the same. Vary between light and dark themes, different fonts, different aesthetics. NEVER converge on common choices (Space Grotesk, for example) across generations. + +**IMPORTANT**: Match implementation complexity to the aesthetic vision. Maximalist designs need elaborate code with extensive animations and effects. Minimalist or refined designs need restraint, precision, and careful attention to spacing, typography, and subtle details. Elegance comes from executing the vision well. + +Remember: Claude is capable of extraordinary creative work. Don't hold back, show what can truly be created when thinking outside the box and committing fully to a distinctive vision. diff --git a/skills/internal-comms/LICENSE.txt b/skills/internal-comms/LICENSE.txt new file mode 100644 index 0000000..7a4a3ea --- /dev/null +++ b/skills/internal-comms/LICENSE.txt @@ -0,0 +1,202 @@ + + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [yyyy] [name of copyright owner] + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. \ No newline at end of file diff --git a/skills/internal-comms/SKILL.md b/skills/internal-comms/SKILL.md new file mode 100644 index 0000000..56ea935 --- /dev/null +++ b/skills/internal-comms/SKILL.md @@ -0,0 +1,32 @@ +--- +name: internal-comms +description: A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.). +license: Complete terms in LICENSE.txt +--- + +## When to use this skill +To write internal communications, use this skill for: +- 3P updates (Progress, Plans, Problems) +- Company newsletters +- FAQ responses +- Status reports +- Leadership updates +- Project updates +- Incident reports + +## How to use this skill + +To write any internal communication: + +1. **Identify the communication type** from the request +2. **Load the appropriate guideline file** from the `examples/` directory: + - `examples/3p-updates.md` - For Progress/Plans/Problems team updates + - `examples/company-newsletter.md` - For company-wide newsletters + - `examples/faq-answers.md` - For answering frequently asked questions + - `examples/general-comms.md` - For anything else that doesn't explicitly match one of the above +3. **Follow the specific instructions** in that file for formatting, tone, and content gathering + +If the communication type doesn't match any existing guideline, ask for clarification or more context about the desired format. + +## Keywords +3P updates, company newsletter, company comms, weekly update, faqs, common questions, updates, internal comms diff --git a/skills/internal-comms/examples/3p-updates.md b/skills/internal-comms/examples/3p-updates.md new file mode 100644 index 0000000..5329bfb --- /dev/null +++ b/skills/internal-comms/examples/3p-updates.md @@ -0,0 +1,47 @@ +## Instructions +You are being asked to write a 3P update. 3P updates stand for "Progress, Plans, Problems." The main audience is for executives, leadership, other teammates, etc. They're meant to be very succinct and to-the-point: think something you can read in 30-60sec or less. They're also for people with some, but not a lot of context on what the team does. + +3Ps can cover a team of any size, ranging all the way up to the entire company. The bigger the team, the less granular the tasks should be. For example, "mobile team" might have "shipped feature" or "fixed bugs," whereas the company might have really meaty 3Ps, like "hired 20 new people" or "closed 10 new deals." + +They represent the work of the team across a time period, almost always one week. They include three sections: +1) Progress: what the team has accomplished over the next time period. Focus mainly on things shipped, milestones achieved, tasks created, etc. +2) Plans: what the team plans to do over the next time period. Focus on what things are top-of-mind, really high priority, etc. for the team. +3) Problems: anything that is slowing the team down. This could be things like too few people, bugs or blockers that are preventing the team from moving forward, some deal that fell through, etc. + +Before writing them, make sure that you know the team name. If it's not specified, you can ask explicitly what the team name you're writing for is. + + +## Tools Available +Whenever possible, try to pull from available sources to get the information you need: +- Slack: posts from team members with their updates - ideally look for posts in large channels with lots of reactions +- Google Drive: docs written from critical team members with lots of views +- Email: emails with lots of responses of lots of content that seems relevant +- Calendar: non-recurring meetings that have a lot of importance, like product reviews, etc. + + +Try to gather as much context as you can, focusing on the things that covered the time period you're writing for: +- Progress: anything between a week ago and today +- Plans: anything from today to the next week +- Problems: anything between a week ago and today + + +If you don't have access, you can ask the user for things they want to cover. They might also include these things to you directly, in which case you're mostly just formatting for this particular format. + +## Workflow + +1. **Clarify scope**: Confirm the team name and time period (usually past week for Progress/Problems, next +week for Plans) +2. **Gather information**: Use available tools or ask the user directly +3. **Draft the update**: Follow the strict formatting guidelines +4. **Review**: Ensure it's concise (30-60 seconds to read) and data-driven + +## Formatting + +The format is always the same, very strict formatting. Never use any formatting other than this. Pick an emoji that is fun and captures the vibe of the team and update. + +[pick an emoji] [Team Name] (Dates Covered, usually a week) +Progress: [1-3 sentences of content] +Plans: [1-3 sentences of content] +Problems: [1-3 sentences of content] + +Each section should be no more than 1-3 sentences: clear, to the point. It should be data-driven, and generally include metrics where possible. The tone should be very matter-of-fact, not super prose-heavy. \ No newline at end of file diff --git a/skills/internal-comms/examples/company-newsletter.md b/skills/internal-comms/examples/company-newsletter.md new file mode 100644 index 0000000..4997a07 --- /dev/null +++ b/skills/internal-comms/examples/company-newsletter.md @@ -0,0 +1,65 @@ +## Instructions +You are being asked to write a company-wide newsletter update. You are meant to summarize the past week/month of a company in the form of a newsletter that the entire company will read. It should be maybe ~20-25 bullet points long. It will be sent via Slack and email, so make it consumable for that. + +Ideally it includes the following attributes: +- Lots of links: pulling documents from Google Drive that are very relevant, linking to prominent Slack messages in announce channels and from executives, perhgaps referencing emails that went company-wide, highlighting significant things that have happened in the company. +- Short and to-the-point: each bullet should probably be no longer than ~1-2 sentences +- Use the "we" tense, as you are part of the company. Many of the bullets should say "we did this" or "we did that" + +## Tools to use +If you have access to the following tools, please try to use them. If not, you can also let the user know directly that their responses would be better if they gave them access. + +- Slack: look for messages in channels with lots of people, with lots of reactions or lots of responses within the thread +- Email: look for things from executives that discuss company-wide announcements +- Calendar: if there were meetings with large attendee lists, particularly things like All-Hands meetings, big company announcements, etc. If there were documents attached to those meetings, those are great links to include. +- Documents: if there were new docs published in the last week or two that got a lot of attention, you can link them. These should be things like company-wide vision docs, plans for the upcoming quarter or half, things authored by critical executives, etc. +- External press: if you see references to articles or press we've received over the past week, that could be really cool too. + +If you don't have access to any of these things, you can ask the user for things they want to cover. In this case, you'll mostly just be polishing up and fitting to this format more directly. + +## Sections +The company is pretty big: 1000+ people. There are a variety of different teams and initiatives going on across the company. To make sure the update works well, try breaking it into sections of similar things. You might break into clusters like {product development, go to market, finance} or {recruiting, execution, vision}, or {external news, internal news} etc. Try to make sure the different areas of the company are highlighted well. + +## Prioritization +Focus on: +- Company-wide impact (not team-specific details) +- Announcements from leadership +- Major milestones and achievements +- Information that affects most employees +- External recognition or press + +Avoid: +- Overly granular team updates (save those for 3Ps) +- Information only relevant to small groups +- Duplicate information already communicated + +## Example Formats + +:megaphone: Company Announcements +- Announcement 1 +- Announcement 2 +- Announcement 3 + +:dart: Progress on Priorities +- Area 1 + - Sub-area 1 + - Sub-area 2 + - Sub-area 3 +- Area 2 + - Sub-area 1 + - Sub-area 2 + - Sub-area 3 +- Area 3 + - Sub-area 1 + - Sub-area 2 + - Sub-area 3 + +:pillar: Leadership Updates +- Post 1 +- Post 2 +- Post 3 + +:thread: Social Updates +- Update 1 +- Update 2 +- Update 3 diff --git a/skills/internal-comms/examples/faq-answers.md b/skills/internal-comms/examples/faq-answers.md new file mode 100644 index 0000000..395262a --- /dev/null +++ b/skills/internal-comms/examples/faq-answers.md @@ -0,0 +1,30 @@ +## Instructions +You are an assistant for answering questions that are being asked across the company. Every week, there are lots of questions that get asked across the company, and your goal is to try to summarize what those questions are. We want our company to be well-informed and on the same page, so your job is to produce a set of frequently asked questions that our employees are asking and attempt to answer them. Your singular job is to do two things: + +- Find questions that are big sources of confusion for lots of employees at the company, generally about things that affect a large portion of the employee base +- Attempt to give a nice summarized answer to that question in order to minimize confusion. + +Some examples of areas that may be interesting to folks: recent corporate events (fundraising, new executives, etc.), upcoming launches, hiring progress, changes to vision or focus, etc. + + +## Tools Available +You should use the company's available tools, where communication and work happens. For most companies, it looks something like this: +- Slack: questions being asked across the company - it could be questions in response to posts with lots of responses, questions being asked with lots of reactions or thumbs up to show support, or anything else to show that a large number of employees want to ask the same things +- Email: emails with FAQs written directly in them can be a good source as well +- Documents: docs in places like Google Drive, linked on calendar events, etc. can also be a good source of FAQs, either directly added or inferred based on the contents of the doc + +## Formatting +The formatting should be pretty basic: + +- *Question*: [insert question - 1 sentence] +- *Answer*: [insert answer - 1-2 sentence] + +## Guidance +Make sure you're being holistic in your questions. Don't focus too much on just the user in question or the team they are a part of, but try to capture the entire company. Try to be as holistic as you can in reading all the tools available, producing responses that are relevant to all at the company. + +## Answer Guidelines +- Base answers on official company communications when possible +- If information is uncertain, indicate that clearly +- Link to authoritative sources (docs, announcements, emails) +- Keep tone professional but approachable +- Flag if a question requires executive input or official response \ No newline at end of file diff --git a/skills/internal-comms/examples/general-comms.md b/skills/internal-comms/examples/general-comms.md new file mode 100644 index 0000000..0ea9770 --- /dev/null +++ b/skills/internal-comms/examples/general-comms.md @@ -0,0 +1,16 @@ + ## Instructions + You are being asked to write internal company communication that doesn't fit into the standard formats (3P + updates, newsletters, or FAQs). + + Before proceeding: + 1. Ask the user about their target audience + 2. Understand the communication's purpose + 3. Clarify the desired tone (formal, casual, urgent, informational) + 4. Confirm any specific formatting requirements + + Use these general principles: + - Be clear and concise + - Use active voice + - Put the most important information first + - Include relevant links and references + - Match the company's communication style \ No newline at end of file diff --git a/skills/mcp-builder/LICENSE.txt b/skills/mcp-builder/LICENSE.txt new file mode 100644 index 0000000..7a4a3ea --- /dev/null +++ b/skills/mcp-builder/LICENSE.txt @@ -0,0 +1,202 @@ + + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [yyyy] [name of copyright owner] + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. \ No newline at end of file diff --git a/skills/mcp-builder/SKILL.md b/skills/mcp-builder/SKILL.md new file mode 100644 index 0000000..8a1a77a --- /dev/null +++ b/skills/mcp-builder/SKILL.md @@ -0,0 +1,236 @@ +--- +name: mcp-builder +description: Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). +license: Complete terms in LICENSE.txt +--- + +# MCP Server Development Guide + +## Overview + +Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks. + +--- + +# Process + +## 🚀 High-Level Workflow + +Creating a high-quality MCP server involves four main phases: + +### Phase 1: Deep Research and Planning + +#### 1.1 Understand Modern MCP Design + +**API Coverage vs. Workflow Tools:** +Balance comprehensive API endpoint coverage with specialized workflow tools. Workflow tools can be more convenient for specific tasks, while comprehensive coverage gives agents flexibility to compose operations. Performance varies by client—some clients benefit from code execution that combines basic tools, while others work better with higher-level workflows. When uncertain, prioritize comprehensive API coverage. + +**Tool Naming and Discoverability:** +Clear, descriptive tool names help agents find the right tools quickly. Use consistent prefixes (e.g., `github_create_issue`, `github_list_repos`) and action-oriented naming. + +**Context Management:** +Agents benefit from concise tool descriptions and the ability to filter/paginate results. Design tools that return focused, relevant data. Some clients support code execution which can help agents filter and process data efficiently. + +**Actionable Error Messages:** +Error messages should guide agents toward solutions with specific suggestions and next steps. + +#### 1.2 Study MCP Protocol Documentation + +**Navigate the MCP specification:** + +Start with the sitemap to find relevant pages: `https://modelcontextprotocol.io/sitemap.xml` + +Then fetch specific pages with `.md` suffix for markdown format (e.g., `https://modelcontextprotocol.io/specification/draft.md`). + +Key pages to review: +- Specification overview and architecture +- Transport mechanisms (streamable HTTP, stdio) +- Tool, resource, and prompt definitions + +#### 1.3 Study Framework Documentation + +**Recommended stack:** +- **Language**: TypeScript (high-quality SDK support and good compatibility in many execution environments e.g. MCPB. Plus AI models are good at generating TypeScript code, benefiting from its broad usage, static typing and good linting tools) +- **Transport**: Streamable HTTP for remote servers, using stateless JSON (simpler to scale and maintain, as opposed to stateful sessions and streaming responses). stdio for local servers. + +**Load framework documentation:** + +- **MCP Best Practices**: [📋 View Best Practices](./reference/mcp_best_practices.md) - Core guidelines + +**For TypeScript (recommended):** +- **TypeScript SDK**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md` +- [⚡ TypeScript Guide](./reference/node_mcp_server.md) - TypeScript patterns and examples + +**For Python:** +- **Python SDK**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md` +- [🐍 Python Guide](./reference/python_mcp_server.md) - Python patterns and examples + +#### 1.4 Plan Your Implementation + +**Understand the API:** +Review the service's API documentation to identify key endpoints, authentication requirements, and data models. Use web search and WebFetch as needed. + +**Tool Selection:** +Prioritize comprehensive API coverage. List endpoints to implement, starting with the most common operations. + +--- + +### Phase 2: Implementation + +#### 2.1 Set Up Project Structure + +See language-specific guides for project setup: +- [⚡ TypeScript Guide](./reference/node_mcp_server.md) - Project structure, package.json, tsconfig.json +- [🐍 Python Guide](./reference/python_mcp_server.md) - Module organization, dependencies + +#### 2.2 Implement Core Infrastructure + +Create shared utilities: +- API client with authentication +- Error handling helpers +- Response formatting (JSON/Markdown) +- Pagination support + +#### 2.3 Implement Tools + +For each tool: + +**Input Schema:** +- Use Zod (TypeScript) or Pydantic (Python) +- Include constraints and clear descriptions +- Add examples in field descriptions + +**Output Schema:** +- Define `outputSchema` where possible for structured data +- Use `structuredContent` in tool responses (TypeScript SDK feature) +- Helps clients understand and process tool outputs + +**Tool Description:** +- Concise summary of functionality +- Parameter descriptions +- Return type schema + +**Implementation:** +- Async/await for I/O operations +- Proper error handling with actionable messages +- Support pagination where applicable +- Return both text content and structured data when using modern SDKs + +**Annotations:** +- `readOnlyHint`: true/false +- `destructiveHint`: true/false +- `idempotentHint`: true/false +- `openWorldHint`: true/false + +--- + +### Phase 3: Review and Test + +#### 3.1 Code Quality + +Review for: +- No duplicated code (DRY principle) +- Consistent error handling +- Full type coverage +- Clear tool descriptions + +#### 3.2 Build and Test + +**TypeScript:** +- Run `npm run build` to verify compilation +- Test with MCP Inspector: `npx @modelcontextprotocol/inspector` + +**Python:** +- Verify syntax: `python -m py_compile your_server.py` +- Test with MCP Inspector + +See language-specific guides for detailed testing approaches and quality checklists. + +--- + +### Phase 4: Create Evaluations + +After implementing your MCP server, create comprehensive evaluations to test its effectiveness. + +**Load [✅ Evaluation Guide](./reference/evaluation.md) for complete evaluation guidelines.** + +#### 4.1 Understand Evaluation Purpose + +Use evaluations to test whether LLMs can effectively use your MCP server to answer realistic, complex questions. + +#### 4.2 Create 10 Evaluation Questions + +To create effective evaluations, follow the process outlined in the evaluation guide: + +1. **Tool Inspection**: List available tools and understand their capabilities +2. **Content Exploration**: Use READ-ONLY operations to explore available data +3. **Question Generation**: Create 10 complex, realistic questions +4. **Answer Verification**: Solve each question yourself to verify answers + +#### 4.3 Evaluation Requirements + +Ensure each question is: +- **Independent**: Not dependent on other questions +- **Read-only**: Only non-destructive operations required +- **Complex**: Requiring multiple tool calls and deep exploration +- **Realistic**: Based on real use cases humans would care about +- **Verifiable**: Single, clear answer that can be verified by string comparison +- **Stable**: Answer won't change over time + +#### 4.4 Output Format + +Create an XML file with this structure: + +```xml + + + Find discussions about AI model launches with animal codenames. One model needed a specific safety designation that uses the format ASL-X. What number X was being determined for the model named after a spotted wild cat? + 3 + + + +``` + +--- + +# Reference Files + +## 📚 Documentation Library + +Load these resources as needed during development: + +### Core MCP Documentation (Load First) +- **MCP Protocol**: Start with sitemap at `https://modelcontextprotocol.io/sitemap.xml`, then fetch specific pages with `.md` suffix +- [📋 MCP Best Practices](./reference/mcp_best_practices.md) - Universal MCP guidelines including: + - Server and tool naming conventions + - Response format guidelines (JSON vs Markdown) + - Pagination best practices + - Transport selection (streamable HTTP vs stdio) + - Security and error handling standards + +### SDK Documentation (Load During Phase 1/2) +- **Python SDK**: Fetch from `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md` +- **TypeScript SDK**: Fetch from `https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md` + +### Language-Specific Implementation Guides (Load During Phase 2) +- [🐍 Python Implementation Guide](./reference/python_mcp_server.md) - Complete Python/FastMCP guide with: + - Server initialization patterns + - Pydantic model examples + - Tool registration with `@mcp.tool` + - Complete working examples + - Quality checklist + +- [⚡ TypeScript Implementation Guide](./reference/node_mcp_server.md) - Complete TypeScript guide with: + - Project structure + - Zod schema patterns + - Tool registration with `server.registerTool` + - Complete working examples + - Quality checklist + +### Evaluation Guide (Load During Phase 4) +- [✅ Evaluation Guide](./reference/evaluation.md) - Complete evaluation creation guide with: + - Question creation guidelines + - Answer verification strategies + - XML format specifications + - Example questions and answers + - Running an evaluation with the provided scripts diff --git a/skills/mcp-builder/reference/evaluation.md b/skills/mcp-builder/reference/evaluation.md new file mode 100644 index 0000000..87e9bb7 --- /dev/null +++ b/skills/mcp-builder/reference/evaluation.md @@ -0,0 +1,602 @@ +# MCP Server Evaluation Guide + +## Overview + +This document provides guidance on creating comprehensive evaluations for MCP servers. Evaluations test whether LLMs can effectively use your MCP server to answer realistic, complex questions using only the tools provided. + +--- + +## Quick Reference + +### Evaluation Requirements +- Create 10 human-readable questions +- Questions must be READ-ONLY, INDEPENDENT, NON-DESTRUCTIVE +- Each question requires multiple tool calls (potentially dozens) +- Answers must be single, verifiable values +- Answers must be STABLE (won't change over time) + +### Output Format +```xml + + + Your question here + Single verifiable answer + + +``` + +--- + +## Purpose of Evaluations + +The measure of quality of an MCP server is NOT how well or comprehensively the server implements tools, but how well these implementations (input/output schemas, docstrings/descriptions, functionality) enable LLMs with no other context and access ONLY to the MCP servers to answer realistic and difficult questions. + +## Evaluation Overview + +Create 10 human-readable questions requiring ONLY READ-ONLY, INDEPENDENT, NON-DESTRUCTIVE, and IDEMPOTENT operations to answer. Each question should be: +- Realistic +- Clear and concise +- Unambiguous +- Complex, requiring potentially dozens of tool calls or steps +- Answerable with a single, verifiable value that you identify in advance + +## Question Guidelines + +### Core Requirements + +1. **Questions MUST be independent** + - Each question should NOT depend on the answer to any other question + - Should not assume prior write operations from processing another question + +2. **Questions MUST require ONLY NON-DESTRUCTIVE AND IDEMPOTENT tool use** + - Should not instruct or require modifying state to arrive at the correct answer + +3. **Questions must be REALISTIC, CLEAR, CONCISE, and COMPLEX** + - Must require another LLM to use multiple (potentially dozens of) tools or steps to answer + +### Complexity and Depth + +4. **Questions must require deep exploration** + - Consider multi-hop questions requiring multiple sub-questions and sequential tool calls + - Each step should benefit from information found in previous questions + +5. **Questions may require extensive paging** + - May need paging through multiple pages of results + - May require querying old data (1-2 years out-of-date) to find niche information + - The questions must be DIFFICULT + +6. **Questions must require deep understanding** + - Rather than surface-level knowledge + - May pose complex ideas as True/False questions requiring evidence + - May use multiple-choice format where LLM must search different hypotheses + +7. **Questions must not be solvable with straightforward keyword search** + - Do not include specific keywords from the target content + - Use synonyms, related concepts, or paraphrases + - Require multiple searches, analyzing multiple related items, extracting context, then deriving the answer + +### Tool Testing + +8. **Questions should stress-test tool return values** + - May elicit tools returning large JSON objects or lists, overwhelming the LLM + - Should require understanding multiple modalities of data: + - IDs and names + - Timestamps and datetimes (months, days, years, seconds) + - File IDs, names, extensions, and mimetypes + - URLs, GIDs, etc. + - Should probe the tool's ability to return all useful forms of data + +9. **Questions should MOSTLY reflect real human use cases** + - The kinds of information retrieval tasks that HUMANS assisted by an LLM would care about + +10. **Questions may require dozens of tool calls** + - This challenges LLMs with limited context + - Encourages MCP server tools to reduce information returned + +11. **Include ambiguous questions** + - May be ambiguous OR require difficult decisions on which tools to call + - Force the LLM to potentially make mistakes or misinterpret + - Ensure that despite AMBIGUITY, there is STILL A SINGLE VERIFIABLE ANSWER + +### Stability + +12. **Questions must be designed so the answer DOES NOT CHANGE** + - Do not ask questions that rely on "current state" which is dynamic + - For example, do not count: + - Number of reactions to a post + - Number of replies to a thread + - Number of members in a channel + +13. **DO NOT let the MCP server RESTRICT the kinds of questions you create** + - Create challenging and complex questions + - Some may not be solvable with the available MCP server tools + - Questions may require specific output formats (datetime vs. epoch time, JSON vs. MARKDOWN) + - Questions may require dozens of tool calls to complete + +## Answer Guidelines + +### Verification + +1. **Answers must be VERIFIABLE via direct string comparison** + - If the answer can be re-written in many formats, clearly specify the output format in the QUESTION + - Examples: "Use YYYY/MM/DD.", "Respond True or False.", "Answer A, B, C, or D and nothing else." + - Answer should be a single VERIFIABLE value such as: + - User ID, user name, display name, first name, last name + - Channel ID, channel name + - Message ID, string + - URL, title + - Numerical quantity + - Timestamp, datetime + - Boolean (for True/False questions) + - Email address, phone number + - File ID, file name, file extension + - Multiple choice answer + - Answers must not require special formatting or complex, structured output + - Answer will be verified using DIRECT STRING COMPARISON + +### Readability + +2. **Answers should generally prefer HUMAN-READABLE formats** + - Examples: names, first name, last name, datetime, file name, message string, URL, yes/no, true/false, a/b/c/d + - Rather than opaque IDs (though IDs are acceptable) + - The VAST MAJORITY of answers should be human-readable + +### Stability + +3. **Answers must be STABLE/STATIONARY** + - Look at old content (e.g., conversations that have ended, projects that have launched, questions answered) + - Create QUESTIONS based on "closed" concepts that will always return the same answer + - Questions may ask to consider a fixed time window to insulate from non-stationary answers + - Rely on context UNLIKELY to change + - Example: if finding a paper name, be SPECIFIC enough so answer is not confused with papers published later + +4. **Answers must be CLEAR and UNAMBIGUOUS** + - Questions must be designed so there is a single, clear answer + - Answer can be derived from using the MCP server tools + +### Diversity + +5. **Answers must be DIVERSE** + - Answer should be a single VERIFIABLE value in diverse modalities and formats + - User concept: user ID, user name, display name, first name, last name, email address, phone number + - Channel concept: channel ID, channel name, channel topic + - Message concept: message ID, message string, timestamp, month, day, year + +6. **Answers must NOT be complex structures** + - Not a list of values + - Not a complex object + - Not a list of IDs or strings + - Not natural language text + - UNLESS the answer can be straightforwardly verified using DIRECT STRING COMPARISON + - And can be realistically reproduced + - It should be unlikely that an LLM would return the same list in any other order or format + +## Evaluation Process + +### Step 1: Documentation Inspection + +Read the documentation of the target API to understand: +- Available endpoints and functionality +- If ambiguity exists, fetch additional information from the web +- Parallelize this step AS MUCH AS POSSIBLE +- Ensure each subagent is ONLY examining documentation from the file system or on the web + +### Step 2: Tool Inspection + +List the tools available in the MCP server: +- Inspect the MCP server directly +- Understand input/output schemas, docstrings, and descriptions +- WITHOUT calling the tools themselves at this stage + +### Step 3: Developing Understanding + +Repeat steps 1 & 2 until you have a good understanding: +- Iterate multiple times +- Think about the kinds of tasks you want to create +- Refine your understanding +- At NO stage should you READ the code of the MCP server implementation itself +- Use your intuition and understanding to create reasonable, realistic, but VERY challenging tasks + +### Step 4: Read-Only Content Inspection + +After understanding the API and tools, USE the MCP server tools: +- Inspect content using READ-ONLY and NON-DESTRUCTIVE operations ONLY +- Goal: identify specific content (e.g., users, channels, messages, projects, tasks) for creating realistic questions +- Should NOT call any tools that modify state +- Will NOT read the code of the MCP server implementation itself +- Parallelize this step with individual sub-agents pursuing independent explorations +- Ensure each subagent is only performing READ-ONLY, NON-DESTRUCTIVE, and IDEMPOTENT operations +- BE CAREFUL: SOME TOOLS may return LOTS OF DATA which would cause you to run out of CONTEXT +- Make INCREMENTAL, SMALL, AND TARGETED tool calls for exploration +- In all tool call requests, use the `limit` parameter to limit results (<10) +- Use pagination + +### Step 5: Task Generation + +After inspecting the content, create 10 human-readable questions: +- An LLM should be able to answer these with the MCP server +- Follow all question and answer guidelines above + +## Output Format + +Each QA pair consists of a question and an answer. The output should be an XML file with this structure: + +```xml + + + Find the project created in Q2 2024 with the highest number of completed tasks. What is the project name? + Website Redesign + + + Search for issues labeled as "bug" that were closed in March 2024. Which user closed the most issues? Provide their username. + sarah_dev + + + Look for pull requests that modified files in the /api directory and were merged between January 1 and January 31, 2024. How many different contributors worked on these PRs? + 7 + + + Find the repository with the most stars that was created before 2023. What is the repository name? + data-pipeline + + +``` + +## Evaluation Examples + +### Good Questions + +**Example 1: Multi-hop question requiring deep exploration (GitHub MCP)** +```xml + + Find the repository that was archived in Q3 2023 and had previously been the most forked project in the organization. What was the primary programming language used in that repository? + Python + +``` + +This question is good because: +- Requires multiple searches to find archived repositories +- Needs to identify which had the most forks before archival +- Requires examining repository details for the language +- Answer is a simple, verifiable value +- Based on historical (closed) data that won't change + +**Example 2: Requires understanding context without keyword matching (Project Management MCP)** +```xml + + Locate the initiative focused on improving customer onboarding that was completed in late 2023. The project lead created a retrospective document after completion. What was the lead's role title at that time? + Product Manager + +``` + +This question is good because: +- Doesn't use specific project name ("initiative focused on improving customer onboarding") +- Requires finding completed projects from specific timeframe +- Needs to identify the project lead and their role +- Requires understanding context from retrospective documents +- Answer is human-readable and stable +- Based on completed work (won't change) + +**Example 3: Complex aggregation requiring multiple steps (Issue Tracker MCP)** +```xml + + Among all bugs reported in January 2024 that were marked as critical priority, which assignee resolved the highest percentage of their assigned bugs within 48 hours? Provide the assignee's username. + alex_eng + +``` + +This question is good because: +- Requires filtering bugs by date, priority, and status +- Needs to group by assignee and calculate resolution rates +- Requires understanding timestamps to determine 48-hour windows +- Tests pagination (potentially many bugs to process) +- Answer is a single username +- Based on historical data from specific time period + +**Example 4: Requires synthesis across multiple data types (CRM MCP)** +```xml + + Find the account that upgraded from the Starter to Enterprise plan in Q4 2023 and had the highest annual contract value. What industry does this account operate in? + Healthcare + +``` + +This question is good because: +- Requires understanding subscription tier changes +- Needs to identify upgrade events in specific timeframe +- Requires comparing contract values +- Must access account industry information +- Answer is simple and verifiable +- Based on completed historical transactions + +### Poor Questions + +**Example 1: Answer changes over time** +```xml + + How many open issues are currently assigned to the engineering team? + 47 + +``` + +This question is poor because: +- The answer will change as issues are created, closed, or reassigned +- Not based on stable/stationary data +- Relies on "current state" which is dynamic + +**Example 2: Too easy with keyword search** +```xml + + Find the pull request with title "Add authentication feature" and tell me who created it. + developer123 + +``` + +This question is poor because: +- Can be solved with a straightforward keyword search for exact title +- Doesn't require deep exploration or understanding +- No synthesis or analysis needed + +**Example 3: Ambiguous answer format** +```xml + + List all the repositories that have Python as their primary language. + repo1, repo2, repo3, data-pipeline, ml-tools + +``` + +This question is poor because: +- Answer is a list that could be returned in any order +- Difficult to verify with direct string comparison +- LLM might format differently (JSON array, comma-separated, newline-separated) +- Better to ask for a specific aggregate (count) or superlative (most stars) + +## Verification Process + +After creating evaluations: + +1. **Examine the XML file** to understand the schema +2. **Load each task instruction** and in parallel using the MCP server and tools, identify the correct answer by attempting to solve the task YOURSELF +3. **Flag any operations** that require WRITE or DESTRUCTIVE operations +4. **Accumulate all CORRECT answers** and replace any incorrect answers in the document +5. **Remove any ``** that require WRITE or DESTRUCTIVE operations + +Remember to parallelize solving tasks to avoid running out of context, then accumulate all answers and make changes to the file at the end. + +## Tips for Creating Quality Evaluations + +1. **Think Hard and Plan Ahead** before generating tasks +2. **Parallelize Where Opportunity Arises** to speed up the process and manage context +3. **Focus on Realistic Use Cases** that humans would actually want to accomplish +4. **Create Challenging Questions** that test the limits of the MCP server's capabilities +5. **Ensure Stability** by using historical data and closed concepts +6. **Verify Answers** by solving the questions yourself using the MCP server tools +7. **Iterate and Refine** based on what you learn during the process + +--- + +# Running Evaluations + +After creating your evaluation file, you can use the provided evaluation harness to test your MCP server. + +## Setup + +1. **Install Dependencies** + + ```bash + pip install -r scripts/requirements.txt + ``` + + Or install manually: + ```bash + pip install anthropic mcp + ``` + +2. **Set API Key** + + ```bash + export ANTHROPIC_API_KEY=your_api_key_here + ``` + +## Evaluation File Format + +Evaluation files use XML format with `` elements: + +```xml + + + Find the project created in Q2 2024 with the highest number of completed tasks. What is the project name? + Website Redesign + + + Search for issues labeled as "bug" that were closed in March 2024. Which user closed the most issues? Provide their username. + sarah_dev + + +``` + +## Running Evaluations + +The evaluation script (`scripts/evaluation.py`) supports three transport types: + +**Important:** +- **stdio transport**: The evaluation script automatically launches and manages the MCP server process for you. Do not run the server manually. +- **sse/http transports**: You must start the MCP server separately before running the evaluation. The script connects to the already-running server at the specified URL. + +### 1. Local STDIO Server + +For locally-run MCP servers (script launches the server automatically): + +```bash +python scripts/evaluation.py \ + -t stdio \ + -c python \ + -a my_mcp_server.py \ + evaluation.xml +``` + +With environment variables: +```bash +python scripts/evaluation.py \ + -t stdio \ + -c python \ + -a my_mcp_server.py \ + -e API_KEY=abc123 \ + -e DEBUG=true \ + evaluation.xml +``` + +### 2. Server-Sent Events (SSE) + +For SSE-based MCP servers (you must start the server first): + +```bash +python scripts/evaluation.py \ + -t sse \ + -u https://example.com/mcp \ + -H "Authorization: Bearer token123" \ + -H "X-Custom-Header: value" \ + evaluation.xml +``` + +### 3. HTTP (Streamable HTTP) + +For HTTP-based MCP servers (you must start the server first): + +```bash +python scripts/evaluation.py \ + -t http \ + -u https://example.com/mcp \ + -H "Authorization: Bearer token123" \ + evaluation.xml +``` + +## Command-Line Options + +``` +usage: evaluation.py [-h] [-t {stdio,sse,http}] [-m MODEL] [-c COMMAND] + [-a ARGS [ARGS ...]] [-e ENV [ENV ...]] [-u URL] + [-H HEADERS [HEADERS ...]] [-o OUTPUT] + eval_file + +positional arguments: + eval_file Path to evaluation XML file + +optional arguments: + -h, --help Show help message + -t, --transport Transport type: stdio, sse, or http (default: stdio) + -m, --model Claude model to use (default: claude-3-7-sonnet-20250219) + -o, --output Output file for report (default: print to stdout) + +stdio options: + -c, --command Command to run MCP server (e.g., python, node) + -a, --args Arguments for the command (e.g., server.py) + -e, --env Environment variables in KEY=VALUE format + +sse/http options: + -u, --url MCP server URL + -H, --header HTTP headers in 'Key: Value' format +``` + +## Output + +The evaluation script generates a detailed report including: + +- **Summary Statistics**: + - Accuracy (correct/total) + - Average task duration + - Average tool calls per task + - Total tool calls + +- **Per-Task Results**: + - Prompt and expected response + - Actual response from the agent + - Whether the answer was correct (✅/❌) + - Duration and tool call details + - Agent's summary of its approach + - Agent's feedback on the tools + +### Save Report to File + +```bash +python scripts/evaluation.py \ + -t stdio \ + -c python \ + -a my_server.py \ + -o evaluation_report.md \ + evaluation.xml +``` + +## Complete Example Workflow + +Here's a complete example of creating and running an evaluation: + +1. **Create your evaluation file** (`my_evaluation.xml`): + +```xml + + + Find the user who created the most issues in January 2024. What is their username? + alice_developer + + + Among all pull requests merged in Q1 2024, which repository had the highest number? Provide the repository name. + backend-api + + + Find the project that was completed in December 2023 and had the longest duration from start to finish. How many days did it take? + 127 + + +``` + +2. **Install dependencies**: + +```bash +pip install -r scripts/requirements.txt +export ANTHROPIC_API_KEY=your_api_key +``` + +3. **Run evaluation**: + +```bash +python scripts/evaluation.py \ + -t stdio \ + -c python \ + -a github_mcp_server.py \ + -e GITHUB_TOKEN=ghp_xxx \ + -o github_eval_report.md \ + my_evaluation.xml +``` + +4. **Review the report** in `github_eval_report.md` to: + - See which questions passed/failed + - Read the agent's feedback on your tools + - Identify areas for improvement + - Iterate on your MCP server design + +## Troubleshooting + +### Connection Errors + +If you get connection errors: +- **STDIO**: Verify the command and arguments are correct +- **SSE/HTTP**: Check the URL is accessible and headers are correct +- Ensure any required API keys are set in environment variables or headers + +### Low Accuracy + +If many evaluations fail: +- Review the agent's feedback for each task +- Check if tool descriptions are clear and comprehensive +- Verify input parameters are well-documented +- Consider whether tools return too much or too little data +- Ensure error messages are actionable + +### Timeout Issues + +If tasks are timing out: +- Use a more capable model (e.g., `claude-3-7-sonnet-20250219`) +- Check if tools are returning too much data +- Verify pagination is working correctly +- Consider simplifying complex questions \ No newline at end of file diff --git a/skills/mcp-builder/reference/mcp_best_practices.md b/skills/mcp-builder/reference/mcp_best_practices.md new file mode 100644 index 0000000..b9d343c --- /dev/null +++ b/skills/mcp-builder/reference/mcp_best_practices.md @@ -0,0 +1,249 @@ +# MCP Server Best Practices + +## Quick Reference + +### Server Naming +- **Python**: `{service}_mcp` (e.g., `slack_mcp`) +- **Node/TypeScript**: `{service}-mcp-server` (e.g., `slack-mcp-server`) + +### Tool Naming +- Use snake_case with service prefix +- Format: `{service}_{action}_{resource}` +- Example: `slack_send_message`, `github_create_issue` + +### Response Formats +- Support both JSON and Markdown formats +- JSON for programmatic processing +- Markdown for human readability + +### Pagination +- Always respect `limit` parameter +- Return `has_more`, `next_offset`, `total_count` +- Default to 20-50 items + +### Transport +- **Streamable HTTP**: For remote servers, multi-client scenarios +- **stdio**: For local integrations, command-line tools +- Avoid SSE (deprecated in favor of streamable HTTP) + +--- + +## Server Naming Conventions + +Follow these standardized naming patterns: + +**Python**: Use format `{service}_mcp` (lowercase with underscores) +- Examples: `slack_mcp`, `github_mcp`, `jira_mcp` + +**Node/TypeScript**: Use format `{service}-mcp-server` (lowercase with hyphens) +- Examples: `slack-mcp-server`, `github-mcp-server`, `jira-mcp-server` + +The name should be general, descriptive of the service being integrated, easy to infer from the task description, and without version numbers. + +--- + +## Tool Naming and Design + +### Tool Naming + +1. **Use snake_case**: `search_users`, `create_project`, `get_channel_info` +2. **Include service prefix**: Anticipate that your MCP server may be used alongside other MCP servers + - Use `slack_send_message` instead of just `send_message` + - Use `github_create_issue` instead of just `create_issue` +3. **Be action-oriented**: Start with verbs (get, list, search, create, etc.) +4. **Be specific**: Avoid generic names that could conflict with other servers + +### Tool Design + +- Tool descriptions must narrowly and unambiguously describe functionality +- Descriptions must precisely match actual functionality +- Provide tool annotations (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) +- Keep tool operations focused and atomic + +--- + +## Response Formats + +All tools that return data should support multiple formats: + +### JSON Format (`response_format="json"`) +- Machine-readable structured data +- Include all available fields and metadata +- Consistent field names and types +- Use for programmatic processing + +### Markdown Format (`response_format="markdown"`, typically default) +- Human-readable formatted text +- Use headers, lists, and formatting for clarity +- Convert timestamps to human-readable format +- Show display names with IDs in parentheses +- Omit verbose metadata + +--- + +## Pagination + +For tools that list resources: + +- **Always respect the `limit` parameter** +- **Implement pagination**: Use `offset` or cursor-based pagination +- **Return pagination metadata**: Include `has_more`, `next_offset`/`next_cursor`, `total_count` +- **Never load all results into memory**: Especially important for large datasets +- **Default to reasonable limits**: 20-50 items is typical + +Example pagination response: +```json +{ + "total": 150, + "count": 20, + "offset": 0, + "items": [...], + "has_more": true, + "next_offset": 20 +} +``` + +--- + +## Transport Options + +### Streamable HTTP + +**Best for**: Remote servers, web services, multi-client scenarios + +**Characteristics**: +- Bidirectional communication over HTTP +- Supports multiple simultaneous clients +- Can be deployed as a web service +- Enables server-to-client notifications + +**Use when**: +- Serving multiple clients simultaneously +- Deploying as a cloud service +- Integration with web applications + +### stdio + +**Best for**: Local integrations, command-line tools + +**Characteristics**: +- Standard input/output stream communication +- Simple setup, no network configuration needed +- Runs as a subprocess of the client + +**Use when**: +- Building tools for local development environments +- Integrating with desktop applications +- Single-user, single-session scenarios + +**Note**: stdio servers should NOT log to stdout (use stderr for logging) + +### Transport Selection + +| Criterion | stdio | Streamable HTTP | +|-----------|-------|-----------------| +| **Deployment** | Local | Remote | +| **Clients** | Single | Multiple | +| **Complexity** | Low | Medium | +| **Real-time** | No | Yes | + +--- + +## Security Best Practices + +### Authentication and Authorization + +**OAuth 2.1**: +- Use secure OAuth 2.1 with certificates from recognized authorities +- Validate access tokens before processing requests +- Only accept tokens specifically intended for your server + +**API Keys**: +- Store API keys in environment variables, never in code +- Validate keys on server startup +- Provide clear error messages when authentication fails + +### Input Validation + +- Sanitize file paths to prevent directory traversal +- Validate URLs and external identifiers +- Check parameter sizes and ranges +- Prevent command injection in system calls +- Use schema validation (Pydantic/Zod) for all inputs + +### Error Handling + +- Don't expose internal errors to clients +- Log security-relevant errors server-side +- Provide helpful but not revealing error messages +- Clean up resources after errors + +### DNS Rebinding Protection + +For streamable HTTP servers running locally: +- Enable DNS rebinding protection +- Validate the `Origin` header on all incoming connections +- Bind to `127.0.0.1` rather than `0.0.0.0` + +--- + +## Tool Annotations + +Provide annotations to help clients understand tool behavior: + +| Annotation | Type | Default | Description | +|-----------|------|---------|-------------| +| `readOnlyHint` | boolean | false | Tool does not modify its environment | +| `destructiveHint` | boolean | true | Tool may perform destructive updates | +| `idempotentHint` | boolean | false | Repeated calls with same args have no additional effect | +| `openWorldHint` | boolean | true | Tool interacts with external entities | + +**Important**: Annotations are hints, not security guarantees. Clients should not make security-critical decisions based solely on annotations. + +--- + +## Error Handling + +- Use standard JSON-RPC error codes +- Report tool errors within result objects (not protocol-level errors) +- Provide helpful, specific error messages with suggested next steps +- Don't expose internal implementation details +- Clean up resources properly on errors + +Example error handling: +```typescript +try { + const result = performOperation(); + return { content: [{ type: "text", text: result }] }; +} catch (error) { + return { + isError: true, + content: [{ + type: "text", + text: `Error: ${error.message}. Try using filter='active_only' to reduce results.` + }] + }; +} +``` + +--- + +## Testing Requirements + +Comprehensive testing should cover: + +- **Functional testing**: Verify correct execution with valid/invalid inputs +- **Integration testing**: Test interaction with external systems +- **Security testing**: Validate auth, input sanitization, rate limiting +- **Performance testing**: Check behavior under load, timeouts +- **Error handling**: Ensure proper error reporting and cleanup + +--- + +## Documentation Requirements + +- Provide clear documentation of all tools and capabilities +- Include working examples (at least 3 per major feature) +- Document security considerations +- Specify required permissions and access levels +- Document rate limits and performance characteristics diff --git a/skills/mcp-builder/reference/node_mcp_server.md b/skills/mcp-builder/reference/node_mcp_server.md new file mode 100644 index 0000000..f6e5df9 --- /dev/null +++ b/skills/mcp-builder/reference/node_mcp_server.md @@ -0,0 +1,970 @@ +# Node/TypeScript MCP Server Implementation Guide + +## Overview + +This document provides Node/TypeScript-specific best practices and examples for implementing MCP servers using the MCP TypeScript SDK. It covers project structure, server setup, tool registration patterns, input validation with Zod, error handling, and complete working examples. + +--- + +## Quick Reference + +### Key Imports +```typescript +import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; +import { StreamableHTTPServerTransport } from "@modelcontextprotocol/sdk/server/streamableHttp.js"; +import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js"; +import express from "express"; +import { z } from "zod"; +``` + +### Server Initialization +```typescript +const server = new McpServer({ + name: "service-mcp-server", + version: "1.0.0" +}); +``` + +### Tool Registration Pattern +```typescript +server.registerTool( + "tool_name", + { + title: "Tool Display Name", + description: "What the tool does", + inputSchema: { param: z.string() }, + outputSchema: { result: z.string() } + }, + async ({ param }) => { + const output = { result: `Processed: ${param}` }; + return { + content: [{ type: "text", text: JSON.stringify(output) }], + structuredContent: output // Modern pattern for structured data + }; + } +); +``` + +--- + +## MCP TypeScript SDK + +The official MCP TypeScript SDK provides: +- `McpServer` class for server initialization +- `registerTool` method for tool registration +- Zod schema integration for runtime input validation +- Type-safe tool handler implementations + +**IMPORTANT - Use Modern APIs Only:** +- **DO use**: `server.registerTool()`, `server.registerResource()`, `server.registerPrompt()` +- **DO NOT use**: Old deprecated APIs such as `server.tool()`, `server.setRequestHandler(ListToolsRequestSchema, ...)`, or manual handler registration +- The `register*` methods provide better type safety, automatic schema handling, and are the recommended approach + +See the MCP SDK documentation in the references for complete details. + +## Server Naming Convention + +Node/TypeScript MCP servers must follow this naming pattern: +- **Format**: `{service}-mcp-server` (lowercase with hyphens) +- **Examples**: `github-mcp-server`, `jira-mcp-server`, `stripe-mcp-server` + +The name should be: +- General (not tied to specific features) +- Descriptive of the service/API being integrated +- Easy to infer from the task description +- Without version numbers or dates + +## Project Structure + +Create the following structure for Node/TypeScript MCP servers: + +``` +{service}-mcp-server/ +├── package.json +├── tsconfig.json +├── README.md +├── src/ +│ ├── index.ts # Main entry point with McpServer initialization +│ ├── types.ts # TypeScript type definitions and interfaces +│ ├── tools/ # Tool implementations (one file per domain) +│ ├── services/ # API clients and shared utilities +│ ├── schemas/ # Zod validation schemas +│ └── constants.ts # Shared constants (API_URL, CHARACTER_LIMIT, etc.) +└── dist/ # Built JavaScript files (entry point: dist/index.js) +``` + +## Tool Implementation + +### Tool Naming + +Use snake_case for tool names (e.g., "search_users", "create_project", "get_channel_info") with clear, action-oriented names. + +**Avoid Naming Conflicts**: Include the service context to prevent overlaps: +- Use "slack_send_message" instead of just "send_message" +- Use "github_create_issue" instead of just "create_issue" +- Use "asana_list_tasks" instead of just "list_tasks" + +### Tool Structure + +Tools are registered using the `registerTool` method with the following requirements: +- Use Zod schemas for runtime input validation and type safety +- The `description` field must be explicitly provided - JSDoc comments are NOT automatically extracted +- Explicitly provide `title`, `description`, `inputSchema`, and `annotations` +- The `inputSchema` must be a Zod schema object (not a JSON schema) +- Type all parameters and return values explicitly + +```typescript +import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; +import { z } from "zod"; + +const server = new McpServer({ + name: "example-mcp", + version: "1.0.0" +}); + +// Zod schema for input validation +const UserSearchInputSchema = z.object({ + query: z.string() + .min(2, "Query must be at least 2 characters") + .max(200, "Query must not exceed 200 characters") + .describe("Search string to match against names/emails"), + limit: z.number() + .int() + .min(1) + .max(100) + .default(20) + .describe("Maximum results to return"), + offset: z.number() + .int() + .min(0) + .default(0) + .describe("Number of results to skip for pagination"), + response_format: z.nativeEnum(ResponseFormat) + .default(ResponseFormat.MARKDOWN) + .describe("Output format: 'markdown' for human-readable or 'json' for machine-readable") +}).strict(); + +// Type definition from Zod schema +type UserSearchInput = z.infer; + +server.registerTool( + "example_search_users", + { + title: "Search Example Users", + description: `Search for users in the Example system by name, email, or team. + +This tool searches across all user profiles in the Example platform, supporting partial matches and various search filters. It does NOT create or modify users, only searches existing ones. + +Args: + - query (string): Search string to match against names/emails + - limit (number): Maximum results to return, between 1-100 (default: 20) + - offset (number): Number of results to skip for pagination (default: 0) + - response_format ('markdown' | 'json'): Output format (default: 'markdown') + +Returns: + For JSON format: Structured data with schema: + { + "total": number, // Total number of matches found + "count": number, // Number of results in this response + "offset": number, // Current pagination offset + "users": [ + { + "id": string, // User ID (e.g., "U123456789") + "name": string, // Full name (e.g., "John Doe") + "email": string, // Email address + "team": string, // Team name (optional) + "active": boolean // Whether user is active + } + ], + "has_more": boolean, // Whether more results are available + "next_offset": number // Offset for next page (if has_more is true) + } + +Examples: + - Use when: "Find all marketing team members" -> params with query="team:marketing" + - Use when: "Search for John's account" -> params with query="john" + - Don't use when: You need to create a user (use example_create_user instead) + +Error Handling: + - Returns "Error: Rate limit exceeded" if too many requests (429 status) + - Returns "No users found matching ''" if search returns empty`, + inputSchema: UserSearchInputSchema, + annotations: { + readOnlyHint: true, + destructiveHint: false, + idempotentHint: true, + openWorldHint: true + } + }, + async (params: UserSearchInput) => { + try { + // Input validation is handled by Zod schema + // Make API request using validated parameters + const data = await makeApiRequest( + "users/search", + "GET", + undefined, + { + q: params.query, + limit: params.limit, + offset: params.offset + } + ); + + const users = data.users || []; + const total = data.total || 0; + + if (!users.length) { + return { + content: [{ + type: "text", + text: `No users found matching '${params.query}'` + }] + }; + } + + // Prepare structured output + const output = { + total, + count: users.length, + offset: params.offset, + users: users.map((user: any) => ({ + id: user.id, + name: user.name, + email: user.email, + ...(user.team ? { team: user.team } : {}), + active: user.active ?? true + })), + has_more: total > params.offset + users.length, + ...(total > params.offset + users.length ? { + next_offset: params.offset + users.length + } : {}) + }; + + // Format text representation based on requested format + let textContent: string; + if (params.response_format === ResponseFormat.MARKDOWN) { + const lines = [`# User Search Results: '${params.query}'`, "", + `Found ${total} users (showing ${users.length})`, ""]; + for (const user of users) { + lines.push(`## ${user.name} (${user.id})`); + lines.push(`- **Email**: ${user.email}`); + if (user.team) lines.push(`- **Team**: ${user.team}`); + lines.push(""); + } + textContent = lines.join("\n"); + } else { + textContent = JSON.stringify(output, null, 2); + } + + return { + content: [{ type: "text", text: textContent }], + structuredContent: output // Modern pattern for structured data + }; + } catch (error) { + return { + content: [{ + type: "text", + text: handleApiError(error) + }] + }; + } + } +); +``` + +## Zod Schemas for Input Validation + +Zod provides runtime type validation: + +```typescript +import { z } from "zod"; + +// Basic schema with validation +const CreateUserSchema = z.object({ + name: z.string() + .min(1, "Name is required") + .max(100, "Name must not exceed 100 characters"), + email: z.string() + .email("Invalid email format"), + age: z.number() + .int("Age must be a whole number") + .min(0, "Age cannot be negative") + .max(150, "Age cannot be greater than 150") +}).strict(); // Use .strict() to forbid extra fields + +// Enums +enum ResponseFormat { + MARKDOWN = "markdown", + JSON = "json" +} + +const SearchSchema = z.object({ + response_format: z.nativeEnum(ResponseFormat) + .default(ResponseFormat.MARKDOWN) + .describe("Output format") +}); + +// Optional fields with defaults +const PaginationSchema = z.object({ + limit: z.number() + .int() + .min(1) + .max(100) + .default(20) + .describe("Maximum results to return"), + offset: z.number() + .int() + .min(0) + .default(0) + .describe("Number of results to skip") +}); +``` + +## Response Format Options + +Support multiple output formats for flexibility: + +```typescript +enum ResponseFormat { + MARKDOWN = "markdown", + JSON = "json" +} + +const inputSchema = z.object({ + query: z.string(), + response_format: z.nativeEnum(ResponseFormat) + .default(ResponseFormat.MARKDOWN) + .describe("Output format: 'markdown' for human-readable or 'json' for machine-readable") +}); +``` + +**Markdown format**: +- Use headers, lists, and formatting for clarity +- Convert timestamps to human-readable format +- Show display names with IDs in parentheses +- Omit verbose metadata +- Group related information logically + +**JSON format**: +- Return complete, structured data suitable for programmatic processing +- Include all available fields and metadata +- Use consistent field names and types + +## Pagination Implementation + +For tools that list resources: + +```typescript +const ListSchema = z.object({ + limit: z.number().int().min(1).max(100).default(20), + offset: z.number().int().min(0).default(0) +}); + +async function listItems(params: z.infer) { + const data = await apiRequest(params.limit, params.offset); + + const response = { + total: data.total, + count: data.items.length, + offset: params.offset, + items: data.items, + has_more: data.total > params.offset + data.items.length, + next_offset: data.total > params.offset + data.items.length + ? params.offset + data.items.length + : undefined + }; + + return JSON.stringify(response, null, 2); +} +``` + +## Character Limits and Truncation + +Add a CHARACTER_LIMIT constant to prevent overwhelming responses: + +```typescript +// At module level in constants.ts +export const CHARACTER_LIMIT = 25000; // Maximum response size in characters + +async function searchTool(params: SearchInput) { + let result = generateResponse(data); + + // Check character limit and truncate if needed + if (result.length > CHARACTER_LIMIT) { + const truncatedData = data.slice(0, Math.max(1, data.length / 2)); + response.data = truncatedData; + response.truncated = true; + response.truncation_message = + `Response truncated from ${data.length} to ${truncatedData.length} items. ` + + `Use 'offset' parameter or add filters to see more results.`; + result = JSON.stringify(response, null, 2); + } + + return result; +} +``` + +## Error Handling + +Provide clear, actionable error messages: + +```typescript +import axios, { AxiosError } from "axios"; + +function handleApiError(error: unknown): string { + if (error instanceof AxiosError) { + if (error.response) { + switch (error.response.status) { + case 404: + return "Error: Resource not found. Please check the ID is correct."; + case 403: + return "Error: Permission denied. You don't have access to this resource."; + case 429: + return "Error: Rate limit exceeded. Please wait before making more requests."; + default: + return `Error: API request failed with status ${error.response.status}`; + } + } else if (error.code === "ECONNABORTED") { + return "Error: Request timed out. Please try again."; + } + } + return `Error: Unexpected error occurred: ${error instanceof Error ? error.message : String(error)}`; +} +``` + +## Shared Utilities + +Extract common functionality into reusable functions: + +```typescript +// Shared API request function +async function makeApiRequest( + endpoint: string, + method: "GET" | "POST" | "PUT" | "DELETE" = "GET", + data?: any, + params?: any +): Promise { + try { + const response = await axios({ + method, + url: `${API_BASE_URL}/${endpoint}`, + data, + params, + timeout: 30000, + headers: { + "Content-Type": "application/json", + "Accept": "application/json" + } + }); + return response.data; + } catch (error) { + throw error; + } +} +``` + +## Async/Await Best Practices + +Always use async/await for network requests and I/O operations: + +```typescript +// Good: Async network request +async function fetchData(resourceId: string): Promise { + const response = await axios.get(`${API_URL}/resource/${resourceId}`); + return response.data; +} + +// Bad: Promise chains +function fetchData(resourceId: string): Promise { + return axios.get(`${API_URL}/resource/${resourceId}`) + .then(response => response.data); // Harder to read and maintain +} +``` + +## TypeScript Best Practices + +1. **Use Strict TypeScript**: Enable strict mode in tsconfig.json +2. **Define Interfaces**: Create clear interface definitions for all data structures +3. **Avoid `any`**: Use proper types or `unknown` instead of `any` +4. **Zod for Runtime Validation**: Use Zod schemas to validate external data +5. **Type Guards**: Create type guard functions for complex type checking +6. **Error Handling**: Always use try-catch with proper error type checking +7. **Null Safety**: Use optional chaining (`?.`) and nullish coalescing (`??`) + +```typescript +// Good: Type-safe with Zod and interfaces +interface UserResponse { + id: string; + name: string; + email: string; + team?: string; + active: boolean; +} + +const UserSchema = z.object({ + id: z.string(), + name: z.string(), + email: z.string().email(), + team: z.string().optional(), + active: z.boolean() +}); + +type User = z.infer; + +async function getUser(id: string): Promise { + const data = await apiCall(`/users/${id}`); + return UserSchema.parse(data); // Runtime validation +} + +// Bad: Using any +async function getUser(id: string): Promise { + return await apiCall(`/users/${id}`); // No type safety +} +``` + +## Package Configuration + +### package.json + +```json +{ + "name": "{service}-mcp-server", + "version": "1.0.0", + "description": "MCP server for {Service} API integration", + "type": "module", + "main": "dist/index.js", + "scripts": { + "start": "node dist/index.js", + "dev": "tsx watch src/index.ts", + "build": "tsc", + "clean": "rm -rf dist" + }, + "engines": { + "node": ">=18" + }, + "dependencies": { + "@modelcontextprotocol/sdk": "^1.6.1", + "axios": "^1.7.9", + "zod": "^3.23.8" + }, + "devDependencies": { + "@types/node": "^22.10.0", + "tsx": "^4.19.2", + "typescript": "^5.7.2" + } +} +``` + +### tsconfig.json + +```json +{ + "compilerOptions": { + "target": "ES2022", + "module": "Node16", + "moduleResolution": "Node16", + "lib": ["ES2022"], + "outDir": "./dist", + "rootDir": "./src", + "strict": true, + "esModuleInterop": true, + "skipLibCheck": true, + "forceConsistentCasingInFileNames": true, + "declaration": true, + "declarationMap": true, + "sourceMap": true, + "allowSyntheticDefaultImports": true + }, + "include": ["src/**/*"], + "exclude": ["node_modules", "dist"] +} +``` + +## Complete Example + +```typescript +#!/usr/bin/env node +/** + * MCP Server for Example Service. + * + * This server provides tools to interact with Example API, including user search, + * project management, and data export capabilities. + */ + +import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js"; +import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js"; +import { z } from "zod"; +import axios, { AxiosError } from "axios"; + +// Constants +const API_BASE_URL = "https://api.example.com/v1"; +const CHARACTER_LIMIT = 25000; + +// Enums +enum ResponseFormat { + MARKDOWN = "markdown", + JSON = "json" +} + +// Zod schemas +const UserSearchInputSchema = z.object({ + query: z.string() + .min(2, "Query must be at least 2 characters") + .max(200, "Query must not exceed 200 characters") + .describe("Search string to match against names/emails"), + limit: z.number() + .int() + .min(1) + .max(100) + .default(20) + .describe("Maximum results to return"), + offset: z.number() + .int() + .min(0) + .default(0) + .describe("Number of results to skip for pagination"), + response_format: z.nativeEnum(ResponseFormat) + .default(ResponseFormat.MARKDOWN) + .describe("Output format: 'markdown' for human-readable or 'json' for machine-readable") +}).strict(); + +type UserSearchInput = z.infer; + +// Shared utility functions +async function makeApiRequest( + endpoint: string, + method: "GET" | "POST" | "PUT" | "DELETE" = "GET", + data?: any, + params?: any +): Promise { + try { + const response = await axios({ + method, + url: `${API_BASE_URL}/${endpoint}`, + data, + params, + timeout: 30000, + headers: { + "Content-Type": "application/json", + "Accept": "application/json" + } + }); + return response.data; + } catch (error) { + throw error; + } +} + +function handleApiError(error: unknown): string { + if (error instanceof AxiosError) { + if (error.response) { + switch (error.response.status) { + case 404: + return "Error: Resource not found. Please check the ID is correct."; + case 403: + return "Error: Permission denied. You don't have access to this resource."; + case 429: + return "Error: Rate limit exceeded. Please wait before making more requests."; + default: + return `Error: API request failed with status ${error.response.status}`; + } + } else if (error.code === "ECONNABORTED") { + return "Error: Request timed out. Please try again."; + } + } + return `Error: Unexpected error occurred: ${error instanceof Error ? error.message : String(error)}`; +} + +// Create MCP server instance +const server = new McpServer({ + name: "example-mcp", + version: "1.0.0" +}); + +// Register tools +server.registerTool( + "example_search_users", + { + title: "Search Example Users", + description: `[Full description as shown above]`, + inputSchema: UserSearchInputSchema, + annotations: { + readOnlyHint: true, + destructiveHint: false, + idempotentHint: true, + openWorldHint: true + } + }, + async (params: UserSearchInput) => { + // Implementation as shown above + } +); + +// Main function +// For stdio (local): +async function runStdio() { + if (!process.env.EXAMPLE_API_KEY) { + console.error("ERROR: EXAMPLE_API_KEY environment variable is required"); + process.exit(1); + } + + const transport = new StdioServerTransport(); + await server.connect(transport); + console.error("MCP server running via stdio"); +} + +// For streamable HTTP (remote): +async function runHTTP() { + if (!process.env.EXAMPLE_API_KEY) { + console.error("ERROR: EXAMPLE_API_KEY environment variable is required"); + process.exit(1); + } + + const app = express(); + app.use(express.json()); + + app.post('/mcp', async (req, res) => { + const transport = new StreamableHTTPServerTransport({ + sessionIdGenerator: undefined, + enableJsonResponse: true + }); + res.on('close', () => transport.close()); + await server.connect(transport); + await transport.handleRequest(req, res, req.body); + }); + + const port = parseInt(process.env.PORT || '3000'); + app.listen(port, () => { + console.error(`MCP server running on http://localhost:${port}/mcp`); + }); +} + +// Choose transport based on environment +const transport = process.env.TRANSPORT || 'stdio'; +if (transport === 'http') { + runHTTP().catch(error => { + console.error("Server error:", error); + process.exit(1); + }); +} else { + runStdio().catch(error => { + console.error("Server error:", error); + process.exit(1); + }); +} +``` + +--- + +## Advanced MCP Features + +### Resource Registration + +Expose data as resources for efficient, URI-based access: + +```typescript +import { ResourceTemplate } from "@modelcontextprotocol/sdk/types.js"; + +// Register a resource with URI template +server.registerResource( + { + uri: "file://documents/{name}", + name: "Document Resource", + description: "Access documents by name", + mimeType: "text/plain" + }, + async (uri: string) => { + // Extract parameter from URI + const match = uri.match(/^file:\/\/documents\/(.+)$/); + if (!match) { + throw new Error("Invalid URI format"); + } + + const documentName = match[1]; + const content = await loadDocument(documentName); + + return { + contents: [{ + uri, + mimeType: "text/plain", + text: content + }] + }; + } +); + +// List available resources dynamically +server.registerResourceList(async () => { + const documents = await getAvailableDocuments(); + return { + resources: documents.map(doc => ({ + uri: `file://documents/${doc.name}`, + name: doc.name, + mimeType: "text/plain", + description: doc.description + })) + }; +}); +``` + +**When to use Resources vs Tools:** +- **Resources**: For data access with simple URI-based parameters +- **Tools**: For complex operations requiring validation and business logic +- **Resources**: When data is relatively static or template-based +- **Tools**: When operations have side effects or complex workflows + +### Transport Options + +The TypeScript SDK supports two main transport mechanisms: + +#### Streamable HTTP (Recommended for Remote Servers) + +```typescript +import { StreamableHTTPServerTransport } from "@modelcontextprotocol/sdk/server/streamableHttp.js"; +import express from "express"; + +const app = express(); +app.use(express.json()); + +app.post('/mcp', async (req, res) => { + // Create new transport for each request (stateless, prevents request ID collisions) + const transport = new StreamableHTTPServerTransport({ + sessionIdGenerator: undefined, + enableJsonResponse: true + }); + + res.on('close', () => transport.close()); + + await server.connect(transport); + await transport.handleRequest(req, res, req.body); +}); + +app.listen(3000); +``` + +#### stdio (For Local Integrations) + +```typescript +import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js"; + +const transport = new StdioServerTransport(); +await server.connect(transport); +``` + +**Transport selection:** +- **Streamable HTTP**: Web services, remote access, multiple clients +- **stdio**: Command-line tools, local development, subprocess integration + +### Notification Support + +Notify clients when server state changes: + +```typescript +// Notify when tools list changes +server.notification({ + method: "notifications/tools/list_changed" +}); + +// Notify when resources change +server.notification({ + method: "notifications/resources/list_changed" +}); +``` + +Use notifications sparingly - only when server capabilities genuinely change. + +--- + +## Code Best Practices + +### Code Composability and Reusability + +Your implementation MUST prioritize composability and code reuse: + +1. **Extract Common Functionality**: + - Create reusable helper functions for operations used across multiple tools + - Build shared API clients for HTTP requests instead of duplicating code + - Centralize error handling logic in utility functions + - Extract business logic into dedicated functions that can be composed + - Extract shared markdown or JSON field selection & formatting functionality + +2. **Avoid Duplication**: + - NEVER copy-paste similar code between tools + - If you find yourself writing similar logic twice, extract it into a function + - Common operations like pagination, filtering, field selection, and formatting should be shared + - Authentication/authorization logic should be centralized + +## Building and Running + +Always build your TypeScript code before running: + +```bash +# Build the project +npm run build + +# Run the server +npm start + +# Development with auto-reload +npm run dev +``` + +Always ensure `npm run build` completes successfully before considering the implementation complete. + +## Quality Checklist + +Before finalizing your Node/TypeScript MCP server implementation, ensure: + +### Strategic Design +- [ ] Tools enable complete workflows, not just API endpoint wrappers +- [ ] Tool names reflect natural task subdivisions +- [ ] Response formats optimize for agent context efficiency +- [ ] Human-readable identifiers used where appropriate +- [ ] Error messages guide agents toward correct usage + +### Implementation Quality +- [ ] FOCUSED IMPLEMENTATION: Most important and valuable tools implemented +- [ ] All tools registered using `registerTool` with complete configuration +- [ ] All tools include `title`, `description`, `inputSchema`, and `annotations` +- [ ] Annotations correctly set (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) +- [ ] All tools use Zod schemas for runtime input validation with `.strict()` enforcement +- [ ] All Zod schemas have proper constraints and descriptive error messages +- [ ] All tools have comprehensive descriptions with explicit input/output types +- [ ] Descriptions include return value examples and complete schema documentation +- [ ] Error messages are clear, actionable, and educational + +### TypeScript Quality +- [ ] TypeScript interfaces are defined for all data structures +- [ ] Strict TypeScript is enabled in tsconfig.json +- [ ] No use of `any` type - use `unknown` or proper types instead +- [ ] All async functions have explicit Promise return types +- [ ] Error handling uses proper type guards (e.g., `axios.isAxiosError`, `z.ZodError`) + +### Advanced Features (where applicable) +- [ ] Resources registered for appropriate data endpoints +- [ ] Appropriate transport configured (stdio or streamable HTTP) +- [ ] Notifications implemented for dynamic server capabilities +- [ ] Type-safe with SDK interfaces + +### Project Configuration +- [ ] Package.json includes all necessary dependencies +- [ ] Build script produces working JavaScript in dist/ directory +- [ ] Main entry point is properly configured as dist/index.js +- [ ] Server name follows format: `{service}-mcp-server` +- [ ] tsconfig.json properly configured with strict mode + +### Code Quality +- [ ] Pagination is properly implemented where applicable +- [ ] Large responses check CHARACTER_LIMIT constant and truncate with clear messages +- [ ] Filtering options are provided for potentially large result sets +- [ ] All network operations handle timeouts and connection errors gracefully +- [ ] Common functionality is extracted into reusable functions +- [ ] Return types are consistent across similar operations + +### Testing and Build +- [ ] `npm run build` completes successfully without errors +- [ ] dist/index.js created and executable +- [ ] Server runs: `node dist/index.js --help` +- [ ] All imports resolve correctly +- [ ] Sample tool calls work as expected \ No newline at end of file diff --git a/skills/mcp-builder/reference/python_mcp_server.md b/skills/mcp-builder/reference/python_mcp_server.md new file mode 100644 index 0000000..cf7ec99 --- /dev/null +++ b/skills/mcp-builder/reference/python_mcp_server.md @@ -0,0 +1,719 @@ +# Python MCP Server Implementation Guide + +## Overview + +This document provides Python-specific best practices and examples for implementing MCP servers using the MCP Python SDK. It covers server setup, tool registration patterns, input validation with Pydantic, error handling, and complete working examples. + +--- + +## Quick Reference + +### Key Imports +```python +from mcp.server.fastmcp import FastMCP +from pydantic import BaseModel, Field, field_validator, ConfigDict +from typing import Optional, List, Dict, Any +from enum import Enum +import httpx +``` + +### Server Initialization +```python +mcp = FastMCP("service_mcp") +``` + +### Tool Registration Pattern +```python +@mcp.tool(name="tool_name", annotations={...}) +async def tool_function(params: InputModel) -> str: + # Implementation + pass +``` + +--- + +## MCP Python SDK and FastMCP + +The official MCP Python SDK provides FastMCP, a high-level framework for building MCP servers. It provides: +- Automatic description and inputSchema generation from function signatures and docstrings +- Pydantic model integration for input validation +- Decorator-based tool registration with `@mcp.tool` + +**For complete SDK documentation, use WebFetch to load:** +`https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md` + +## Server Naming Convention + +Python MCP servers must follow this naming pattern: +- **Format**: `{service}_mcp` (lowercase with underscores) +- **Examples**: `github_mcp`, `jira_mcp`, `stripe_mcp` + +The name should be: +- General (not tied to specific features) +- Descriptive of the service/API being integrated +- Easy to infer from the task description +- Without version numbers or dates + +## Tool Implementation + +### Tool Naming + +Use snake_case for tool names (e.g., "search_users", "create_project", "get_channel_info") with clear, action-oriented names. + +**Avoid Naming Conflicts**: Include the service context to prevent overlaps: +- Use "slack_send_message" instead of just "send_message" +- Use "github_create_issue" instead of just "create_issue" +- Use "asana_list_tasks" instead of just "list_tasks" + +### Tool Structure with FastMCP + +Tools are defined using the `@mcp.tool` decorator with Pydantic models for input validation: + +```python +from pydantic import BaseModel, Field, ConfigDict +from mcp.server.fastmcp import FastMCP + +# Initialize the MCP server +mcp = FastMCP("example_mcp") + +# Define Pydantic model for input validation +class ServiceToolInput(BaseModel): + '''Input model for service tool operation.''' + model_config = ConfigDict( + str_strip_whitespace=True, # Auto-strip whitespace from strings + validate_assignment=True, # Validate on assignment + extra='forbid' # Forbid extra fields + ) + + param1: str = Field(..., description="First parameter description (e.g., 'user123', 'project-abc')", min_length=1, max_length=100) + param2: Optional[int] = Field(default=None, description="Optional integer parameter with constraints", ge=0, le=1000) + tags: Optional[List[str]] = Field(default_factory=list, description="List of tags to apply", max_items=10) + +@mcp.tool( + name="service_tool_name", + annotations={ + "title": "Human-Readable Tool Title", + "readOnlyHint": True, # Tool does not modify environment + "destructiveHint": False, # Tool does not perform destructive operations + "idempotentHint": True, # Repeated calls have no additional effect + "openWorldHint": False # Tool does not interact with external entities + } +) +async def service_tool_name(params: ServiceToolInput) -> str: + '''Tool description automatically becomes the 'description' field. + + This tool performs a specific operation on the service. It validates all inputs + using the ServiceToolInput Pydantic model before processing. + + Args: + params (ServiceToolInput): Validated input parameters containing: + - param1 (str): First parameter description + - param2 (Optional[int]): Optional parameter with default + - tags (Optional[List[str]]): List of tags + + Returns: + str: JSON-formatted response containing operation results + ''' + # Implementation here + pass +``` + +## Pydantic v2 Key Features + +- Use `model_config` instead of nested `Config` class +- Use `field_validator` instead of deprecated `validator` +- Use `model_dump()` instead of deprecated `dict()` +- Validators require `@classmethod` decorator +- Type hints are required for validator methods + +```python +from pydantic import BaseModel, Field, field_validator, ConfigDict + +class CreateUserInput(BaseModel): + model_config = ConfigDict( + str_strip_whitespace=True, + validate_assignment=True + ) + + name: str = Field(..., description="User's full name", min_length=1, max_length=100) + email: str = Field(..., description="User's email address", pattern=r'^[\w\.-]+@[\w\.-]+\.\w+$') + age: int = Field(..., description="User's age", ge=0, le=150) + + @field_validator('email') + @classmethod + def validate_email(cls, v: str) -> str: + if not v.strip(): + raise ValueError("Email cannot be empty") + return v.lower() +``` + +## Response Format Options + +Support multiple output formats for flexibility: + +```python +from enum import Enum + +class ResponseFormat(str, Enum): + '''Output format for tool responses.''' + MARKDOWN = "markdown" + JSON = "json" + +class UserSearchInput(BaseModel): + query: str = Field(..., description="Search query") + response_format: ResponseFormat = Field( + default=ResponseFormat.MARKDOWN, + description="Output format: 'markdown' for human-readable or 'json' for machine-readable" + ) +``` + +**Markdown format**: +- Use headers, lists, and formatting for clarity +- Convert timestamps to human-readable format (e.g., "2024-01-15 10:30:00 UTC" instead of epoch) +- Show display names with IDs in parentheses (e.g., "@john.doe (U123456)") +- Omit verbose metadata (e.g., show only one profile image URL, not all sizes) +- Group related information logically + +**JSON format**: +- Return complete, structured data suitable for programmatic processing +- Include all available fields and metadata +- Use consistent field names and types + +## Pagination Implementation + +For tools that list resources: + +```python +class ListInput(BaseModel): + limit: Optional[int] = Field(default=20, description="Maximum results to return", ge=1, le=100) + offset: Optional[int] = Field(default=0, description="Number of results to skip for pagination", ge=0) + +async def list_items(params: ListInput) -> str: + # Make API request with pagination + data = await api_request(limit=params.limit, offset=params.offset) + + # Return pagination info + response = { + "total": data["total"], + "count": len(data["items"]), + "offset": params.offset, + "items": data["items"], + "has_more": data["total"] > params.offset + len(data["items"]), + "next_offset": params.offset + len(data["items"]) if data["total"] > params.offset + len(data["items"]) else None + } + return json.dumps(response, indent=2) +``` + +## Error Handling + +Provide clear, actionable error messages: + +```python +def _handle_api_error(e: Exception) -> str: + '''Consistent error formatting across all tools.''' + if isinstance(e, httpx.HTTPStatusError): + if e.response.status_code == 404: + return "Error: Resource not found. Please check the ID is correct." + elif e.response.status_code == 403: + return "Error: Permission denied. You don't have access to this resource." + elif e.response.status_code == 429: + return "Error: Rate limit exceeded. Please wait before making more requests." + return f"Error: API request failed with status {e.response.status_code}" + elif isinstance(e, httpx.TimeoutException): + return "Error: Request timed out. Please try again." + return f"Error: Unexpected error occurred: {type(e).__name__}" +``` + +## Shared Utilities + +Extract common functionality into reusable functions: + +```python +# Shared API request function +async def _make_api_request(endpoint: str, method: str = "GET", **kwargs) -> dict: + '''Reusable function for all API calls.''' + async with httpx.AsyncClient() as client: + response = await client.request( + method, + f"{API_BASE_URL}/{endpoint}", + timeout=30.0, + **kwargs + ) + response.raise_for_status() + return response.json() +``` + +## Async/Await Best Practices + +Always use async/await for network requests and I/O operations: + +```python +# Good: Async network request +async def fetch_data(resource_id: str) -> dict: + async with httpx.AsyncClient() as client: + response = await client.get(f"{API_URL}/resource/{resource_id}") + response.raise_for_status() + return response.json() + +# Bad: Synchronous request +def fetch_data(resource_id: str) -> dict: + response = requests.get(f"{API_URL}/resource/{resource_id}") # Blocks + return response.json() +``` + +## Type Hints + +Use type hints throughout: + +```python +from typing import Optional, List, Dict, Any + +async def get_user(user_id: str) -> Dict[str, Any]: + data = await fetch_user(user_id) + return {"id": data["id"], "name": data["name"]} +``` + +## Tool Docstrings + +Every tool must have comprehensive docstrings with explicit type information: + +```python +async def search_users(params: UserSearchInput) -> str: + ''' + Search for users in the Example system by name, email, or team. + + This tool searches across all user profiles in the Example platform, + supporting partial matches and various search filters. It does NOT + create or modify users, only searches existing ones. + + Args: + params (UserSearchInput): Validated input parameters containing: + - query (str): Search string to match against names/emails (e.g., "john", "@example.com", "team:marketing") + - limit (Optional[int]): Maximum results to return, between 1-100 (default: 20) + - offset (Optional[int]): Number of results to skip for pagination (default: 0) + + Returns: + str: JSON-formatted string containing search results with the following schema: + + Success response: + { + "total": int, # Total number of matches found + "count": int, # Number of results in this response + "offset": int, # Current pagination offset + "users": [ + { + "id": str, # User ID (e.g., "U123456789") + "name": str, # Full name (e.g., "John Doe") + "email": str, # Email address (e.g., "john@example.com") + "team": str # Team name (e.g., "Marketing") - optional + } + ] + } + + Error response: + "Error: " or "No users found matching ''" + + Examples: + - Use when: "Find all marketing team members" -> params with query="team:marketing" + - Use when: "Search for John's account" -> params with query="john" + - Don't use when: You need to create a user (use example_create_user instead) + - Don't use when: You have a user ID and need full details (use example_get_user instead) + + Error Handling: + - Input validation errors are handled by Pydantic model + - Returns "Error: Rate limit exceeded" if too many requests (429 status) + - Returns "Error: Invalid API authentication" if API key is invalid (401 status) + - Returns formatted list of results or "No users found matching 'query'" + ''' +``` + +## Complete Example + +See below for a complete Python MCP server example: + +```python +#!/usr/bin/env python3 +''' +MCP Server for Example Service. + +This server provides tools to interact with Example API, including user search, +project management, and data export capabilities. +''' + +from typing import Optional, List, Dict, Any +from enum import Enum +import httpx +from pydantic import BaseModel, Field, field_validator, ConfigDict +from mcp.server.fastmcp import FastMCP + +# Initialize the MCP server +mcp = FastMCP("example_mcp") + +# Constants +API_BASE_URL = "https://api.example.com/v1" + +# Enums +class ResponseFormat(str, Enum): + '''Output format for tool responses.''' + MARKDOWN = "markdown" + JSON = "json" + +# Pydantic Models for Input Validation +class UserSearchInput(BaseModel): + '''Input model for user search operations.''' + model_config = ConfigDict( + str_strip_whitespace=True, + validate_assignment=True + ) + + query: str = Field(..., description="Search string to match against names/emails", min_length=2, max_length=200) + limit: Optional[int] = Field(default=20, description="Maximum results to return", ge=1, le=100) + offset: Optional[int] = Field(default=0, description="Number of results to skip for pagination", ge=0) + response_format: ResponseFormat = Field(default=ResponseFormat.MARKDOWN, description="Output format") + + @field_validator('query') + @classmethod + def validate_query(cls, v: str) -> str: + if not v.strip(): + raise ValueError("Query cannot be empty or whitespace only") + return v.strip() + +# Shared utility functions +async def _make_api_request(endpoint: str, method: str = "GET", **kwargs) -> dict: + '''Reusable function for all API calls.''' + async with httpx.AsyncClient() as client: + response = await client.request( + method, + f"{API_BASE_URL}/{endpoint}", + timeout=30.0, + **kwargs + ) + response.raise_for_status() + return response.json() + +def _handle_api_error(e: Exception) -> str: + '''Consistent error formatting across all tools.''' + if isinstance(e, httpx.HTTPStatusError): + if e.response.status_code == 404: + return "Error: Resource not found. Please check the ID is correct." + elif e.response.status_code == 403: + return "Error: Permission denied. You don't have access to this resource." + elif e.response.status_code == 429: + return "Error: Rate limit exceeded. Please wait before making more requests." + return f"Error: API request failed with status {e.response.status_code}" + elif isinstance(e, httpx.TimeoutException): + return "Error: Request timed out. Please try again." + return f"Error: Unexpected error occurred: {type(e).__name__}" + +# Tool definitions +@mcp.tool( + name="example_search_users", + annotations={ + "title": "Search Example Users", + "readOnlyHint": True, + "destructiveHint": False, + "idempotentHint": True, + "openWorldHint": True + } +) +async def example_search_users(params: UserSearchInput) -> str: + '''Search for users in the Example system by name, email, or team. + + [Full docstring as shown above] + ''' + try: + # Make API request using validated parameters + data = await _make_api_request( + "users/search", + params={ + "q": params.query, + "limit": params.limit, + "offset": params.offset + } + ) + + users = data.get("users", []) + total = data.get("total", 0) + + if not users: + return f"No users found matching '{params.query}'" + + # Format response based on requested format + if params.response_format == ResponseFormat.MARKDOWN: + lines = [f"# User Search Results: '{params.query}'", ""] + lines.append(f"Found {total} users (showing {len(users)})") + lines.append("") + + for user in users: + lines.append(f"## {user['name']} ({user['id']})") + lines.append(f"- **Email**: {user['email']}") + if user.get('team'): + lines.append(f"- **Team**: {user['team']}") + lines.append("") + + return "\n".join(lines) + + else: + # Machine-readable JSON format + import json + response = { + "total": total, + "count": len(users), + "offset": params.offset, + "users": users + } + return json.dumps(response, indent=2) + + except Exception as e: + return _handle_api_error(e) + +if __name__ == "__main__": + mcp.run() +``` + +--- + +## Advanced FastMCP Features + +### Context Parameter Injection + +FastMCP can automatically inject a `Context` parameter into tools for advanced capabilities like logging, progress reporting, resource reading, and user interaction: + +```python +from mcp.server.fastmcp import FastMCP, Context + +mcp = FastMCP("example_mcp") + +@mcp.tool() +async def advanced_search(query: str, ctx: Context) -> str: + '''Advanced tool with context access for logging and progress.''' + + # Report progress for long operations + await ctx.report_progress(0.25, "Starting search...") + + # Log information for debugging + await ctx.log_info("Processing query", {"query": query, "timestamp": datetime.now()}) + + # Perform search + results = await search_api(query) + await ctx.report_progress(0.75, "Formatting results...") + + # Access server configuration + server_name = ctx.fastmcp.name + + return format_results(results) + +@mcp.tool() +async def interactive_tool(resource_id: str, ctx: Context) -> str: + '''Tool that can request additional input from users.''' + + # Request sensitive information when needed + api_key = await ctx.elicit( + prompt="Please provide your API key:", + input_type="password" + ) + + # Use the provided key + return await api_call(resource_id, api_key) +``` + +**Context capabilities:** +- `ctx.report_progress(progress, message)` - Report progress for long operations +- `ctx.log_info(message, data)` / `ctx.log_error()` / `ctx.log_debug()` - Logging +- `ctx.elicit(prompt, input_type)` - Request input from users +- `ctx.fastmcp.name` - Access server configuration +- `ctx.read_resource(uri)` - Read MCP resources + +### Resource Registration + +Expose data as resources for efficient, template-based access: + +```python +@mcp.resource("file://documents/{name}") +async def get_document(name: str) -> str: + '''Expose documents as MCP resources. + + Resources are useful for static or semi-static data that doesn't + require complex parameters. They use URI templates for flexible access. + ''' + document_path = f"./docs/{name}" + with open(document_path, "r") as f: + return f.read() + +@mcp.resource("config://settings/{key}") +async def get_setting(key: str, ctx: Context) -> str: + '''Expose configuration as resources with context.''' + settings = await load_settings() + return json.dumps(settings.get(key, {})) +``` + +**When to use Resources vs Tools:** +- **Resources**: For data access with simple parameters (URI templates) +- **Tools**: For complex operations with validation and business logic + +### Structured Output Types + +FastMCP supports multiple return types beyond strings: + +```python +from typing import TypedDict +from dataclasses import dataclass +from pydantic import BaseModel + +# TypedDict for structured returns +class UserData(TypedDict): + id: str + name: str + email: str + +@mcp.tool() +async def get_user_typed(user_id: str) -> UserData: + '''Returns structured data - FastMCP handles serialization.''' + return {"id": user_id, "name": "John Doe", "email": "john@example.com"} + +# Pydantic models for complex validation +class DetailedUser(BaseModel): + id: str + name: str + email: str + created_at: datetime + metadata: Dict[str, Any] + +@mcp.tool() +async def get_user_detailed(user_id: str) -> DetailedUser: + '''Returns Pydantic model - automatically generates schema.''' + user = await fetch_user(user_id) + return DetailedUser(**user) +``` + +### Lifespan Management + +Initialize resources that persist across requests: + +```python +from contextlib import asynccontextmanager + +@asynccontextmanager +async def app_lifespan(): + '''Manage resources that live for the server's lifetime.''' + # Initialize connections, load config, etc. + db = await connect_to_database() + config = load_configuration() + + # Make available to all tools + yield {"db": db, "config": config} + + # Cleanup on shutdown + await db.close() + +mcp = FastMCP("example_mcp", lifespan=app_lifespan) + +@mcp.tool() +async def query_data(query: str, ctx: Context) -> str: + '''Access lifespan resources through context.''' + db = ctx.request_context.lifespan_state["db"] + results = await db.query(query) + return format_results(results) +``` + +### Transport Options + +FastMCP supports two main transport mechanisms: + +```python +# stdio transport (for local tools) - default +if __name__ == "__main__": + mcp.run() + +# Streamable HTTP transport (for remote servers) +if __name__ == "__main__": + mcp.run(transport="streamable_http", port=8000) +``` + +**Transport selection:** +- **stdio**: Command-line tools, local integrations, subprocess execution +- **Streamable HTTP**: Web services, remote access, multiple clients + +--- + +## Code Best Practices + +### Code Composability and Reusability + +Your implementation MUST prioritize composability and code reuse: + +1. **Extract Common Functionality**: + - Create reusable helper functions for operations used across multiple tools + - Build shared API clients for HTTP requests instead of duplicating code + - Centralize error handling logic in utility functions + - Extract business logic into dedicated functions that can be composed + - Extract shared markdown or JSON field selection & formatting functionality + +2. **Avoid Duplication**: + - NEVER copy-paste similar code between tools + - If you find yourself writing similar logic twice, extract it into a function + - Common operations like pagination, filtering, field selection, and formatting should be shared + - Authentication/authorization logic should be centralized + +### Python-Specific Best Practices + +1. **Use Type Hints**: Always include type annotations for function parameters and return values +2. **Pydantic Models**: Define clear Pydantic models for all input validation +3. **Avoid Manual Validation**: Let Pydantic handle input validation with constraints +4. **Proper Imports**: Group imports (standard library, third-party, local) +5. **Error Handling**: Use specific exception types (httpx.HTTPStatusError, not generic Exception) +6. **Async Context Managers**: Use `async with` for resources that need cleanup +7. **Constants**: Define module-level constants in UPPER_CASE + +## Quality Checklist + +Before finalizing your Python MCP server implementation, ensure: + +### Strategic Design +- [ ] Tools enable complete workflows, not just API endpoint wrappers +- [ ] Tool names reflect natural task subdivisions +- [ ] Response formats optimize for agent context efficiency +- [ ] Human-readable identifiers used where appropriate +- [ ] Error messages guide agents toward correct usage + +### Implementation Quality +- [ ] FOCUSED IMPLEMENTATION: Most important and valuable tools implemented +- [ ] All tools have descriptive names and documentation +- [ ] Return types are consistent across similar operations +- [ ] Error handling is implemented for all external calls +- [ ] Server name follows format: `{service}_mcp` +- [ ] All network operations use async/await +- [ ] Common functionality is extracted into reusable functions +- [ ] Error messages are clear, actionable, and educational +- [ ] Outputs are properly validated and formatted + +### Tool Configuration +- [ ] All tools implement 'name' and 'annotations' in the decorator +- [ ] Annotations correctly set (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) +- [ ] All tools use Pydantic BaseModel for input validation with Field() definitions +- [ ] All Pydantic Fields have explicit types and descriptions with constraints +- [ ] All tools have comprehensive docstrings with explicit input/output types +- [ ] Docstrings include complete schema structure for dict/JSON returns +- [ ] Pydantic models handle input validation (no manual validation needed) + +### Advanced Features (where applicable) +- [ ] Context injection used for logging, progress, or elicitation +- [ ] Resources registered for appropriate data endpoints +- [ ] Lifespan management implemented for persistent connections +- [ ] Structured output types used (TypedDict, Pydantic models) +- [ ] Appropriate transport configured (stdio or streamable HTTP) + +### Code Quality +- [ ] File includes proper imports including Pydantic imports +- [ ] Pagination is properly implemented where applicable +- [ ] Filtering options are provided for potentially large result sets +- [ ] All async functions are properly defined with `async def` +- [ ] HTTP client usage follows async patterns with proper context managers +- [ ] Type hints are used throughout the code +- [ ] Constants are defined at module level in UPPER_CASE + +### Testing +- [ ] Server runs successfully: `python your_server.py --help` +- [ ] All imports resolve correctly +- [ ] Sample tool calls work as expected +- [ ] Error scenarios handled gracefully \ No newline at end of file diff --git a/skills/mcp-builder/scripts/connections.py b/skills/mcp-builder/scripts/connections.py new file mode 100644 index 0000000..ffcd0da --- /dev/null +++ b/skills/mcp-builder/scripts/connections.py @@ -0,0 +1,151 @@ +"""Lightweight connection handling for MCP servers.""" + +from abc import ABC, abstractmethod +from contextlib import AsyncExitStack +from typing import Any + +from mcp import ClientSession, StdioServerParameters +from mcp.client.sse import sse_client +from mcp.client.stdio import stdio_client +from mcp.client.streamable_http import streamablehttp_client + + +class MCPConnection(ABC): + """Base class for MCP server connections.""" + + def __init__(self): + self.session = None + self._stack = None + + @abstractmethod + def _create_context(self): + """Create the connection context based on connection type.""" + + async def __aenter__(self): + """Initialize MCP server connection.""" + self._stack = AsyncExitStack() + await self._stack.__aenter__() + + try: + ctx = self._create_context() + result = await self._stack.enter_async_context(ctx) + + if len(result) == 2: + read, write = result + elif len(result) == 3: + read, write, _ = result + else: + raise ValueError(f"Unexpected context result: {result}") + + session_ctx = ClientSession(read, write) + self.session = await self._stack.enter_async_context(session_ctx) + await self.session.initialize() + return self + except BaseException: + await self._stack.__aexit__(None, None, None) + raise + + async def __aexit__(self, exc_type, exc_val, exc_tb): + """Clean up MCP server connection resources.""" + if self._stack: + await self._stack.__aexit__(exc_type, exc_val, exc_tb) + self.session = None + self._stack = None + + async def list_tools(self) -> list[dict[str, Any]]: + """Retrieve available tools from the MCP server.""" + response = await self.session.list_tools() + return [ + { + "name": tool.name, + "description": tool.description, + "input_schema": tool.inputSchema, + } + for tool in response.tools + ] + + async def call_tool(self, tool_name: str, arguments: dict[str, Any]) -> Any: + """Call a tool on the MCP server with provided arguments.""" + result = await self.session.call_tool(tool_name, arguments=arguments) + return result.content + + +class MCPConnectionStdio(MCPConnection): + """MCP connection using standard input/output.""" + + def __init__(self, command: str, args: list[str] = None, env: dict[str, str] = None): + super().__init__() + self.command = command + self.args = args or [] + self.env = env + + def _create_context(self): + return stdio_client( + StdioServerParameters(command=self.command, args=self.args, env=self.env) + ) + + +class MCPConnectionSSE(MCPConnection): + """MCP connection using Server-Sent Events.""" + + def __init__(self, url: str, headers: dict[str, str] = None): + super().__init__() + self.url = url + self.headers = headers or {} + + def _create_context(self): + return sse_client(url=self.url, headers=self.headers) + + +class MCPConnectionHTTP(MCPConnection): + """MCP connection using Streamable HTTP.""" + + def __init__(self, url: str, headers: dict[str, str] = None): + super().__init__() + self.url = url + self.headers = headers or {} + + def _create_context(self): + return streamablehttp_client(url=self.url, headers=self.headers) + + +def create_connection( + transport: str, + command: str = None, + args: list[str] = None, + env: dict[str, str] = None, + url: str = None, + headers: dict[str, str] = None, +) -> MCPConnection: + """Factory function to create the appropriate MCP connection. + + Args: + transport: Connection type ("stdio", "sse", or "http") + command: Command to run (stdio only) + args: Command arguments (stdio only) + env: Environment variables (stdio only) + url: Server URL (sse and http only) + headers: HTTP headers (sse and http only) + + Returns: + MCPConnection instance + """ + transport = transport.lower() + + if transport == "stdio": + if not command: + raise ValueError("Command is required for stdio transport") + return MCPConnectionStdio(command=command, args=args, env=env) + + elif transport == "sse": + if not url: + raise ValueError("URL is required for sse transport") + return MCPConnectionSSE(url=url, headers=headers) + + elif transport in ["http", "streamable_http", "streamable-http"]: + if not url: + raise ValueError("URL is required for http transport") + return MCPConnectionHTTP(url=url, headers=headers) + + else: + raise ValueError(f"Unsupported transport type: {transport}. Use 'stdio', 'sse', or 'http'") diff --git a/skills/mcp-builder/scripts/evaluation.py b/skills/mcp-builder/scripts/evaluation.py new file mode 100644 index 0000000..4177856 --- /dev/null +++ b/skills/mcp-builder/scripts/evaluation.py @@ -0,0 +1,373 @@ +"""MCP Server Evaluation Harness + +This script evaluates MCP servers by running test questions against them using Claude. +""" + +import argparse +import asyncio +import json +import re +import sys +import time +import traceback +import xml.etree.ElementTree as ET +from pathlib import Path +from typing import Any + +from anthropic import Anthropic + +from connections import create_connection + +EVALUATION_PROMPT = """You are an AI assistant with access to tools. + +When given a task, you MUST: +1. Use the available tools to complete the task +2. Provide summary of each step in your approach, wrapped in tags +3. Provide feedback on the tools provided, wrapped in tags +4. Provide your final response, wrapped in tags + +Summary Requirements: +- In your tags, you must explain: + - The steps you took to complete the task + - Which tools you used, in what order, and why + - The inputs you provided to each tool + - The outputs you received from each tool + - A summary for how you arrived at the response + +Feedback Requirements: +- In your tags, provide constructive feedback on the tools: + - Comment on tool names: Are they clear and descriptive? + - Comment on input parameters: Are they well-documented? Are required vs optional parameters clear? + - Comment on descriptions: Do they accurately describe what the tool does? + - Comment on any errors encountered during tool usage: Did the tool fail to execute? Did the tool return too many tokens? + - Identify specific areas for improvement and explain WHY they would help + - Be specific and actionable in your suggestions + +Response Requirements: +- Your response should be concise and directly address what was asked +- Always wrap your final response in tags +- If you cannot solve the task return NOT_FOUND +- For numeric responses, provide just the number +- For IDs, provide just the ID +- For names or text, provide the exact text requested +- Your response should go last""" + + +def parse_evaluation_file(file_path: Path) -> list[dict[str, Any]]: + """Parse XML evaluation file with qa_pair elements.""" + try: + tree = ET.parse(file_path) + root = tree.getroot() + evaluations = [] + + for qa_pair in root.findall(".//qa_pair"): + question_elem = qa_pair.find("question") + answer_elem = qa_pair.find("answer") + + if question_elem is not None and answer_elem is not None: + evaluations.append({ + "question": (question_elem.text or "").strip(), + "answer": (answer_elem.text or "").strip(), + }) + + return evaluations + except Exception as e: + print(f"Error parsing evaluation file {file_path}: {e}") + return [] + + +def extract_xml_content(text: str, tag: str) -> str | None: + """Extract content from XML tags.""" + pattern = rf"<{tag}>(.*?)" + matches = re.findall(pattern, text, re.DOTALL) + return matches[-1].strip() if matches else None + + +async def agent_loop( + client: Anthropic, + model: str, + question: str, + tools: list[dict[str, Any]], + connection: Any, +) -> tuple[str, dict[str, Any]]: + """Run the agent loop with MCP tools.""" + messages = [{"role": "user", "content": question}] + + response = await asyncio.to_thread( + client.messages.create, + model=model, + max_tokens=4096, + system=EVALUATION_PROMPT, + messages=messages, + tools=tools, + ) + + messages.append({"role": "assistant", "content": response.content}) + + tool_metrics = {} + + while response.stop_reason == "tool_use": + tool_use = next(block for block in response.content if block.type == "tool_use") + tool_name = tool_use.name + tool_input = tool_use.input + + tool_start_ts = time.time() + try: + tool_result = await connection.call_tool(tool_name, tool_input) + tool_response = json.dumps(tool_result) if isinstance(tool_result, (dict, list)) else str(tool_result) + except Exception as e: + tool_response = f"Error executing tool {tool_name}: {str(e)}\n" + tool_response += traceback.format_exc() + tool_duration = time.time() - tool_start_ts + + if tool_name not in tool_metrics: + tool_metrics[tool_name] = {"count": 0, "durations": []} + tool_metrics[tool_name]["count"] += 1 + tool_metrics[tool_name]["durations"].append(tool_duration) + + messages.append({ + "role": "user", + "content": [{ + "type": "tool_result", + "tool_use_id": tool_use.id, + "content": tool_response, + }] + }) + + response = await asyncio.to_thread( + client.messages.create, + model=model, + max_tokens=4096, + system=EVALUATION_PROMPT, + messages=messages, + tools=tools, + ) + messages.append({"role": "assistant", "content": response.content}) + + response_text = next( + (block.text for block in response.content if hasattr(block, "text")), + None, + ) + return response_text, tool_metrics + + +async def evaluate_single_task( + client: Anthropic, + model: str, + qa_pair: dict[str, Any], + tools: list[dict[str, Any]], + connection: Any, + task_index: int, +) -> dict[str, Any]: + """Evaluate a single QA pair with the given tools.""" + start_time = time.time() + + print(f"Task {task_index + 1}: Running task with question: {qa_pair['question']}") + response, tool_metrics = await agent_loop(client, model, qa_pair["question"], tools, connection) + + response_value = extract_xml_content(response, "response") + summary = extract_xml_content(response, "summary") + feedback = extract_xml_content(response, "feedback") + + duration_seconds = time.time() - start_time + + return { + "question": qa_pair["question"], + "expected": qa_pair["answer"], + "actual": response_value, + "score": int(response_value == qa_pair["answer"]) if response_value else 0, + "total_duration": duration_seconds, + "tool_calls": tool_metrics, + "num_tool_calls": sum(len(metrics["durations"]) for metrics in tool_metrics.values()), + "summary": summary, + "feedback": feedback, + } + + +REPORT_HEADER = """ +# Evaluation Report + +## Summary + +- **Accuracy**: {correct}/{total} ({accuracy:.1f}%) +- **Average Task Duration**: {average_duration_s:.2f}s +- **Average Tool Calls per Task**: {average_tool_calls:.2f} +- **Total Tool Calls**: {total_tool_calls} + +--- +""" + +TASK_TEMPLATE = """ +### Task {task_num} + +**Question**: {question} +**Ground Truth Answer**: `{expected_answer}` +**Actual Answer**: `{actual_answer}` +**Correct**: {correct_indicator} +**Duration**: {total_duration:.2f}s +**Tool Calls**: {tool_calls} + +**Summary** +{summary} + +**Feedback** +{feedback} + +--- +""" + + +async def run_evaluation( + eval_path: Path, + connection: Any, + model: str = "claude-3-7-sonnet-20250219", +) -> str: + """Run evaluation with MCP server tools.""" + print("🚀 Starting Evaluation") + + client = Anthropic() + + tools = await connection.list_tools() + print(f"📋 Loaded {len(tools)} tools from MCP server") + + qa_pairs = parse_evaluation_file(eval_path) + print(f"📋 Loaded {len(qa_pairs)} evaluation tasks") + + results = [] + for i, qa_pair in enumerate(qa_pairs): + print(f"Processing task {i + 1}/{len(qa_pairs)}") + result = await evaluate_single_task(client, model, qa_pair, tools, connection, i) + results.append(result) + + correct = sum(r["score"] for r in results) + accuracy = (correct / len(results)) * 100 if results else 0 + average_duration_s = sum(r["total_duration"] for r in results) / len(results) if results else 0 + average_tool_calls = sum(r["num_tool_calls"] for r in results) / len(results) if results else 0 + total_tool_calls = sum(r["num_tool_calls"] for r in results) + + report = REPORT_HEADER.format( + correct=correct, + total=len(results), + accuracy=accuracy, + average_duration_s=average_duration_s, + average_tool_calls=average_tool_calls, + total_tool_calls=total_tool_calls, + ) + + report += "".join([ + TASK_TEMPLATE.format( + task_num=i + 1, + question=qa_pair["question"], + expected_answer=qa_pair["answer"], + actual_answer=result["actual"] or "N/A", + correct_indicator="✅" if result["score"] else "❌", + total_duration=result["total_duration"], + tool_calls=json.dumps(result["tool_calls"], indent=2), + summary=result["summary"] or "N/A", + feedback=result["feedback"] or "N/A", + ) + for i, (qa_pair, result) in enumerate(zip(qa_pairs, results)) + ]) + + return report + + +def parse_headers(header_list: list[str]) -> dict[str, str]: + """Parse header strings in format 'Key: Value' into a dictionary.""" + headers = {} + if not header_list: + return headers + + for header in header_list: + if ":" in header: + key, value = header.split(":", 1) + headers[key.strip()] = value.strip() + else: + print(f"Warning: Ignoring malformed header: {header}") + return headers + + +def parse_env_vars(env_list: list[str]) -> dict[str, str]: + """Parse environment variable strings in format 'KEY=VALUE' into a dictionary.""" + env = {} + if not env_list: + return env + + for env_var in env_list: + if "=" in env_var: + key, value = env_var.split("=", 1) + env[key.strip()] = value.strip() + else: + print(f"Warning: Ignoring malformed environment variable: {env_var}") + return env + + +async def main(): + parser = argparse.ArgumentParser( + description="Evaluate MCP servers using test questions", + formatter_class=argparse.RawDescriptionHelpFormatter, + epilog=""" +Examples: + # Evaluate a local stdio MCP server + python evaluation.py -t stdio -c python -a my_server.py eval.xml + + # Evaluate an SSE MCP server + python evaluation.py -t sse -u https://example.com/mcp -H "Authorization: Bearer token" eval.xml + + # Evaluate an HTTP MCP server with custom model + python evaluation.py -t http -u https://example.com/mcp -m claude-3-5-sonnet-20241022 eval.xml + """, + ) + + parser.add_argument("eval_file", type=Path, help="Path to evaluation XML file") + parser.add_argument("-t", "--transport", choices=["stdio", "sse", "http"], default="stdio", help="Transport type (default: stdio)") + parser.add_argument("-m", "--model", default="claude-3-7-sonnet-20250219", help="Claude model to use (default: claude-3-7-sonnet-20250219)") + + stdio_group = parser.add_argument_group("stdio options") + stdio_group.add_argument("-c", "--command", help="Command to run MCP server (stdio only)") + stdio_group.add_argument("-a", "--args", nargs="+", help="Arguments for the command (stdio only)") + stdio_group.add_argument("-e", "--env", nargs="+", help="Environment variables in KEY=VALUE format (stdio only)") + + remote_group = parser.add_argument_group("sse/http options") + remote_group.add_argument("-u", "--url", help="MCP server URL (sse/http only)") + remote_group.add_argument("-H", "--header", nargs="+", dest="headers", help="HTTP headers in 'Key: Value' format (sse/http only)") + + parser.add_argument("-o", "--output", type=Path, help="Output file for evaluation report (default: stdout)") + + args = parser.parse_args() + + if not args.eval_file.exists(): + print(f"Error: Evaluation file not found: {args.eval_file}") + sys.exit(1) + + headers = parse_headers(args.headers) if args.headers else None + env_vars = parse_env_vars(args.env) if args.env else None + + try: + connection = create_connection( + transport=args.transport, + command=args.command, + args=args.args, + env=env_vars, + url=args.url, + headers=headers, + ) + except ValueError as e: + print(f"Error: {e}") + sys.exit(1) + + print(f"🔗 Connecting to MCP server via {args.transport}...") + + async with connection: + print("✅ Connected successfully") + report = await run_evaluation(args.eval_file, connection, args.model) + + if args.output: + args.output.write_text(report) + print(f"\n✅ Report saved to {args.output}") + else: + print("\n" + report) + + +if __name__ == "__main__": + asyncio.run(main()) diff --git a/skills/mcp-builder/scripts/example_evaluation.xml b/skills/mcp-builder/scripts/example_evaluation.xml new file mode 100644 index 0000000..41e4459 --- /dev/null +++ b/skills/mcp-builder/scripts/example_evaluation.xml @@ -0,0 +1,22 @@ + + + Calculate the compound interest on $10,000 invested at 5% annual interest rate, compounded monthly for 3 years. What is the final amount in dollars (rounded to 2 decimal places)? + 11614.72 + + + A projectile is launched at a 45-degree angle with an initial velocity of 50 m/s. Calculate the total distance (in meters) it has traveled from the launch point after 2 seconds, assuming g=9.8 m/s². Round to 2 decimal places. + 87.25 + + + A sphere has a volume of 500 cubic meters. Calculate its surface area in square meters. Round to 2 decimal places. + 304.65 + + + Calculate the population standard deviation of this dataset: [12, 15, 18, 22, 25, 30, 35]. Round to 2 decimal places. + 7.61 + + + Calculate the pH of a solution with a hydrogen ion concentration of 3.5 × 10^-5 M. Round to 2 decimal places. + 4.46 + + diff --git a/skills/mcp-builder/scripts/requirements.txt b/skills/mcp-builder/scripts/requirements.txt new file mode 100644 index 0000000..e73e5d1 --- /dev/null +++ b/skills/mcp-builder/scripts/requirements.txt @@ -0,0 +1,2 @@ +anthropic>=0.39.0 +mcp>=1.1.0 diff --git a/skills/pdf/LICENSE.txt b/skills/pdf/LICENSE.txt new file mode 100644 index 0000000..c55ab42 --- /dev/null +++ b/skills/pdf/LICENSE.txt @@ -0,0 +1,30 @@ +© 2025 Anthropic, PBC. All rights reserved. + +LICENSE: Use of these materials (including all code, prompts, assets, files, +and other components of this Skill) is governed by your agreement with +Anthropic regarding use of Anthropic's services. If no separate agreement +exists, use is governed by Anthropic's Consumer Terms of Service or +Commercial Terms of Service, as applicable: +https://www.anthropic.com/legal/consumer-terms +https://www.anthropic.com/legal/commercial-terms +Your applicable agreement is referred to as the "Agreement." "Services" are +as defined in the Agreement. + +ADDITIONAL RESTRICTIONS: Notwithstanding anything in the Agreement to the +contrary, users may not: + +- Extract these materials from the Services or retain copies of these + materials outside the Services +- Reproduce or copy these materials, except for temporary copies created + automatically during authorized use of the Services +- Create derivative works based on these materials +- Distribute, sublicense, or transfer these materials to any third party +- Make, offer to sell, sell, or import any inventions embodied in these + materials +- Reverse engineer, decompile, or disassemble these materials + +The receipt, viewing, or possession of these materials does not convey or +imply any license or right beyond those expressly granted above. + +Anthropic retains all right, title, and interest in these materials, +including all copyrights, patents, and other intellectual property rights. diff --git a/skills/pdf/SKILL.md b/skills/pdf/SKILL.md new file mode 100644 index 0000000..f6a22dd --- /dev/null +++ b/skills/pdf/SKILL.md @@ -0,0 +1,294 @@ +--- +name: pdf +description: Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale. +license: Proprietary. LICENSE.txt has complete terms +--- + +# PDF Processing Guide + +## Overview + +This guide covers essential PDF processing operations using Python libraries and command-line tools. For advanced features, JavaScript libraries, and detailed examples, see reference.md. If you need to fill out a PDF form, read forms.md and follow its instructions. + +## Quick Start + +```python +from pypdf import PdfReader, PdfWriter + +# Read a PDF +reader = PdfReader("document.pdf") +print(f"Pages: {len(reader.pages)}") + +# Extract text +text = "" +for page in reader.pages: + text += page.extract_text() +``` + +## Python Libraries + +### pypdf - Basic Operations + +#### Merge PDFs +```python +from pypdf import PdfWriter, PdfReader + +writer = PdfWriter() +for pdf_file in ["doc1.pdf", "doc2.pdf", "doc3.pdf"]: + reader = PdfReader(pdf_file) + for page in reader.pages: + writer.add_page(page) + +with open("merged.pdf", "wb") as output: + writer.write(output) +``` + +#### Split PDF +```python +reader = PdfReader("input.pdf") +for i, page in enumerate(reader.pages): + writer = PdfWriter() + writer.add_page(page) + with open(f"page_{i+1}.pdf", "wb") as output: + writer.write(output) +``` + +#### Extract Metadata +```python +reader = PdfReader("document.pdf") +meta = reader.metadata +print(f"Title: {meta.title}") +print(f"Author: {meta.author}") +print(f"Subject: {meta.subject}") +print(f"Creator: {meta.creator}") +``` + +#### Rotate Pages +```python +reader = PdfReader("input.pdf") +writer = PdfWriter() + +page = reader.pages[0] +page.rotate(90) # Rotate 90 degrees clockwise +writer.add_page(page) + +with open("rotated.pdf", "wb") as output: + writer.write(output) +``` + +### pdfplumber - Text and Table Extraction + +#### Extract Text with Layout +```python +import pdfplumber + +with pdfplumber.open("document.pdf") as pdf: + for page in pdf.pages: + text = page.extract_text() + print(text) +``` + +#### Extract Tables +```python +with pdfplumber.open("document.pdf") as pdf: + for i, page in enumerate(pdf.pages): + tables = page.extract_tables() + for j, table in enumerate(tables): + print(f"Table {j+1} on page {i+1}:") + for row in table: + print(row) +``` + +#### Advanced Table Extraction +```python +import pandas as pd + +with pdfplumber.open("document.pdf") as pdf: + all_tables = [] + for page in pdf.pages: + tables = page.extract_tables() + for table in tables: + if table: # Check if table is not empty + df = pd.DataFrame(table[1:], columns=table[0]) + all_tables.append(df) + +# Combine all tables +if all_tables: + combined_df = pd.concat(all_tables, ignore_index=True) + combined_df.to_excel("extracted_tables.xlsx", index=False) +``` + +### reportlab - Create PDFs + +#### Basic PDF Creation +```python +from reportlab.lib.pagesizes import letter +from reportlab.pdfgen import canvas + +c = canvas.Canvas("hello.pdf", pagesize=letter) +width, height = letter + +# Add text +c.drawString(100, height - 100, "Hello World!") +c.drawString(100, height - 120, "This is a PDF created with reportlab") + +# Add a line +c.line(100, height - 140, 400, height - 140) + +# Save +c.save() +``` + +#### Create PDF with Multiple Pages +```python +from reportlab.lib.pagesizes import letter +from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, PageBreak +from reportlab.lib.styles import getSampleStyleSheet + +doc = SimpleDocTemplate("report.pdf", pagesize=letter) +styles = getSampleStyleSheet() +story = [] + +# Add content +title = Paragraph("Report Title", styles['Title']) +story.append(title) +story.append(Spacer(1, 12)) + +body = Paragraph("This is the body of the report. " * 20, styles['Normal']) +story.append(body) +story.append(PageBreak()) + +# Page 2 +story.append(Paragraph("Page 2", styles['Heading1'])) +story.append(Paragraph("Content for page 2", styles['Normal'])) + +# Build PDF +doc.build(story) +``` + +## Command-Line Tools + +### pdftotext (poppler-utils) +```bash +# Extract text +pdftotext input.pdf output.txt + +# Extract text preserving layout +pdftotext -layout input.pdf output.txt + +# Extract specific pages +pdftotext -f 1 -l 5 input.pdf output.txt # Pages 1-5 +``` + +### qpdf +```bash +# Merge PDFs +qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf + +# Split pages +qpdf input.pdf --pages . 1-5 -- pages1-5.pdf +qpdf input.pdf --pages . 6-10 -- pages6-10.pdf + +# Rotate pages +qpdf input.pdf output.pdf --rotate=+90:1 # Rotate page 1 by 90 degrees + +# Remove password +qpdf --password=mypassword --decrypt encrypted.pdf decrypted.pdf +``` + +### pdftk (if available) +```bash +# Merge +pdftk file1.pdf file2.pdf cat output merged.pdf + +# Split +pdftk input.pdf burst + +# Rotate +pdftk input.pdf rotate 1east output rotated.pdf +``` + +## Common Tasks + +### Extract Text from Scanned PDFs +```python +# Requires: pip install pytesseract pdf2image +import pytesseract +from pdf2image import convert_from_path + +# Convert PDF to images +images = convert_from_path('scanned.pdf') + +# OCR each page +text = "" +for i, image in enumerate(images): + text += f"Page {i+1}:\n" + text += pytesseract.image_to_string(image) + text += "\n\n" + +print(text) +``` + +### Add Watermark +```python +from pypdf import PdfReader, PdfWriter + +# Create watermark (or load existing) +watermark = PdfReader("watermark.pdf").pages[0] + +# Apply to all pages +reader = PdfReader("document.pdf") +writer = PdfWriter() + +for page in reader.pages: + page.merge_page(watermark) + writer.add_page(page) + +with open("watermarked.pdf", "wb") as output: + writer.write(output) +``` + +### Extract Images +```bash +# Using pdfimages (poppler-utils) +pdfimages -j input.pdf output_prefix + +# This extracts all images as output_prefix-000.jpg, output_prefix-001.jpg, etc. +``` + +### Password Protection +```python +from pypdf import PdfReader, PdfWriter + +reader = PdfReader("input.pdf") +writer = PdfWriter() + +for page in reader.pages: + writer.add_page(page) + +# Add password +writer.encrypt("userpassword", "ownerpassword") + +with open("encrypted.pdf", "wb") as output: + writer.write(output) +``` + +## Quick Reference + +| Task | Best Tool | Command/Code | +|------|-----------|--------------| +| Merge PDFs | pypdf | `writer.add_page(page)` | +| Split PDFs | pypdf | One page per file | +| Extract text | pdfplumber | `page.extract_text()` | +| Extract tables | pdfplumber | `page.extract_tables()` | +| Create PDFs | reportlab | Canvas or Platypus | +| Command line merge | qpdf | `qpdf --empty --pages ...` | +| OCR scanned PDFs | pytesseract | Convert to image first | +| Fill PDF forms | pdf-lib or pypdf (see forms.md) | See forms.md | + +## Next Steps + +- For advanced pypdfium2 usage, see reference.md +- For JavaScript libraries (pdf-lib), see reference.md +- If you need to fill out a PDF form, follow the instructions in forms.md +- For troubleshooting guides, see reference.md diff --git a/skills/pdf/forms.md b/skills/pdf/forms.md new file mode 100644 index 0000000..4e23450 --- /dev/null +++ b/skills/pdf/forms.md @@ -0,0 +1,205 @@ +**CRITICAL: You MUST complete these steps in order. Do not skip ahead to writing code.** + +If you need to fill out a PDF form, first check to see if the PDF has fillable form fields. Run this script from this file's directory: + `python scripts/check_fillable_fields `, and depending on the result go to either the "Fillable fields" or "Non-fillable fields" and follow those instructions. + +# Fillable fields +If the PDF has fillable form fields: +- Run this script from this file's directory: `python scripts/extract_form_field_info.py `. It will create a JSON file with a list of fields in this format: +``` +[ + { + "field_id": (unique ID for the field), + "page": (page number, 1-based), + "rect": ([left, bottom, right, top] bounding box in PDF coordinates, y=0 is the bottom of the page), + "type": ("text", "checkbox", "radio_group", or "choice"), + }, + // Checkboxes have "checked_value" and "unchecked_value" properties: + { + "field_id": (unique ID for the field), + "page": (page number, 1-based), + "type": "checkbox", + "checked_value": (Set the field to this value to check the checkbox), + "unchecked_value": (Set the field to this value to uncheck the checkbox), + }, + // Radio groups have a "radio_options" list with the possible choices. + { + "field_id": (unique ID for the field), + "page": (page number, 1-based), + "type": "radio_group", + "radio_options": [ + { + "value": (set the field to this value to select this radio option), + "rect": (bounding box for the radio button for this option) + }, + // Other radio options + ] + }, + // Multiple choice fields have a "choice_options" list with the possible choices: + { + "field_id": (unique ID for the field), + "page": (page number, 1-based), + "type": "choice", + "choice_options": [ + { + "value": (set the field to this value to select this option), + "text": (display text of the option) + }, + // Other choice options + ], + } +] +``` +- Convert the PDF to PNGs (one image for each page) with this script (run from this file's directory): +`python scripts/convert_pdf_to_images.py ` +Then analyze the images to determine the purpose of each form field (make sure to convert the bounding box PDF coordinates to image coordinates). +- Create a `field_values.json` file in this format with the values to be entered for each field: +``` +[ + { + "field_id": "last_name", // Must match the field_id from `extract_form_field_info.py` + "description": "The user's last name", + "page": 1, // Must match the "page" value in field_info.json + "value": "Simpson" + }, + { + "field_id": "Checkbox12", + "description": "Checkbox to be checked if the user is 18 or over", + "page": 1, + "value": "/On" // If this is a checkbox, use its "checked_value" value to check it. If it's a radio button group, use one of the "value" values in "radio_options". + }, + // more fields +] +``` +- Run the `fill_fillable_fields.py` script from this file's directory to create a filled-in PDF: +`python scripts/fill_fillable_fields.py ` +This script will verify that the field IDs and values you provide are valid; if it prints error messages, correct the appropriate fields and try again. + +# Non-fillable fields +If the PDF doesn't have fillable form fields, you'll need to visually determine where the data should be added and create text annotations. Follow the below steps *exactly*. You MUST perform all of these steps to ensure that the the form is accurately completed. Details for each step are below. +- Convert the PDF to PNG images and determine field bounding boxes. +- Create a JSON file with field information and validation images showing the bounding boxes. +- Validate the the bounding boxes. +- Use the bounding boxes to fill in the form. + +## Step 1: Visual Analysis (REQUIRED) +- Convert the PDF to PNG images. Run this script from this file's directory: +`python scripts/convert_pdf_to_images.py ` +The script will create a PNG image for each page in the PDF. +- Carefully examine each PNG image and identify all form fields and areas where the user should enter data. For each form field where the user should enter text, determine bounding boxes for both the form field label, and the area where the user should enter text. The label and entry bounding boxes MUST NOT INTERSECT; the text entry box should only include the area where data should be entered. Usually this area will be immediately to the side, above, or below its label. Entry bounding boxes must be tall and wide enough to contain their text. + +These are some examples of form structures that you might see: + +*Label inside box* +``` +┌────────────────────────┐ +│ Name: │ +└────────────────────────┘ +``` +The input area should be to the right of the "Name" label and extend to the edge of the box. + +*Label before line* +``` +Email: _______________________ +``` +The input area should be above the line and include its entire width. + +*Label under line* +``` +_________________________ +Name +``` +The input area should be above the line and include the entire width of the line. This is common for signature and date fields. + +*Label above line* +``` +Please enter any special requests: +________________________________________________ +``` +The input area should extend from the bottom of the label to the line, and should include the entire width of the line. + +*Checkboxes* +``` +Are you a US citizen? Yes □ No □ +``` +For checkboxes: +- Look for small square boxes (□) - these are the actual checkboxes to target. They may be to the left or right of their labels. +- Distinguish between label text ("Yes", "No") and the clickable checkbox squares. +- The entry bounding box should cover ONLY the small square, not the text label. + +### Step 2: Create fields.json and validation images (REQUIRED) +- Create a file named `fields.json` with information for the form fields and bounding boxes in this format: +``` +{ + "pages": [ + { + "page_number": 1, + "image_width": (first page image width in pixels), + "image_height": (first page image height in pixels), + }, + { + "page_number": 2, + "image_width": (second page image width in pixels), + "image_height": (second page image height in pixels), + } + // additional pages + ], + "form_fields": [ + // Example for a text field. + { + "page_number": 1, + "description": "The user's last name should be entered here", + // Bounding boxes are [left, top, right, bottom]. The bounding boxes for the label and text entry should not overlap. + "field_label": "Last name", + "label_bounding_box": [30, 125, 95, 142], + "entry_bounding_box": [100, 125, 280, 142], + "entry_text": { + "text": "Johnson", // This text will be added as an annotation at the entry_bounding_box location + "font_size": 14, // optional, defaults to 14 + "font_color": "000000", // optional, RRGGBB format, defaults to 000000 (black) + } + }, + // Example for a checkbox. TARGET THE SQUARE for the entry bounding box, NOT THE TEXT + { + "page_number": 2, + "description": "Checkbox that should be checked if the user is over 18", + "entry_bounding_box": [140, 525, 155, 540], // Small box over checkbox square + "field_label": "Yes", + "label_bounding_box": [100, 525, 132, 540], // Box containing "Yes" text + // Use "X" to check a checkbox. + "entry_text": { + "text": "X", + } + } + // additional form field entries + ] +} +``` + +Create validation images by running this script from this file's directory for each page: +`python scripts/create_validation_image.py + +The validation images will have red rectangles where text should be entered, and blue rectangles covering label text. + +### Step 3: Validate Bounding Boxes (REQUIRED) +#### Automated intersection check +- Verify that none of bounding boxes intersect and that the entry bounding boxes are tall enough by checking the fields.json file with the `check_bounding_boxes.py` script (run from this file's directory): +`python scripts/check_bounding_boxes.py ` + +If there are errors, reanalyze the relevant fields, adjust the bounding boxes, and iterate until there are no remaining errors. Remember: label (blue) bounding boxes should contain text labels, entry (red) boxes should not. + +#### Manual image inspection +**CRITICAL: Do not proceed without visually inspecting validation images** +- Red rectangles must ONLY cover input areas +- Red rectangles MUST NOT contain any text +- Blue rectangles should contain label text +- For checkboxes: + - Red rectangle MUST be centered on the checkbox square + - Blue rectangle should cover the text label for the checkbox + +- If any rectangles look wrong, fix fields.json, regenerate the validation images, and verify again. Repeat this process until the bounding boxes are fully accurate. + + +### Step 4: Add annotations to the PDF +Run this script from this file's directory to create a filled-out PDF using the information in fields.json: +`python scripts/fill_pdf_form_with_annotations.py diff --git a/skills/pdf/reference.md b/skills/pdf/reference.md new file mode 100644 index 0000000..41400bf --- /dev/null +++ b/skills/pdf/reference.md @@ -0,0 +1,612 @@ +# PDF Processing Advanced Reference + +This document contains advanced PDF processing features, detailed examples, and additional libraries not covered in the main skill instructions. + +## pypdfium2 Library (Apache/BSD License) + +### Overview +pypdfium2 is a Python binding for PDFium (Chromium's PDF library). It's excellent for fast PDF rendering, image generation, and serves as a PyMuPDF replacement. + +### Render PDF to Images +```python +import pypdfium2 as pdfium +from PIL import Image + +# Load PDF +pdf = pdfium.PdfDocument("document.pdf") + +# Render page to image +page = pdf[0] # First page +bitmap = page.render( + scale=2.0, # Higher resolution + rotation=0 # No rotation +) + +# Convert to PIL Image +img = bitmap.to_pil() +img.save("page_1.png", "PNG") + +# Process multiple pages +for i, page in enumerate(pdf): + bitmap = page.render(scale=1.5) + img = bitmap.to_pil() + img.save(f"page_{i+1}.jpg", "JPEG", quality=90) +``` + +### Extract Text with pypdfium2 +```python +import pypdfium2 as pdfium + +pdf = pdfium.PdfDocument("document.pdf") +for i, page in enumerate(pdf): + text = page.get_text() + print(f"Page {i+1} text length: {len(text)} chars") +``` + +## JavaScript Libraries + +### pdf-lib (MIT License) + +pdf-lib is a powerful JavaScript library for creating and modifying PDF documents in any JavaScript environment. + +#### Load and Manipulate Existing PDF +```javascript +import { PDFDocument } from 'pdf-lib'; +import fs from 'fs'; + +async function manipulatePDF() { + // Load existing PDF + const existingPdfBytes = fs.readFileSync('input.pdf'); + const pdfDoc = await PDFDocument.load(existingPdfBytes); + + // Get page count + const pageCount = pdfDoc.getPageCount(); + console.log(`Document has ${pageCount} pages`); + + // Add new page + const newPage = pdfDoc.addPage([600, 400]); + newPage.drawText('Added by pdf-lib', { + x: 100, + y: 300, + size: 16 + }); + + // Save modified PDF + const pdfBytes = await pdfDoc.save(); + fs.writeFileSync('modified.pdf', pdfBytes); +} +``` + +#### Create Complex PDFs from Scratch +```javascript +import { PDFDocument, rgb, StandardFonts } from 'pdf-lib'; +import fs from 'fs'; + +async function createPDF() { + const pdfDoc = await PDFDocument.create(); + + // Add fonts + const helveticaFont = await pdfDoc.embedFont(StandardFonts.Helvetica); + const helveticaBold = await pdfDoc.embedFont(StandardFonts.HelveticaBold); + + // Add page + const page = pdfDoc.addPage([595, 842]); // A4 size + const { width, height } = page.getSize(); + + // Add text with styling + page.drawText('Invoice #12345', { + x: 50, + y: height - 50, + size: 18, + font: helveticaBold, + color: rgb(0.2, 0.2, 0.8) + }); + + // Add rectangle (header background) + page.drawRectangle({ + x: 40, + y: height - 100, + width: width - 80, + height: 30, + color: rgb(0.9, 0.9, 0.9) + }); + + // Add table-like content + const items = [ + ['Item', 'Qty', 'Price', 'Total'], + ['Widget', '2', '$50', '$100'], + ['Gadget', '1', '$75', '$75'] + ]; + + let yPos = height - 150; + items.forEach(row => { + let xPos = 50; + row.forEach(cell => { + page.drawText(cell, { + x: xPos, + y: yPos, + size: 12, + font: helveticaFont + }); + xPos += 120; + }); + yPos -= 25; + }); + + const pdfBytes = await pdfDoc.save(); + fs.writeFileSync('created.pdf', pdfBytes); +} +``` + +#### Advanced Merge and Split Operations +```javascript +import { PDFDocument } from 'pdf-lib'; +import fs from 'fs'; + +async function mergePDFs() { + // Create new document + const mergedPdf = await PDFDocument.create(); + + // Load source PDFs + const pdf1Bytes = fs.readFileSync('doc1.pdf'); + const pdf2Bytes = fs.readFileSync('doc2.pdf'); + + const pdf1 = await PDFDocument.load(pdf1Bytes); + const pdf2 = await PDFDocument.load(pdf2Bytes); + + // Copy pages from first PDF + const pdf1Pages = await mergedPdf.copyPages(pdf1, pdf1.getPageIndices()); + pdf1Pages.forEach(page => mergedPdf.addPage(page)); + + // Copy specific pages from second PDF (pages 0, 2, 4) + const pdf2Pages = await mergedPdf.copyPages(pdf2, [0, 2, 4]); + pdf2Pages.forEach(page => mergedPdf.addPage(page)); + + const mergedPdfBytes = await mergedPdf.save(); + fs.writeFileSync('merged.pdf', mergedPdfBytes); +} +``` + +### pdfjs-dist (Apache License) + +PDF.js is Mozilla's JavaScript library for rendering PDFs in the browser. + +#### Basic PDF Loading and Rendering +```javascript +import * as pdfjsLib from 'pdfjs-dist'; + +// Configure worker (important for performance) +pdfjsLib.GlobalWorkerOptions.workerSrc = './pdf.worker.js'; + +async function renderPDF() { + // Load PDF + const loadingTask = pdfjsLib.getDocument('document.pdf'); + const pdf = await loadingTask.promise; + + console.log(`Loaded PDF with ${pdf.numPages} pages`); + + // Get first page + const page = await pdf.getPage(1); + const viewport = page.getViewport({ scale: 1.5 }); + + // Render to canvas + const canvas = document.createElement('canvas'); + const context = canvas.getContext('2d'); + canvas.height = viewport.height; + canvas.width = viewport.width; + + const renderContext = { + canvasContext: context, + viewport: viewport + }; + + await page.render(renderContext).promise; + document.body.appendChild(canvas); +} +``` + +#### Extract Text with Coordinates +```javascript +import * as pdfjsLib from 'pdfjs-dist'; + +async function extractText() { + const loadingTask = pdfjsLib.getDocument('document.pdf'); + const pdf = await loadingTask.promise; + + let fullText = ''; + + // Extract text from all pages + for (let i = 1; i <= pdf.numPages; i++) { + const page = await pdf.getPage(i); + const textContent = await page.getTextContent(); + + const pageText = textContent.items + .map(item => item.str) + .join(' '); + + fullText += `\n--- Page ${i} ---\n${pageText}`; + + // Get text with coordinates for advanced processing + const textWithCoords = textContent.items.map(item => ({ + text: item.str, + x: item.transform[4], + y: item.transform[5], + width: item.width, + height: item.height + })); + } + + console.log(fullText); + return fullText; +} +``` + +#### Extract Annotations and Forms +```javascript +import * as pdfjsLib from 'pdfjs-dist'; + +async function extractAnnotations() { + const loadingTask = pdfjsLib.getDocument('annotated.pdf'); + const pdf = await loadingTask.promise; + + for (let i = 1; i <= pdf.numPages; i++) { + const page = await pdf.getPage(i); + const annotations = await page.getAnnotations(); + + annotations.forEach(annotation => { + console.log(`Annotation type: ${annotation.subtype}`); + console.log(`Content: ${annotation.contents}`); + console.log(`Coordinates: ${JSON.stringify(annotation.rect)}`); + }); + } +} +``` + +## Advanced Command-Line Operations + +### poppler-utils Advanced Features + +#### Extract Text with Bounding Box Coordinates +```bash +# Extract text with bounding box coordinates (essential for structured data) +pdftotext -bbox-layout document.pdf output.xml + +# The XML output contains precise coordinates for each text element +``` + +#### Advanced Image Conversion +```bash +# Convert to PNG images with specific resolution +pdftoppm -png -r 300 document.pdf output_prefix + +# Convert specific page range with high resolution +pdftoppm -png -r 600 -f 1 -l 3 document.pdf high_res_pages + +# Convert to JPEG with quality setting +pdftoppm -jpeg -jpegopt quality=85 -r 200 document.pdf jpeg_output +``` + +#### Extract Embedded Images +```bash +# Extract all embedded images with metadata +pdfimages -j -p document.pdf page_images + +# List image info without extracting +pdfimages -list document.pdf + +# Extract images in their original format +pdfimages -all document.pdf images/img +``` + +### qpdf Advanced Features + +#### Complex Page Manipulation +```bash +# Split PDF into groups of pages +qpdf --split-pages=3 input.pdf output_group_%02d.pdf + +# Extract specific pages with complex ranges +qpdf input.pdf --pages input.pdf 1,3-5,8,10-end -- extracted.pdf + +# Merge specific pages from multiple PDFs +qpdf --empty --pages doc1.pdf 1-3 doc2.pdf 5-7 doc3.pdf 2,4 -- combined.pdf +``` + +#### PDF Optimization and Repair +```bash +# Optimize PDF for web (linearize for streaming) +qpdf --linearize input.pdf optimized.pdf + +# Remove unused objects and compress +qpdf --optimize-level=all input.pdf compressed.pdf + +# Attempt to repair corrupted PDF structure +qpdf --check input.pdf +qpdf --fix-qdf damaged.pdf repaired.pdf + +# Show detailed PDF structure for debugging +qpdf --show-all-pages input.pdf > structure.txt +``` + +#### Advanced Encryption +```bash +# Add password protection with specific permissions +qpdf --encrypt user_pass owner_pass 256 --print=none --modify=none -- input.pdf encrypted.pdf + +# Check encryption status +qpdf --show-encryption encrypted.pdf + +# Remove password protection (requires password) +qpdf --password=secret123 --decrypt encrypted.pdf decrypted.pdf +``` + +## Advanced Python Techniques + +### pdfplumber Advanced Features + +#### Extract Text with Precise Coordinates +```python +import pdfplumber + +with pdfplumber.open("document.pdf") as pdf: + page = pdf.pages[0] + + # Extract all text with coordinates + chars = page.chars + for char in chars[:10]: # First 10 characters + print(f"Char: '{char['text']}' at x:{char['x0']:.1f} y:{char['y0']:.1f}") + + # Extract text by bounding box (left, top, right, bottom) + bbox_text = page.within_bbox((100, 100, 400, 200)).extract_text() +``` + +#### Advanced Table Extraction with Custom Settings +```python +import pdfplumber +import pandas as pd + +with pdfplumber.open("complex_table.pdf") as pdf: + page = pdf.pages[0] + + # Extract tables with custom settings for complex layouts + table_settings = { + "vertical_strategy": "lines", + "horizontal_strategy": "lines", + "snap_tolerance": 3, + "intersection_tolerance": 15 + } + tables = page.extract_tables(table_settings) + + # Visual debugging for table extraction + img = page.to_image(resolution=150) + img.save("debug_layout.png") +``` + +### reportlab Advanced Features + +#### Create Professional Reports with Tables +```python +from reportlab.platypus import SimpleDocTemplate, Table, TableStyle, Paragraph +from reportlab.lib.styles import getSampleStyleSheet +from reportlab.lib import colors + +# Sample data +data = [ + ['Product', 'Q1', 'Q2', 'Q3', 'Q4'], + ['Widgets', '120', '135', '142', '158'], + ['Gadgets', '85', '92', '98', '105'] +] + +# Create PDF with table +doc = SimpleDocTemplate("report.pdf") +elements = [] + +# Add title +styles = getSampleStyleSheet() +title = Paragraph("Quarterly Sales Report", styles['Title']) +elements.append(title) + +# Add table with advanced styling +table = Table(data) +table.setStyle(TableStyle([ + ('BACKGROUND', (0, 0), (-1, 0), colors.grey), + ('TEXTCOLOR', (0, 0), (-1, 0), colors.whitesmoke), + ('ALIGN', (0, 0), (-1, -1), 'CENTER'), + ('FONTNAME', (0, 0), (-1, 0), 'Helvetica-Bold'), + ('FONTSIZE', (0, 0), (-1, 0), 14), + ('BOTTOMPADDING', (0, 0), (-1, 0), 12), + ('BACKGROUND', (0, 1), (-1, -1), colors.beige), + ('GRID', (0, 0), (-1, -1), 1, colors.black) +])) +elements.append(table) + +doc.build(elements) +``` + +## Complex Workflows + +### Extract Figures/Images from PDF + +#### Method 1: Using pdfimages (fastest) +```bash +# Extract all images with original quality +pdfimages -all document.pdf images/img +``` + +#### Method 2: Using pypdfium2 + Image Processing +```python +import pypdfium2 as pdfium +from PIL import Image +import numpy as np + +def extract_figures(pdf_path, output_dir): + pdf = pdfium.PdfDocument(pdf_path) + + for page_num, page in enumerate(pdf): + # Render high-resolution page + bitmap = page.render(scale=3.0) + img = bitmap.to_pil() + + # Convert to numpy for processing + img_array = np.array(img) + + # Simple figure detection (non-white regions) + mask = np.any(img_array != [255, 255, 255], axis=2) + + # Find contours and extract bounding boxes + # (This is simplified - real implementation would need more sophisticated detection) + + # Save detected figures + # ... implementation depends on specific needs +``` + +### Batch PDF Processing with Error Handling +```python +import os +import glob +from pypdf import PdfReader, PdfWriter +import logging + +logging.basicConfig(level=logging.INFO) +logger = logging.getLogger(__name__) + +def batch_process_pdfs(input_dir, operation='merge'): + pdf_files = glob.glob(os.path.join(input_dir, "*.pdf")) + + if operation == 'merge': + writer = PdfWriter() + for pdf_file in pdf_files: + try: + reader = PdfReader(pdf_file) + for page in reader.pages: + writer.add_page(page) + logger.info(f"Processed: {pdf_file}") + except Exception as e: + logger.error(f"Failed to process {pdf_file}: {e}") + continue + + with open("batch_merged.pdf", "wb") as output: + writer.write(output) + + elif operation == 'extract_text': + for pdf_file in pdf_files: + try: + reader = PdfReader(pdf_file) + text = "" + for page in reader.pages: + text += page.extract_text() + + output_file = pdf_file.replace('.pdf', '.txt') + with open(output_file, 'w', encoding='utf-8') as f: + f.write(text) + logger.info(f"Extracted text from: {pdf_file}") + + except Exception as e: + logger.error(f"Failed to extract text from {pdf_file}: {e}") + continue +``` + +### Advanced PDF Cropping +```python +from pypdf import PdfWriter, PdfReader + +reader = PdfReader("input.pdf") +writer = PdfWriter() + +# Crop page (left, bottom, right, top in points) +page = reader.pages[0] +page.mediabox.left = 50 +page.mediabox.bottom = 50 +page.mediabox.right = 550 +page.mediabox.top = 750 + +writer.add_page(page) +with open("cropped.pdf", "wb") as output: + writer.write(output) +``` + +## Performance Optimization Tips + +### 1. For Large PDFs +- Use streaming approaches instead of loading entire PDF in memory +- Use `qpdf --split-pages` for splitting large files +- Process pages individually with pypdfium2 + +### 2. For Text Extraction +- `pdftotext -bbox-layout` is fastest for plain text extraction +- Use pdfplumber for structured data and tables +- Avoid `pypdf.extract_text()` for very large documents + +### 3. For Image Extraction +- `pdfimages` is much faster than rendering pages +- Use low resolution for previews, high resolution for final output + +### 4. For Form Filling +- pdf-lib maintains form structure better than most alternatives +- Pre-validate form fields before processing + +### 5. Memory Management +```python +# Process PDFs in chunks +def process_large_pdf(pdf_path, chunk_size=10): + reader = PdfReader(pdf_path) + total_pages = len(reader.pages) + + for start_idx in range(0, total_pages, chunk_size): + end_idx = min(start_idx + chunk_size, total_pages) + writer = PdfWriter() + + for i in range(start_idx, end_idx): + writer.add_page(reader.pages[i]) + + # Process chunk + with open(f"chunk_{start_idx//chunk_size}.pdf", "wb") as output: + writer.write(output) +``` + +## Troubleshooting Common Issues + +### Encrypted PDFs +```python +# Handle password-protected PDFs +from pypdf import PdfReader + +try: + reader = PdfReader("encrypted.pdf") + if reader.is_encrypted: + reader.decrypt("password") +except Exception as e: + print(f"Failed to decrypt: {e}") +``` + +### Corrupted PDFs +```bash +# Use qpdf to repair +qpdf --check corrupted.pdf +qpdf --replace-input corrupted.pdf +``` + +### Text Extraction Issues +```python +# Fallback to OCR for scanned PDFs +import pytesseract +from pdf2image import convert_from_path + +def extract_text_with_ocr(pdf_path): + images = convert_from_path(pdf_path) + text = "" + for i, image in enumerate(images): + text += pytesseract.image_to_string(image) + return text +``` + +## License Information + +- **pypdf**: BSD License +- **pdfplumber**: MIT License +- **pypdfium2**: Apache/BSD License +- **reportlab**: BSD License +- **poppler-utils**: GPL-2 License +- **qpdf**: Apache License +- **pdf-lib**: MIT License +- **pdfjs-dist**: Apache License \ No newline at end of file diff --git a/skills/pdf/scripts/check_bounding_boxes.py b/skills/pdf/scripts/check_bounding_boxes.py new file mode 100644 index 0000000..7443660 --- /dev/null +++ b/skills/pdf/scripts/check_bounding_boxes.py @@ -0,0 +1,70 @@ +from dataclasses import dataclass +import json +import sys + + +# Script to check that the `fields.json` file that Claude creates when analyzing PDFs +# does not have overlapping bounding boxes. See forms.md. + + +@dataclass +class RectAndField: + rect: list[float] + rect_type: str + field: dict + + +# Returns a list of messages that are printed to stdout for Claude to read. +def get_bounding_box_messages(fields_json_stream) -> list[str]: + messages = [] + fields = json.load(fields_json_stream) + messages.append(f"Read {len(fields['form_fields'])} fields") + + def rects_intersect(r1, r2): + disjoint_horizontal = r1[0] >= r2[2] or r1[2] <= r2[0] + disjoint_vertical = r1[1] >= r2[3] or r1[3] <= r2[1] + return not (disjoint_horizontal or disjoint_vertical) + + rects_and_fields = [] + for f in fields["form_fields"]: + rects_and_fields.append(RectAndField(f["label_bounding_box"], "label", f)) + rects_and_fields.append(RectAndField(f["entry_bounding_box"], "entry", f)) + + has_error = False + for i, ri in enumerate(rects_and_fields): + # This is O(N^2); we can optimize if it becomes a problem. + for j in range(i + 1, len(rects_and_fields)): + rj = rects_and_fields[j] + if ri.field["page_number"] == rj.field["page_number"] and rects_intersect(ri.rect, rj.rect): + has_error = True + if ri.field is rj.field: + messages.append(f"FAILURE: intersection between label and entry bounding boxes for `{ri.field['description']}` ({ri.rect}, {rj.rect})") + else: + messages.append(f"FAILURE: intersection between {ri.rect_type} bounding box for `{ri.field['description']}` ({ri.rect}) and {rj.rect_type} bounding box for `{rj.field['description']}` ({rj.rect})") + if len(messages) >= 20: + messages.append("Aborting further checks; fix bounding boxes and try again") + return messages + if ri.rect_type == "entry": + if "entry_text" in ri.field: + font_size = ri.field["entry_text"].get("font_size", 14) + entry_height = ri.rect[3] - ri.rect[1] + if entry_height < font_size: + has_error = True + messages.append(f"FAILURE: entry bounding box height ({entry_height}) for `{ri.field['description']}` is too short for the text content (font size: {font_size}). Increase the box height or decrease the font size.") + if len(messages) >= 20: + messages.append("Aborting further checks; fix bounding boxes and try again") + return messages + + if not has_error: + messages.append("SUCCESS: All bounding boxes are valid") + return messages + +if __name__ == "__main__": + if len(sys.argv) != 2: + print("Usage: check_bounding_boxes.py [fields.json]") + sys.exit(1) + # Input file should be in the `fields.json` format described in forms.md. + with open(sys.argv[1]) as f: + messages = get_bounding_box_messages(f) + for msg in messages: + print(msg) diff --git a/skills/pdf/scripts/check_bounding_boxes_test.py b/skills/pdf/scripts/check_bounding_boxes_test.py new file mode 100644 index 0000000..1dbb463 --- /dev/null +++ b/skills/pdf/scripts/check_bounding_boxes_test.py @@ -0,0 +1,226 @@ +import unittest +import json +import io +from check_bounding_boxes import get_bounding_box_messages + + +# Currently this is not run automatically in CI; it's just for documentation and manual checking. +class TestGetBoundingBoxMessages(unittest.TestCase): + + def create_json_stream(self, data): + """Helper to create a JSON stream from data""" + return io.StringIO(json.dumps(data)) + + def test_no_intersections(self): + """Test case with no bounding box intersections""" + data = { + "form_fields": [ + { + "description": "Name", + "page_number": 1, + "label_bounding_box": [10, 10, 50, 30], + "entry_bounding_box": [60, 10, 150, 30] + }, + { + "description": "Email", + "page_number": 1, + "label_bounding_box": [10, 40, 50, 60], + "entry_bounding_box": [60, 40, 150, 60] + } + ] + } + + stream = self.create_json_stream(data) + messages = get_bounding_box_messages(stream) + self.assertTrue(any("SUCCESS" in msg for msg in messages)) + self.assertFalse(any("FAILURE" in msg for msg in messages)) + + def test_label_entry_intersection_same_field(self): + """Test intersection between label and entry of the same field""" + data = { + "form_fields": [ + { + "description": "Name", + "page_number": 1, + "label_bounding_box": [10, 10, 60, 30], + "entry_bounding_box": [50, 10, 150, 30] # Overlaps with label + } + ] + } + + stream = self.create_json_stream(data) + messages = get_bounding_box_messages(stream) + self.assertTrue(any("FAILURE" in msg and "intersection" in msg for msg in messages)) + self.assertFalse(any("SUCCESS" in msg for msg in messages)) + + def test_intersection_between_different_fields(self): + """Test intersection between bounding boxes of different fields""" + data = { + "form_fields": [ + { + "description": "Name", + "page_number": 1, + "label_bounding_box": [10, 10, 50, 30], + "entry_bounding_box": [60, 10, 150, 30] + }, + { + "description": "Email", + "page_number": 1, + "label_bounding_box": [40, 20, 80, 40], # Overlaps with Name's boxes + "entry_bounding_box": [160, 10, 250, 30] + } + ] + } + + stream = self.create_json_stream(data) + messages = get_bounding_box_messages(stream) + self.assertTrue(any("FAILURE" in msg and "intersection" in msg for msg in messages)) + self.assertFalse(any("SUCCESS" in msg for msg in messages)) + + def test_different_pages_no_intersection(self): + """Test that boxes on different pages don't count as intersecting""" + data = { + "form_fields": [ + { + "description": "Name", + "page_number": 1, + "label_bounding_box": [10, 10, 50, 30], + "entry_bounding_box": [60, 10, 150, 30] + }, + { + "description": "Email", + "page_number": 2, + "label_bounding_box": [10, 10, 50, 30], # Same coordinates but different page + "entry_bounding_box": [60, 10, 150, 30] + } + ] + } + + stream = self.create_json_stream(data) + messages = get_bounding_box_messages(stream) + self.assertTrue(any("SUCCESS" in msg for msg in messages)) + self.assertFalse(any("FAILURE" in msg for msg in messages)) + + def test_entry_height_too_small(self): + """Test that entry box height is checked against font size""" + data = { + "form_fields": [ + { + "description": "Name", + "page_number": 1, + "label_bounding_box": [10, 10, 50, 30], + "entry_bounding_box": [60, 10, 150, 20], # Height is 10 + "entry_text": { + "font_size": 14 # Font size larger than height + } + } + ] + } + + stream = self.create_json_stream(data) + messages = get_bounding_box_messages(stream) + self.assertTrue(any("FAILURE" in msg and "height" in msg for msg in messages)) + self.assertFalse(any("SUCCESS" in msg for msg in messages)) + + def test_entry_height_adequate(self): + """Test that adequate entry box height passes""" + data = { + "form_fields": [ + { + "description": "Name", + "page_number": 1, + "label_bounding_box": [10, 10, 50, 30], + "entry_bounding_box": [60, 10, 150, 30], # Height is 20 + "entry_text": { + "font_size": 14 # Font size smaller than height + } + } + ] + } + + stream = self.create_json_stream(data) + messages = get_bounding_box_messages(stream) + self.assertTrue(any("SUCCESS" in msg for msg in messages)) + self.assertFalse(any("FAILURE" in msg for msg in messages)) + + def test_default_font_size(self): + """Test that default font size is used when not specified""" + data = { + "form_fields": [ + { + "description": "Name", + "page_number": 1, + "label_bounding_box": [10, 10, 50, 30], + "entry_bounding_box": [60, 10, 150, 20], # Height is 10 + "entry_text": {} # No font_size specified, should use default 14 + } + ] + } + + stream = self.create_json_stream(data) + messages = get_bounding_box_messages(stream) + self.assertTrue(any("FAILURE" in msg and "height" in msg for msg in messages)) + self.assertFalse(any("SUCCESS" in msg for msg in messages)) + + def test_no_entry_text(self): + """Test that missing entry_text doesn't cause height check""" + data = { + "form_fields": [ + { + "description": "Name", + "page_number": 1, + "label_bounding_box": [10, 10, 50, 30], + "entry_bounding_box": [60, 10, 150, 20] # Small height but no entry_text + } + ] + } + + stream = self.create_json_stream(data) + messages = get_bounding_box_messages(stream) + self.assertTrue(any("SUCCESS" in msg for msg in messages)) + self.assertFalse(any("FAILURE" in msg for msg in messages)) + + def test_multiple_errors_limit(self): + """Test that error messages are limited to prevent excessive output""" + fields = [] + # Create many overlapping fields + for i in range(25): + fields.append({ + "description": f"Field{i}", + "page_number": 1, + "label_bounding_box": [10, 10, 50, 30], # All overlap + "entry_bounding_box": [20, 15, 60, 35] # All overlap + }) + + data = {"form_fields": fields} + + stream = self.create_json_stream(data) + messages = get_bounding_box_messages(stream) + # Should abort after ~20 messages + self.assertTrue(any("Aborting" in msg for msg in messages)) + # Should have some FAILURE messages but not hundreds + failure_count = sum(1 for msg in messages if "FAILURE" in msg) + self.assertGreater(failure_count, 0) + self.assertLess(len(messages), 30) # Should be limited + + def test_edge_touching_boxes(self): + """Test that boxes touching at edges don't count as intersecting""" + data = { + "form_fields": [ + { + "description": "Name", + "page_number": 1, + "label_bounding_box": [10, 10, 50, 30], + "entry_bounding_box": [50, 10, 150, 30] # Touches at x=50 + } + ] + } + + stream = self.create_json_stream(data) + messages = get_bounding_box_messages(stream) + self.assertTrue(any("SUCCESS" in msg for msg in messages)) + self.assertFalse(any("FAILURE" in msg for msg in messages)) + + +if __name__ == '__main__': + unittest.main() diff --git a/skills/pdf/scripts/check_fillable_fields.py b/skills/pdf/scripts/check_fillable_fields.py new file mode 100644 index 0000000..dc43d18 --- /dev/null +++ b/skills/pdf/scripts/check_fillable_fields.py @@ -0,0 +1,12 @@ +import sys +from pypdf import PdfReader + + +# Script for Claude to run to determine whether a PDF has fillable form fields. See forms.md. + + +reader = PdfReader(sys.argv[1]) +if (reader.get_fields()): + print("This PDF has fillable form fields") +else: + print("This PDF does not have fillable form fields; you will need to visually determine where to enter data") diff --git a/skills/pdf/scripts/convert_pdf_to_images.py b/skills/pdf/scripts/convert_pdf_to_images.py new file mode 100644 index 0000000..f8a4ec5 --- /dev/null +++ b/skills/pdf/scripts/convert_pdf_to_images.py @@ -0,0 +1,35 @@ +import os +import sys + +from pdf2image import convert_from_path + + +# Converts each page of a PDF to a PNG image. + + +def convert(pdf_path, output_dir, max_dim=1000): + images = convert_from_path(pdf_path, dpi=200) + + for i, image in enumerate(images): + # Scale image if needed to keep width/height under `max_dim` + width, height = image.size + if width > max_dim or height > max_dim: + scale_factor = min(max_dim / width, max_dim / height) + new_width = int(width * scale_factor) + new_height = int(height * scale_factor) + image = image.resize((new_width, new_height)) + + image_path = os.path.join(output_dir, f"page_{i+1}.png") + image.save(image_path) + print(f"Saved page {i+1} as {image_path} (size: {image.size})") + + print(f"Converted {len(images)} pages to PNG images") + + +if __name__ == "__main__": + if len(sys.argv) != 3: + print("Usage: convert_pdf_to_images.py [input pdf] [output directory]") + sys.exit(1) + pdf_path = sys.argv[1] + output_directory = sys.argv[2] + convert(pdf_path, output_directory) diff --git a/skills/pdf/scripts/create_validation_image.py b/skills/pdf/scripts/create_validation_image.py new file mode 100644 index 0000000..4913f8f --- /dev/null +++ b/skills/pdf/scripts/create_validation_image.py @@ -0,0 +1,41 @@ +import json +import sys + +from PIL import Image, ImageDraw + + +# Creates "validation" images with rectangles for the bounding box information that +# Claude creates when determining where to add text annotations in PDFs. See forms.md. + + +def create_validation_image(page_number, fields_json_path, input_path, output_path): + # Input file should be in the `fields.json` format described in forms.md. + with open(fields_json_path, 'r') as f: + data = json.load(f) + + img = Image.open(input_path) + draw = ImageDraw.Draw(img) + num_boxes = 0 + + for field in data["form_fields"]: + if field["page_number"] == page_number: + entry_box = field['entry_bounding_box'] + label_box = field['label_bounding_box'] + # Draw red rectangle over entry bounding box and blue rectangle over the label. + draw.rectangle(entry_box, outline='red', width=2) + draw.rectangle(label_box, outline='blue', width=2) + num_boxes += 2 + + img.save(output_path) + print(f"Created validation image at {output_path} with {num_boxes} bounding boxes") + + +if __name__ == "__main__": + if len(sys.argv) != 5: + print("Usage: create_validation_image.py [page number] [fields.json file] [input image path] [output image path]") + sys.exit(1) + page_number = int(sys.argv[1]) + fields_json_path = sys.argv[2] + input_image_path = sys.argv[3] + output_image_path = sys.argv[4] + create_validation_image(page_number, fields_json_path, input_image_path, output_image_path) diff --git a/skills/pdf/scripts/extract_form_field_info.py b/skills/pdf/scripts/extract_form_field_info.py new file mode 100644 index 0000000..f42a2df --- /dev/null +++ b/skills/pdf/scripts/extract_form_field_info.py @@ -0,0 +1,152 @@ +import json +import sys + +from pypdf import PdfReader + + +# Extracts data for the fillable form fields in a PDF and outputs JSON that +# Claude uses to fill the fields. See forms.md. + + +# This matches the format used by PdfReader `get_fields` and `update_page_form_field_values` methods. +def get_full_annotation_field_id(annotation): + components = [] + while annotation: + field_name = annotation.get('/T') + if field_name: + components.append(field_name) + annotation = annotation.get('/Parent') + return ".".join(reversed(components)) if components else None + + +def make_field_dict(field, field_id): + field_dict = {"field_id": field_id} + ft = field.get('/FT') + if ft == "/Tx": + field_dict["type"] = "text" + elif ft == "/Btn": + field_dict["type"] = "checkbox" # radio groups handled separately + states = field.get("/_States_", []) + if len(states) == 2: + # "/Off" seems to always be the unchecked value, as suggested by + # https://opensource.adobe.com/dc-acrobat-sdk-docs/standards/pdfstandards/pdf/PDF32000_2008.pdf#page=448 + # It can be either first or second in the "/_States_" list. + if "/Off" in states: + field_dict["checked_value"] = states[0] if states[0] != "/Off" else states[1] + field_dict["unchecked_value"] = "/Off" + else: + print(f"Unexpected state values for checkbox `${field_id}`. Its checked and unchecked values may not be correct; if you're trying to check it, visually verify the results.") + field_dict["checked_value"] = states[0] + field_dict["unchecked_value"] = states[1] + elif ft == "/Ch": + field_dict["type"] = "choice" + states = field.get("/_States_", []) + field_dict["choice_options"] = [{ + "value": state[0], + "text": state[1], + } for state in states] + else: + field_dict["type"] = f"unknown ({ft})" + return field_dict + + +# Returns a list of fillable PDF fields: +# [ +# { +# "field_id": "name", +# "page": 1, +# "type": ("text", "checkbox", "radio_group", or "choice") +# // Per-type additional fields described in forms.md +# }, +# ] +def get_field_info(reader: PdfReader): + fields = reader.get_fields() + + field_info_by_id = {} + possible_radio_names = set() + + for field_id, field in fields.items(): + # Skip if this is a container field with children, except that it might be + # a parent group for radio button options. + if field.get("/Kids"): + if field.get("/FT") == "/Btn": + possible_radio_names.add(field_id) + continue + field_info_by_id[field_id] = make_field_dict(field, field_id) + + # Bounding rects are stored in annotations in page objects. + + # Radio button options have a separate annotation for each choice; + # all choices have the same field name. + # See https://westhealth.github.io/exploring-fillable-forms-with-pdfrw.html + radio_fields_by_id = {} + + for page_index, page in enumerate(reader.pages): + annotations = page.get('/Annots', []) + for ann in annotations: + field_id = get_full_annotation_field_id(ann) + if field_id in field_info_by_id: + field_info_by_id[field_id]["page"] = page_index + 1 + field_info_by_id[field_id]["rect"] = ann.get('/Rect') + elif field_id in possible_radio_names: + try: + # ann['/AP']['/N'] should have two items. One of them is '/Off', + # the other is the active value. + on_values = [v for v in ann["/AP"]["/N"] if v != "/Off"] + except KeyError: + continue + if len(on_values) == 1: + rect = ann.get("/Rect") + if field_id not in radio_fields_by_id: + radio_fields_by_id[field_id] = { + "field_id": field_id, + "type": "radio_group", + "page": page_index + 1, + "radio_options": [], + } + # Note: at least on macOS 15.7, Preview.app doesn't show selected + # radio buttons correctly. (It does if you remove the leading slash + # from the value, but that causes them not to appear correctly in + # Chrome/Firefox/Acrobat/etc). + radio_fields_by_id[field_id]["radio_options"].append({ + "value": on_values[0], + "rect": rect, + }) + + # Some PDFs have form field definitions without corresponding annotations, + # so we can't tell where they are. Ignore these fields for now. + fields_with_location = [] + for field_info in field_info_by_id.values(): + if "page" in field_info: + fields_with_location.append(field_info) + else: + print(f"Unable to determine location for field id: {field_info.get('field_id')}, ignoring") + + # Sort by page number, then Y position (flipped in PDF coordinate system), then X. + def sort_key(f): + if "radio_options" in f: + rect = f["radio_options"][0]["rect"] or [0, 0, 0, 0] + else: + rect = f.get("rect") or [0, 0, 0, 0] + adjusted_position = [-rect[1], rect[0]] + return [f.get("page"), adjusted_position] + + sorted_fields = fields_with_location + list(radio_fields_by_id.values()) + sorted_fields.sort(key=sort_key) + + return sorted_fields + + +def write_field_info(pdf_path: str, json_output_path: str): + reader = PdfReader(pdf_path) + field_info = get_field_info(reader) + with open(json_output_path, "w") as f: + json.dump(field_info, f, indent=2) + print(f"Wrote {len(field_info)} fields to {json_output_path}") + + +if __name__ == "__main__": + if len(sys.argv) != 3: + print("Usage: extract_form_field_info.py [input pdf] [output json]") + sys.exit(1) + write_field_info(sys.argv[1], sys.argv[2]) diff --git a/skills/pdf/scripts/fill_fillable_fields.py b/skills/pdf/scripts/fill_fillable_fields.py new file mode 100644 index 0000000..ac35753 --- /dev/null +++ b/skills/pdf/scripts/fill_fillable_fields.py @@ -0,0 +1,114 @@ +import json +import sys + +from pypdf import PdfReader, PdfWriter + +from extract_form_field_info import get_field_info + + +# Fills fillable form fields in a PDF. See forms.md. + + +def fill_pdf_fields(input_pdf_path: str, fields_json_path: str, output_pdf_path: str): + with open(fields_json_path) as f: + fields = json.load(f) + # Group by page number. + fields_by_page = {} + for field in fields: + if "value" in field: + field_id = field["field_id"] + page = field["page"] + if page not in fields_by_page: + fields_by_page[page] = {} + fields_by_page[page][field_id] = field["value"] + + reader = PdfReader(input_pdf_path) + + has_error = False + field_info = get_field_info(reader) + fields_by_ids = {f["field_id"]: f for f in field_info} + for field in fields: + existing_field = fields_by_ids.get(field["field_id"]) + if not existing_field: + has_error = True + print(f"ERROR: `{field['field_id']}` is not a valid field ID") + elif field["page"] != existing_field["page"]: + has_error = True + print(f"ERROR: Incorrect page number for `{field['field_id']}` (got {field['page']}, expected {existing_field['page']})") + else: + if "value" in field: + err = validation_error_for_field_value(existing_field, field["value"]) + if err: + print(err) + has_error = True + if has_error: + sys.exit(1) + + writer = PdfWriter(clone_from=reader) + for page, field_values in fields_by_page.items(): + writer.update_page_form_field_values(writer.pages[page - 1], field_values, auto_regenerate=False) + + # This seems to be necessary for many PDF viewers to format the form values correctly. + # It may cause the viewer to show a "save changes" dialog even if the user doesn't make any changes. + writer.set_need_appearances_writer(True) + + with open(output_pdf_path, "wb") as f: + writer.write(f) + + +def validation_error_for_field_value(field_info, field_value): + field_type = field_info["type"] + field_id = field_info["field_id"] + if field_type == "checkbox": + checked_val = field_info["checked_value"] + unchecked_val = field_info["unchecked_value"] + if field_value != checked_val and field_value != unchecked_val: + return f'ERROR: Invalid value "{field_value}" for checkbox field "{field_id}". The checked value is "{checked_val}" and the unchecked value is "{unchecked_val}"' + elif field_type == "radio_group": + option_values = [opt["value"] for opt in field_info["radio_options"]] + if field_value not in option_values: + return f'ERROR: Invalid value "{field_value}" for radio group field "{field_id}". Valid values are: {option_values}' + elif field_type == "choice": + choice_values = [opt["value"] for opt in field_info["choice_options"]] + if field_value not in choice_values: + return f'ERROR: Invalid value "{field_value}" for choice field "{field_id}". Valid values are: {choice_values}' + return None + + +# pypdf (at least version 5.7.0) has a bug when setting the value for a selection list field. +# In _writer.py around line 966: +# +# if field.get(FA.FT, "/Tx") == "/Ch" and field_flags & FA.FfBits.Combo == 0: +# txt = "\n".join(annotation.get_inherited(FA.Opt, [])) +# +# The problem is that for selection lists, `get_inherited` returns a list of two-element lists like +# [["value1", "Text 1"], ["value2", "Text 2"], ...] +# This causes `join` to throw a TypeError because it expects an iterable of strings. +# The horrible workaround is to patch `get_inherited` to return a list of the value strings. +# We call the original method and adjust the return value only if the argument to `get_inherited` +# is `FA.Opt` and if the return value is a list of two-element lists. +def monkeypatch_pydpf_method(): + from pypdf.generic import DictionaryObject + from pypdf.constants import FieldDictionaryAttributes + + original_get_inherited = DictionaryObject.get_inherited + + def patched_get_inherited(self, key: str, default = None): + result = original_get_inherited(self, key, default) + if key == FieldDictionaryAttributes.Opt: + if isinstance(result, list) and all(isinstance(v, list) and len(v) == 2 for v in result): + result = [r[0] for r in result] + return result + + DictionaryObject.get_inherited = patched_get_inherited + + +if __name__ == "__main__": + if len(sys.argv) != 4: + print("Usage: fill_fillable_fields.py [input pdf] [field_values.json] [output pdf]") + sys.exit(1) + monkeypatch_pydpf_method() + input_pdf = sys.argv[1] + fields_json = sys.argv[2] + output_pdf = sys.argv[3] + fill_pdf_fields(input_pdf, fields_json, output_pdf) diff --git a/skills/pdf/scripts/fill_pdf_form_with_annotations.py b/skills/pdf/scripts/fill_pdf_form_with_annotations.py new file mode 100644 index 0000000..f980531 --- /dev/null +++ b/skills/pdf/scripts/fill_pdf_form_with_annotations.py @@ -0,0 +1,108 @@ +import json +import sys + +from pypdf import PdfReader, PdfWriter +from pypdf.annotations import FreeText + + +# Fills a PDF by adding text annotations defined in `fields.json`. See forms.md. + + +def transform_coordinates(bbox, image_width, image_height, pdf_width, pdf_height): + """Transform bounding box from image coordinates to PDF coordinates""" + # Image coordinates: origin at top-left, y increases downward + # PDF coordinates: origin at bottom-left, y increases upward + x_scale = pdf_width / image_width + y_scale = pdf_height / image_height + + left = bbox[0] * x_scale + right = bbox[2] * x_scale + + # Flip Y coordinates for PDF + top = pdf_height - (bbox[1] * y_scale) + bottom = pdf_height - (bbox[3] * y_scale) + + return left, bottom, right, top + + +def fill_pdf_form(input_pdf_path, fields_json_path, output_pdf_path): + """Fill the PDF form with data from fields.json""" + + # `fields.json` format described in forms.md. + with open(fields_json_path, "r") as f: + fields_data = json.load(f) + + # Open the PDF + reader = PdfReader(input_pdf_path) + writer = PdfWriter() + + # Copy all pages to writer + writer.append(reader) + + # Get PDF dimensions for each page + pdf_dimensions = {} + for i, page in enumerate(reader.pages): + mediabox = page.mediabox + pdf_dimensions[i + 1] = [mediabox.width, mediabox.height] + + # Process each form field + annotations = [] + for field in fields_data["form_fields"]: + page_num = field["page_number"] + + # Get page dimensions and transform coordinates. + page_info = next(p for p in fields_data["pages"] if p["page_number"] == page_num) + image_width = page_info["image_width"] + image_height = page_info["image_height"] + pdf_width, pdf_height = pdf_dimensions[page_num] + + transformed_entry_box = transform_coordinates( + field["entry_bounding_box"], + image_width, image_height, + pdf_width, pdf_height + ) + + # Skip empty fields + if "entry_text" not in field or "text" not in field["entry_text"]: + continue + entry_text = field["entry_text"] + text = entry_text["text"] + if not text: + continue + + font_name = entry_text.get("font", "Arial") + font_size = str(entry_text.get("font_size", 14)) + "pt" + font_color = entry_text.get("font_color", "000000") + + # Font size/color seems to not work reliably across viewers: + # https://github.com/py-pdf/pypdf/issues/2084 + annotation = FreeText( + text=text, + rect=transformed_entry_box, + font=font_name, + font_size=font_size, + font_color=font_color, + border_color=None, + background_color=None, + ) + annotations.append(annotation) + # page_number is 0-based for pypdf + writer.add_annotation(page_number=page_num - 1, annotation=annotation) + + # Save the filled PDF + with open(output_pdf_path, "wb") as output: + writer.write(output) + + print(f"Successfully filled PDF form and saved to {output_pdf_path}") + print(f"Added {len(annotations)} text annotations") + + +if __name__ == "__main__": + if len(sys.argv) != 4: + print("Usage: fill_pdf_form_with_annotations.py [input pdf] [fields.json] [output pdf]") + sys.exit(1) + input_pdf = sys.argv[1] + fields_json = sys.argv[2] + output_pdf = sys.argv[3] + + fill_pdf_form(input_pdf, fields_json, output_pdf) \ No newline at end of file diff --git a/skills/pptx/LICENSE.txt b/skills/pptx/LICENSE.txt new file mode 100644 index 0000000..c55ab42 --- /dev/null +++ b/skills/pptx/LICENSE.txt @@ -0,0 +1,30 @@ +© 2025 Anthropic, PBC. All rights reserved. + +LICENSE: Use of these materials (including all code, prompts, assets, files, +and other components of this Skill) is governed by your agreement with +Anthropic regarding use of Anthropic's services. If no separate agreement +exists, use is governed by Anthropic's Consumer Terms of Service or +Commercial Terms of Service, as applicable: +https://www.anthropic.com/legal/consumer-terms +https://www.anthropic.com/legal/commercial-terms +Your applicable agreement is referred to as the "Agreement." "Services" are +as defined in the Agreement. + +ADDITIONAL RESTRICTIONS: Notwithstanding anything in the Agreement to the +contrary, users may not: + +- Extract these materials from the Services or retain copies of these + materials outside the Services +- Reproduce or copy these materials, except for temporary copies created + automatically during authorized use of the Services +- Create derivative works based on these materials +- Distribute, sublicense, or transfer these materials to any third party +- Make, offer to sell, sell, or import any inventions embodied in these + materials +- Reverse engineer, decompile, or disassemble these materials + +The receipt, viewing, or possession of these materials does not convey or +imply any license or right beyond those expressly granted above. + +Anthropic retains all right, title, and interest in these materials, +including all copyrights, patents, and other intellectual property rights. diff --git a/skills/pptx/SKILL.md b/skills/pptx/SKILL.md new file mode 100644 index 0000000..b93b875 --- /dev/null +++ b/skills/pptx/SKILL.md @@ -0,0 +1,484 @@ +--- +name: pptx +description: "Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks" +license: Proprietary. LICENSE.txt has complete terms +--- + +# PPTX creation, editing, and analysis + +## Overview + +A user may ask you to create, edit, or analyze the contents of a .pptx file. A .pptx file is essentially a ZIP archive containing XML files and other resources that you can read or edit. You have different tools and workflows available for different tasks. + +## Reading and analyzing content + +### Text extraction +If you just need to read the text contents of a presentation, you should convert the document to markdown: + +```bash +# Convert document to markdown +python -m markitdown path-to-file.pptx +``` + +### Raw XML access +You need raw XML access for: comments, speaker notes, slide layouts, animations, design elements, and complex formatting. For any of these features, you'll need to unpack a presentation and read its raw XML contents. + +#### Unpacking a file +`python ooxml/scripts/unpack.py ` + +**Note**: The unpack.py script is located at `skills/pptx/ooxml/scripts/unpack.py` relative to the project root. If the script doesn't exist at this path, use `find . -name "unpack.py"` to locate it. + +#### Key file structures +* `ppt/presentation.xml` - Main presentation metadata and slide references +* `ppt/slides/slide{N}.xml` - Individual slide contents (slide1.xml, slide2.xml, etc.) +* `ppt/notesSlides/notesSlide{N}.xml` - Speaker notes for each slide +* `ppt/comments/modernComment_*.xml` - Comments for specific slides +* `ppt/slideLayouts/` - Layout templates for slides +* `ppt/slideMasters/` - Master slide templates +* `ppt/theme/` - Theme and styling information +* `ppt/media/` - Images and other media files + +#### Typography and color extraction +**When given an example design to emulate**: Always analyze the presentation's typography and colors first using the methods below: +1. **Read theme file**: Check `ppt/theme/theme1.xml` for colors (``) and fonts (``) +2. **Sample slide content**: Examine `ppt/slides/slide1.xml` for actual font usage (``) and colors +3. **Search for patterns**: Use grep to find color (``, ``) and font references across all XML files + +## Creating a new PowerPoint presentation **without a template** + +When creating a new PowerPoint presentation from scratch, use the **html2pptx** workflow to convert HTML slides to PowerPoint with accurate positioning. + +### Design Principles + +**CRITICAL**: Before creating any presentation, analyze the content and choose appropriate design elements: +1. **Consider the subject matter**: What is this presentation about? What tone, industry, or mood does it suggest? +2. **Check for branding**: If the user mentions a company/organization, consider their brand colors and identity +3. **Match palette to content**: Select colors that reflect the subject +4. **State your approach**: Explain your design choices before writing code + +**Requirements**: +- ✅ State your content-informed design approach BEFORE writing code +- ✅ Use web-safe fonts only: Arial, Helvetica, Times New Roman, Georgia, Courier New, Verdana, Tahoma, Trebuchet MS, Impact +- ✅ Create clear visual hierarchy through size, weight, and color +- ✅ Ensure readability: strong contrast, appropriately sized text, clean alignment +- ✅ Be consistent: repeat patterns, spacing, and visual language across slides + +#### Color Palette Selection + +**Choosing colors creatively**: +- **Think beyond defaults**: What colors genuinely match this specific topic? Avoid autopilot choices. +- **Consider multiple angles**: Topic, industry, mood, energy level, target audience, brand identity (if mentioned) +- **Be adventurous**: Try unexpected combinations - a healthcare presentation doesn't have to be green, finance doesn't have to be navy +- **Build your palette**: Pick 3-5 colors that work together (dominant colors + supporting tones + accent) +- **Ensure contrast**: Text must be clearly readable on backgrounds + +**Example color palettes** (use these to spark creativity - choose one, adapt it, or create your own): + +1. **Classic Blue**: Deep navy (#1C2833), slate gray (#2E4053), silver (#AAB7B8), off-white (#F4F6F6) +2. **Teal & Coral**: Teal (#5EA8A7), deep teal (#277884), coral (#FE4447), white (#FFFFFF) +3. **Bold Red**: Red (#C0392B), bright red (#E74C3C), orange (#F39C12), yellow (#F1C40F), green (#2ECC71) +4. **Warm Blush**: Mauve (#A49393), blush (#EED6D3), rose (#E8B4B8), cream (#FAF7F2) +5. **Burgundy Luxury**: Burgundy (#5D1D2E), crimson (#951233), rust (#C15937), gold (#997929) +6. **Deep Purple & Emerald**: Purple (#B165FB), dark blue (#181B24), emerald (#40695B), white (#FFFFFF) +7. **Cream & Forest Green**: Cream (#FFE1C7), forest green (#40695B), white (#FCFCFC) +8. **Pink & Purple**: Pink (#F8275B), coral (#FF574A), rose (#FF737D), purple (#3D2F68) +9. **Lime & Plum**: Lime (#C5DE82), plum (#7C3A5F), coral (#FD8C6E), blue-gray (#98ACB5) +10. **Black & Gold**: Gold (#BF9A4A), black (#000000), cream (#F4F6F6) +11. **Sage & Terracotta**: Sage (#87A96B), terracotta (#E07A5F), cream (#F4F1DE), charcoal (#2C2C2C) +12. **Charcoal & Red**: Charcoal (#292929), red (#E33737), light gray (#CCCBCB) +13. **Vibrant Orange**: Orange (#F96D00), light gray (#F2F2F2), charcoal (#222831) +14. **Forest Green**: Black (#191A19), green (#4E9F3D), dark green (#1E5128), white (#FFFFFF) +15. **Retro Rainbow**: Purple (#722880), pink (#D72D51), orange (#EB5C18), amber (#F08800), gold (#DEB600) +16. **Vintage Earthy**: Mustard (#E3B448), sage (#CBD18F), forest green (#3A6B35), cream (#F4F1DE) +17. **Coastal Rose**: Old rose (#AD7670), beaver (#B49886), eggshell (#F3ECDC), ash gray (#BFD5BE) +18. **Orange & Turquoise**: Light orange (#FC993E), grayish turquoise (#667C6F), white (#FCFCFC) + +#### Visual Details Options + +**Geometric Patterns**: +- Diagonal section dividers instead of horizontal +- Asymmetric column widths (30/70, 40/60, 25/75) +- Rotated text headers at 90° or 270° +- Circular/hexagonal frames for images +- Triangular accent shapes in corners +- Overlapping shapes for depth + +**Border & Frame Treatments**: +- Thick single-color borders (10-20pt) on one side only +- Double-line borders with contrasting colors +- Corner brackets instead of full frames +- L-shaped borders (top+left or bottom+right) +- Underline accents beneath headers (3-5pt thick) + +**Typography Treatments**: +- Extreme size contrast (72pt headlines vs 11pt body) +- All-caps headers with wide letter spacing +- Numbered sections in oversized display type +- Monospace (Courier New) for data/stats/technical content +- Condensed fonts (Arial Narrow) for dense information +- Outlined text for emphasis + +**Chart & Data Styling**: +- Monochrome charts with single accent color for key data +- Horizontal bar charts instead of vertical +- Dot plots instead of bar charts +- Minimal gridlines or none at all +- Data labels directly on elements (no legends) +- Oversized numbers for key metrics + +**Layout Innovations**: +- Full-bleed images with text overlays +- Sidebar column (20-30% width) for navigation/context +- Modular grid systems (3×3, 4×4 blocks) +- Z-pattern or F-pattern content flow +- Floating text boxes over colored shapes +- Magazine-style multi-column layouts + +**Background Treatments**: +- Solid color blocks occupying 40-60% of slide +- Gradient fills (vertical or diagonal only) +- Split backgrounds (two colors, diagonal or vertical) +- Edge-to-edge color bands +- Negative space as a design element + +### Layout Tips +**When creating slides with charts or tables:** +- **Two-column layout (PREFERRED)**: Use a header spanning the full width, then two columns below - text/bullets in one column and the featured content in the other. This provides better balance and makes charts/tables more readable. Use flexbox with unequal column widths (e.g., 40%/60% split) to optimize space for each content type. +- **Full-slide layout**: Let the featured content (chart/table) take up the entire slide for maximum impact and readability +- **NEVER vertically stack**: Do not place charts/tables below text in a single column - this causes poor readability and layout issues + +### Workflow +1. **MANDATORY - READ ENTIRE FILE**: Read [`html2pptx.md`](html2pptx.md) completely from start to finish. **NEVER set any range limits when reading this file.** Read the full file content for detailed syntax, critical formatting rules, and best practices before proceeding with presentation creation. +2. Create an HTML file for each slide with proper dimensions (e.g., 720pt × 405pt for 16:9) + - Use `

`, `

`-`

`, `
    `, `
      ` for all text content + - Use `class="placeholder"` for areas where charts/tables will be added (render with gray background for visibility) + - **CRITICAL**: Rasterize gradients and icons as PNG images FIRST using Sharp, then reference in HTML + - **LAYOUT**: For slides with charts/tables/images, use either full-slide layout or two-column layout for better readability +3. Create and run a JavaScript file using the [`html2pptx.js`](scripts/html2pptx.js) library to convert HTML slides to PowerPoint and save the presentation + - Use the `html2pptx()` function to process each HTML file + - Add charts and tables to placeholder areas using PptxGenJS API + - Save the presentation using `pptx.writeFile()` +4. **Visual validation**: Generate thumbnails and inspect for layout issues + - Create thumbnail grid: `python scripts/thumbnail.py output.pptx workspace/thumbnails --cols 4` + - Read and carefully examine the thumbnail image for: + - **Text cutoff**: Text being cut off by header bars, shapes, or slide edges + - **Text overlap**: Text overlapping with other text or shapes + - **Positioning issues**: Content too close to slide boundaries or other elements + - **Contrast issues**: Insufficient contrast between text and backgrounds + - If issues found, adjust HTML margins/spacing/colors and regenerate the presentation + - Repeat until all slides are visually correct + +## Editing an existing PowerPoint presentation + +When edit slides in an existing PowerPoint presentation, you need to work with the raw Office Open XML (OOXML) format. This involves unpacking the .pptx file, editing the XML content, and repacking it. + +### Workflow +1. **MANDATORY - READ ENTIRE FILE**: Read [`ooxml.md`](ooxml.md) (~500 lines) completely from start to finish. **NEVER set any range limits when reading this file.** Read the full file content for detailed guidance on OOXML structure and editing workflows before any presentation editing. +2. Unpack the presentation: `python ooxml/scripts/unpack.py ` +3. Edit the XML files (primarily `ppt/slides/slide{N}.xml` and related files) +4. **CRITICAL**: Validate immediately after each edit and fix any validation errors before proceeding: `python ooxml/scripts/validate.py --original ` +5. Pack the final presentation: `python ooxml/scripts/pack.py ` + +## Creating a new PowerPoint presentation **using a template** + +When you need to create a presentation that follows an existing template's design, you'll need to duplicate and re-arrange template slides before then replacing placeholder context. + +### Workflow +1. **Extract template text AND create visual thumbnail grid**: + * Extract text: `python -m markitdown template.pptx > template-content.md` + * Read `template-content.md`: Read the entire file to understand the contents of the template presentation. **NEVER set any range limits when reading this file.** + * Create thumbnail grids: `python scripts/thumbnail.py template.pptx` + * See [Creating Thumbnail Grids](#creating-thumbnail-grids) section for more details + +2. **Analyze template and save inventory to a file**: + * **Visual Analysis**: Review thumbnail grid(s) to understand slide layouts, design patterns, and visual structure + * Create and save a template inventory file at `template-inventory.md` containing: + ```markdown + # Template Inventory Analysis + **Total Slides: [count]** + **IMPORTANT: Slides are 0-indexed (first slide = 0, last slide = count-1)** + + ## [Category Name] + - Slide 0: [Layout code if available] - Description/purpose + - Slide 1: [Layout code] - Description/purpose + - Slide 2: [Layout code] - Description/purpose + [... EVERY slide must be listed individually with its index ...] + ``` + * **Using the thumbnail grid**: Reference the visual thumbnails to identify: + - Layout patterns (title slides, content layouts, section dividers) + - Image placeholder locations and counts + - Design consistency across slide groups + - Visual hierarchy and structure + * This inventory file is REQUIRED for selecting appropriate templates in the next step + +3. **Create presentation outline based on template inventory**: + * Review available templates from step 2. + * Choose an intro or title template for the first slide. This should be one of the first templates. + * Choose safe, text-based layouts for the other slides. + * **CRITICAL: Match layout structure to actual content**: + - Single-column layouts: Use for unified narrative or single topic + - Two-column layouts: Use ONLY when you have exactly 2 distinct items/concepts + - Three-column layouts: Use ONLY when you have exactly 3 distinct items/concepts + - Image + text layouts: Use ONLY when you have actual images to insert + - Quote layouts: Use ONLY for actual quotes from people (with attribution), never for emphasis + - Never use layouts with more placeholders than you have content + - If you have 2 items, don't force them into a 3-column layout + - If you have 4+ items, consider breaking into multiple slides or using a list format + * Count your actual content pieces BEFORE selecting the layout + * Verify each placeholder in the chosen layout will be filled with meaningful content + * Select one option representing the **best** layout for each content section. + * Save `outline.md` with content AND template mapping that leverages available designs + * Example template mapping: + ``` + # Template slides to use (0-based indexing) + # WARNING: Verify indices are within range! Template with 73 slides has indices 0-72 + # Mapping: slide numbers from outline -> template slide indices + template_mapping = [ + 0, # Use slide 0 (Title/Cover) + 34, # Use slide 34 (B1: Title and body) + 34, # Use slide 34 again (duplicate for second B1) + 50, # Use slide 50 (E1: Quote) + 54, # Use slide 54 (F2: Closing + Text) + ] + ``` + +4. **Duplicate, reorder, and delete slides using `rearrange.py`**: + * Use the `scripts/rearrange.py` script to create a new presentation with slides in the desired order: + ```bash + python scripts/rearrange.py template.pptx working.pptx 0,34,34,50,52 + ``` + * The script handles duplicating repeated slides, deleting unused slides, and reordering automatically + * Slide indices are 0-based (first slide is 0, second is 1, etc.) + * The same slide index can appear multiple times to duplicate that slide + +5. **Extract ALL text using the `inventory.py` script**: + * **Run inventory extraction**: + ```bash + python scripts/inventory.py working.pptx text-inventory.json + ``` + * **Read text-inventory.json**: Read the entire text-inventory.json file to understand all shapes and their properties. **NEVER set any range limits when reading this file.** + + * The inventory JSON structure: + ```json + { + "slide-0": { + "shape-0": { + "placeholder_type": "TITLE", // or null for non-placeholders + "left": 1.5, // position in inches + "top": 2.0, + "width": 7.5, + "height": 1.2, + "paragraphs": [ + { + "text": "Paragraph text", + // Optional properties (only included when non-default): + "bullet": true, // explicit bullet detected + "level": 0, // only included when bullet is true + "alignment": "CENTER", // CENTER, RIGHT (not LEFT) + "space_before": 10.0, // space before paragraph in points + "space_after": 6.0, // space after paragraph in points + "line_spacing": 22.4, // line spacing in points + "font_name": "Arial", // from first run + "font_size": 14.0, // in points + "bold": true, + "italic": false, + "underline": false, + "color": "FF0000" // RGB color + } + ] + } + } + } + ``` + + * Key features: + - **Slides**: Named as "slide-0", "slide-1", etc. + - **Shapes**: Ordered by visual position (top-to-bottom, left-to-right) as "shape-0", "shape-1", etc. + - **Placeholder types**: TITLE, CENTER_TITLE, SUBTITLE, BODY, OBJECT, or null + - **Default font size**: `default_font_size` in points extracted from layout placeholders (when available) + - **Slide numbers are filtered**: Shapes with SLIDE_NUMBER placeholder type are automatically excluded from inventory + - **Bullets**: When `bullet: true`, `level` is always included (even if 0) + - **Spacing**: `space_before`, `space_after`, and `line_spacing` in points (only included when set) + - **Colors**: `color` for RGB (e.g., "FF0000"), `theme_color` for theme colors (e.g., "DARK_1") + - **Properties**: Only non-default values are included in the output + +6. **Generate replacement text and save the data to a JSON file** + Based on the text inventory from the previous step: + - **CRITICAL**: First verify which shapes exist in the inventory - only reference shapes that are actually present + - **VALIDATION**: The replace.py script will validate that all shapes in your replacement JSON exist in the inventory + - If you reference a non-existent shape, you'll get an error showing available shapes + - If you reference a non-existent slide, you'll get an error indicating the slide doesn't exist + - All validation errors are shown at once before the script exits + - **IMPORTANT**: The replace.py script uses inventory.py internally to identify ALL text shapes + - **AUTOMATIC CLEARING**: ALL text shapes from the inventory will be cleared unless you provide "paragraphs" for them + - Add a "paragraphs" field to shapes that need content (not "replacement_paragraphs") + - Shapes without "paragraphs" in the replacement JSON will have their text cleared automatically + - Paragraphs with bullets will be automatically left aligned. Don't set the `alignment` property on when `"bullet": true` + - Generate appropriate replacement content for placeholder text + - Use shape size to determine appropriate content length + - **CRITICAL**: Include paragraph properties from the original inventory - don't just provide text + - **IMPORTANT**: When bullet: true, do NOT include bullet symbols (•, -, *) in text - they're added automatically + - **ESSENTIAL FORMATTING RULES**: + - Headers/titles should typically have `"bold": true` + - List items should have `"bullet": true, "level": 0` (level is required when bullet is true) + - Preserve any alignment properties (e.g., `"alignment": "CENTER"` for centered text) + - Include font properties when different from default (e.g., `"font_size": 14.0`, `"font_name": "Lora"`) + - Colors: Use `"color": "FF0000"` for RGB or `"theme_color": "DARK_1"` for theme colors + - The replacement script expects **properly formatted paragraphs**, not just text strings + - **Overlapping shapes**: Prefer shapes with larger default_font_size or more appropriate placeholder_type + - Save the updated inventory with replacements to `replacement-text.json` + - **WARNING**: Different template layouts have different shape counts - always check the actual inventory before creating replacements + + Example paragraphs field showing proper formatting: + ```json + "paragraphs": [ + { + "text": "New presentation title text", + "alignment": "CENTER", + "bold": true + }, + { + "text": "Section Header", + "bold": true + }, + { + "text": "First bullet point without bullet symbol", + "bullet": true, + "level": 0 + }, + { + "text": "Red colored text", + "color": "FF0000" + }, + { + "text": "Theme colored text", + "theme_color": "DARK_1" + }, + { + "text": "Regular paragraph text without special formatting" + } + ] + ``` + + **Shapes not listed in the replacement JSON are automatically cleared**: + ```json + { + "slide-0": { + "shape-0": { + "paragraphs": [...] // This shape gets new text + } + // shape-1 and shape-2 from inventory will be cleared automatically + } + } + ``` + + **Common formatting patterns for presentations**: + - Title slides: Bold text, sometimes centered + - Section headers within slides: Bold text + - Bullet lists: Each item needs `"bullet": true, "level": 0` + - Body text: Usually no special properties needed + - Quotes: May have special alignment or font properties + +7. **Apply replacements using the `replace.py` script** + ```bash + python scripts/replace.py working.pptx replacement-text.json output.pptx + ``` + + The script will: + - First extract the inventory of ALL text shapes using functions from inventory.py + - Validate that all shapes in the replacement JSON exist in the inventory + - Clear text from ALL shapes identified in the inventory + - Apply new text only to shapes with "paragraphs" defined in the replacement JSON + - Preserve formatting by applying paragraph properties from the JSON + - Handle bullets, alignment, font properties, and colors automatically + - Save the updated presentation + + Example validation errors: + ``` + ERROR: Invalid shapes in replacement JSON: + - Shape 'shape-99' not found on 'slide-0'. Available shapes: shape-0, shape-1, shape-4 + - Slide 'slide-999' not found in inventory + ``` + + ``` + ERROR: Replacement text made overflow worse in these shapes: + - slide-0/shape-2: overflow worsened by 1.25" (was 0.00", now 1.25") + ``` + +## Creating Thumbnail Grids + +To create visual thumbnail grids of PowerPoint slides for quick analysis and reference: + +```bash +python scripts/thumbnail.py template.pptx [output_prefix] +``` + +**Features**: +- Creates: `thumbnails.jpg` (or `thumbnails-1.jpg`, `thumbnails-2.jpg`, etc. for large decks) +- Default: 5 columns, max 30 slides per grid (5×6) +- Custom prefix: `python scripts/thumbnail.py template.pptx my-grid` + - Note: The output prefix should include the path if you want output in a specific directory (e.g., `workspace/my-grid`) +- Adjust columns: `--cols 4` (range: 3-6, affects slides per grid) +- Grid limits: 3 cols = 12 slides/grid, 4 cols = 20, 5 cols = 30, 6 cols = 42 +- Slides are zero-indexed (Slide 0, Slide 1, etc.) + +**Use cases**: +- Template analysis: Quickly understand slide layouts and design patterns +- Content review: Visual overview of entire presentation +- Navigation reference: Find specific slides by their visual appearance +- Quality check: Verify all slides are properly formatted + +**Examples**: +```bash +# Basic usage +python scripts/thumbnail.py presentation.pptx + +# Combine options: custom name, columns +python scripts/thumbnail.py template.pptx analysis --cols 4 +``` + +## Converting Slides to Images + +To visually analyze PowerPoint slides, convert them to images using a two-step process: + +1. **Convert PPTX to PDF**: + ```bash + soffice --headless --convert-to pdf template.pptx + ``` + +2. **Convert PDF pages to JPEG images**: + ```bash + pdftoppm -jpeg -r 150 template.pdf slide + ``` + This creates files like `slide-1.jpg`, `slide-2.jpg`, etc. + +Options: +- `-r 150`: Sets resolution to 150 DPI (adjust for quality/size balance) +- `-jpeg`: Output JPEG format (use `-png` for PNG if preferred) +- `-f N`: First page to convert (e.g., `-f 2` starts from page 2) +- `-l N`: Last page to convert (e.g., `-l 5` stops at page 5) +- `slide`: Prefix for output files + +Example for specific range: +```bash +pdftoppm -jpeg -r 150 -f 2 -l 5 template.pdf slide # Converts only pages 2-5 +``` + +## Code Style Guidelines +**IMPORTANT**: When generating code for PPTX operations: +- Write concise code +- Avoid verbose variable names and redundant operations +- Avoid unnecessary print statements + +## Dependencies + +Required dependencies (should already be installed): + +- **markitdown**: `pip install "markitdown[pptx]"` (for text extraction from presentations) +- **pptxgenjs**: `npm install -g pptxgenjs` (for creating presentations via html2pptx) +- **playwright**: `npm install -g playwright` (for HTML rendering in html2pptx) +- **react-icons**: `npm install -g react-icons react react-dom` (for icons) +- **sharp**: `npm install -g sharp` (for SVG rasterization and image processing) +- **LibreOffice**: `sudo apt-get install libreoffice` (for PDF conversion) +- **Poppler**: `sudo apt-get install poppler-utils` (for pdftoppm to convert PDF to images) +- **defusedxml**: `pip install defusedxml` (for secure XML parsing) \ No newline at end of file diff --git a/skills/pptx/html2pptx.md b/skills/pptx/html2pptx.md new file mode 100644 index 0000000..106adf7 --- /dev/null +++ b/skills/pptx/html2pptx.md @@ -0,0 +1,625 @@ +# HTML to PowerPoint Guide + +Convert HTML slides to PowerPoint presentations with accurate positioning using the `html2pptx.js` library. + +## Table of Contents + +1. [Creating HTML Slides](#creating-html-slides) +2. [Using the html2pptx Library](#using-the-html2pptx-library) +3. [Using PptxGenJS](#using-pptxgenjs) + +--- + +## Creating HTML Slides + +Every HTML slide must include proper body dimensions: + +### Layout Dimensions + +- **16:9** (default): `width: 720pt; height: 405pt` +- **4:3**: `width: 720pt; height: 540pt` +- **16:10**: `width: 720pt; height: 450pt` + +### Supported Elements + +- `

      `, `

      `-`

      ` - Text with styling +- `
        `, `
          ` - Lists (never use manual bullets •, -, *) +- ``, `` - Bold text (inline formatting) +- ``, `` - Italic text (inline formatting) +- `` - Underlined text (inline formatting) +- `` - Inline formatting with CSS styles (bold, italic, underline, color) +- `
          ` - Line breaks +- `
          ` with bg/border - Becomes shape +- `` - Images +- `class="placeholder"` - Reserved space for charts (returns `{ id, x, y, w, h }`) + +### Critical Text Rules + +**ALL text MUST be inside `

          `, `

          `-`

          `, `
            `, or `
              ` tags:** +- ✅ Correct: `

              Text here

              ` +- ❌ Wrong: `
              Text here
              ` - **Text will NOT appear in PowerPoint** +- ❌ Wrong: `Text` - **Text will NOT appear in PowerPoint** +- Text in `
              ` or `` without a text tag will be silently ignored + +**NEVER use manual bullet symbols (•, -, *, etc.)** - Use `
                ` or `
                  ` lists instead + +**ONLY use web-safe fonts that are universally available:** +- ✅ Web-safe fonts: `Arial`, `Helvetica`, `Times New Roman`, `Georgia`, `Courier New`, `Verdana`, `Tahoma`, `Trebuchet MS`, `Impact`, `Comic Sans MS` +- ❌ Wrong: `'Segoe UI'`, `'SF Pro'`, `'Roboto'`, custom fonts - **Might cause rendering issues** + +### Styling + +- Use `display: flex` on body to prevent margin collapse from breaking overflow validation +- Use `margin` for spacing (padding included in size) +- Inline formatting: Use ``, ``, `` tags OR `` with CSS styles + - `` supports: `font-weight: bold`, `font-style: italic`, `text-decoration: underline`, `color: #rrggbb` + - `` does NOT support: `margin`, `padding` (not supported in PowerPoint text runs) + - Example: `Bold blue text` +- Flexbox works - positions calculated from rendered layout +- Use hex colors with `#` prefix in CSS +- **Text alignment**: Use CSS `text-align` (`center`, `right`, etc.) when needed as a hint to PptxGenJS for text formatting if text lengths are slightly off + +### Shape Styling (DIV elements only) + +**IMPORTANT: Backgrounds, borders, and shadows only work on `
                  ` elements, NOT on text elements (`

                  `, `

                  `-`

                  `, `
                    `, `
                      `)** + +- **Backgrounds**: CSS `background` or `background-color` on `
                      ` elements only + - Example: `
                      ` - Creates a shape with background +- **Borders**: CSS `border` on `
                      ` elements converts to PowerPoint shape borders + - Supports uniform borders: `border: 2px solid #333333` + - Supports partial borders: `border-left`, `border-right`, `border-top`, `border-bottom` (rendered as line shapes) + - Example: `
                      ` +- **Border radius**: CSS `border-radius` on `
                      ` elements for rounded corners + - `border-radius: 50%` or higher creates circular shape + - Percentages <50% calculated relative to shape's smaller dimension + - Supports px and pt units (e.g., `border-radius: 8pt;`, `border-radius: 12px;`) + - Example: `
                      ` on 100x200px box = 25% of 100px = 25px radius +- **Box shadows**: CSS `box-shadow` on `
                      ` elements converts to PowerPoint shadows + - Supports outer shadows only (inset shadows are ignored to prevent corruption) + - Example: `
                      ` + - Note: Inset/inner shadows are not supported by PowerPoint and will be skipped + +### Icons & Gradients + +- **CRITICAL: Never use CSS gradients (`linear-gradient`, `radial-gradient`)** - They don't convert to PowerPoint +- **ALWAYS create gradient/icon PNGs FIRST using Sharp, then reference in HTML** +- For gradients: Rasterize SVG to PNG background images +- For icons: Rasterize react-icons SVG to PNG images +- All visual effects must be pre-rendered as raster images before HTML rendering + +**Rasterizing Icons with Sharp:** + +```javascript +const React = require('react'); +const ReactDOMServer = require('react-dom/server'); +const sharp = require('sharp'); +const { FaHome } = require('react-icons/fa'); + +async function rasterizeIconPng(IconComponent, color, size = "256", filename) { + const svgString = ReactDOMServer.renderToStaticMarkup( + React.createElement(IconComponent, { color: `#${color}`, size: size }) + ); + + // Convert SVG to PNG using Sharp + await sharp(Buffer.from(svgString)) + .png() + .toFile(filename); + + return filename; +} + +// Usage: Rasterize icon before using in HTML +const iconPath = await rasterizeIconPng(FaHome, "4472c4", "256", "home-icon.png"); +// Then reference in HTML: +``` + +**Rasterizing Gradients with Sharp:** + +```javascript +const sharp = require('sharp'); + +async function createGradientBackground(filename) { + const svg = ` + + + + + + + + `; + + await sharp(Buffer.from(svg)) + .png() + .toFile(filename); + + return filename; +} + +// Usage: Create gradient background before HTML +const bgPath = await createGradientBackground("gradient-bg.png"); +// Then in HTML: +``` + +### Example + +```html + + + + + + +
                      +

                      Recipe Title

                      +
                        +
                      • Item: Description
                        • +
                      +

                      Text with bold, italic, underline.

                      +
                      + + +
                      +

                      5

                      +
                      +
                      + + +``` + +## Using the html2pptx Library + +### Dependencies + +These libraries have been globally installed and are available to use: +- `pptxgenjs` +- `playwright` +- `sharp` + +### Basic Usage + +```javascript +const pptxgen = require('pptxgenjs'); +const html2pptx = require('./html2pptx'); + +const pptx = new pptxgen(); +pptx.layout = 'LAYOUT_16x9'; // Must match HTML body dimensions + +const { slide, placeholders } = await html2pptx('slide1.html', pptx); + +// Add chart to placeholder area +if (placeholders.length > 0) { + slide.addChart(pptx.charts.LINE, chartData, placeholders[0]); +} + +await pptx.writeFile('output.pptx'); +``` + +### API Reference + +#### Function Signature +```javascript +await html2pptx(htmlFile, pres, options) +``` + +#### Parameters +- `htmlFile` (string): Path to HTML file (absolute or relative) +- `pres` (pptxgen): PptxGenJS presentation instance with layout already set +- `options` (object, optional): + - `tmpDir` (string): Temporary directory for generated files (default: `process.env.TMPDIR || '/tmp'`) + - `slide` (object): Existing slide to reuse (default: creates new slide) + +#### Returns +```javascript +{ + slide: pptxgenSlide, // The created/updated slide + placeholders: [ // Array of placeholder positions + { id: string, x: number, y: number, w: number, h: number }, + ... + ] +} +``` + +### Validation + +The library automatically validates and collects all errors before throwing: + +1. **HTML dimensions must match presentation layout** - Reports dimension mismatches +2. **Content must not overflow body** - Reports overflow with exact measurements +3. **CSS gradients** - Reports unsupported gradient usage +4. **Text element styling** - Reports backgrounds/borders/shadows on text elements (only allowed on divs) + +**All validation errors are collected and reported together** in a single error message, allowing you to fix all issues at once instead of one at a time. + +### Working with Placeholders + +```javascript +const { slide, placeholders } = await html2pptx('slide.html', pptx); + +// Use first placeholder +slide.addChart(pptx.charts.BAR, data, placeholders[0]); + +// Find by ID +const chartArea = placeholders.find(p => p.id === 'chart-area'); +slide.addChart(pptx.charts.LINE, data, chartArea); +``` + +### Complete Example + +```javascript +const pptxgen = require('pptxgenjs'); +const html2pptx = require('./html2pptx'); + +async function createPresentation() { + const pptx = new pptxgen(); + pptx.layout = 'LAYOUT_16x9'; + pptx.author = 'Your Name'; + pptx.title = 'My Presentation'; + + // Slide 1: Title + const { slide: slide1 } = await html2pptx('slides/title.html', pptx); + + // Slide 2: Content with chart + const { slide: slide2, placeholders } = await html2pptx('slides/data.html', pptx); + + const chartData = [{ + name: 'Sales', + labels: ['Q1', 'Q2', 'Q3', 'Q4'], + values: [4500, 5500, 6200, 7100] + }]; + + slide2.addChart(pptx.charts.BAR, chartData, { + ...placeholders[0], + showTitle: true, + title: 'Quarterly Sales', + showCatAxisTitle: true, + catAxisTitle: 'Quarter', + showValAxisTitle: true, + valAxisTitle: 'Sales ($000s)' + }); + + // Save + await pptx.writeFile({ fileName: 'presentation.pptx' }); + console.log('Presentation created successfully!'); +} + +createPresentation().catch(console.error); +``` + +## Using PptxGenJS + +After converting HTML to slides with `html2pptx`, you'll use PptxGenJS to add dynamic content like charts, images, and additional elements. + +### ⚠️ Critical Rules + +#### Colors +- **NEVER use `#` prefix** with hex colors in PptxGenJS - causes file corruption +- ✅ Correct: `color: "FF0000"`, `fill: { color: "0066CC" }` +- ❌ Wrong: `color: "#FF0000"` (breaks document) + +### Adding Images + +Always calculate aspect ratios from actual image dimensions: + +```javascript +// Get image dimensions: identify image.png | grep -o '[0-9]* x [0-9]*' +const imgWidth = 1860, imgHeight = 1519; // From actual file +const aspectRatio = imgWidth / imgHeight; + +const h = 3; // Max height +const w = h * aspectRatio; +const x = (10 - w) / 2; // Center on 16:9 slide + +slide.addImage({ path: "chart.png", x, y: 1.5, w, h }); +``` + +### Adding Text + +```javascript +// Rich text with formatting +slide.addText([ + { text: "Bold ", options: { bold: true } }, + { text: "Italic ", options: { italic: true } }, + { text: "Normal" } +], { + x: 1, y: 2, w: 8, h: 1 +}); +``` + +### Adding Shapes + +```javascript +// Rectangle +slide.addShape(pptx.shapes.RECTANGLE, { + x: 1, y: 1, w: 3, h: 2, + fill: { color: "4472C4" }, + line: { color: "000000", width: 2 } +}); + +// Circle +slide.addShape(pptx.shapes.OVAL, { + x: 5, y: 1, w: 2, h: 2, + fill: { color: "ED7D31" } +}); + +// Rounded rectangle +slide.addShape(pptx.shapes.ROUNDED_RECTANGLE, { + x: 1, y: 4, w: 3, h: 1.5, + fill: { color: "70AD47" }, + rectRadius: 0.2 +}); +``` + +### Adding Charts + +**Required for most charts:** Axis labels using `catAxisTitle` (category) and `valAxisTitle` (value). + +**Chart Data Format:** +- Use **single series with all labels** for simple bar/line charts +- Each series creates a separate legend entry +- Labels array defines X-axis values + +**Time Series Data - Choose Correct Granularity:** +- **< 30 days**: Use daily grouping (e.g., "10-01", "10-02") - avoid monthly aggregation that creates single-point charts +- **30-365 days**: Use monthly grouping (e.g., "2024-01", "2024-02") +- **> 365 days**: Use yearly grouping (e.g., "2023", "2024") +- **Validate**: Charts with only 1 data point likely indicate incorrect aggregation for the time period + +```javascript +const { slide, placeholders } = await html2pptx('slide.html', pptx); + +// CORRECT: Single series with all labels +slide.addChart(pptx.charts.BAR, [{ + name: "Sales 2024", + labels: ["Q1", "Q2", "Q3", "Q4"], + values: [4500, 5500, 6200, 7100] +}], { + ...placeholders[0], // Use placeholder position + barDir: 'col', // 'col' = vertical bars, 'bar' = horizontal + showTitle: true, + title: 'Quarterly Sales', + showLegend: false, // No legend needed for single series + // Required axis labels + showCatAxisTitle: true, + catAxisTitle: 'Quarter', + showValAxisTitle: true, + valAxisTitle: 'Sales ($000s)', + // Optional: Control scaling (adjust min based on data range for better visualization) + valAxisMaxVal: 8000, + valAxisMinVal: 0, // Use 0 for counts/amounts; for clustered data (e.g., 4500-7100), consider starting closer to min value + valAxisMajorUnit: 2000, // Control y-axis label spacing to prevent crowding + catAxisLabelRotate: 45, // Rotate labels if crowded + dataLabelPosition: 'outEnd', + dataLabelColor: '000000', + // Use single color for single-series charts + chartColors: ["4472C4"] // All bars same color +}); +``` + +#### Scatter Chart + +**IMPORTANT**: Scatter chart data format is unusual - first series contains X-axis values, subsequent series contain Y-values: + +```javascript +// Prepare data +const data1 = [{ x: 10, y: 20 }, { x: 15, y: 25 }, { x: 20, y: 30 }]; +const data2 = [{ x: 12, y: 18 }, { x: 18, y: 22 }]; + +const allXValues = [...data1.map(d => d.x), ...data2.map(d => d.x)]; + +slide.addChart(pptx.charts.SCATTER, [ + { name: 'X-Axis', values: allXValues }, // First series = X values + { name: 'Series 1', values: data1.map(d => d.y) }, // Y values only + { name: 'Series 2', values: data2.map(d => d.y) } // Y values only +], { + x: 1, y: 1, w: 8, h: 4, + lineSize: 0, // 0 = no connecting lines + lineDataSymbol: 'circle', + lineDataSymbolSize: 6, + showCatAxisTitle: true, + catAxisTitle: 'X Axis', + showValAxisTitle: true, + valAxisTitle: 'Y Axis', + chartColors: ["4472C4", "ED7D31"] +}); +``` + +#### Line Chart + +```javascript +slide.addChart(pptx.charts.LINE, [{ + name: "Temperature", + labels: ["Jan", "Feb", "Mar", "Apr"], + values: [32, 35, 42, 55] +}], { + x: 1, y: 1, w: 8, h: 4, + lineSize: 4, + lineSmooth: true, + // Required axis labels + showCatAxisTitle: true, + catAxisTitle: 'Month', + showValAxisTitle: true, + valAxisTitle: 'Temperature (°F)', + // Optional: Y-axis range (set min based on data range for better visualization) + valAxisMinVal: 0, // For ranges starting at 0 (counts, percentages, etc.) + valAxisMaxVal: 60, + valAxisMajorUnit: 20, // Control y-axis label spacing to prevent crowding (e.g., 10, 20, 25) + // valAxisMinVal: 30, // PREFERRED: For data clustered in a range (e.g., 32-55 or ratings 3-5), start axis closer to min value to show variation + // Optional: Chart colors + chartColors: ["4472C4", "ED7D31", "A5A5A5"] +}); +``` + +#### Pie Chart (No Axis Labels Required) + +**CRITICAL**: Pie charts require a **single data series** with all categories in the `labels` array and corresponding values in the `values` array. + +```javascript +slide.addChart(pptx.charts.PIE, [{ + name: "Market Share", + labels: ["Product A", "Product B", "Other"], // All categories in one array + values: [35, 45, 20] // All values in one array +}], { + x: 2, y: 1, w: 6, h: 4, + showPercent: true, + showLegend: true, + legendPos: 'r', // right + chartColors: ["4472C4", "ED7D31", "A5A5A5"] +}); +``` + +#### Multiple Data Series + +```javascript +slide.addChart(pptx.charts.LINE, [ + { + name: "Product A", + labels: ["Q1", "Q2", "Q3", "Q4"], + values: [10, 20, 30, 40] + }, + { + name: "Product B", + labels: ["Q1", "Q2", "Q3", "Q4"], + values: [15, 25, 20, 35] + } +], { + x: 1, y: 1, w: 8, h: 4, + showCatAxisTitle: true, + catAxisTitle: 'Quarter', + showValAxisTitle: true, + valAxisTitle: 'Revenue ($M)' +}); +``` + +### Chart Colors + +**CRITICAL**: Use hex colors **without** the `#` prefix - including `#` causes file corruption. + +**Align chart colors with your chosen design palette**, ensuring sufficient contrast and distinctiveness for data visualization. Adjust colors for: +- Strong contrast between adjacent series +- Readability against slide backgrounds +- Accessibility (avoid red-green only combinations) + +```javascript +// Example: Ocean palette-inspired chart colors (adjusted for contrast) +const chartColors = ["16A085", "FF6B9D", "2C3E50", "F39C12", "9B59B6"]; + +// Single-series chart: Use one color for all bars/points +slide.addChart(pptx.charts.BAR, [{ + name: "Sales", + labels: ["Q1", "Q2", "Q3", "Q4"], + values: [4500, 5500, 6200, 7100] +}], { + ...placeholders[0], + chartColors: ["16A085"], // All bars same color + showLegend: false +}); + +// Multi-series chart: Each series gets a different color +slide.addChart(pptx.charts.LINE, [ + { name: "Product A", labels: ["Q1", "Q2", "Q3"], values: [10, 20, 30] }, + { name: "Product B", labels: ["Q1", "Q2", "Q3"], values: [15, 25, 20] } +], { + ...placeholders[0], + chartColors: ["16A085", "FF6B9D"] // One color per series +}); +``` + +### Adding Tables + +Tables can be added with basic or advanced formatting: + +#### Basic Table + +```javascript +slide.addTable([ + ["Header 1", "Header 2", "Header 3"], + ["Row 1, Col 1", "Row 1, Col 2", "Row 1, Col 3"], + ["Row 2, Col 1", "Row 2, Col 2", "Row 2, Col 3"] +], { + x: 0.5, + y: 1, + w: 9, + h: 3, + border: { pt: 1, color: "999999" }, + fill: { color: "F1F1F1" } +}); +``` + +#### Table with Custom Formatting + +```javascript +const tableData = [ + // Header row with custom styling + [ + { text: "Product", options: { fill: { color: "4472C4" }, color: "FFFFFF", bold: true } }, + { text: "Revenue", options: { fill: { color: "4472C4" }, color: "FFFFFF", bold: true } }, + { text: "Growth", options: { fill: { color: "4472C4" }, color: "FFFFFF", bold: true } } + ], + // Data rows + ["Product A", "$50M", "+15%"], + ["Product B", "$35M", "+22%"], + ["Product C", "$28M", "+8%"] +]; + +slide.addTable(tableData, { + x: 1, + y: 1.5, + w: 8, + h: 3, + colW: [3, 2.5, 2.5], // Column widths + rowH: [0.5, 0.6, 0.6, 0.6], // Row heights + border: { pt: 1, color: "CCCCCC" }, + align: "center", + valign: "middle", + fontSize: 14 +}); +``` + +#### Table with Merged Cells + +```javascript +const mergedTableData = [ + [ + { text: "Q1 Results", options: { colspan: 3, fill: { color: "4472C4" }, color: "FFFFFF", bold: true } } + ], + ["Product", "Sales", "Market Share"], + ["Product A", "$25M", "35%"], + ["Product B", "$18M", "25%"] +]; + +slide.addTable(mergedTableData, { + x: 1, + y: 1, + w: 8, + h: 2.5, + colW: [3, 2.5, 2.5], + border: { pt: 1, color: "DDDDDD" } +}); +``` + +### Table Options + +Common table options: +- `x, y, w, h` - Position and size +- `colW` - Array of column widths (in inches) +- `rowH` - Array of row heights (in inches) +- `border` - Border style: `{ pt: 1, color: "999999" }` +- `fill` - Background color (no # prefix) +- `align` - Text alignment: "left", "center", "right" +- `valign` - Vertical alignment: "top", "middle", "bottom" +- `fontSize` - Text size +- `autoPage` - Auto-create new slides if content overflows \ No newline at end of file diff --git a/skills/pptx/ooxml.md b/skills/pptx/ooxml.md new file mode 100644 index 0000000..951b3cf --- /dev/null +++ b/skills/pptx/ooxml.md @@ -0,0 +1,427 @@ +# Office Open XML Technical Reference for PowerPoint + +**Important: Read this entire document before starting.** Critical XML schema rules and formatting requirements are covered throughout. Incorrect implementation can create invalid PPTX files that PowerPoint cannot open. + +## Technical Guidelines + +### Schema Compliance +- **Element ordering in ``**: ``, ``, `` +- **Whitespace**: Add `xml:space='preserve'` to `` elements with leading/trailing spaces +- **Unicode**: Escape characters in ASCII content: `"` becomes `“` +- **Images**: Add to `ppt/media/`, reference in slide XML, set dimensions to fit slide bounds +- **Relationships**: Update `ppt/slides/_rels/slideN.xml.rels` for each slide's resources +- **Dirty attribute**: Add `dirty="0"` to `` and `` elements to indicate clean state + +## Presentation Structure + +### Basic Slide Structure +```xml + + + + + ... + ... + + + + +``` + +### Text Box / Shape with Text +```xml + + + + + + + + + + + + + + + + + + + + + + Slide Title + + + + +``` + +### Text Formatting +```xml + + + + Bold Text + + + + + + Italic Text + + + + + + Underlined + + + + + + + + + + Highlighted Text + + + + + + + + + + Colored Arial 24pt + + + + + + + + + + Formatted text + +``` + +### Lists +```xml + + + + + + + First bullet point + + + + + + + + + + First numbered item + + + + + + + + + + Indented bullet + + +``` + +### Shapes +```xml + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +``` + +### Images +```xml + + + + + + + + + + + + + + + + + + + + + + + + + + +``` + +### Tables +```xml + + + + + + + + + + + + + + + + + + + + + + + + + + + Cell 1 + + + + + + + + + + + Cell 2 + + + + + + + + + +``` + +### Slide Layouts + +```xml + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +``` + +## File Updates + +When adding content, update these files: + +**`ppt/_rels/presentation.xml.rels`:** +```xml + + +``` + +**`ppt/slides/_rels/slide1.xml.rels`:** +```xml + + +``` + +**`[Content_Types].xml`:** +```xml + + + +``` + +**`ppt/presentation.xml`:** +```xml + + + + +``` + +**`docProps/app.xml`:** Update slide count and statistics +```xml +2 +10 +50 +``` + +## Slide Operations + +### Adding a New Slide +When adding a slide to the end of the presentation: + +1. **Create the slide file** (`ppt/slides/slideN.xml`) +2. **Update `[Content_Types].xml`**: Add Override for the new slide +3. **Update `ppt/_rels/presentation.xml.rels`**: Add relationship for the new slide +4. **Update `ppt/presentation.xml`**: Add slide ID to `` +5. **Create slide relationships** (`ppt/slides/_rels/slideN.xml.rels`) if needed +6. **Update `docProps/app.xml`**: Increment slide count and update statistics (if present) + +### Duplicating a Slide +1. Copy the source slide XML file with a new name +2. Update all IDs in the new slide to be unique +3. Follow the "Adding a New Slide" steps above +4. **CRITICAL**: Remove or update any notes slide references in `_rels` files +5. Remove references to unused media files + +### Reordering Slides +1. **Update `ppt/presentation.xml`**: Reorder `` elements in `` +2. The order of `` elements determines slide order +3. Keep slide IDs and relationship IDs unchanged + +Example: +```xml + + + + + + + + + + + + + +``` + +### Deleting a Slide +1. **Remove from `ppt/presentation.xml`**: Delete the `` entry +2. **Remove from `ppt/_rels/presentation.xml.rels`**: Delete the relationship +3. **Remove from `[Content_Types].xml`**: Delete the Override entry +4. **Delete files**: Remove `ppt/slides/slideN.xml` and `ppt/slides/_rels/slideN.xml.rels` +5. **Update `docProps/app.xml`**: Decrement slide count and update statistics +6. **Clean up unused media**: Remove orphaned images from `ppt/media/` + +Note: Don't renumber remaining slides - keep their original IDs and filenames. + + +## Common Errors to Avoid + +- **Encodings**: Escape unicode characters in ASCII content: `"` becomes `“` +- **Images**: Add to `ppt/media/` and update relationship files +- **Lists**: Omit bullets from list headers +- **IDs**: Use valid hexadecimal values for UUIDs +- **Themes**: Check all themes in `theme` directory for colors + +## Validation Checklist for Template-Based Presentations + +### Before Packing, Always: +- **Clean unused resources**: Remove unreferenced media, fonts, and notes directories +- **Fix Content_Types.xml**: Declare ALL slides, layouts, and themes present in the package +- **Fix relationship IDs**: + - Remove font embed references if not using embedded fonts +- **Remove broken references**: Check all `_rels` files for references to deleted resources + +### Common Template Duplication Pitfalls: +- Multiple slides referencing the same notes slide after duplication +- Image/media references from template slides that no longer exist +- Font embedding references when fonts aren't included +- Missing slideLayout declarations for layouts 12-25 +- docProps directory may not unpack - this is optional \ No newline at end of file diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-chart.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-chart.xsd new file mode 100644 index 0000000..6454ef9 --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-chart.xsd @@ -0,0 +1,1499 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd new file mode 100644 index 0000000..afa4f46 --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd @@ -0,0 +1,146 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd new file mode 100644 index 0000000..64e66b8 --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd @@ -0,0 +1,1085 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd new file mode 100644 index 0000000..687eea8 --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd @@ -0,0 +1,11 @@ + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-main.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-main.xsd new file mode 100644 index 0000000..6ac81b0 --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-main.xsd @@ -0,0 +1,3081 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-picture.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-picture.xsd new file mode 100644 index 0000000..1dbf051 --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-picture.xsd @@ -0,0 +1,23 @@ + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd new file mode 100644 index 0000000..f1af17d --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd @@ -0,0 +1,185 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd new file mode 100644 index 0000000..0a185ab --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd @@ -0,0 +1,287 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/pml.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/pml.xsd new file mode 100644 index 0000000..14ef488 --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/pml.xsd @@ -0,0 +1,1676 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd new file mode 100644 index 0000000..c20f3bf --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd @@ -0,0 +1,28 @@ + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd new file mode 100644 index 0000000..ac60252 --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd @@ -0,0 +1,144 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd new file mode 100644 index 0000000..424b8ba --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd @@ -0,0 +1,174 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd new file mode 100644 index 0000000..2bddce2 --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd @@ -0,0 +1,25 @@ + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd new file mode 100644 index 0000000..8a8c18b --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd @@ -0,0 +1,18 @@ + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd new file mode 100644 index 0000000..5c42706 --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd @@ -0,0 +1,59 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd new file mode 100644 index 0000000..853c341 --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd @@ -0,0 +1,56 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd new file mode 100644 index 0000000..da835ee --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd @@ -0,0 +1,195 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-math.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-math.xsd new file mode 100644 index 0000000..87ad265 --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-math.xsd @@ -0,0 +1,582 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd new file mode 100644 index 0000000..9e86f1b --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd @@ -0,0 +1,25 @@ + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/sml.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/sml.xsd new file mode 100644 index 0000000..d0be42e --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/sml.xsd @@ -0,0 +1,4439 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/vml-main.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/vml-main.xsd new file mode 100644 index 0000000..8821dd1 --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/vml-main.xsd @@ -0,0 +1,570 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd new file mode 100644 index 0000000..ca2575c --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd @@ -0,0 +1,509 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd new file mode 100644 index 0000000..dd079e6 --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd @@ -0,0 +1,12 @@ + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd new file mode 100644 index 0000000..3dd6cf6 --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd @@ -0,0 +1,108 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd new file mode 100644 index 0000000..f1041e3 --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd @@ -0,0 +1,96 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/wml.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/wml.xsd new file mode 100644 index 0000000..9c5b7a6 --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/wml.xsd @@ -0,0 +1,3646 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/xml.xsd b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/xml.xsd new file mode 100644 index 0000000..0f13678 --- /dev/null +++ b/skills/pptx/ooxml/schemas/ISO-IEC29500-4_2016/xml.xsd @@ -0,0 +1,116 @@ + + + + + + See http://www.w3.org/XML/1998/namespace.html and + http://www.w3.org/TR/REC-xml for information about this namespace. + + This schema document describes the XML namespace, in a form + suitable for import by other schema documents. + + Note that local names in this namespace are intended to be defined + only by the World Wide Web Consortium or its subgroups. The + following names are currently defined in this namespace and should + not be used with conflicting semantics by any Working Group, + specification, or document instance: + + base (as an attribute name): denotes an attribute whose value + provides a URI to be used as the base for interpreting any + relative URIs in the scope of the element on which it + appears; its value is inherited. This name is reserved + by virtue of its definition in the XML Base specification. + + lang (as an attribute name): denotes an attribute whose value + is a language code for the natural language of the content of + any element; its value is inherited. This name is reserved + by virtue of its definition in the XML specification. + + space (as an attribute name): denotes an attribute whose + value is a keyword indicating what whitespace processing + discipline is intended for the content of the element; its + value is inherited. This name is reserved by virtue of its + definition in the XML specification. + + Father (in any context at all): denotes Jon Bosak, the chair of + the original XML Working Group. This name is reserved by + the following decision of the W3C XML Plenary and + XML Coordination groups: + + In appreciation for his vision, leadership and dedication + the W3C XML Plenary on this 10th day of February, 2000 + reserves for Jon Bosak in perpetuity the XML name + xml:Father + + + + + This schema defines attributes and an attribute group + suitable for use by + schemas wishing to allow xml:base, xml:lang or xml:space attributes + on elements they define. + + To enable this, such a schema must import this schema + for the XML namespace, e.g. as follows: + <schema . . .> + . . . + <import namespace="http://www.w3.org/XML/1998/namespace" + schemaLocation="http://www.w3.org/2001/03/xml.xsd"/> + + Subsequently, qualified reference to any of the attributes + or the group defined below will have the desired effect, e.g. + + <type . . .> + . . . + <attributeGroup ref="xml:specialAttrs"/> + + will define a type which will schema-validate an instance + element with any of those attributes + + + + In keeping with the XML Schema WG's standard versioning + policy, this schema document will persist at + http://www.w3.org/2001/03/xml.xsd. + At the date of issue it can also be found at + http://www.w3.org/2001/xml.xsd. + The schema document at that URI may however change in the future, + in order to remain compatible with the latest version of XML Schema + itself. In other words, if the XML Schema namespace changes, the version + of this document at + http://www.w3.org/2001/xml.xsd will change + accordingly; the version at + http://www.w3.org/2001/03/xml.xsd will not change. + + + + + + In due course, we should install the relevant ISO 2- and 3-letter + codes as the enumerated possible values . . . + + + + + + + + + + + + + + + See http://www.w3.org/TR/xmlbase/ for + information about this attribute. + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ecma/fouth-edition/opc-contentTypes.xsd b/skills/pptx/ooxml/schemas/ecma/fouth-edition/opc-contentTypes.xsd new file mode 100644 index 0000000..a6de9d2 --- /dev/null +++ b/skills/pptx/ooxml/schemas/ecma/fouth-edition/opc-contentTypes.xsd @@ -0,0 +1,42 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ecma/fouth-edition/opc-coreProperties.xsd b/skills/pptx/ooxml/schemas/ecma/fouth-edition/opc-coreProperties.xsd new file mode 100644 index 0000000..10e978b --- /dev/null +++ b/skills/pptx/ooxml/schemas/ecma/fouth-edition/opc-coreProperties.xsd @@ -0,0 +1,50 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ecma/fouth-edition/opc-digSig.xsd b/skills/pptx/ooxml/schemas/ecma/fouth-edition/opc-digSig.xsd new file mode 100644 index 0000000..4248bf7 --- /dev/null +++ b/skills/pptx/ooxml/schemas/ecma/fouth-edition/opc-digSig.xsd @@ -0,0 +1,49 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/ecma/fouth-edition/opc-relationships.xsd b/skills/pptx/ooxml/schemas/ecma/fouth-edition/opc-relationships.xsd new file mode 100644 index 0000000..5649746 --- /dev/null +++ b/skills/pptx/ooxml/schemas/ecma/fouth-edition/opc-relationships.xsd @@ -0,0 +1,33 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/mce/mc.xsd b/skills/pptx/ooxml/schemas/mce/mc.xsd new file mode 100644 index 0000000..ef72545 --- /dev/null +++ b/skills/pptx/ooxml/schemas/mce/mc.xsd @@ -0,0 +1,75 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/microsoft/wml-2010.xsd b/skills/pptx/ooxml/schemas/microsoft/wml-2010.xsd new file mode 100644 index 0000000..f65f777 --- /dev/null +++ b/skills/pptx/ooxml/schemas/microsoft/wml-2010.xsd @@ -0,0 +1,560 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/microsoft/wml-2012.xsd b/skills/pptx/ooxml/schemas/microsoft/wml-2012.xsd new file mode 100644 index 0000000..6b00755 --- /dev/null +++ b/skills/pptx/ooxml/schemas/microsoft/wml-2012.xsd @@ -0,0 +1,67 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/microsoft/wml-2018.xsd b/skills/pptx/ooxml/schemas/microsoft/wml-2018.xsd new file mode 100644 index 0000000..f321d33 --- /dev/null +++ b/skills/pptx/ooxml/schemas/microsoft/wml-2018.xsd @@ -0,0 +1,14 @@ + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/microsoft/wml-cex-2018.xsd b/skills/pptx/ooxml/schemas/microsoft/wml-cex-2018.xsd new file mode 100644 index 0000000..364c6a9 --- /dev/null +++ b/skills/pptx/ooxml/schemas/microsoft/wml-cex-2018.xsd @@ -0,0 +1,20 @@ + + + + + + + + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/microsoft/wml-cid-2016.xsd b/skills/pptx/ooxml/schemas/microsoft/wml-cid-2016.xsd new file mode 100644 index 0000000..fed9d15 --- /dev/null +++ b/skills/pptx/ooxml/schemas/microsoft/wml-cid-2016.xsd @@ -0,0 +1,13 @@ + + + + + + + + + + + + + diff --git a/skills/pptx/ooxml/schemas/microsoft/wml-sdtdatahash-2020.xsd b/skills/pptx/ooxml/schemas/microsoft/wml-sdtdatahash-2020.xsd new file mode 100644 index 0000000..680cf15 --- /dev/null +++ b/skills/pptx/ooxml/schemas/microsoft/wml-sdtdatahash-2020.xsd @@ -0,0 +1,4 @@ + + + + diff --git a/skills/pptx/ooxml/schemas/microsoft/wml-symex-2015.xsd b/skills/pptx/ooxml/schemas/microsoft/wml-symex-2015.xsd new file mode 100644 index 0000000..89ada90 --- /dev/null +++ b/skills/pptx/ooxml/schemas/microsoft/wml-symex-2015.xsd @@ -0,0 +1,8 @@ + + + + + + + + diff --git a/skills/pptx/ooxml/scripts/pack.py b/skills/pptx/ooxml/scripts/pack.py new file mode 100755 index 0000000..68bc088 --- /dev/null +++ b/skills/pptx/ooxml/scripts/pack.py @@ -0,0 +1,159 @@ +#!/usr/bin/env python3 +""" +Tool to pack a directory into a .docx, .pptx, or .xlsx file with XML formatting undone. + +Example usage: + python pack.py [--force] +""" + +import argparse +import shutil +import subprocess +import sys +import tempfile +import defusedxml.minidom +import zipfile +from pathlib import Path + + +def main(): + parser = argparse.ArgumentParser(description="Pack a directory into an Office file") + parser.add_argument("input_directory", help="Unpacked Office document directory") + parser.add_argument("output_file", help="Output Office file (.docx/.pptx/.xlsx)") + parser.add_argument("--force", action="store_true", help="Skip validation") + args = parser.parse_args() + + try: + success = pack_document( + args.input_directory, args.output_file, validate=not args.force + ) + + # Show warning if validation was skipped + if args.force: + print("Warning: Skipped validation, file may be corrupt", file=sys.stderr) + # Exit with error if validation failed + elif not success: + print("Contents would produce a corrupt file.", file=sys.stderr) + print("Please validate XML before repacking.", file=sys.stderr) + print("Use --force to skip validation and pack anyway.", file=sys.stderr) + sys.exit(1) + + except ValueError as e: + sys.exit(f"Error: {e}") + + +def pack_document(input_dir, output_file, validate=False): + """Pack a directory into an Office file (.docx/.pptx/.xlsx). + + Args: + input_dir: Path to unpacked Office document directory + output_file: Path to output Office file + validate: If True, validates with soffice (default: False) + + Returns: + bool: True if successful, False if validation failed + """ + input_dir = Path(input_dir) + output_file = Path(output_file) + + if not input_dir.is_dir(): + raise ValueError(f"{input_dir} is not a directory") + if output_file.suffix.lower() not in {".docx", ".pptx", ".xlsx"}: + raise ValueError(f"{output_file} must be a .docx, .pptx, or .xlsx file") + + # Work in temporary directory to avoid modifying original + with tempfile.TemporaryDirectory() as temp_dir: + temp_content_dir = Path(temp_dir) / "content" + shutil.copytree(input_dir, temp_content_dir) + + # Process XML files to remove pretty-printing whitespace + for pattern in ["*.xml", "*.rels"]: + for xml_file in temp_content_dir.rglob(pattern): + condense_xml(xml_file) + + # Create final Office file as zip archive + output_file.parent.mkdir(parents=True, exist_ok=True) + with zipfile.ZipFile(output_file, "w", zipfile.ZIP_DEFLATED) as zf: + for f in temp_content_dir.rglob("*"): + if f.is_file(): + zf.write(f, f.relative_to(temp_content_dir)) + + # Validate if requested + if validate: + if not validate_document(output_file): + output_file.unlink() # Delete the corrupt file + return False + + return True + + +def validate_document(doc_path): + """Validate document by converting to HTML with soffice.""" + # Determine the correct filter based on file extension + match doc_path.suffix.lower(): + case ".docx": + filter_name = "html:HTML" + case ".pptx": + filter_name = "html:impress_html_Export" + case ".xlsx": + filter_name = "html:HTML (StarCalc)" + + with tempfile.TemporaryDirectory() as temp_dir: + try: + result = subprocess.run( + [ + "soffice", + "--headless", + "--convert-to", + filter_name, + "--outdir", + temp_dir, + str(doc_path), + ], + capture_output=True, + timeout=10, + text=True, + ) + if not (Path(temp_dir) / f"{doc_path.stem}.html").exists(): + error_msg = result.stderr.strip() or "Document validation failed" + print(f"Validation error: {error_msg}", file=sys.stderr) + return False + return True + except FileNotFoundError: + print("Warning: soffice not found. Skipping validation.", file=sys.stderr) + return True + except subprocess.TimeoutExpired: + print("Validation error: Timeout during conversion", file=sys.stderr) + return False + except Exception as e: + print(f"Validation error: {e}", file=sys.stderr) + return False + + +def condense_xml(xml_file): + """Strip unnecessary whitespace and remove comments.""" + with open(xml_file, "r", encoding="utf-8") as f: + dom = defusedxml.minidom.parse(f) + + # Process each element to remove whitespace and comments + for element in dom.getElementsByTagName("*"): + # Skip w:t elements and their processing + if element.tagName.endswith(":t"): + continue + + # Remove whitespace-only text nodes and comment nodes + for child in list(element.childNodes): + if ( + child.nodeType == child.TEXT_NODE + and child.nodeValue + and child.nodeValue.strip() == "" + ) or child.nodeType == child.COMMENT_NODE: + element.removeChild(child) + + # Write back the condensed XML + with open(xml_file, "wb") as f: + f.write(dom.toxml(encoding="UTF-8")) + + +if __name__ == "__main__": + main() diff --git a/skills/pptx/ooxml/scripts/unpack.py b/skills/pptx/ooxml/scripts/unpack.py new file mode 100755 index 0000000..4938798 --- /dev/null +++ b/skills/pptx/ooxml/scripts/unpack.py @@ -0,0 +1,29 @@ +#!/usr/bin/env python3 +"""Unpack and format XML contents of Office files (.docx, .pptx, .xlsx)""" + +import random +import sys +import defusedxml.minidom +import zipfile +from pathlib import Path + +# Get command line arguments +assert len(sys.argv) == 3, "Usage: python unpack.py " +input_file, output_dir = sys.argv[1], sys.argv[2] + +# Extract and format +output_path = Path(output_dir) +output_path.mkdir(parents=True, exist_ok=True) +zipfile.ZipFile(input_file).extractall(output_path) + +# Pretty print all XML files +xml_files = list(output_path.rglob("*.xml")) + list(output_path.rglob("*.rels")) +for xml_file in xml_files: + content = xml_file.read_text(encoding="utf-8") + dom = defusedxml.minidom.parseString(content) + xml_file.write_bytes(dom.toprettyxml(indent=" ", encoding="ascii")) + +# For .docx files, suggest an RSID for tracked changes +if input_file.endswith(".docx"): + suggested_rsid = "".join(random.choices("0123456789ABCDEF", k=8)) + print(f"Suggested RSID for edit session: {suggested_rsid}") diff --git a/skills/pptx/ooxml/scripts/validate.py b/skills/pptx/ooxml/scripts/validate.py new file mode 100755 index 0000000..508c589 --- /dev/null +++ b/skills/pptx/ooxml/scripts/validate.py @@ -0,0 +1,69 @@ +#!/usr/bin/env python3 +""" +Command line tool to validate Office document XML files against XSD schemas and tracked changes. + +Usage: + python validate.py --original +""" + +import argparse +import sys +from pathlib import Path + +from validation import DOCXSchemaValidator, PPTXSchemaValidator, RedliningValidator + + +def main(): + parser = argparse.ArgumentParser(description="Validate Office document XML files") + parser.add_argument( + "unpacked_dir", + help="Path to unpacked Office document directory", + ) + parser.add_argument( + "--original", + required=True, + help="Path to original file (.docx/.pptx/.xlsx)", + ) + parser.add_argument( + "-v", + "--verbose", + action="store_true", + help="Enable verbose output", + ) + args = parser.parse_args() + + # Validate paths + unpacked_dir = Path(args.unpacked_dir) + original_file = Path(args.original) + file_extension = original_file.suffix.lower() + assert unpacked_dir.is_dir(), f"Error: {unpacked_dir} is not a directory" + assert original_file.is_file(), f"Error: {original_file} is not a file" + assert file_extension in [".docx", ".pptx", ".xlsx"], ( + f"Error: {original_file} must be a .docx, .pptx, or .xlsx file" + ) + + # Run validations + match file_extension: + case ".docx": + validators = [DOCXSchemaValidator, RedliningValidator] + case ".pptx": + validators = [PPTXSchemaValidator] + case _: + print(f"Error: Validation not supported for file type {file_extension}") + sys.exit(1) + + # Run validators + success = True + for V in validators: + validator = V(unpacked_dir, original_file, verbose=args.verbose) + if not validator.validate(): + success = False + + if success: + print("All validations PASSED!") + + sys.exit(0 if success else 1) + + +if __name__ == "__main__": + main() diff --git a/skills/pptx/ooxml/scripts/validation/__init__.py b/skills/pptx/ooxml/scripts/validation/__init__.py new file mode 100644 index 0000000..db092ec --- /dev/null +++ b/skills/pptx/ooxml/scripts/validation/__init__.py @@ -0,0 +1,15 @@ +""" +Validation modules for Word document processing. +""" + +from .base import BaseSchemaValidator +from .docx import DOCXSchemaValidator +from .pptx import PPTXSchemaValidator +from .redlining import RedliningValidator + +__all__ = [ + "BaseSchemaValidator", + "DOCXSchemaValidator", + "PPTXSchemaValidator", + "RedliningValidator", +] diff --git a/skills/pptx/ooxml/scripts/validation/base.py b/skills/pptx/ooxml/scripts/validation/base.py new file mode 100644 index 0000000..0681b19 --- /dev/null +++ b/skills/pptx/ooxml/scripts/validation/base.py @@ -0,0 +1,951 @@ +""" +Base validator with common validation logic for document files. +""" + +import re +from pathlib import Path + +import lxml.etree + + +class BaseSchemaValidator: + """Base validator with common validation logic for document files.""" + + # Elements whose 'id' attributes must be unique within their file + # Format: element_name -> (attribute_name, scope) + # scope can be 'file' (unique within file) or 'global' (unique across all files) + UNIQUE_ID_REQUIREMENTS = { + # Word elements + "comment": ("id", "file"), # Comment IDs in comments.xml + "commentrangestart": ("id", "file"), # Must match comment IDs + "commentrangeend": ("id", "file"), # Must match comment IDs + "bookmarkstart": ("id", "file"), # Bookmark start IDs + "bookmarkend": ("id", "file"), # Bookmark end IDs + # Note: ins and del (track changes) can share IDs when part of same revision + # PowerPoint elements + "sldid": ("id", "file"), # Slide IDs in presentation.xml + "sldmasterid": ("id", "global"), # Slide master IDs must be globally unique + "sldlayoutid": ("id", "global"), # Slide layout IDs must be globally unique + "cm": ("authorid", "file"), # Comment author IDs + # Excel elements + "sheet": ("sheetid", "file"), # Sheet IDs in workbook.xml + "definedname": ("id", "file"), # Named range IDs + # Drawing/Shape elements (all formats) + "cxnsp": ("id", "file"), # Connection shape IDs + "sp": ("id", "file"), # Shape IDs + "pic": ("id", "file"), # Picture IDs + "grpsp": ("id", "file"), # Group shape IDs + } + + # Mapping of element names to expected relationship types + # Subclasses should override this with format-specific mappings + ELEMENT_RELATIONSHIP_TYPES = {} + + # Unified schema mappings for all Office document types + SCHEMA_MAPPINGS = { + # Document type specific schemas + "word": "ISO-IEC29500-4_2016/wml.xsd", # Word documents + "ppt": "ISO-IEC29500-4_2016/pml.xsd", # PowerPoint presentations + "xl": "ISO-IEC29500-4_2016/sml.xsd", # Excel spreadsheets + # Common file types + "[Content_Types].xml": "ecma/fouth-edition/opc-contentTypes.xsd", + "app.xml": "ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd", + "core.xml": "ecma/fouth-edition/opc-coreProperties.xsd", + "custom.xml": "ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd", + ".rels": "ecma/fouth-edition/opc-relationships.xsd", + # Word-specific files + "people.xml": "microsoft/wml-2012.xsd", + "commentsIds.xml": "microsoft/wml-cid-2016.xsd", + "commentsExtensible.xml": "microsoft/wml-cex-2018.xsd", + "commentsExtended.xml": "microsoft/wml-2012.xsd", + # Chart files (common across document types) + "chart": "ISO-IEC29500-4_2016/dml-chart.xsd", + # Theme files (common across document types) + "theme": "ISO-IEC29500-4_2016/dml-main.xsd", + # Drawing and media files + "drawing": "ISO-IEC29500-4_2016/dml-main.xsd", + } + + # Unified namespace constants + MC_NAMESPACE = "http://schemas.openxmlformats.org/markup-compatibility/2006" + XML_NAMESPACE = "http://www.w3.org/XML/1998/namespace" + + # Common OOXML namespaces used across validators + PACKAGE_RELATIONSHIPS_NAMESPACE = ( + "http://schemas.openxmlformats.org/package/2006/relationships" + ) + OFFICE_RELATIONSHIPS_NAMESPACE = ( + "http://schemas.openxmlformats.org/officeDocument/2006/relationships" + ) + CONTENT_TYPES_NAMESPACE = ( + "http://schemas.openxmlformats.org/package/2006/content-types" + ) + + # Folders where we should clean ignorable namespaces + MAIN_CONTENT_FOLDERS = {"word", "ppt", "xl"} + + # All allowed OOXML namespaces (superset of all document types) + OOXML_NAMESPACES = { + "http://schemas.openxmlformats.org/officeDocument/2006/math", + "http://schemas.openxmlformats.org/officeDocument/2006/relationships", + "http://schemas.openxmlformats.org/schemaLibrary/2006/main", + "http://schemas.openxmlformats.org/drawingml/2006/main", + "http://schemas.openxmlformats.org/drawingml/2006/chart", + "http://schemas.openxmlformats.org/drawingml/2006/chartDrawing", + "http://schemas.openxmlformats.org/drawingml/2006/diagram", + "http://schemas.openxmlformats.org/drawingml/2006/picture", + "http://schemas.openxmlformats.org/drawingml/2006/spreadsheetDrawing", + "http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing", + "http://schemas.openxmlformats.org/wordprocessingml/2006/main", + "http://schemas.openxmlformats.org/presentationml/2006/main", + "http://schemas.openxmlformats.org/spreadsheetml/2006/main", + "http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes", + "http://www.w3.org/XML/1998/namespace", + } + + def __init__(self, unpacked_dir, original_file, verbose=False): + self.unpacked_dir = Path(unpacked_dir).resolve() + self.original_file = Path(original_file) + self.verbose = verbose + + # Set schemas directory + self.schemas_dir = Path(__file__).parent.parent.parent / "schemas" + + # Get all XML and .rels files + patterns = ["*.xml", "*.rels"] + self.xml_files = [ + f for pattern in patterns for f in self.unpacked_dir.rglob(pattern) + ] + + if not self.xml_files: + print(f"Warning: No XML files found in {self.unpacked_dir}") + + def validate(self): + """Run all validation checks and return True if all pass.""" + raise NotImplementedError("Subclasses must implement the validate method") + + def validate_xml(self): + """Validate that all XML files are well-formed.""" + errors = [] + + for xml_file in self.xml_files: + try: + # Try to parse the XML file + lxml.etree.parse(str(xml_file)) + except lxml.etree.XMLSyntaxError as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {e.lineno}: {e.msg}" + ) + except Exception as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Unexpected error: {str(e)}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} XML violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All XML files are well-formed") + return True + + def validate_namespaces(self): + """Validate that namespace prefixes in Ignorable attributes are declared.""" + errors = [] + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + declared = set(root.nsmap.keys()) - {None} # Exclude default namespace + + for attr_val in [ + v for k, v in root.attrib.items() if k.endswith("Ignorable") + ]: + undeclared = set(attr_val.split()) - declared + errors.extend( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Namespace '{ns}' in Ignorable but not declared" + for ns in undeclared + ) + except lxml.etree.XMLSyntaxError: + continue + + if errors: + print(f"FAILED - {len(errors)} namespace issues:") + for error in errors: + print(error) + return False + if self.verbose: + print("PASSED - All namespace prefixes properly declared") + return True + + def validate_unique_ids(self): + """Validate that specific IDs are unique according to OOXML requirements.""" + errors = [] + global_ids = {} # Track globally unique IDs across all files + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + file_ids = {} # Track IDs that must be unique within this file + + # Remove all mc:AlternateContent elements from the tree + mc_elements = root.xpath( + ".//mc:AlternateContent", namespaces={"mc": self.MC_NAMESPACE} + ) + for elem in mc_elements: + elem.getparent().remove(elem) + + # Now check IDs in the cleaned tree + for elem in root.iter(): + # Get the element name without namespace + tag = ( + elem.tag.split("}")[-1].lower() + if "}" in elem.tag + else elem.tag.lower() + ) + + # Check if this element type has ID uniqueness requirements + if tag in self.UNIQUE_ID_REQUIREMENTS: + attr_name, scope = self.UNIQUE_ID_REQUIREMENTS[tag] + + # Look for the specified attribute + id_value = None + for attr, value in elem.attrib.items(): + attr_local = ( + attr.split("}")[-1].lower() + if "}" in attr + else attr.lower() + ) + if attr_local == attr_name: + id_value = value + break + + if id_value is not None: + if scope == "global": + # Check global uniqueness + if id_value in global_ids: + prev_file, prev_line, prev_tag = global_ids[ + id_value + ] + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: Global ID '{id_value}' in <{tag}> " + f"already used in {prev_file} at line {prev_line} in <{prev_tag}>" + ) + else: + global_ids[id_value] = ( + xml_file.relative_to(self.unpacked_dir), + elem.sourceline, + tag, + ) + elif scope == "file": + # Check file-level uniqueness + key = (tag, attr_name) + if key not in file_ids: + file_ids[key] = {} + + if id_value in file_ids[key]: + prev_line = file_ids[key][id_value] + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: Duplicate {attr_name}='{id_value}' in <{tag}> " + f"(first occurrence at line {prev_line})" + ) + else: + file_ids[key][id_value] = elem.sourceline + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} ID uniqueness violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All required IDs are unique") + return True + + def validate_file_references(self): + """ + Validate that all .rels files properly reference files and that all files are referenced. + """ + errors = [] + + # Find all .rels files + rels_files = list(self.unpacked_dir.rglob("*.rels")) + + if not rels_files: + if self.verbose: + print("PASSED - No .rels files found") + return True + + # Get all files in the unpacked directory (excluding reference files) + all_files = [] + for file_path in self.unpacked_dir.rglob("*"): + if ( + file_path.is_file() + and file_path.name != "[Content_Types].xml" + and not file_path.name.endswith(".rels") + ): # This file is not referenced by .rels + all_files.append(file_path.resolve()) + + # Track all files that are referenced by any .rels file + all_referenced_files = set() + + if self.verbose: + print( + f"Found {len(rels_files)} .rels files and {len(all_files)} target files" + ) + + # Check each .rels file + for rels_file in rels_files: + try: + # Parse relationships file + rels_root = lxml.etree.parse(str(rels_file)).getroot() + + # Get the directory where this .rels file is located + rels_dir = rels_file.parent + + # Find all relationships and their targets + referenced_files = set() + broken_refs = [] + + for rel in rels_root.findall( + ".//ns:Relationship", + namespaces={"ns": self.PACKAGE_RELATIONSHIPS_NAMESPACE}, + ): + target = rel.get("Target") + if target and not target.startswith( + ("http", "mailto:") + ): # Skip external URLs + # Resolve the target path relative to the .rels file location + if rels_file.name == ".rels": + # Root .rels file - targets are relative to unpacked_dir + target_path = self.unpacked_dir / target + else: + # Other .rels files - targets are relative to their parent's parent + # e.g., word/_rels/document.xml.rels -> targets relative to word/ + base_dir = rels_dir.parent + target_path = base_dir / target + + # Normalize the path and check if it exists + try: + target_path = target_path.resolve() + if target_path.exists() and target_path.is_file(): + referenced_files.add(target_path) + all_referenced_files.add(target_path) + else: + broken_refs.append((target, rel.sourceline)) + except (OSError, ValueError): + broken_refs.append((target, rel.sourceline)) + + # Report broken references + if broken_refs: + rel_path = rels_file.relative_to(self.unpacked_dir) + for broken_ref, line_num in broken_refs: + errors.append( + f" {rel_path}: Line {line_num}: Broken reference to {broken_ref}" + ) + + except Exception as e: + rel_path = rels_file.relative_to(self.unpacked_dir) + errors.append(f" Error parsing {rel_path}: {e}") + + # Check for unreferenced files (files that exist but are not referenced anywhere) + unreferenced_files = set(all_files) - all_referenced_files + + if unreferenced_files: + for unref_file in sorted(unreferenced_files): + unref_rel_path = unref_file.relative_to(self.unpacked_dir) + errors.append(f" Unreferenced file: {unref_rel_path}") + + if errors: + print(f"FAILED - Found {len(errors)} relationship validation errors:") + for error in errors: + print(error) + print( + "CRITICAL: These errors will cause the document to appear corrupt. " + + "Broken references MUST be fixed, " + + "and unreferenced files MUST be referenced or removed." + ) + return False + else: + if self.verbose: + print( + "PASSED - All references are valid and all files are properly referenced" + ) + return True + + def validate_all_relationship_ids(self): + """ + Validate that all r:id attributes in XML files reference existing IDs + in their corresponding .rels files, and optionally validate relationship types. + """ + import lxml.etree + + errors = [] + + # Process each XML file that might contain r:id references + for xml_file in self.xml_files: + # Skip .rels files themselves + if xml_file.suffix == ".rels": + continue + + # Determine the corresponding .rels file + # For dir/file.xml, it's dir/_rels/file.xml.rels + rels_dir = xml_file.parent / "_rels" + rels_file = rels_dir / f"{xml_file.name}.rels" + + # Skip if there's no corresponding .rels file (that's okay) + if not rels_file.exists(): + continue + + try: + # Parse the .rels file to get valid relationship IDs and their types + rels_root = lxml.etree.parse(str(rels_file)).getroot() + rid_to_type = {} + + for rel in rels_root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rid = rel.get("Id") + rel_type = rel.get("Type", "") + if rid: + # Check for duplicate rIds + if rid in rid_to_type: + rels_rel_path = rels_file.relative_to(self.unpacked_dir) + errors.append( + f" {rels_rel_path}: Line {rel.sourceline}: " + f"Duplicate relationship ID '{rid}' (IDs must be unique)" + ) + # Extract just the type name from the full URL + type_name = ( + rel_type.split("/")[-1] if "/" in rel_type else rel_type + ) + rid_to_type[rid] = type_name + + # Parse the XML file to find all r:id references + xml_root = lxml.etree.parse(str(xml_file)).getroot() + + # Find all elements with r:id attributes + for elem in xml_root.iter(): + # Check for r:id attribute (relationship ID) + rid_attr = elem.get(f"{{{self.OFFICE_RELATIONSHIPS_NAMESPACE}}}id") + if rid_attr: + xml_rel_path = xml_file.relative_to(self.unpacked_dir) + elem_name = ( + elem.tag.split("}")[-1] if "}" in elem.tag else elem.tag + ) + + # Check if the ID exists + if rid_attr not in rid_to_type: + errors.append( + f" {xml_rel_path}: Line {elem.sourceline}: " + f"<{elem_name}> references non-existent relationship '{rid_attr}' " + f"(valid IDs: {', '.join(sorted(rid_to_type.keys())[:5])}{'...' if len(rid_to_type) > 5 else ''})" + ) + # Check if we have type expectations for this element + elif self.ELEMENT_RELATIONSHIP_TYPES: + expected_type = self._get_expected_relationship_type( + elem_name + ) + if expected_type: + actual_type = rid_to_type[rid_attr] + # Check if the actual type matches or contains the expected type + if expected_type not in actual_type.lower(): + errors.append( + f" {xml_rel_path}: Line {elem.sourceline}: " + f"<{elem_name}> references '{rid_attr}' which points to '{actual_type}' " + f"but should point to a '{expected_type}' relationship" + ) + + except Exception as e: + xml_rel_path = xml_file.relative_to(self.unpacked_dir) + errors.append(f" Error processing {xml_rel_path}: {e}") + + if errors: + print(f"FAILED - Found {len(errors)} relationship ID reference errors:") + for error in errors: + print(error) + print("\nThese ID mismatches will cause the document to appear corrupt!") + return False + else: + if self.verbose: + print("PASSED - All relationship ID references are valid") + return True + + def _get_expected_relationship_type(self, element_name): + """ + Get the expected relationship type for an element. + First checks the explicit mapping, then tries pattern detection. + """ + # Normalize element name to lowercase + elem_lower = element_name.lower() + + # Check explicit mapping first + if elem_lower in self.ELEMENT_RELATIONSHIP_TYPES: + return self.ELEMENT_RELATIONSHIP_TYPES[elem_lower] + + # Try pattern detection for common patterns + # Pattern 1: Elements ending in "Id" often expect a relationship of the prefix type + if elem_lower.endswith("id") and len(elem_lower) > 2: + # e.g., "sldId" -> "sld", "sldMasterId" -> "sldMaster" + prefix = elem_lower[:-2] # Remove "id" + # Check if this might be a compound like "sldMasterId" + if prefix.endswith("master"): + return prefix.lower() + elif prefix.endswith("layout"): + return prefix.lower() + else: + # Simple case like "sldId" -> "slide" + # Common transformations + if prefix == "sld": + return "slide" + return prefix.lower() + + # Pattern 2: Elements ending in "Reference" expect a relationship of the prefix type + if elem_lower.endswith("reference") and len(elem_lower) > 9: + prefix = elem_lower[:-9] # Remove "reference" + return prefix.lower() + + return None + + def validate_content_types(self): + """Validate that all content files are properly declared in [Content_Types].xml.""" + errors = [] + + # Find [Content_Types].xml file + content_types_file = self.unpacked_dir / "[Content_Types].xml" + if not content_types_file.exists(): + print("FAILED - [Content_Types].xml file not found") + return False + + try: + # Parse and get all declared parts and extensions + root = lxml.etree.parse(str(content_types_file)).getroot() + declared_parts = set() + declared_extensions = set() + + # Get Override declarations (specific files) + for override in root.findall( + f".//{{{self.CONTENT_TYPES_NAMESPACE}}}Override" + ): + part_name = override.get("PartName") + if part_name is not None: + declared_parts.add(part_name.lstrip("/")) + + # Get Default declarations (by extension) + for default in root.findall( + f".//{{{self.CONTENT_TYPES_NAMESPACE}}}Default" + ): + extension = default.get("Extension") + if extension is not None: + declared_extensions.add(extension.lower()) + + # Root elements that require content type declaration + declarable_roots = { + "sld", + "sldLayout", + "sldMaster", + "presentation", # PowerPoint + "document", # Word + "workbook", + "worksheet", # Excel + "theme", # Common + } + + # Common media file extensions that should be declared + media_extensions = { + "png": "image/png", + "jpg": "image/jpeg", + "jpeg": "image/jpeg", + "gif": "image/gif", + "bmp": "image/bmp", + "tiff": "image/tiff", + "wmf": "image/x-wmf", + "emf": "image/x-emf", + } + + # Get all files in the unpacked directory + all_files = list(self.unpacked_dir.rglob("*")) + all_files = [f for f in all_files if f.is_file()] + + # Check all XML files for Override declarations + for xml_file in self.xml_files: + path_str = str(xml_file.relative_to(self.unpacked_dir)).replace( + "\\", "/" + ) + + # Skip non-content files + if any( + skip in path_str + for skip in [".rels", "[Content_Types]", "docProps/", "_rels/"] + ): + continue + + try: + root_tag = lxml.etree.parse(str(xml_file)).getroot().tag + root_name = root_tag.split("}")[-1] if "}" in root_tag else root_tag + + if root_name in declarable_roots and path_str not in declared_parts: + errors.append( + f" {path_str}: File with <{root_name}> root not declared in [Content_Types].xml" + ) + + except Exception: + continue # Skip unparseable files + + # Check all non-XML files for Default extension declarations + for file_path in all_files: + # Skip XML files and metadata files (already checked above) + if file_path.suffix.lower() in {".xml", ".rels"}: + continue + if file_path.name == "[Content_Types].xml": + continue + if "_rels" in file_path.parts or "docProps" in file_path.parts: + continue + + extension = file_path.suffix.lstrip(".").lower() + if extension and extension not in declared_extensions: + # Check if it's a known media extension that should be declared + if extension in media_extensions: + relative_path = file_path.relative_to(self.unpacked_dir) + errors.append( + f' {relative_path}: File with extension \'{extension}\' not declared in [Content_Types].xml - should add: ' + ) + + except Exception as e: + errors.append(f" Error parsing [Content_Types].xml: {e}") + + if errors: + print(f"FAILED - Found {len(errors)} content type declaration errors:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print( + "PASSED - All content files are properly declared in [Content_Types].xml" + ) + return True + + def validate_file_against_xsd(self, xml_file, verbose=False): + """Validate a single XML file against XSD schema, comparing with original. + + Args: + xml_file: Path to XML file to validate + verbose: Enable verbose output + + Returns: + tuple: (is_valid, new_errors_set) where is_valid is True/False/None (skipped) + """ + # Resolve both paths to handle symlinks + xml_file = Path(xml_file).resolve() + unpacked_dir = self.unpacked_dir.resolve() + + # Validate current file + is_valid, current_errors = self._validate_single_file_xsd( + xml_file, unpacked_dir + ) + + if is_valid is None: + return None, set() # Skipped + elif is_valid: + return True, set() # Valid, no errors + + # Get errors from original file for this specific file + original_errors = self._get_original_file_errors(xml_file) + + # Compare with original (both are guaranteed to be sets here) + assert current_errors is not None + new_errors = current_errors - original_errors + + if new_errors: + if verbose: + relative_path = xml_file.relative_to(unpacked_dir) + print(f"FAILED - {relative_path}: {len(new_errors)} new error(s)") + for error in list(new_errors)[:3]: + truncated = error[:250] + "..." if len(error) > 250 else error + print(f" - {truncated}") + return False, new_errors + else: + # All errors existed in original + if verbose: + print( + f"PASSED - No new errors (original had {len(current_errors)} errors)" + ) + return True, set() + + def validate_against_xsd(self): + """Validate XML files against XSD schemas, showing only new errors compared to original.""" + new_errors = [] + original_error_count = 0 + valid_count = 0 + skipped_count = 0 + + for xml_file in self.xml_files: + relative_path = str(xml_file.relative_to(self.unpacked_dir)) + is_valid, new_file_errors = self.validate_file_against_xsd( + xml_file, verbose=False + ) + + if is_valid is None: + skipped_count += 1 + continue + elif is_valid and not new_file_errors: + valid_count += 1 + continue + elif is_valid: + # Had errors but all existed in original + original_error_count += 1 + valid_count += 1 + continue + + # Has new errors + new_errors.append(f" {relative_path}: {len(new_file_errors)} new error(s)") + for error in list(new_file_errors)[:3]: # Show first 3 errors + new_errors.append( + f" - {error[:250]}..." if len(error) > 250 else f" - {error}" + ) + + # Print summary + if self.verbose: + print(f"Validated {len(self.xml_files)} files:") + print(f" - Valid: {valid_count}") + print(f" - Skipped (no schema): {skipped_count}") + if original_error_count: + print(f" - With original errors (ignored): {original_error_count}") + print( + f" - With NEW errors: {len(new_errors) > 0 and len([e for e in new_errors if not e.startswith(' ')]) or 0}" + ) + + if new_errors: + print("\nFAILED - Found NEW validation errors:") + for error in new_errors: + print(error) + return False + else: + if self.verbose: + print("\nPASSED - No new XSD validation errors introduced") + return True + + def _get_schema_path(self, xml_file): + """Determine the appropriate schema path for an XML file.""" + # Check exact filename match + if xml_file.name in self.SCHEMA_MAPPINGS: + return self.schemas_dir / self.SCHEMA_MAPPINGS[xml_file.name] + + # Check .rels files + if xml_file.suffix == ".rels": + return self.schemas_dir / self.SCHEMA_MAPPINGS[".rels"] + + # Check chart files + if "charts/" in str(xml_file) and xml_file.name.startswith("chart"): + return self.schemas_dir / self.SCHEMA_MAPPINGS["chart"] + + # Check theme files + if "theme/" in str(xml_file) and xml_file.name.startswith("theme"): + return self.schemas_dir / self.SCHEMA_MAPPINGS["theme"] + + # Check if file is in a main content folder and use appropriate schema + if xml_file.parent.name in self.MAIN_CONTENT_FOLDERS: + return self.schemas_dir / self.SCHEMA_MAPPINGS[xml_file.parent.name] + + return None + + def _clean_ignorable_namespaces(self, xml_doc): + """Remove attributes and elements not in allowed namespaces.""" + # Create a clean copy + xml_string = lxml.etree.tostring(xml_doc, encoding="unicode") + xml_copy = lxml.etree.fromstring(xml_string) + + # Remove attributes not in allowed namespaces + for elem in xml_copy.iter(): + attrs_to_remove = [] + + for attr in elem.attrib: + # Check if attribute is from a namespace other than allowed ones + if "{" in attr: + ns = attr.split("}")[0][1:] + if ns not in self.OOXML_NAMESPACES: + attrs_to_remove.append(attr) + + # Remove collected attributes + for attr in attrs_to_remove: + del elem.attrib[attr] + + # Remove elements not in allowed namespaces + self._remove_ignorable_elements(xml_copy) + + return lxml.etree.ElementTree(xml_copy) + + def _remove_ignorable_elements(self, root): + """Recursively remove all elements not in allowed namespaces.""" + elements_to_remove = [] + + # Find elements to remove + for elem in list(root): + # Skip non-element nodes (comments, processing instructions, etc.) + if not hasattr(elem, "tag") or callable(elem.tag): + continue + + tag_str = str(elem.tag) + if tag_str.startswith("{"): + ns = tag_str.split("}")[0][1:] + if ns not in self.OOXML_NAMESPACES: + elements_to_remove.append(elem) + continue + + # Recursively clean child elements + self._remove_ignorable_elements(elem) + + # Remove collected elements + for elem in elements_to_remove: + root.remove(elem) + + def _preprocess_for_mc_ignorable(self, xml_doc): + """Preprocess XML to handle mc:Ignorable attribute properly.""" + # Remove mc:Ignorable attributes before validation + root = xml_doc.getroot() + + # Remove mc:Ignorable attribute from root + if f"{{{self.MC_NAMESPACE}}}Ignorable" in root.attrib: + del root.attrib[f"{{{self.MC_NAMESPACE}}}Ignorable"] + + return xml_doc + + def _validate_single_file_xsd(self, xml_file, base_path): + """Validate a single XML file against XSD schema. Returns (is_valid, errors_set).""" + schema_path = self._get_schema_path(xml_file) + if not schema_path: + return None, None # Skip file + + try: + # Load schema + with open(schema_path, "rb") as xsd_file: + parser = lxml.etree.XMLParser() + xsd_doc = lxml.etree.parse( + xsd_file, parser=parser, base_url=str(schema_path) + ) + schema = lxml.etree.XMLSchema(xsd_doc) + + # Load and preprocess XML + with open(xml_file, "r") as f: + xml_doc = lxml.etree.parse(f) + + xml_doc, _ = self._remove_template_tags_from_text_nodes(xml_doc) + xml_doc = self._preprocess_for_mc_ignorable(xml_doc) + + # Clean ignorable namespaces if needed + relative_path = xml_file.relative_to(base_path) + if ( + relative_path.parts + and relative_path.parts[0] in self.MAIN_CONTENT_FOLDERS + ): + xml_doc = self._clean_ignorable_namespaces(xml_doc) + + # Validate + if schema.validate(xml_doc): + return True, set() + else: + errors = set() + for error in schema.error_log: + # Store normalized error message (without line numbers for comparison) + errors.add(error.message) + return False, errors + + except Exception as e: + return False, {str(e)} + + def _get_original_file_errors(self, xml_file): + """Get XSD validation errors from a single file in the original document. + + Args: + xml_file: Path to the XML file in unpacked_dir to check + + Returns: + set: Set of error messages from the original file + """ + import tempfile + import zipfile + + # Resolve both paths to handle symlinks (e.g., /var vs /private/var on macOS) + xml_file = Path(xml_file).resolve() + unpacked_dir = self.unpacked_dir.resolve() + relative_path = xml_file.relative_to(unpacked_dir) + + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + # Extract original file + with zipfile.ZipFile(self.original_file, "r") as zip_ref: + zip_ref.extractall(temp_path) + + # Find corresponding file in original + original_xml_file = temp_path / relative_path + + if not original_xml_file.exists(): + # File didn't exist in original, so no original errors + return set() + + # Validate the specific file in original + is_valid, errors = self._validate_single_file_xsd( + original_xml_file, temp_path + ) + return errors if errors else set() + + def _remove_template_tags_from_text_nodes(self, xml_doc): + """Remove template tags from XML text nodes and collect warnings. + + Template tags follow the pattern {{ ... }} and are used as placeholders + for content replacement. They should be removed from text content before + XSD validation while preserving XML structure. + + Returns: + tuple: (cleaned_xml_doc, warnings_list) + """ + warnings = [] + template_pattern = re.compile(r"\{\{[^}]*\}\}") + + # Create a copy of the document to avoid modifying the original + xml_string = lxml.etree.tostring(xml_doc, encoding="unicode") + xml_copy = lxml.etree.fromstring(xml_string) + + def process_text_content(text, content_type): + if not text: + return text + matches = list(template_pattern.finditer(text)) + if matches: + for match in matches: + warnings.append( + f"Found template tag in {content_type}: {match.group()}" + ) + return template_pattern.sub("", text) + return text + + # Process all text nodes in the document + for elem in xml_copy.iter(): + # Skip processing if this is a w:t element + if not hasattr(elem, "tag") or callable(elem.tag): + continue + tag_str = str(elem.tag) + if tag_str.endswith("}t") or tag_str == "t": + continue + + elem.text = process_text_content(elem.text, "text content") + elem.tail = process_text_content(elem.tail, "tail content") + + return lxml.etree.ElementTree(xml_copy), warnings + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/skills/pptx/ooxml/scripts/validation/docx.py b/skills/pptx/ooxml/scripts/validation/docx.py new file mode 100644 index 0000000..602c470 --- /dev/null +++ b/skills/pptx/ooxml/scripts/validation/docx.py @@ -0,0 +1,274 @@ +""" +Validator for Word document XML files against XSD schemas. +""" + +import re +import tempfile +import zipfile + +import lxml.etree + +from .base import BaseSchemaValidator + + +class DOCXSchemaValidator(BaseSchemaValidator): + """Validator for Word document XML files against XSD schemas.""" + + # Word-specific namespace + WORD_2006_NAMESPACE = "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + + # Word-specific element to relationship type mappings + # Start with empty mapping - add specific cases as we discover them + ELEMENT_RELATIONSHIP_TYPES = {} + + def validate(self): + """Run all validation checks and return True if all pass.""" + # Test 0: XML well-formedness + if not self.validate_xml(): + return False + + # Test 1: Namespace declarations + all_valid = True + if not self.validate_namespaces(): + all_valid = False + + # Test 2: Unique IDs + if not self.validate_unique_ids(): + all_valid = False + + # Test 3: Relationship and file reference validation + if not self.validate_file_references(): + all_valid = False + + # Test 4: Content type declarations + if not self.validate_content_types(): + all_valid = False + + # Test 5: XSD schema validation + if not self.validate_against_xsd(): + all_valid = False + + # Test 6: Whitespace preservation + if not self.validate_whitespace_preservation(): + all_valid = False + + # Test 7: Deletion validation + if not self.validate_deletions(): + all_valid = False + + # Test 8: Insertion validation + if not self.validate_insertions(): + all_valid = False + + # Test 9: Relationship ID reference validation + if not self.validate_all_relationship_ids(): + all_valid = False + + # Count and compare paragraphs + self.compare_paragraph_counts() + + return all_valid + + def validate_whitespace_preservation(self): + """ + Validate that w:t elements with whitespace have xml:space='preserve'. + """ + errors = [] + + for xml_file in self.xml_files: + # Only check document.xml files + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + + # Find all w:t elements + for elem in root.iter(f"{{{self.WORD_2006_NAMESPACE}}}t"): + if elem.text: + text = elem.text + # Check if text starts or ends with whitespace + if re.match(r"^\s.*", text) or re.match(r".*\s$", text): + # Check if xml:space="preserve" attribute exists + xml_space_attr = f"{{{self.XML_NAMESPACE}}}space" + if ( + xml_space_attr not in elem.attrib + or elem.attrib[xml_space_attr] != "preserve" + ): + # Show a preview of the text + text_preview = ( + repr(text)[:50] + "..." + if len(repr(text)) > 50 + else repr(text) + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: w:t element with whitespace missing xml:space='preserve': {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} whitespace preservation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All whitespace is properly preserved") + return True + + def validate_deletions(self): + """ + Validate that w:t elements are not within w:del elements. + For some reason, XSD validation does not catch this, so we do it manually. + """ + errors = [] + + for xml_file in self.xml_files: + # Only check document.xml files + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + + # Find all w:t elements that are descendants of w:del elements + namespaces = {"w": self.WORD_2006_NAMESPACE} + xpath_expression = ".//w:del//w:t" + problematic_t_elements = root.xpath( + xpath_expression, namespaces=namespaces + ) + for t_elem in problematic_t_elements: + if t_elem.text: + # Show a preview of the text + text_preview = ( + repr(t_elem.text)[:50] + "..." + if len(repr(t_elem.text)) > 50 + else repr(t_elem.text) + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {t_elem.sourceline}: found within : {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} deletion validation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - No w:t elements found within w:del elements") + return True + + def count_paragraphs_in_unpacked(self): + """Count the number of paragraphs in the unpacked document.""" + count = 0 + + for xml_file in self.xml_files: + # Only check document.xml files + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + # Count all w:p elements + paragraphs = root.findall(f".//{{{self.WORD_2006_NAMESPACE}}}p") + count = len(paragraphs) + except Exception as e: + print(f"Error counting paragraphs in unpacked document: {e}") + + return count + + def count_paragraphs_in_original(self): + """Count the number of paragraphs in the original docx file.""" + count = 0 + + try: + # Create temporary directory to unpack original + with tempfile.TemporaryDirectory() as temp_dir: + # Unpack original docx + with zipfile.ZipFile(self.original_file, "r") as zip_ref: + zip_ref.extractall(temp_dir) + + # Parse document.xml + doc_xml_path = temp_dir + "/word/document.xml" + root = lxml.etree.parse(doc_xml_path).getroot() + + # Count all w:p elements + paragraphs = root.findall(f".//{{{self.WORD_2006_NAMESPACE}}}p") + count = len(paragraphs) + + except Exception as e: + print(f"Error counting paragraphs in original document: {e}") + + return count + + def validate_insertions(self): + """ + Validate that w:delText elements are not within w:ins elements. + w:delText is only allowed in w:ins if nested within a w:del. + """ + errors = [] + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + namespaces = {"w": self.WORD_2006_NAMESPACE} + + # Find w:delText in w:ins that are NOT within w:del + invalid_elements = root.xpath( + ".//w:ins//w:delText[not(ancestor::w:del)]", + namespaces=namespaces + ) + + for elem in invalid_elements: + text_preview = ( + repr(elem.text or "")[:50] + "..." + if len(repr(elem.text or "")) > 50 + else repr(elem.text or "") + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: within : {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} insertion validation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - No w:delText elements within w:ins elements") + return True + + def compare_paragraph_counts(self): + """Compare paragraph counts between original and new document.""" + original_count = self.count_paragraphs_in_original() + new_count = self.count_paragraphs_in_unpacked() + + diff = new_count - original_count + diff_str = f"+{diff}" if diff > 0 else str(diff) + print(f"\nParagraphs: {original_count} → {new_count} ({diff_str})") + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/skills/pptx/ooxml/scripts/validation/pptx.py b/skills/pptx/ooxml/scripts/validation/pptx.py new file mode 100644 index 0000000..66d5b1e --- /dev/null +++ b/skills/pptx/ooxml/scripts/validation/pptx.py @@ -0,0 +1,315 @@ +""" +Validator for PowerPoint presentation XML files against XSD schemas. +""" + +import re + +from .base import BaseSchemaValidator + + +class PPTXSchemaValidator(BaseSchemaValidator): + """Validator for PowerPoint presentation XML files against XSD schemas.""" + + # PowerPoint presentation namespace + PRESENTATIONML_NAMESPACE = ( + "http://schemas.openxmlformats.org/presentationml/2006/main" + ) + + # PowerPoint-specific element to relationship type mappings + ELEMENT_RELATIONSHIP_TYPES = { + "sldid": "slide", + "sldmasterid": "slidemaster", + "notesmasterid": "notesmaster", + "sldlayoutid": "slidelayout", + "themeid": "theme", + "tablestyleid": "tablestyles", + } + + def validate(self): + """Run all validation checks and return True if all pass.""" + # Test 0: XML well-formedness + if not self.validate_xml(): + return False + + # Test 1: Namespace declarations + all_valid = True + if not self.validate_namespaces(): + all_valid = False + + # Test 2: Unique IDs + if not self.validate_unique_ids(): + all_valid = False + + # Test 3: UUID ID validation + if not self.validate_uuid_ids(): + all_valid = False + + # Test 4: Relationship and file reference validation + if not self.validate_file_references(): + all_valid = False + + # Test 5: Slide layout ID validation + if not self.validate_slide_layout_ids(): + all_valid = False + + # Test 6: Content type declarations + if not self.validate_content_types(): + all_valid = False + + # Test 7: XSD schema validation + if not self.validate_against_xsd(): + all_valid = False + + # Test 8: Notes slide reference validation + if not self.validate_notes_slide_references(): + all_valid = False + + # Test 9: Relationship ID reference validation + if not self.validate_all_relationship_ids(): + all_valid = False + + # Test 10: Duplicate slide layout references validation + if not self.validate_no_duplicate_slide_layouts(): + all_valid = False + + return all_valid + + def validate_uuid_ids(self): + """Validate that ID attributes that look like UUIDs contain only hex values.""" + import lxml.etree + + errors = [] + # UUID pattern: 8-4-4-4-12 hex digits with optional braces/hyphens + uuid_pattern = re.compile( + r"^[\{\(]?[0-9A-Fa-f]{8}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{12}[\}\)]?$" + ) + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + + # Check all elements for ID attributes + for elem in root.iter(): + for attr, value in elem.attrib.items(): + # Check if this is an ID attribute + attr_name = attr.split("}")[-1].lower() + if attr_name == "id" or attr_name.endswith("id"): + # Check if value looks like a UUID (has the right length and pattern structure) + if self._looks_like_uuid(value): + # Validate that it contains only hex characters in the right positions + if not uuid_pattern.match(value): + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: ID '{value}' appears to be a UUID but contains invalid hex characters" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} UUID ID validation errors:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All UUID-like IDs contain valid hex values") + return True + + def _looks_like_uuid(self, value): + """Check if a value has the general structure of a UUID.""" + # Remove common UUID delimiters + clean_value = value.strip("{}()").replace("-", "") + # Check if it's 32 hex-like characters (could include invalid hex chars) + return len(clean_value) == 32 and all(c.isalnum() for c in clean_value) + + def validate_slide_layout_ids(self): + """Validate that sldLayoutId elements in slide masters reference valid slide layouts.""" + import lxml.etree + + errors = [] + + # Find all slide master files + slide_masters = list(self.unpacked_dir.glob("ppt/slideMasters/*.xml")) + + if not slide_masters: + if self.verbose: + print("PASSED - No slide masters found") + return True + + for slide_master in slide_masters: + try: + # Parse the slide master file + root = lxml.etree.parse(str(slide_master)).getroot() + + # Find the corresponding _rels file for this slide master + rels_file = slide_master.parent / "_rels" / f"{slide_master.name}.rels" + + if not rels_file.exists(): + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: " + f"Missing relationships file: {rels_file.relative_to(self.unpacked_dir)}" + ) + continue + + # Parse the relationships file + rels_root = lxml.etree.parse(str(rels_file)).getroot() + + # Build a set of valid relationship IDs that point to slide layouts + valid_layout_rids = set() + for rel in rels_root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rel_type = rel.get("Type", "") + if "slideLayout" in rel_type: + valid_layout_rids.add(rel.get("Id")) + + # Find all sldLayoutId elements in the slide master + for sld_layout_id in root.findall( + f".//{{{self.PRESENTATIONML_NAMESPACE}}}sldLayoutId" + ): + r_id = sld_layout_id.get( + f"{{{self.OFFICE_RELATIONSHIPS_NAMESPACE}}}id" + ) + layout_id = sld_layout_id.get("id") + + if r_id and r_id not in valid_layout_rids: + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: " + f"Line {sld_layout_id.sourceline}: sldLayoutId with id='{layout_id}' " + f"references r:id='{r_id}' which is not found in slide layout relationships" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} slide layout ID validation errors:") + for error in errors: + print(error) + print( + "Remove invalid references or add missing slide layouts to the relationships file." + ) + return False + else: + if self.verbose: + print("PASSED - All slide layout IDs reference valid slide layouts") + return True + + def validate_no_duplicate_slide_layouts(self): + """Validate that each slide has exactly one slideLayout reference.""" + import lxml.etree + + errors = [] + slide_rels_files = list(self.unpacked_dir.glob("ppt/slides/_rels/*.xml.rels")) + + for rels_file in slide_rels_files: + try: + root = lxml.etree.parse(str(rels_file)).getroot() + + # Find all slideLayout relationships + layout_rels = [ + rel + for rel in root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ) + if "slideLayout" in rel.get("Type", "") + ] + + if len(layout_rels) > 1: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: has {len(layout_rels)} slideLayout references" + ) + + except Exception as e: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print("FAILED - Found slides with duplicate slideLayout references:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All slides have exactly one slideLayout reference") + return True + + def validate_notes_slide_references(self): + """Validate that each notesSlide file is referenced by only one slide.""" + import lxml.etree + + errors = [] + notes_slide_references = {} # Track which slides reference each notesSlide + + # Find all slide relationship files + slide_rels_files = list(self.unpacked_dir.glob("ppt/slides/_rels/*.xml.rels")) + + if not slide_rels_files: + if self.verbose: + print("PASSED - No slide relationship files found") + return True + + for rels_file in slide_rels_files: + try: + # Parse the relationships file + root = lxml.etree.parse(str(rels_file)).getroot() + + # Find all notesSlide relationships + for rel in root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rel_type = rel.get("Type", "") + if "notesSlide" in rel_type: + target = rel.get("Target", "") + if target: + # Normalize the target path to handle relative paths + normalized_target = target.replace("../", "") + + # Track which slide references this notesSlide + slide_name = rels_file.stem.replace( + ".xml", "" + ) # e.g., "slide1" + + if normalized_target not in notes_slide_references: + notes_slide_references[normalized_target] = [] + notes_slide_references[normalized_target].append( + (slide_name, rels_file) + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + # Check for duplicate references + for target, references in notes_slide_references.items(): + if len(references) > 1: + slide_names = [ref[0] for ref in references] + errors.append( + f" Notes slide '{target}' is referenced by multiple slides: {', '.join(slide_names)}" + ) + for slide_name, rels_file in references: + errors.append(f" - {rels_file.relative_to(self.unpacked_dir)}") + + if errors: + print( + f"FAILED - Found {len([e for e in errors if not e.startswith(' ')])} notes slide reference validation errors:" + ) + for error in errors: + print(error) + print("Each slide may optionally have its own slide file.") + return False + else: + if self.verbose: + print("PASSED - All notes slide references are unique") + return True + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/skills/pptx/ooxml/scripts/validation/redlining.py b/skills/pptx/ooxml/scripts/validation/redlining.py new file mode 100644 index 0000000..7ed425e --- /dev/null +++ b/skills/pptx/ooxml/scripts/validation/redlining.py @@ -0,0 +1,279 @@ +""" +Validator for tracked changes in Word documents. +""" + +import subprocess +import tempfile +import zipfile +from pathlib import Path + + +class RedliningValidator: + """Validator for tracked changes in Word documents.""" + + def __init__(self, unpacked_dir, original_docx, verbose=False): + self.unpacked_dir = Path(unpacked_dir) + self.original_docx = Path(original_docx) + self.verbose = verbose + self.namespaces = { + "w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + } + + def validate(self): + """Main validation method that returns True if valid, False otherwise.""" + # Verify unpacked directory exists and has correct structure + modified_file = self.unpacked_dir / "word" / "document.xml" + if not modified_file.exists(): + print(f"FAILED - Modified document.xml not found at {modified_file}") + return False + + # First, check if there are any tracked changes by Claude to validate + try: + import xml.etree.ElementTree as ET + + tree = ET.parse(modified_file) + root = tree.getroot() + + # Check for w:del or w:ins tags authored by Claude + del_elements = root.findall(".//w:del", self.namespaces) + ins_elements = root.findall(".//w:ins", self.namespaces) + + # Filter to only include changes by Claude + claude_del_elements = [ + elem + for elem in del_elements + if elem.get(f"{{{self.namespaces['w']}}}author") == "Claude" + ] + claude_ins_elements = [ + elem + for elem in ins_elements + if elem.get(f"{{{self.namespaces['w']}}}author") == "Claude" + ] + + # Redlining validation is only needed if tracked changes by Claude have been used. + if not claude_del_elements and not claude_ins_elements: + if self.verbose: + print("PASSED - No tracked changes by Claude found.") + return True + + except Exception: + # If we can't parse the XML, continue with full validation + pass + + # Create temporary directory for unpacking original docx + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + # Unpack original docx + try: + with zipfile.ZipFile(self.original_docx, "r") as zip_ref: + zip_ref.extractall(temp_path) + except Exception as e: + print(f"FAILED - Error unpacking original docx: {e}") + return False + + original_file = temp_path / "word" / "document.xml" + if not original_file.exists(): + print( + f"FAILED - Original document.xml not found in {self.original_docx}" + ) + return False + + # Parse both XML files using xml.etree.ElementTree for redlining validation + try: + import xml.etree.ElementTree as ET + + modified_tree = ET.parse(modified_file) + modified_root = modified_tree.getroot() + original_tree = ET.parse(original_file) + original_root = original_tree.getroot() + except ET.ParseError as e: + print(f"FAILED - Error parsing XML files: {e}") + return False + + # Remove Claude's tracked changes from both documents + self._remove_claude_tracked_changes(original_root) + self._remove_claude_tracked_changes(modified_root) + + # Extract and compare text content + modified_text = self._extract_text_content(modified_root) + original_text = self._extract_text_content(original_root) + + if modified_text != original_text: + # Show detailed character-level differences for each paragraph + error_message = self._generate_detailed_diff( + original_text, modified_text + ) + print(error_message) + return False + + if self.verbose: + print("PASSED - All changes by Claude are properly tracked") + return True + + def _generate_detailed_diff(self, original_text, modified_text): + """Generate detailed word-level differences using git word diff.""" + error_parts = [ + "FAILED - Document text doesn't match after removing Claude's tracked changes", + "", + "Likely causes:", + " 1. Modified text inside another author's or tags", + " 2. Made edits without proper tracked changes", + " 3. Didn't nest inside when deleting another's insertion", + "", + "For pre-redlined documents, use correct patterns:", + " - To reject another's INSERTION: Nest inside their ", + " - To restore another's DELETION: Add new AFTER their ", + "", + ] + + # Show git word diff + git_diff = self._get_git_word_diff(original_text, modified_text) + if git_diff: + error_parts.extend(["Differences:", "============", git_diff]) + else: + error_parts.append("Unable to generate word diff (git not available)") + + return "\n".join(error_parts) + + def _get_git_word_diff(self, original_text, modified_text): + """Generate word diff using git with character-level precision.""" + try: + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + # Create two files + original_file = temp_path / "original.txt" + modified_file = temp_path / "modified.txt" + + original_file.write_text(original_text, encoding="utf-8") + modified_file.write_text(modified_text, encoding="utf-8") + + # Try character-level diff first for precise differences + result = subprocess.run( + [ + "git", + "diff", + "--word-diff=plain", + "--word-diff-regex=.", # Character-by-character diff + "-U0", # Zero lines of context - show only changed lines + "--no-index", + str(original_file), + str(modified_file), + ], + capture_output=True, + text=True, + ) + + if result.stdout.strip(): + # Clean up the output - remove git diff header lines + lines = result.stdout.split("\n") + # Skip the header lines (diff --git, index, +++, ---, @@) + content_lines = [] + in_content = False + for line in lines: + if line.startswith("@@"): + in_content = True + continue + if in_content and line.strip(): + content_lines.append(line) + + if content_lines: + return "\n".join(content_lines) + + # Fallback to word-level diff if character-level is too verbose + result = subprocess.run( + [ + "git", + "diff", + "--word-diff=plain", + "-U0", # Zero lines of context + "--no-index", + str(original_file), + str(modified_file), + ], + capture_output=True, + text=True, + ) + + if result.stdout.strip(): + lines = result.stdout.split("\n") + content_lines = [] + in_content = False + for line in lines: + if line.startswith("@@"): + in_content = True + continue + if in_content and line.strip(): + content_lines.append(line) + return "\n".join(content_lines) + + except (subprocess.CalledProcessError, FileNotFoundError, Exception): + # Git not available or other error, return None to use fallback + pass + + return None + + def _remove_claude_tracked_changes(self, root): + """Remove tracked changes authored by Claude from the XML root.""" + ins_tag = f"{{{self.namespaces['w']}}}ins" + del_tag = f"{{{self.namespaces['w']}}}del" + author_attr = f"{{{self.namespaces['w']}}}author" + + # Remove w:ins elements + for parent in root.iter(): + to_remove = [] + for child in parent: + if child.tag == ins_tag and child.get(author_attr) == "Claude": + to_remove.append(child) + for elem in to_remove: + parent.remove(elem) + + # Unwrap content in w:del elements where author is "Claude" + deltext_tag = f"{{{self.namespaces['w']}}}delText" + t_tag = f"{{{self.namespaces['w']}}}t" + + for parent in root.iter(): + to_process = [] + for child in parent: + if child.tag == del_tag and child.get(author_attr) == "Claude": + to_process.append((child, list(parent).index(child))) + + # Process in reverse order to maintain indices + for del_elem, del_index in reversed(to_process): + # Convert w:delText to w:t before moving + for elem in del_elem.iter(): + if elem.tag == deltext_tag: + elem.tag = t_tag + + # Move all children of w:del to its parent before removing w:del + for child in reversed(list(del_elem)): + parent.insert(del_index, child) + parent.remove(del_elem) + + def _extract_text_content(self, root): + """Extract text content from Word XML, preserving paragraph structure. + + Empty paragraphs are skipped to avoid false positives when tracked + insertions add only structural elements without text content. + """ + p_tag = f"{{{self.namespaces['w']}}}p" + t_tag = f"{{{self.namespaces['w']}}}t" + + paragraphs = [] + for p_elem in root.findall(f".//{p_tag}"): + # Get all text elements within this paragraph + text_parts = [] + for t_elem in p_elem.findall(f".//{t_tag}"): + if t_elem.text: + text_parts.append(t_elem.text) + paragraph_text = "".join(text_parts) + # Skip empty paragraphs - they don't affect content validation + if paragraph_text: + paragraphs.append(paragraph_text) + + return "\n".join(paragraphs) + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/skills/pptx/scripts/html2pptx.js b/skills/pptx/scripts/html2pptx.js new file mode 100755 index 0000000..437bf7c --- /dev/null +++ b/skills/pptx/scripts/html2pptx.js @@ -0,0 +1,979 @@ +/** + * html2pptx - Convert HTML slide to pptxgenjs slide with positioned elements + * + * USAGE: + * const pptx = new pptxgen(); + * pptx.layout = 'LAYOUT_16x9'; // Must match HTML body dimensions + * + * const { slide, placeholders } = await html2pptx('slide.html', pptx); + * slide.addChart(pptx.charts.LINE, data, placeholders[0]); + * + * await pptx.writeFile('output.pptx'); + * + * FEATURES: + * - Converts HTML to PowerPoint with accurate positioning + * - Supports text, images, shapes, and bullet lists + * - Extracts placeholder elements (class="placeholder") with positions + * - Handles CSS gradients, borders, and margins + * + * VALIDATION: + * - Uses body width/height from HTML for viewport sizing + * - Throws error if HTML dimensions don't match presentation layout + * - Throws error if content overflows body (with overflow details) + * + * RETURNS: + * { slide, placeholders } where placeholders is an array of { id, x, y, w, h } + */ + +const { chromium } = require('playwright'); +const path = require('path'); +const sharp = require('sharp'); + +const PT_PER_PX = 0.75; +const PX_PER_IN = 96; +const EMU_PER_IN = 914400; + +// Helper: Get body dimensions and check for overflow +async function getBodyDimensions(page) { + const bodyDimensions = await page.evaluate(() => { + const body = document.body; + const style = window.getComputedStyle(body); + + return { + width: parseFloat(style.width), + height: parseFloat(style.height), + scrollWidth: body.scrollWidth, + scrollHeight: body.scrollHeight + }; + }); + + const errors = []; + const widthOverflowPx = Math.max(0, bodyDimensions.scrollWidth - bodyDimensions.width - 1); + const heightOverflowPx = Math.max(0, bodyDimensions.scrollHeight - bodyDimensions.height - 1); + + const widthOverflowPt = widthOverflowPx * PT_PER_PX; + const heightOverflowPt = heightOverflowPx * PT_PER_PX; + + if (widthOverflowPt > 0 || heightOverflowPt > 0) { + const directions = []; + if (widthOverflowPt > 0) directions.push(`${widthOverflowPt.toFixed(1)}pt horizontally`); + if (heightOverflowPt > 0) directions.push(`${heightOverflowPt.toFixed(1)}pt vertically`); + const reminder = heightOverflowPt > 0 ? ' (Remember: leave 0.5" margin at bottom of slide)' : ''; + errors.push(`HTML content overflows body by ${directions.join(' and ')}${reminder}`); + } + + return { ...bodyDimensions, errors }; +} + +// Helper: Validate dimensions match presentation layout +function validateDimensions(bodyDimensions, pres) { + const errors = []; + const widthInches = bodyDimensions.width / PX_PER_IN; + const heightInches = bodyDimensions.height / PX_PER_IN; + + if (pres.presLayout) { + const layoutWidth = pres.presLayout.width / EMU_PER_IN; + const layoutHeight = pres.presLayout.height / EMU_PER_IN; + + if (Math.abs(layoutWidth - widthInches) > 0.1 || Math.abs(layoutHeight - heightInches) > 0.1) { + errors.push( + `HTML dimensions (${widthInches.toFixed(1)}" × ${heightInches.toFixed(1)}") ` + + `don't match presentation layout (${layoutWidth.toFixed(1)}" × ${layoutHeight.toFixed(1)}")` + ); + } + } + return errors; +} + +function validateTextBoxPosition(slideData, bodyDimensions) { + const errors = []; + const slideHeightInches = bodyDimensions.height / PX_PER_IN; + const minBottomMargin = 0.5; // 0.5 inches from bottom + + for (const el of slideData.elements) { + // Check text elements (p, h1-h6, list) + if (['p', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'list'].includes(el.type)) { + const fontSize = el.style?.fontSize || 0; + const bottomEdge = el.position.y + el.position.h; + const distanceFromBottom = slideHeightInches - bottomEdge; + + if (fontSize > 12 && distanceFromBottom < minBottomMargin) { + const getText = () => { + if (typeof el.text === 'string') return el.text; + if (Array.isArray(el.text)) return el.text.find(t => t.text)?.text || ''; + if (Array.isArray(el.items)) return el.items.find(item => item.text)?.text || ''; + return ''; + }; + const textPrefix = getText().substring(0, 50) + (getText().length > 50 ? '...' : ''); + + errors.push( + `Text box "${textPrefix}" ends too close to bottom edge ` + + `(${distanceFromBottom.toFixed(2)}" from bottom, minimum ${minBottomMargin}" required)` + ); + } + } + } + + return errors; +} + +// Helper: Add background to slide +async function addBackground(slideData, targetSlide, tmpDir) { + if (slideData.background.type === 'image' && slideData.background.path) { + let imagePath = slideData.background.path.startsWith('file://') + ? slideData.background.path.replace('file://', '') + : slideData.background.path; + targetSlide.background = { path: imagePath }; + } else if (slideData.background.type === 'color' && slideData.background.value) { + targetSlide.background = { color: slideData.background.value }; + } +} + +// Helper: Add elements to slide +function addElements(slideData, targetSlide, pres) { + for (const el of slideData.elements) { + if (el.type === 'image') { + let imagePath = el.src.startsWith('file://') ? el.src.replace('file://', '') : el.src; + targetSlide.addImage({ + path: imagePath, + x: el.position.x, + y: el.position.y, + w: el.position.w, + h: el.position.h + }); + } else if (el.type === 'line') { + targetSlide.addShape(pres.ShapeType.line, { + x: el.x1, + y: el.y1, + w: el.x2 - el.x1, + h: el.y2 - el.y1, + line: { color: el.color, width: el.width } + }); + } else if (el.type === 'shape') { + const shapeOptions = { + x: el.position.x, + y: el.position.y, + w: el.position.w, + h: el.position.h, + shape: el.shape.rectRadius > 0 ? pres.ShapeType.roundRect : pres.ShapeType.rect + }; + + if (el.shape.fill) { + shapeOptions.fill = { color: el.shape.fill }; + if (el.shape.transparency != null) shapeOptions.fill.transparency = el.shape.transparency; + } + if (el.shape.line) shapeOptions.line = el.shape.line; + if (el.shape.rectRadius > 0) shapeOptions.rectRadius = el.shape.rectRadius; + if (el.shape.shadow) shapeOptions.shadow = el.shape.shadow; + + targetSlide.addText(el.text || '', shapeOptions); + } else if (el.type === 'list') { + const listOptions = { + x: el.position.x, + y: el.position.y, + w: el.position.w, + h: el.position.h, + fontSize: el.style.fontSize, + fontFace: el.style.fontFace, + color: el.style.color, + align: el.style.align, + valign: 'top', + lineSpacing: el.style.lineSpacing, + paraSpaceBefore: el.style.paraSpaceBefore, + paraSpaceAfter: el.style.paraSpaceAfter, + margin: el.style.margin + }; + if (el.style.margin) listOptions.margin = el.style.margin; + targetSlide.addText(el.items, listOptions); + } else { + // Check if text is single-line (height suggests one line) + const lineHeight = el.style.lineSpacing || el.style.fontSize * 1.2; + const isSingleLine = el.position.h <= lineHeight * 1.5; + + let adjustedX = el.position.x; + let adjustedW = el.position.w; + + // Make single-line text 2% wider to account for underestimate + if (isSingleLine) { + const widthIncrease = el.position.w * 0.02; + const align = el.style.align; + + if (align === 'center') { + // Center: expand both sides + adjustedX = el.position.x - (widthIncrease / 2); + adjustedW = el.position.w + widthIncrease; + } else if (align === 'right') { + // Right: expand to the left + adjustedX = el.position.x - widthIncrease; + adjustedW = el.position.w + widthIncrease; + } else { + // Left (default): expand to the right + adjustedW = el.position.w + widthIncrease; + } + } + + const textOptions = { + x: adjustedX, + y: el.position.y, + w: adjustedW, + h: el.position.h, + fontSize: el.style.fontSize, + fontFace: el.style.fontFace, + color: el.style.color, + bold: el.style.bold, + italic: el.style.italic, + underline: el.style.underline, + valign: 'top', + lineSpacing: el.style.lineSpacing, + paraSpaceBefore: el.style.paraSpaceBefore, + paraSpaceAfter: el.style.paraSpaceAfter, + inset: 0 // Remove default PowerPoint internal padding + }; + + if (el.style.align) textOptions.align = el.style.align; + if (el.style.margin) textOptions.margin = el.style.margin; + if (el.style.rotate !== undefined) textOptions.rotate = el.style.rotate; + if (el.style.transparency !== null && el.style.transparency !== undefined) textOptions.transparency = el.style.transparency; + + targetSlide.addText(el.text, textOptions); + } + } +} + +// Helper: Extract slide data from HTML page +async function extractSlideData(page) { + return await page.evaluate(() => { + const PT_PER_PX = 0.75; + const PX_PER_IN = 96; + + // Fonts that are single-weight and should not have bold applied + // (applying bold causes PowerPoint to use faux bold which makes text wider) + const SINGLE_WEIGHT_FONTS = ['impact']; + + // Helper: Check if a font should skip bold formatting + const shouldSkipBold = (fontFamily) => { + if (!fontFamily) return false; + const normalizedFont = fontFamily.toLowerCase().replace(/['"]/g, '').split(',')[0].trim(); + return SINGLE_WEIGHT_FONTS.includes(normalizedFont); + }; + + // Unit conversion helpers + const pxToInch = (px) => px / PX_PER_IN; + const pxToPoints = (pxStr) => parseFloat(pxStr) * PT_PER_PX; + const rgbToHex = (rgbStr) => { + // Handle transparent backgrounds by defaulting to white + if (rgbStr === 'rgba(0, 0, 0, 0)' || rgbStr === 'transparent') return 'FFFFFF'; + + const match = rgbStr.match(/rgba?\((\d+),\s*(\d+),\s*(\d+)/); + if (!match) return 'FFFFFF'; + return match.slice(1).map(n => parseInt(n).toString(16).padStart(2, '0')).join(''); + }; + + const extractAlpha = (rgbStr) => { + const match = rgbStr.match(/rgba\((\d+),\s*(\d+),\s*(\d+),\s*([\d.]+)\)/); + if (!match || !match[4]) return null; + const alpha = parseFloat(match[4]); + return Math.round((1 - alpha) * 100); + }; + + const applyTextTransform = (text, textTransform) => { + if (textTransform === 'uppercase') return text.toUpperCase(); + if (textTransform === 'lowercase') return text.toLowerCase(); + if (textTransform === 'capitalize') { + return text.replace(/\b\w/g, c => c.toUpperCase()); + } + return text; + }; + + // Extract rotation angle from CSS transform and writing-mode + const getRotation = (transform, writingMode) => { + let angle = 0; + + // Handle writing-mode first + // PowerPoint: 90° = text rotated 90° clockwise (reads top to bottom, letters upright) + // PowerPoint: 270° = text rotated 270° clockwise (reads bottom to top, letters upright) + if (writingMode === 'vertical-rl') { + // vertical-rl alone = text reads top to bottom = 90° in PowerPoint + angle = 90; + } else if (writingMode === 'vertical-lr') { + // vertical-lr alone = text reads bottom to top = 270° in PowerPoint + angle = 270; + } + + // Then add any transform rotation + if (transform && transform !== 'none') { + // Try to match rotate() function + const rotateMatch = transform.match(/rotate\((-?\d+(?:\.\d+)?)deg\)/); + if (rotateMatch) { + angle += parseFloat(rotateMatch[1]); + } else { + // Browser may compute as matrix - extract rotation from matrix + const matrixMatch = transform.match(/matrix\(([^)]+)\)/); + if (matrixMatch) { + const values = matrixMatch[1].split(',').map(parseFloat); + // matrix(a, b, c, d, e, f) where rotation = atan2(b, a) + const matrixAngle = Math.atan2(values[1], values[0]) * (180 / Math.PI); + angle += Math.round(matrixAngle); + } + } + } + + // Normalize to 0-359 range + angle = angle % 360; + if (angle < 0) angle += 360; + + return angle === 0 ? null : angle; + }; + + // Get position/dimensions accounting for rotation + const getPositionAndSize = (el, rect, rotation) => { + if (rotation === null) { + return { x: rect.left, y: rect.top, w: rect.width, h: rect.height }; + } + + // For 90° or 270° rotations, swap width and height + // because PowerPoint applies rotation to the original (unrotated) box + const isVertical = rotation === 90 || rotation === 270; + + if (isVertical) { + // The browser shows us the rotated dimensions (tall box for vertical text) + // But PowerPoint needs the pre-rotation dimensions (wide box that will be rotated) + // So we swap: browser's height becomes PPT's width, browser's width becomes PPT's height + const centerX = rect.left + rect.width / 2; + const centerY = rect.top + rect.height / 2; + + return { + x: centerX - rect.height / 2, + y: centerY - rect.width / 2, + w: rect.height, + h: rect.width + }; + } + + // For other rotations, use element's offset dimensions + const centerX = rect.left + rect.width / 2; + const centerY = rect.top + rect.height / 2; + return { + x: centerX - el.offsetWidth / 2, + y: centerY - el.offsetHeight / 2, + w: el.offsetWidth, + h: el.offsetHeight + }; + }; + + // Parse CSS box-shadow into PptxGenJS shadow properties + const parseBoxShadow = (boxShadow) => { + if (!boxShadow || boxShadow === 'none') return null; + + // Browser computed style format: "rgba(0, 0, 0, 0.3) 2px 2px 8px 0px [inset]" + // CSS format: "[inset] 2px 2px 8px 0px rgba(0, 0, 0, 0.3)" + + const insetMatch = boxShadow.match(/inset/); + + // IMPORTANT: PptxGenJS/PowerPoint doesn't properly support inset shadows + // Only process outer shadows to avoid file corruption + if (insetMatch) return null; + + // Extract color first (rgba or rgb at start) + const colorMatch = boxShadow.match(/rgba?\([^)]+\)/); + + // Extract numeric values (handles both px and pt units) + const parts = boxShadow.match(/([-\d.]+)(px|pt)/g); + + if (!parts || parts.length < 2) return null; + + const offsetX = parseFloat(parts[0]); + const offsetY = parseFloat(parts[1]); + const blur = parts.length > 2 ? parseFloat(parts[2]) : 0; + + // Calculate angle from offsets (in degrees, 0 = right, 90 = down) + let angle = 0; + if (offsetX !== 0 || offsetY !== 0) { + angle = Math.atan2(offsetY, offsetX) * (180 / Math.PI); + if (angle < 0) angle += 360; + } + + // Calculate offset distance (hypotenuse) + const offset = Math.sqrt(offsetX * offsetX + offsetY * offsetY) * PT_PER_PX; + + // Extract opacity from rgba + let opacity = 0.5; + if (colorMatch) { + const opacityMatch = colorMatch[0].match(/[\d.]+\)$/); + if (opacityMatch) { + opacity = parseFloat(opacityMatch[0].replace(')', '')); + } + } + + return { + type: 'outer', + angle: Math.round(angle), + blur: blur * 0.75, // Convert to points + color: colorMatch ? rgbToHex(colorMatch[0]) : '000000', + offset: offset, + opacity + }; + }; + + // Parse inline formatting tags (, , , , , ) into text runs + const parseInlineFormatting = (element, baseOptions = {}, runs = [], baseTextTransform = (x) => x) => { + let prevNodeIsText = false; + + element.childNodes.forEach((node) => { + let textTransform = baseTextTransform; + + const isText = node.nodeType === Node.TEXT_NODE || node.tagName === 'BR'; + if (isText) { + const text = node.tagName === 'BR' ? '\n' : textTransform(node.textContent.replace(/\s+/g, ' ')); + const prevRun = runs[runs.length - 1]; + if (prevNodeIsText && prevRun) { + prevRun.text += text; + } else { + runs.push({ text, options: { ...baseOptions } }); + } + + } else if (node.nodeType === Node.ELEMENT_NODE && node.textContent.trim()) { + const options = { ...baseOptions }; + const computed = window.getComputedStyle(node); + + // Handle inline elements with computed styles + if (node.tagName === 'SPAN' || node.tagName === 'B' || node.tagName === 'STRONG' || node.tagName === 'I' || node.tagName === 'EM' || node.tagName === 'U') { + const isBold = computed.fontWeight === 'bold' || parseInt(computed.fontWeight) >= 600; + if (isBold && !shouldSkipBold(computed.fontFamily)) options.bold = true; + if (computed.fontStyle === 'italic') options.italic = true; + if (computed.textDecoration && computed.textDecoration.includes('underline')) options.underline = true; + if (computed.color && computed.color !== 'rgb(0, 0, 0)') { + options.color = rgbToHex(computed.color); + const transparency = extractAlpha(computed.color); + if (transparency !== null) options.transparency = transparency; + } + if (computed.fontSize) options.fontSize = pxToPoints(computed.fontSize); + + // Apply text-transform on the span element itself + if (computed.textTransform && computed.textTransform !== 'none') { + const transformStr = computed.textTransform; + textTransform = (text) => applyTextTransform(text, transformStr); + } + + // Validate: Check for margins on inline elements + if (computed.marginLeft && parseFloat(computed.marginLeft) > 0) { + errors.push(`Inline element <${node.tagName.toLowerCase()}> has margin-left which is not supported in PowerPoint. Remove margin from inline elements.`); + } + if (computed.marginRight && parseFloat(computed.marginRight) > 0) { + errors.push(`Inline element <${node.tagName.toLowerCase()}> has margin-right which is not supported in PowerPoint. Remove margin from inline elements.`); + } + if (computed.marginTop && parseFloat(computed.marginTop) > 0) { + errors.push(`Inline element <${node.tagName.toLowerCase()}> has margin-top which is not supported in PowerPoint. Remove margin from inline elements.`); + } + if (computed.marginBottom && parseFloat(computed.marginBottom) > 0) { + errors.push(`Inline element <${node.tagName.toLowerCase()}> has margin-bottom which is not supported in PowerPoint. Remove margin from inline elements.`); + } + + // Recursively process the child node. This will flatten nested spans into multiple runs. + parseInlineFormatting(node, options, runs, textTransform); + } + } + + prevNodeIsText = isText; + }); + + // Trim leading space from first run and trailing space from last run + if (runs.length > 0) { + runs[0].text = runs[0].text.replace(/^\s+/, ''); + runs[runs.length - 1].text = runs[runs.length - 1].text.replace(/\s+$/, ''); + } + + return runs.filter(r => r.text.length > 0); + }; + + // Extract background from body (image or color) + const body = document.body; + const bodyStyle = window.getComputedStyle(body); + const bgImage = bodyStyle.backgroundImage; + const bgColor = bodyStyle.backgroundColor; + + // Collect validation errors + const errors = []; + + // Validate: Check for CSS gradients + if (bgImage && (bgImage.includes('linear-gradient') || bgImage.includes('radial-gradient'))) { + errors.push( + 'CSS gradients are not supported. Use Sharp to rasterize gradients as PNG images first, ' + + 'then reference with background-image: url(\'gradient.png\')' + ); + } + + let background; + if (bgImage && bgImage !== 'none') { + // Extract URL from url("...") or url(...) + const urlMatch = bgImage.match(/url\(["']?([^"')]+)["']?\)/); + if (urlMatch) { + background = { + type: 'image', + path: urlMatch[1] + }; + } else { + background = { + type: 'color', + value: rgbToHex(bgColor) + }; + } + } else { + background = { + type: 'color', + value: rgbToHex(bgColor) + }; + } + + // Process all elements + const elements = []; + const placeholders = []; + const textTags = ['P', 'H1', 'H2', 'H3', 'H4', 'H5', 'H6', 'UL', 'OL', 'LI']; + const processed = new Set(); + + document.querySelectorAll('*').forEach((el) => { + if (processed.has(el)) return; + + // Validate text elements don't have backgrounds, borders, or shadows + if (textTags.includes(el.tagName)) { + const computed = window.getComputedStyle(el); + const hasBg = computed.backgroundColor && computed.backgroundColor !== 'rgba(0, 0, 0, 0)'; + const hasBorder = (computed.borderWidth && parseFloat(computed.borderWidth) > 0) || + (computed.borderTopWidth && parseFloat(computed.borderTopWidth) > 0) || + (computed.borderRightWidth && parseFloat(computed.borderRightWidth) > 0) || + (computed.borderBottomWidth && parseFloat(computed.borderBottomWidth) > 0) || + (computed.borderLeftWidth && parseFloat(computed.borderLeftWidth) > 0); + const hasShadow = computed.boxShadow && computed.boxShadow !== 'none'; + + if (hasBg || hasBorder || hasShadow) { + errors.push( + `Text element <${el.tagName.toLowerCase()}> has ${hasBg ? 'background' : hasBorder ? 'border' : 'shadow'}. ` + + 'Backgrounds, borders, and shadows are only supported on
                      elements, not text elements.' + ); + return; + } + } + + // Extract placeholder elements (for charts, etc.) + if (el.className && el.className.includes('placeholder')) { + const rect = el.getBoundingClientRect(); + if (rect.width === 0 || rect.height === 0) { + errors.push( + `Placeholder "${el.id || 'unnamed'}" has ${rect.width === 0 ? 'width: 0' : 'height: 0'}. Check the layout CSS.` + ); + } else { + placeholders.push({ + id: el.id || `placeholder-${placeholders.length}`, + x: pxToInch(rect.left), + y: pxToInch(rect.top), + w: pxToInch(rect.width), + h: pxToInch(rect.height) + }); + } + processed.add(el); + return; + } + + // Extract images + if (el.tagName === 'IMG') { + const rect = el.getBoundingClientRect(); + if (rect.width > 0 && rect.height > 0) { + elements.push({ + type: 'image', + src: el.src, + position: { + x: pxToInch(rect.left), + y: pxToInch(rect.top), + w: pxToInch(rect.width), + h: pxToInch(rect.height) + } + }); + processed.add(el); + return; + } + } + + // Extract DIVs with backgrounds/borders as shapes + const isContainer = el.tagName === 'DIV' && !textTags.includes(el.tagName); + if (isContainer) { + const computed = window.getComputedStyle(el); + const hasBg = computed.backgroundColor && computed.backgroundColor !== 'rgba(0, 0, 0, 0)'; + + // Validate: Check for unwrapped text content in DIV + for (const node of el.childNodes) { + if (node.nodeType === Node.TEXT_NODE) { + const text = node.textContent.trim(); + if (text) { + errors.push( + `DIV element contains unwrapped text "${text.substring(0, 50)}${text.length > 50 ? '...' : ''}". ` + + 'All text must be wrapped in

                      ,

                      -

                      ,
                        , or
                          tags to appear in PowerPoint.' + ); + } + } + } + + // Check for background images on shapes + const bgImage = computed.backgroundImage; + if (bgImage && bgImage !== 'none') { + errors.push( + 'Background images on DIV elements are not supported. ' + + 'Use solid colors or borders for shapes, or use slide.addImage() in PptxGenJS to layer images.' + ); + return; + } + + // Check for borders - both uniform and partial + const borderTop = computed.borderTopWidth; + const borderRight = computed.borderRightWidth; + const borderBottom = computed.borderBottomWidth; + const borderLeft = computed.borderLeftWidth; + const borders = [borderTop, borderRight, borderBottom, borderLeft].map(b => parseFloat(b) || 0); + const hasBorder = borders.some(b => b > 0); + const hasUniformBorder = hasBorder && borders.every(b => b === borders[0]); + const borderLines = []; + + if (hasBorder && !hasUniformBorder) { + const rect = el.getBoundingClientRect(); + const x = pxToInch(rect.left); + const y = pxToInch(rect.top); + const w = pxToInch(rect.width); + const h = pxToInch(rect.height); + + // Collect lines to add after shape (inset by half the line width to center on edge) + if (parseFloat(borderTop) > 0) { + const widthPt = pxToPoints(borderTop); + const inset = (widthPt / 72) / 2; // Convert points to inches, then half + borderLines.push({ + type: 'line', + x1: x, y1: y + inset, x2: x + w, y2: y + inset, + width: widthPt, + color: rgbToHex(computed.borderTopColor) + }); + } + if (parseFloat(borderRight) > 0) { + const widthPt = pxToPoints(borderRight); + const inset = (widthPt / 72) / 2; + borderLines.push({ + type: 'line', + x1: x + w - inset, y1: y, x2: x + w - inset, y2: y + h, + width: widthPt, + color: rgbToHex(computed.borderRightColor) + }); + } + if (parseFloat(borderBottom) > 0) { + const widthPt = pxToPoints(borderBottom); + const inset = (widthPt / 72) / 2; + borderLines.push({ + type: 'line', + x1: x, y1: y + h - inset, x2: x + w, y2: y + h - inset, + width: widthPt, + color: rgbToHex(computed.borderBottomColor) + }); + } + if (parseFloat(borderLeft) > 0) { + const widthPt = pxToPoints(borderLeft); + const inset = (widthPt / 72) / 2; + borderLines.push({ + type: 'line', + x1: x + inset, y1: y, x2: x + inset, y2: y + h, + width: widthPt, + color: rgbToHex(computed.borderLeftColor) + }); + } + } + + if (hasBg || hasBorder) { + const rect = el.getBoundingClientRect(); + if (rect.width > 0 && rect.height > 0) { + const shadow = parseBoxShadow(computed.boxShadow); + + // Only add shape if there's background or uniform border + if (hasBg || hasUniformBorder) { + elements.push({ + type: 'shape', + text: '', // Shape only - child text elements render on top + position: { + x: pxToInch(rect.left), + y: pxToInch(rect.top), + w: pxToInch(rect.width), + h: pxToInch(rect.height) + }, + shape: { + fill: hasBg ? rgbToHex(computed.backgroundColor) : null, + transparency: hasBg ? extractAlpha(computed.backgroundColor) : null, + line: hasUniformBorder ? { + color: rgbToHex(computed.borderColor), + width: pxToPoints(computed.borderWidth) + } : null, + // Convert border-radius to rectRadius (in inches) + // % values: 50%+ = circle (1), <50% = percentage of min dimension + // pt values: divide by 72 (72pt = 1 inch) + // px values: divide by 96 (96px = 1 inch) + rectRadius: (() => { + const radius = computed.borderRadius; + const radiusValue = parseFloat(radius); + if (radiusValue === 0) return 0; + + if (radius.includes('%')) { + if (radiusValue >= 50) return 1; + // Calculate percentage of smaller dimension + const minDim = Math.min(rect.width, rect.height); + return (radiusValue / 100) * pxToInch(minDim); + } + + if (radius.includes('pt')) return radiusValue / 72; + return radiusValue / PX_PER_IN; + })(), + shadow: shadow + } + }); + } + + // Add partial border lines + elements.push(...borderLines); + + processed.add(el); + return; + } + } + } + + // Extract bullet lists as single text block + if (el.tagName === 'UL' || el.tagName === 'OL') { + const rect = el.getBoundingClientRect(); + if (rect.width === 0 || rect.height === 0) return; + + const liElements = Array.from(el.querySelectorAll('li')); + const items = []; + const ulComputed = window.getComputedStyle(el); + const ulPaddingLeftPt = pxToPoints(ulComputed.paddingLeft); + + // Split: margin-left for bullet position, indent for text position + // margin-left + indent = ul padding-left + const marginLeft = ulPaddingLeftPt * 0.5; + const textIndent = ulPaddingLeftPt * 0.5; + + liElements.forEach((li, idx) => { + const isLast = idx === liElements.length - 1; + const runs = parseInlineFormatting(li, { breakLine: false }); + // Clean manual bullets from first run + if (runs.length > 0) { + runs[0].text = runs[0].text.replace(/^[•\-\*▪▸]\s*/, ''); + runs[0].options.bullet = { indent: textIndent }; + } + // Set breakLine on last run + if (runs.length > 0 && !isLast) { + runs[runs.length - 1].options.breakLine = true; + } + items.push(...runs); + }); + + const computed = window.getComputedStyle(liElements[0] || el); + + elements.push({ + type: 'list', + items: items, + position: { + x: pxToInch(rect.left), + y: pxToInch(rect.top), + w: pxToInch(rect.width), + h: pxToInch(rect.height) + }, + style: { + fontSize: pxToPoints(computed.fontSize), + fontFace: computed.fontFamily.split(',')[0].replace(/['"]/g, '').trim(), + color: rgbToHex(computed.color), + transparency: extractAlpha(computed.color), + align: computed.textAlign === 'start' ? 'left' : computed.textAlign, + lineSpacing: computed.lineHeight && computed.lineHeight !== 'normal' ? pxToPoints(computed.lineHeight) : null, + paraSpaceBefore: 0, + paraSpaceAfter: pxToPoints(computed.marginBottom), + // PptxGenJS margin array is [left, right, bottom, top] + margin: [marginLeft, 0, 0, 0] + } + }); + + liElements.forEach(li => processed.add(li)); + processed.add(el); + return; + } + + // Extract text elements (P, H1, H2, etc.) + if (!textTags.includes(el.tagName)) return; + + const rect = el.getBoundingClientRect(); + const text = el.textContent.trim(); + if (rect.width === 0 || rect.height === 0 || !text) return; + + // Validate: Check for manual bullet symbols in text elements (not in lists) + if (el.tagName !== 'LI' && /^[•\-\*▪▸○●◆◇■□]\s/.test(text.trimStart())) { + errors.push( + `Text element <${el.tagName.toLowerCase()}> starts with bullet symbol "${text.substring(0, 20)}...". ` + + 'Use
                            or
                              lists instead of manual bullet symbols.' + ); + return; + } + + const computed = window.getComputedStyle(el); + const rotation = getRotation(computed.transform, computed.writingMode); + const { x, y, w, h } = getPositionAndSize(el, rect, rotation); + + const baseStyle = { + fontSize: pxToPoints(computed.fontSize), + fontFace: computed.fontFamily.split(',')[0].replace(/['"]/g, '').trim(), + color: rgbToHex(computed.color), + align: computed.textAlign === 'start' ? 'left' : computed.textAlign, + lineSpacing: pxToPoints(computed.lineHeight), + paraSpaceBefore: pxToPoints(computed.marginTop), + paraSpaceAfter: pxToPoints(computed.marginBottom), + // PptxGenJS margin array is [left, right, bottom, top] (not [top, right, bottom, left] as documented) + margin: [ + pxToPoints(computed.paddingLeft), + pxToPoints(computed.paddingRight), + pxToPoints(computed.paddingBottom), + pxToPoints(computed.paddingTop) + ] + }; + + const transparency = extractAlpha(computed.color); + if (transparency !== null) baseStyle.transparency = transparency; + + if (rotation !== null) baseStyle.rotate = rotation; + + const hasFormatting = el.querySelector('b, i, u, strong, em, span, br'); + + if (hasFormatting) { + // Text with inline formatting + const transformStr = computed.textTransform; + const runs = parseInlineFormatting(el, {}, [], (str) => applyTextTransform(str, transformStr)); + + // Adjust lineSpacing based on largest fontSize in runs + const adjustedStyle = { ...baseStyle }; + if (adjustedStyle.lineSpacing) { + const maxFontSize = Math.max( + adjustedStyle.fontSize, + ...runs.map(r => r.options?.fontSize || 0) + ); + if (maxFontSize > adjustedStyle.fontSize) { + const lineHeightMultiplier = adjustedStyle.lineSpacing / adjustedStyle.fontSize; + adjustedStyle.lineSpacing = maxFontSize * lineHeightMultiplier; + } + } + + elements.push({ + type: el.tagName.toLowerCase(), + text: runs, + position: { x: pxToInch(x), y: pxToInch(y), w: pxToInch(w), h: pxToInch(h) }, + style: adjustedStyle + }); + } else { + // Plain text - inherit CSS formatting + const textTransform = computed.textTransform; + const transformedText = applyTextTransform(text, textTransform); + + const isBold = computed.fontWeight === 'bold' || parseInt(computed.fontWeight) >= 600; + + elements.push({ + type: el.tagName.toLowerCase(), + text: transformedText, + position: { x: pxToInch(x), y: pxToInch(y), w: pxToInch(w), h: pxToInch(h) }, + style: { + ...baseStyle, + bold: isBold && !shouldSkipBold(computed.fontFamily), + italic: computed.fontStyle === 'italic', + underline: computed.textDecoration.includes('underline') + } + }); + } + + processed.add(el); + }); + + return { background, elements, placeholders, errors }; + }); +} + +async function html2pptx(htmlFile, pres, options = {}) { + const { + tmpDir = process.env.TMPDIR || '/tmp', + slide = null + } = options; + + try { + // Use Chrome on macOS, default Chromium on Unix + const launchOptions = { env: { TMPDIR: tmpDir } }; + if (process.platform === 'darwin') { + launchOptions.channel = 'chrome'; + } + + const browser = await chromium.launch(launchOptions); + + let bodyDimensions; + let slideData; + + const filePath = path.isAbsolute(htmlFile) ? htmlFile : path.join(process.cwd(), htmlFile); + const validationErrors = []; + + try { + const page = await browser.newPage(); + page.on('console', (msg) => { + // Log the message text to your test runner's console + console.log(`Browser console: ${msg.text()}`); + }); + + await page.goto(`file://${filePath}`); + + bodyDimensions = await getBodyDimensions(page); + + await page.setViewportSize({ + width: Math.round(bodyDimensions.width), + height: Math.round(bodyDimensions.height) + }); + + slideData = await extractSlideData(page); + } finally { + await browser.close(); + } + + // Collect all validation errors + if (bodyDimensions.errors && bodyDimensions.errors.length > 0) { + validationErrors.push(...bodyDimensions.errors); + } + + const dimensionErrors = validateDimensions(bodyDimensions, pres); + if (dimensionErrors.length > 0) { + validationErrors.push(...dimensionErrors); + } + + const textBoxPositionErrors = validateTextBoxPosition(slideData, bodyDimensions); + if (textBoxPositionErrors.length > 0) { + validationErrors.push(...textBoxPositionErrors); + } + + if (slideData.errors && slideData.errors.length > 0) { + validationErrors.push(...slideData.errors); + } + + // Throw all errors at once if any exist + if (validationErrors.length > 0) { + const errorMessage = validationErrors.length === 1 + ? validationErrors[0] + : `Multiple validation errors found:\n${validationErrors.map((e, i) => ` ${i + 1}. ${e}`).join('\n')}`; + throw new Error(errorMessage); + } + + const targetSlide = slide || pres.addSlide(); + + await addBackground(slideData, targetSlide, tmpDir); + addElements(slideData, targetSlide, pres); + + return { slide: targetSlide, placeholders: slideData.placeholders }; + } catch (error) { + if (!error.message.startsWith(htmlFile)) { + throw new Error(`${htmlFile}: ${error.message}`); + } + throw error; + } +} + +module.exports = html2pptx; \ No newline at end of file diff --git a/skills/pptx/scripts/inventory.py b/skills/pptx/scripts/inventory.py new file mode 100755 index 0000000..edda390 --- /dev/null +++ b/skills/pptx/scripts/inventory.py @@ -0,0 +1,1020 @@ +#!/usr/bin/env python3 +""" +Extract structured text content from PowerPoint presentations. + +This module provides functionality to: +- Extract all text content from PowerPoint shapes +- Preserve paragraph formatting (alignment, bullets, fonts, spacing) +- Handle nested GroupShapes recursively with correct absolute positions +- Sort shapes by visual position on slides +- Filter out slide numbers and non-content placeholders +- Export to JSON with clean, structured data + +Classes: + ParagraphData: Represents a text paragraph with formatting + ShapeData: Represents a shape with position and text content + +Main Functions: + extract_text_inventory: Extract all text from a presentation + save_inventory: Save extracted data to JSON + +Usage: + python inventory.py input.pptx output.json +""" + +import argparse +import json +import platform +import sys +from dataclasses import dataclass +from pathlib import Path +from typing import Any, Dict, List, Optional, Tuple, Union + +from PIL import Image, ImageDraw, ImageFont +from pptx import Presentation +from pptx.enum.text import PP_ALIGN +from pptx.shapes.base import BaseShape + +# Type aliases for cleaner signatures +JsonValue = Union[str, int, float, bool, None] +ParagraphDict = Dict[str, JsonValue] +ShapeDict = Dict[ + str, Union[str, float, bool, List[ParagraphDict], List[str], Dict[str, Any], None] +] +InventoryData = Dict[ + str, Dict[str, "ShapeData"] +] # Dict of slide_id -> {shape_id -> ShapeData} +InventoryDict = Dict[str, Dict[str, ShapeDict]] # JSON-serializable inventory + + +def main(): + """Main entry point for command-line usage.""" + parser = argparse.ArgumentParser( + description="Extract text inventory from PowerPoint with proper GroupShape support.", + formatter_class=argparse.RawDescriptionHelpFormatter, + epilog=""" +Examples: + python inventory.py presentation.pptx inventory.json + Extracts text inventory with correct absolute positions for grouped shapes + + python inventory.py presentation.pptx inventory.json --issues-only + Extracts only text shapes that have overflow or overlap issues + +The output JSON includes: + - All text content organized by slide and shape + - Correct absolute positions for shapes in groups + - Visual position and size in inches + - Paragraph properties and formatting + - Issue detection: text overflow and shape overlaps + """, + ) + + parser.add_argument("input", help="Input PowerPoint file (.pptx)") + parser.add_argument("output", help="Output JSON file for inventory") + parser.add_argument( + "--issues-only", + action="store_true", + help="Include only text shapes that have overflow or overlap issues", + ) + + args = parser.parse_args() + + input_path = Path(args.input) + if not input_path.exists(): + print(f"Error: Input file not found: {args.input}") + sys.exit(1) + + if not input_path.suffix.lower() == ".pptx": + print("Error: Input must be a PowerPoint file (.pptx)") + sys.exit(1) + + try: + print(f"Extracting text inventory from: {args.input}") + if args.issues_only: + print( + "Filtering to include only text shapes with issues (overflow/overlap)" + ) + inventory = extract_text_inventory(input_path, issues_only=args.issues_only) + + output_path = Path(args.output) + output_path.parent.mkdir(parents=True, exist_ok=True) + save_inventory(inventory, output_path) + + print(f"Output saved to: {args.output}") + + # Report statistics + total_slides = len(inventory) + total_shapes = sum(len(shapes) for shapes in inventory.values()) + if args.issues_only: + if total_shapes > 0: + print( + f"Found {total_shapes} text elements with issues in {total_slides} slides" + ) + else: + print("No issues discovered") + else: + print( + f"Found text in {total_slides} slides with {total_shapes} text elements" + ) + + except Exception as e: + print(f"Error processing presentation: {e}") + import traceback + + traceback.print_exc() + sys.exit(1) + + +@dataclass +class ShapeWithPosition: + """A shape with its absolute position on the slide.""" + + shape: BaseShape + absolute_left: int # in EMUs + absolute_top: int # in EMUs + + +class ParagraphData: + """Data structure for paragraph properties extracted from a PowerPoint paragraph.""" + + def __init__(self, paragraph: Any): + """Initialize from a PowerPoint paragraph object. + + Args: + paragraph: The PowerPoint paragraph object + """ + self.text: str = paragraph.text.strip() + self.bullet: bool = False + self.level: Optional[int] = None + self.alignment: Optional[str] = None + self.space_before: Optional[float] = None + self.space_after: Optional[float] = None + self.font_name: Optional[str] = None + self.font_size: Optional[float] = None + self.bold: Optional[bool] = None + self.italic: Optional[bool] = None + self.underline: Optional[bool] = None + self.color: Optional[str] = None + self.theme_color: Optional[str] = None + self.line_spacing: Optional[float] = None + + # Check for bullet formatting + if ( + hasattr(paragraph, "_p") + and paragraph._p is not None + and paragraph._p.pPr is not None + ): + pPr = paragraph._p.pPr + ns = "{http://schemas.openxmlformats.org/drawingml/2006/main}" + if ( + pPr.find(f"{ns}buChar") is not None + or pPr.find(f"{ns}buAutoNum") is not None + ): + self.bullet = True + if hasattr(paragraph, "level"): + self.level = paragraph.level + + # Add alignment if not LEFT (default) + if hasattr(paragraph, "alignment") and paragraph.alignment is not None: + alignment_map = { + PP_ALIGN.CENTER: "CENTER", + PP_ALIGN.RIGHT: "RIGHT", + PP_ALIGN.JUSTIFY: "JUSTIFY", + } + if paragraph.alignment in alignment_map: + self.alignment = alignment_map[paragraph.alignment] + + # Add spacing properties if set + if hasattr(paragraph, "space_before") and paragraph.space_before: + self.space_before = paragraph.space_before.pt + if hasattr(paragraph, "space_after") and paragraph.space_after: + self.space_after = paragraph.space_after.pt + + # Extract font properties from first run + if paragraph.runs: + first_run = paragraph.runs[0] + if hasattr(first_run, "font"): + font = first_run.font + if font.name: + self.font_name = font.name + if font.size: + self.font_size = font.size.pt + if font.bold is not None: + self.bold = font.bold + if font.italic is not None: + self.italic = font.italic + if font.underline is not None: + self.underline = font.underline + + # Handle color - both RGB and theme colors + try: + # Try RGB color first + if font.color.rgb: + self.color = str(font.color.rgb) + except (AttributeError, TypeError): + # Fall back to theme color + try: + if font.color.theme_color: + self.theme_color = font.color.theme_color.name + except (AttributeError, TypeError): + pass + + # Add line spacing if set + if hasattr(paragraph, "line_spacing") and paragraph.line_spacing is not None: + if hasattr(paragraph.line_spacing, "pt"): + self.line_spacing = round(paragraph.line_spacing.pt, 2) + else: + # Multiplier - convert to points + font_size = self.font_size if self.font_size else 12.0 + self.line_spacing = round(paragraph.line_spacing * font_size, 2) + + def to_dict(self) -> ParagraphDict: + """Convert to dictionary for JSON serialization, excluding None values.""" + result: ParagraphDict = {"text": self.text} + + # Add optional fields only if they have values + if self.bullet: + result["bullet"] = self.bullet + if self.level is not None: + result["level"] = self.level + if self.alignment: + result["alignment"] = self.alignment + if self.space_before is not None: + result["space_before"] = self.space_before + if self.space_after is not None: + result["space_after"] = self.space_after + if self.font_name: + result["font_name"] = self.font_name + if self.font_size is not None: + result["font_size"] = self.font_size + if self.bold is not None: + result["bold"] = self.bold + if self.italic is not None: + result["italic"] = self.italic + if self.underline is not None: + result["underline"] = self.underline + if self.color: + result["color"] = self.color + if self.theme_color: + result["theme_color"] = self.theme_color + if self.line_spacing is not None: + result["line_spacing"] = self.line_spacing + + return result + + +class ShapeData: + """Data structure for shape properties extracted from a PowerPoint shape.""" + + @staticmethod + def emu_to_inches(emu: int) -> float: + """Convert EMUs (English Metric Units) to inches.""" + return emu / 914400.0 + + @staticmethod + def inches_to_pixels(inches: float, dpi: int = 96) -> int: + """Convert inches to pixels at given DPI.""" + return int(inches * dpi) + + @staticmethod + def get_font_path(font_name: str) -> Optional[str]: + """Get the font file path for a given font name. + + Args: + font_name: Name of the font (e.g., 'Arial', 'Calibri') + + Returns: + Path to the font file, or None if not found + """ + system = platform.system() + + # Common font file variations to try + font_variations = [ + font_name, + font_name.lower(), + font_name.replace(" ", ""), + font_name.replace(" ", "-"), + ] + + # Define font directories and extensions by platform + if system == "Darwin": # macOS + font_dirs = [ + "/System/Library/Fonts/", + "/Library/Fonts/", + "~/Library/Fonts/", + ] + extensions = [".ttf", ".otf", ".ttc", ".dfont"] + else: # Linux + font_dirs = [ + "/usr/share/fonts/truetype/", + "/usr/local/share/fonts/", + "~/.fonts/", + ] + extensions = [".ttf", ".otf"] + + # Try to find the font file + from pathlib import Path + + for font_dir in font_dirs: + font_dir_path = Path(font_dir).expanduser() + if not font_dir_path.exists(): + continue + + # First try exact matches + for variant in font_variations: + for ext in extensions: + font_path = font_dir_path / f"{variant}{ext}" + if font_path.exists(): + return str(font_path) + + # Then try fuzzy matching - find files containing the font name + try: + for file_path in font_dir_path.iterdir(): + if file_path.is_file(): + file_name_lower = file_path.name.lower() + font_name_lower = font_name.lower().replace(" ", "") + if font_name_lower in file_name_lower and any( + file_name_lower.endswith(ext) for ext in extensions + ): + return str(file_path) + except (OSError, PermissionError): + continue + + return None + + @staticmethod + def get_slide_dimensions(slide: Any) -> tuple[Optional[int], Optional[int]]: + """Get slide dimensions from slide object. + + Args: + slide: Slide object + + Returns: + Tuple of (width_emu, height_emu) or (None, None) if not found + """ + try: + prs = slide.part.package.presentation_part.presentation + return prs.slide_width, prs.slide_height + except (AttributeError, TypeError): + return None, None + + @staticmethod + def get_default_font_size(shape: BaseShape, slide_layout: Any) -> Optional[float]: + """Extract default font size from slide layout for a placeholder shape. + + Args: + shape: Placeholder shape + slide_layout: Slide layout containing the placeholder definition + + Returns: + Default font size in points, or None if not found + """ + try: + if not hasattr(shape, "placeholder_format"): + return None + + shape_type = shape.placeholder_format.type # type: ignore + for layout_placeholder in slide_layout.placeholders: + if layout_placeholder.placeholder_format.type == shape_type: + # Find first defRPr element with sz (size) attribute + for elem in layout_placeholder.element.iter(): + if "defRPr" in elem.tag and (sz := elem.get("sz")): + return float(sz) / 100.0 # Convert EMUs to points + break + except Exception: + pass + return None + + def __init__( + self, + shape: BaseShape, + absolute_left: Optional[int] = None, + absolute_top: Optional[int] = None, + slide: Optional[Any] = None, + ): + """Initialize from a PowerPoint shape object. + + Args: + shape: The PowerPoint shape object (should be pre-validated) + absolute_left: Absolute left position in EMUs (for shapes in groups) + absolute_top: Absolute top position in EMUs (for shapes in groups) + slide: Optional slide object to get dimensions and layout information + """ + self.shape = shape # Store reference to original shape + self.shape_id: str = "" # Will be set after sorting + + # Get slide dimensions from slide object + self.slide_width_emu, self.slide_height_emu = ( + self.get_slide_dimensions(slide) if slide else (None, None) + ) + + # Get placeholder type if applicable + self.placeholder_type: Optional[str] = None + self.default_font_size: Optional[float] = None + if hasattr(shape, "is_placeholder") and shape.is_placeholder: # type: ignore + if shape.placeholder_format and shape.placeholder_format.type: # type: ignore + self.placeholder_type = ( + str(shape.placeholder_format.type).split(".")[-1].split(" ")[0] # type: ignore + ) + + # Get default font size from layout + if slide and hasattr(slide, "slide_layout"): + self.default_font_size = self.get_default_font_size( + shape, slide.slide_layout + ) + + # Get position information + # Use absolute positions if provided (for shapes in groups), otherwise use shape's position + left_emu = ( + absolute_left + if absolute_left is not None + else (shape.left if hasattr(shape, "left") else 0) + ) + top_emu = ( + absolute_top + if absolute_top is not None + else (shape.top if hasattr(shape, "top") else 0) + ) + + self.left: float = round(self.emu_to_inches(left_emu), 2) # type: ignore + self.top: float = round(self.emu_to_inches(top_emu), 2) # type: ignore + self.width: float = round( + self.emu_to_inches(shape.width if hasattr(shape, "width") else 0), + 2, # type: ignore + ) + self.height: float = round( + self.emu_to_inches(shape.height if hasattr(shape, "height") else 0), + 2, # type: ignore + ) + + # Store EMU positions for overflow calculations + self.left_emu = left_emu + self.top_emu = top_emu + self.width_emu = shape.width if hasattr(shape, "width") else 0 + self.height_emu = shape.height if hasattr(shape, "height") else 0 + + # Calculate overflow status + self.frame_overflow_bottom: Optional[float] = None + self.slide_overflow_right: Optional[float] = None + self.slide_overflow_bottom: Optional[float] = None + self.overlapping_shapes: Dict[ + str, float + ] = {} # Dict of shape_id -> overlap area in sq inches + self.warnings: List[str] = [] + self._estimate_frame_overflow() + self._calculate_slide_overflow() + self._detect_bullet_issues() + + @property + def paragraphs(self) -> List[ParagraphData]: + """Calculate paragraphs from the shape's text frame.""" + if not self.shape or not hasattr(self.shape, "text_frame"): + return [] + + paragraphs = [] + for paragraph in self.shape.text_frame.paragraphs: # type: ignore + if paragraph.text.strip(): + paragraphs.append(ParagraphData(paragraph)) + return paragraphs + + def _get_default_font_size(self) -> int: + """Get default font size from theme text styles or use conservative default.""" + try: + if not ( + hasattr(self.shape, "part") and hasattr(self.shape.part, "slide_layout") + ): + return 14 + + slide_master = self.shape.part.slide_layout.slide_master # type: ignore + if not hasattr(slide_master, "element"): + return 14 + + # Determine theme style based on placeholder type + style_name = "bodyStyle" # Default + if self.placeholder_type and "TITLE" in self.placeholder_type: + style_name = "titleStyle" + + # Find font size in theme styles + for child in slide_master.element.iter(): + tag = child.tag.split("}")[-1] if "}" in child.tag else child.tag + if tag == style_name: + for elem in child.iter(): + if "sz" in elem.attrib: + return int(elem.attrib["sz"]) // 100 + except Exception: + pass + + return 14 # Conservative default for body text + + def _get_usable_dimensions(self, text_frame) -> Tuple[int, int]: + """Get usable width and height in pixels after accounting for margins.""" + # Default PowerPoint margins in inches + margins = {"top": 0.05, "bottom": 0.05, "left": 0.1, "right": 0.1} + + # Override with actual margins if set + if hasattr(text_frame, "margin_top") and text_frame.margin_top: + margins["top"] = self.emu_to_inches(text_frame.margin_top) + if hasattr(text_frame, "margin_bottom") and text_frame.margin_bottom: + margins["bottom"] = self.emu_to_inches(text_frame.margin_bottom) + if hasattr(text_frame, "margin_left") and text_frame.margin_left: + margins["left"] = self.emu_to_inches(text_frame.margin_left) + if hasattr(text_frame, "margin_right") and text_frame.margin_right: + margins["right"] = self.emu_to_inches(text_frame.margin_right) + + # Calculate usable area + usable_width = self.width - margins["left"] - margins["right"] + usable_height = self.height - margins["top"] - margins["bottom"] + + # Convert to pixels + return ( + self.inches_to_pixels(usable_width), + self.inches_to_pixels(usable_height), + ) + + def _wrap_text_line(self, line: str, max_width_px: int, draw, font) -> List[str]: + """Wrap a single line of text to fit within max_width_px.""" + if not line: + return [""] + + # Use textlength for efficient width calculation + if draw.textlength(line, font=font) <= max_width_px: + return [line] + + # Need to wrap - split into words + wrapped = [] + words = line.split(" ") + current_line = "" + + for word in words: + test_line = current_line + (" " if current_line else "") + word + if draw.textlength(test_line, font=font) <= max_width_px: + current_line = test_line + else: + if current_line: + wrapped.append(current_line) + current_line = word + + if current_line: + wrapped.append(current_line) + + return wrapped + + def _estimate_frame_overflow(self) -> None: + """Estimate if text overflows the shape bounds using PIL text measurement.""" + if not self.shape or not hasattr(self.shape, "text_frame"): + return + + text_frame = self.shape.text_frame # type: ignore + if not text_frame or not text_frame.paragraphs: + return + + # Get usable dimensions after accounting for margins + usable_width_px, usable_height_px = self._get_usable_dimensions(text_frame) + if usable_width_px <= 0 or usable_height_px <= 0: + return + + # Set up PIL for text measurement + dummy_img = Image.new("RGB", (1, 1)) + draw = ImageDraw.Draw(dummy_img) + + # Get default font size from placeholder or use conservative estimate + default_font_size = self._get_default_font_size() + + # Calculate total height of all paragraphs + total_height_px = 0 + + for para_idx, paragraph in enumerate(text_frame.paragraphs): + if not paragraph.text.strip(): + continue + + para_data = ParagraphData(paragraph) + + # Load font for this paragraph + font_name = para_data.font_name or "Arial" + font_size = int(para_data.font_size or default_font_size) + + font = None + font_path = self.get_font_path(font_name) + if font_path: + try: + font = ImageFont.truetype(font_path, size=font_size) + except Exception: + font = ImageFont.load_default() + else: + font = ImageFont.load_default() + + # Wrap all lines in this paragraph + all_wrapped_lines = [] + for line in paragraph.text.split("\n"): + wrapped = self._wrap_text_line(line, usable_width_px, draw, font) + all_wrapped_lines.extend(wrapped) + + if all_wrapped_lines: + # Calculate line height + if para_data.line_spacing: + # Custom line spacing explicitly set + line_height_px = para_data.line_spacing * 96 / 72 + else: + # PowerPoint default single spacing (1.0x font size) + line_height_px = font_size * 96 / 72 + + # Add space_before (except first paragraph) + if para_idx > 0 and para_data.space_before: + total_height_px += para_data.space_before * 96 / 72 + + # Add paragraph text height + total_height_px += len(all_wrapped_lines) * line_height_px + + # Add space_after + if para_data.space_after: + total_height_px += para_data.space_after * 96 / 72 + + # Check for overflow (ignore negligible overflows <= 0.05") + if total_height_px > usable_height_px: + overflow_px = total_height_px - usable_height_px + overflow_inches = round(overflow_px / 96.0, 2) + if overflow_inches > 0.05: # Only report significant overflows + self.frame_overflow_bottom = overflow_inches + + def _calculate_slide_overflow(self) -> None: + """Calculate if shape overflows the slide boundaries.""" + if self.slide_width_emu is None or self.slide_height_emu is None: + return + + # Check right overflow (ignore negligible overflows <= 0.01") + right_edge_emu = self.left_emu + self.width_emu + if right_edge_emu > self.slide_width_emu: + overflow_emu = right_edge_emu - self.slide_width_emu + overflow_inches = round(self.emu_to_inches(overflow_emu), 2) + if overflow_inches > 0.01: # Only report significant overflows + self.slide_overflow_right = overflow_inches + + # Check bottom overflow (ignore negligible overflows <= 0.01") + bottom_edge_emu = self.top_emu + self.height_emu + if bottom_edge_emu > self.slide_height_emu: + overflow_emu = bottom_edge_emu - self.slide_height_emu + overflow_inches = round(self.emu_to_inches(overflow_emu), 2) + if overflow_inches > 0.01: # Only report significant overflows + self.slide_overflow_bottom = overflow_inches + + def _detect_bullet_issues(self) -> None: + """Detect bullet point formatting issues in paragraphs.""" + if not self.shape or not hasattr(self.shape, "text_frame"): + return + + text_frame = self.shape.text_frame # type: ignore + if not text_frame or not text_frame.paragraphs: + return + + # Common bullet symbols that indicate manual bullets + bullet_symbols = ["•", "●", "○"] + + for paragraph in text_frame.paragraphs: + text = paragraph.text.strip() + # Check for manual bullet symbols + if text and any(text.startswith(symbol + " ") for symbol in bullet_symbols): + self.warnings.append( + "manual_bullet_symbol: use proper bullet formatting" + ) + break + + @property + def has_any_issues(self) -> bool: + """Check if shape has any issues (overflow, overlap, or warnings).""" + return ( + self.frame_overflow_bottom is not None + or self.slide_overflow_right is not None + or self.slide_overflow_bottom is not None + or len(self.overlapping_shapes) > 0 + or len(self.warnings) > 0 + ) + + def to_dict(self) -> ShapeDict: + """Convert to dictionary for JSON serialization.""" + result: ShapeDict = { + "left": self.left, + "top": self.top, + "width": self.width, + "height": self.height, + } + + # Add optional fields if present + if self.placeholder_type: + result["placeholder_type"] = self.placeholder_type + + if self.default_font_size: + result["default_font_size"] = self.default_font_size + + # Add overflow information only if there is overflow + overflow_data = {} + + # Add frame overflow if present + if self.frame_overflow_bottom is not None: + overflow_data["frame"] = {"overflow_bottom": self.frame_overflow_bottom} + + # Add slide overflow if present + slide_overflow = {} + if self.slide_overflow_right is not None: + slide_overflow["overflow_right"] = self.slide_overflow_right + if self.slide_overflow_bottom is not None: + slide_overflow["overflow_bottom"] = self.slide_overflow_bottom + if slide_overflow: + overflow_data["slide"] = slide_overflow + + # Only add overflow field if there is overflow + if overflow_data: + result["overflow"] = overflow_data + + # Add overlap field if there are overlapping shapes + if self.overlapping_shapes: + result["overlap"] = {"overlapping_shapes": self.overlapping_shapes} + + # Add warnings field if there are warnings + if self.warnings: + result["warnings"] = self.warnings + + # Add paragraphs after placeholder_type + result["paragraphs"] = [para.to_dict() for para in self.paragraphs] + + return result + + +def is_valid_shape(shape: BaseShape) -> bool: + """Check if a shape contains meaningful text content.""" + # Must have a text frame with content + if not hasattr(shape, "text_frame") or not shape.text_frame: # type: ignore + return False + + text = shape.text_frame.text.strip() # type: ignore + if not text: + return False + + # Skip slide numbers and numeric footers + if hasattr(shape, "is_placeholder") and shape.is_placeholder: # type: ignore + if shape.placeholder_format and shape.placeholder_format.type: # type: ignore + placeholder_type = ( + str(shape.placeholder_format.type).split(".")[-1].split(" ")[0] # type: ignore + ) + if placeholder_type == "SLIDE_NUMBER": + return False + if placeholder_type == "FOOTER" and text.isdigit(): + return False + + return True + + +def collect_shapes_with_absolute_positions( + shape: BaseShape, parent_left: int = 0, parent_top: int = 0 +) -> List[ShapeWithPosition]: + """Recursively collect all shapes with valid text, calculating absolute positions. + + For shapes within groups, their positions are relative to the group. + This function calculates the absolute position on the slide by accumulating + parent group offsets. + + Args: + shape: The shape to process + parent_left: Accumulated left offset from parent groups (in EMUs) + parent_top: Accumulated top offset from parent groups (in EMUs) + + Returns: + List of ShapeWithPosition objects with absolute positions + """ + if hasattr(shape, "shapes"): # GroupShape + result = [] + # Get this group's position + group_left = shape.left if hasattr(shape, "left") else 0 + group_top = shape.top if hasattr(shape, "top") else 0 + + # Calculate absolute position for this group + abs_group_left = parent_left + group_left + abs_group_top = parent_top + group_top + + # Process children with accumulated offsets + for child in shape.shapes: # type: ignore + result.extend( + collect_shapes_with_absolute_positions( + child, abs_group_left, abs_group_top + ) + ) + return result + + # Regular shape - check if it has valid text + if is_valid_shape(shape): + # Calculate absolute position + shape_left = shape.left if hasattr(shape, "left") else 0 + shape_top = shape.top if hasattr(shape, "top") else 0 + + return [ + ShapeWithPosition( + shape=shape, + absolute_left=parent_left + shape_left, + absolute_top=parent_top + shape_top, + ) + ] + + return [] + + +def sort_shapes_by_position(shapes: List[ShapeData]) -> List[ShapeData]: + """Sort shapes by visual position (top-to-bottom, left-to-right). + + Shapes within 0.5 inches vertically are considered on the same row. + """ + if not shapes: + return shapes + + # Sort by top position first + shapes = sorted(shapes, key=lambda s: (s.top, s.left)) + + # Group shapes by row (within 0.5 inches vertically) + result = [] + row = [shapes[0]] + row_top = shapes[0].top + + for shape in shapes[1:]: + if abs(shape.top - row_top) <= 0.5: + row.append(shape) + else: + # Sort current row by left position and add to result + result.extend(sorted(row, key=lambda s: s.left)) + row = [shape] + row_top = shape.top + + # Don't forget the last row + result.extend(sorted(row, key=lambda s: s.left)) + return result + + +def calculate_overlap( + rect1: Tuple[float, float, float, float], + rect2: Tuple[float, float, float, float], + tolerance: float = 0.05, +) -> Tuple[bool, float]: + """Calculate if and how much two rectangles overlap. + + Args: + rect1: (left, top, width, height) of first rectangle in inches + rect2: (left, top, width, height) of second rectangle in inches + tolerance: Minimum overlap in inches to consider as overlapping (default: 0.05") + + Returns: + Tuple of (overlaps, overlap_area) where: + - overlaps: True if rectangles overlap by more than tolerance + - overlap_area: Area of overlap in square inches + """ + left1, top1, w1, h1 = rect1 + left2, top2, w2, h2 = rect2 + + # Calculate overlap dimensions + overlap_width = min(left1 + w1, left2 + w2) - max(left1, left2) + overlap_height = min(top1 + h1, top2 + h2) - max(top1, top2) + + # Check if there's meaningful overlap (more than tolerance) + if overlap_width > tolerance and overlap_height > tolerance: + # Calculate overlap area in square inches + overlap_area = overlap_width * overlap_height + return True, round(overlap_area, 2) + + return False, 0 + + +def detect_overlaps(shapes: List[ShapeData]) -> None: + """Detect overlapping shapes and update their overlapping_shapes dictionaries. + + This function requires each ShapeData to have its shape_id already set. + It modifies the shapes in-place, adding shape IDs with overlap areas in square inches. + + Args: + shapes: List of ShapeData objects with shape_id attributes set + """ + n = len(shapes) + + # Compare each pair of shapes + for i in range(n): + for j in range(i + 1, n): + shape1 = shapes[i] + shape2 = shapes[j] + + # Ensure shape IDs are set + assert shape1.shape_id, f"Shape at index {i} has no shape_id" + assert shape2.shape_id, f"Shape at index {j} has no shape_id" + + rect1 = (shape1.left, shape1.top, shape1.width, shape1.height) + rect2 = (shape2.left, shape2.top, shape2.width, shape2.height) + + overlaps, overlap_area = calculate_overlap(rect1, rect2) + + if overlaps: + # Add shape IDs with overlap area in square inches + shape1.overlapping_shapes[shape2.shape_id] = overlap_area + shape2.overlapping_shapes[shape1.shape_id] = overlap_area + + +def extract_text_inventory( + pptx_path: Path, prs: Optional[Any] = None, issues_only: bool = False +) -> InventoryData: + """Extract text content from all slides in a PowerPoint presentation. + + Args: + pptx_path: Path to the PowerPoint file + prs: Optional Presentation object to use. If not provided, will load from pptx_path. + issues_only: If True, only include shapes that have overflow or overlap issues + + Returns a nested dictionary: {slide-N: {shape-N: ShapeData}} + Shapes are sorted by visual position (top-to-bottom, left-to-right). + The ShapeData objects contain the full shape information and can be + converted to dictionaries for JSON serialization using to_dict(). + """ + if prs is None: + prs = Presentation(str(pptx_path)) + inventory: InventoryData = {} + + for slide_idx, slide in enumerate(prs.slides): + # Collect all valid shapes from this slide with absolute positions + shapes_with_positions = [] + for shape in slide.shapes: # type: ignore + shapes_with_positions.extend(collect_shapes_with_absolute_positions(shape)) + + if not shapes_with_positions: + continue + + # Convert to ShapeData with absolute positions and slide reference + shape_data_list = [ + ShapeData( + swp.shape, + swp.absolute_left, + swp.absolute_top, + slide, + ) + for swp in shapes_with_positions + ] + + # Sort by visual position and assign stable IDs in one step + sorted_shapes = sort_shapes_by_position(shape_data_list) + for idx, shape_data in enumerate(sorted_shapes): + shape_data.shape_id = f"shape-{idx}" + + # Detect overlaps using the stable shape IDs + if len(sorted_shapes) > 1: + detect_overlaps(sorted_shapes) + + # Filter for issues only if requested (after overlap detection) + if issues_only: + sorted_shapes = [sd for sd in sorted_shapes if sd.has_any_issues] + + if not sorted_shapes: + continue + + # Create slide inventory using the stable shape IDs + inventory[f"slide-{slide_idx}"] = { + shape_data.shape_id: shape_data for shape_data in sorted_shapes + } + + return inventory + + +def get_inventory_as_dict(pptx_path: Path, issues_only: bool = False) -> InventoryDict: + """Extract text inventory and return as JSON-serializable dictionaries. + + This is a convenience wrapper around extract_text_inventory that returns + dictionaries instead of ShapeData objects, useful for testing and direct + JSON serialization. + + Args: + pptx_path: Path to the PowerPoint file + issues_only: If True, only include shapes that have overflow or overlap issues + + Returns: + Nested dictionary with all data serialized for JSON + """ + inventory = extract_text_inventory(pptx_path, issues_only=issues_only) + + # Convert ShapeData objects to dictionaries + dict_inventory: InventoryDict = {} + for slide_key, shapes in inventory.items(): + dict_inventory[slide_key] = { + shape_key: shape_data.to_dict() for shape_key, shape_data in shapes.items() + } + + return dict_inventory + + +def save_inventory(inventory: InventoryData, output_path: Path) -> None: + """Save inventory to JSON file with proper formatting. + + Converts ShapeData objects to dictionaries for JSON serialization. + """ + # Convert ShapeData objects to dictionaries + json_inventory: InventoryDict = {} + for slide_key, shapes in inventory.items(): + json_inventory[slide_key] = { + shape_key: shape_data.to_dict() for shape_key, shape_data in shapes.items() + } + + with open(output_path, "w", encoding="utf-8") as f: + json.dump(json_inventory, f, indent=2, ensure_ascii=False) + + +if __name__ == "__main__": + main() diff --git a/skills/pptx/scripts/rearrange.py b/skills/pptx/scripts/rearrange.py new file mode 100755 index 0000000..2519911 --- /dev/null +++ b/skills/pptx/scripts/rearrange.py @@ -0,0 +1,231 @@ +#!/usr/bin/env python3 +""" +Rearrange PowerPoint slides based on a sequence of indices. + +Usage: + python rearrange.py template.pptx output.pptx 0,34,34,50,52 + +This will create output.pptx using slides from template.pptx in the specified order. +Slides can be repeated (e.g., 34 appears twice). +""" + +import argparse +import shutil +import sys +from copy import deepcopy +from pathlib import Path + +import six +from pptx import Presentation + + +def main(): + parser = argparse.ArgumentParser( + description="Rearrange PowerPoint slides based on a sequence of indices.", + formatter_class=argparse.RawDescriptionHelpFormatter, + epilog=""" +Examples: + python rearrange.py template.pptx output.pptx 0,34,34,50,52 + Creates output.pptx using slides 0, 34 (twice), 50, and 52 from template.pptx + + python rearrange.py template.pptx output.pptx 5,3,1,2,4 + Creates output.pptx with slides reordered as specified + +Note: Slide indices are 0-based (first slide is 0, second is 1, etc.) + """, + ) + + parser.add_argument("template", help="Path to template PPTX file") + parser.add_argument("output", help="Path for output PPTX file") + parser.add_argument( + "sequence", help="Comma-separated sequence of slide indices (0-based)" + ) + + args = parser.parse_args() + + # Parse the slide sequence + try: + slide_sequence = [int(x.strip()) for x in args.sequence.split(",")] + except ValueError: + print( + "Error: Invalid sequence format. Use comma-separated integers (e.g., 0,34,34,50,52)" + ) + sys.exit(1) + + # Check template exists + template_path = Path(args.template) + if not template_path.exists(): + print(f"Error: Template file not found: {args.template}") + sys.exit(1) + + # Create output directory if needed + output_path = Path(args.output) + output_path.parent.mkdir(parents=True, exist_ok=True) + + try: + rearrange_presentation(template_path, output_path, slide_sequence) + except ValueError as e: + print(f"Error: {e}") + sys.exit(1) + except Exception as e: + print(f"Error processing presentation: {e}") + sys.exit(1) + + +def duplicate_slide(pres, index): + """Duplicate a slide in the presentation.""" + source = pres.slides[index] + + # Use source's layout to preserve formatting + new_slide = pres.slides.add_slide(source.slide_layout) + + # Collect all image and media relationships from the source slide + image_rels = {} + for rel_id, rel in six.iteritems(source.part.rels): + if "image" in rel.reltype or "media" in rel.reltype: + image_rels[rel_id] = rel + + # CRITICAL: Clear placeholder shapes to avoid duplicates + for shape in new_slide.shapes: + sp = shape.element + sp.getparent().remove(sp) + + # Copy all shapes from source + for shape in source.shapes: + el = shape.element + new_el = deepcopy(el) + new_slide.shapes._spTree.insert_element_before(new_el, "p:extLst") + + # Handle picture shapes - need to update the blip reference + # Look for all blip elements (they can be in pic or other contexts) + # Using the element's own xpath method without namespaces argument + blips = new_el.xpath(".//a:blip[@r:embed]") + for blip in blips: + old_rId = blip.get( + "{http://schemas.openxmlformats.org/officeDocument/2006/relationships}embed" + ) + if old_rId in image_rels: + # Create a new relationship in the destination slide for this image + old_rel = image_rels[old_rId] + # get_or_add returns the rId directly, or adds and returns new rId + new_rId = new_slide.part.rels.get_or_add( + old_rel.reltype, old_rel._target + ) + # Update the blip's embed reference to use the new relationship ID + blip.set( + "{http://schemas.openxmlformats.org/officeDocument/2006/relationships}embed", + new_rId, + ) + + # Copy any additional image/media relationships that might be referenced elsewhere + for rel_id, rel in image_rels.items(): + try: + new_slide.part.rels.get_or_add(rel.reltype, rel._target) + except Exception: + pass # Relationship might already exist + + return new_slide + + +def delete_slide(pres, index): + """Delete a slide from the presentation.""" + rId = pres.slides._sldIdLst[index].rId + pres.part.drop_rel(rId) + del pres.slides._sldIdLst[index] + + +def reorder_slides(pres, slide_index, target_index): + """Move a slide from one position to another.""" + slides = pres.slides._sldIdLst + + # Remove slide element from current position + slide_element = slides[slide_index] + slides.remove(slide_element) + + # Insert at target position + slides.insert(target_index, slide_element) + + +def rearrange_presentation(template_path, output_path, slide_sequence): + """ + Create a new presentation with slides from template in specified order. + + Args: + template_path: Path to template PPTX file + output_path: Path for output PPTX file + slide_sequence: List of slide indices (0-based) to include + """ + # Copy template to preserve dimensions and theme + if template_path != output_path: + shutil.copy2(template_path, output_path) + prs = Presentation(output_path) + else: + prs = Presentation(template_path) + + total_slides = len(prs.slides) + + # Validate indices + for idx in slide_sequence: + if idx < 0 or idx >= total_slides: + raise ValueError(f"Slide index {idx} out of range (0-{total_slides - 1})") + + # Track original slides and their duplicates + slide_map = [] # List of actual slide indices for final presentation + duplicated = {} # Track duplicates: original_idx -> [duplicate_indices] + + # Step 1: DUPLICATE repeated slides + print(f"Processing {len(slide_sequence)} slides from template...") + for i, template_idx in enumerate(slide_sequence): + if template_idx in duplicated and duplicated[template_idx]: + # Already duplicated this slide, use the duplicate + slide_map.append(duplicated[template_idx].pop(0)) + print(f" [{i}] Using duplicate of slide {template_idx}") + elif slide_sequence.count(template_idx) > 1 and template_idx not in duplicated: + # First occurrence of a repeated slide - create duplicates + slide_map.append(template_idx) + duplicates = [] + count = slide_sequence.count(template_idx) - 1 + print( + f" [{i}] Using original slide {template_idx}, creating {count} duplicate(s)" + ) + for _ in range(count): + duplicate_slide(prs, template_idx) + duplicates.append(len(prs.slides) - 1) + duplicated[template_idx] = duplicates + else: + # Unique slide or first occurrence already handled, use original + slide_map.append(template_idx) + print(f" [{i}] Using original slide {template_idx}") + + # Step 2: DELETE unwanted slides (work backwards) + slides_to_keep = set(slide_map) + print(f"\nDeleting {len(prs.slides) - len(slides_to_keep)} unused slides...") + for i in range(len(prs.slides) - 1, -1, -1): + if i not in slides_to_keep: + delete_slide(prs, i) + # Update slide_map indices after deletion + slide_map = [idx - 1 if idx > i else idx for idx in slide_map] + + # Step 3: REORDER to final sequence + print(f"Reordering {len(slide_map)} slides to final sequence...") + for target_pos in range(len(slide_map)): + # Find which slide should be at target_pos + current_pos = slide_map[target_pos] + if current_pos != target_pos: + reorder_slides(prs, current_pos, target_pos) + # Update slide_map: the move shifts other slides + for i in range(len(slide_map)): + if slide_map[i] > current_pos and slide_map[i] <= target_pos: + slide_map[i] -= 1 + elif slide_map[i] < current_pos and slide_map[i] >= target_pos: + slide_map[i] += 1 + slide_map[target_pos] = target_pos + + # Save the presentation + prs.save(output_path) + print(f"\nSaved rearranged presentation to: {output_path}") + print(f"Final presentation has {len(prs.slides)} slides") + + +if __name__ == "__main__": + main() diff --git a/skills/pptx/scripts/replace.py b/skills/pptx/scripts/replace.py new file mode 100755 index 0000000..8f7a8b1 --- /dev/null +++ b/skills/pptx/scripts/replace.py @@ -0,0 +1,385 @@ +#!/usr/bin/env python3 +"""Apply text replacements to PowerPoint presentation. + +Usage: + python replace.py + +The replacements JSON should have the structure output by inventory.py. +ALL text shapes identified by inventory.py will have their text cleared +unless "paragraphs" is specified in the replacements for that shape. +""" + +import json +import sys +from pathlib import Path +from typing import Any, Dict, List + +from inventory import InventoryData, extract_text_inventory +from pptx import Presentation +from pptx.dml.color import RGBColor +from pptx.enum.dml import MSO_THEME_COLOR +from pptx.enum.text import PP_ALIGN +from pptx.oxml.xmlchemy import OxmlElement +from pptx.util import Pt + + +def clear_paragraph_bullets(paragraph): + """Clear bullet formatting from a paragraph.""" + pPr = paragraph._element.get_or_add_pPr() + + # Remove existing bullet elements + for child in list(pPr): + if ( + child.tag.endswith("buChar") + or child.tag.endswith("buNone") + or child.tag.endswith("buAutoNum") + or child.tag.endswith("buFont") + ): + pPr.remove(child) + + return pPr + + +def apply_paragraph_properties(paragraph, para_data: Dict[str, Any]): + """Apply formatting properties to a paragraph.""" + # Get the text but don't set it on paragraph directly yet + text = para_data.get("text", "") + + # Get or create paragraph properties + pPr = clear_paragraph_bullets(paragraph) + + # Handle bullet formatting + if para_data.get("bullet", False): + level = para_data.get("level", 0) + paragraph.level = level + + # Calculate font-proportional indentation + font_size = para_data.get("font_size", 18.0) + level_indent_emu = int((font_size * (1.6 + level * 1.6)) * 12700) + hanging_indent_emu = int(-font_size * 0.8 * 12700) + + # Set indentation + pPr.attrib["marL"] = str(level_indent_emu) + pPr.attrib["indent"] = str(hanging_indent_emu) + + # Add bullet character + buChar = OxmlElement("a:buChar") + buChar.set("char", "•") + pPr.append(buChar) + + # Default to left alignment for bullets if not specified + if "alignment" not in para_data: + paragraph.alignment = PP_ALIGN.LEFT + else: + # Remove indentation for non-bullet text + pPr.attrib["marL"] = "0" + pPr.attrib["indent"] = "0" + + # Add buNone element + buNone = OxmlElement("a:buNone") + pPr.insert(0, buNone) + + # Apply alignment + if "alignment" in para_data: + alignment_map = { + "LEFT": PP_ALIGN.LEFT, + "CENTER": PP_ALIGN.CENTER, + "RIGHT": PP_ALIGN.RIGHT, + "JUSTIFY": PP_ALIGN.JUSTIFY, + } + if para_data["alignment"] in alignment_map: + paragraph.alignment = alignment_map[para_data["alignment"]] + + # Apply spacing + if "space_before" in para_data: + paragraph.space_before = Pt(para_data["space_before"]) + if "space_after" in para_data: + paragraph.space_after = Pt(para_data["space_after"]) + if "line_spacing" in para_data: + paragraph.line_spacing = Pt(para_data["line_spacing"]) + + # Apply run-level formatting + if not paragraph.runs: + run = paragraph.add_run() + run.text = text + else: + run = paragraph.runs[0] + run.text = text + + # Apply font properties + apply_font_properties(run, para_data) + + +def apply_font_properties(run, para_data: Dict[str, Any]): + """Apply font properties to a text run.""" + if "bold" in para_data: + run.font.bold = para_data["bold"] + if "italic" in para_data: + run.font.italic = para_data["italic"] + if "underline" in para_data: + run.font.underline = para_data["underline"] + if "font_size" in para_data: + run.font.size = Pt(para_data["font_size"]) + if "font_name" in para_data: + run.font.name = para_data["font_name"] + + # Apply color - prefer RGB, fall back to theme_color + if "color" in para_data: + color_hex = para_data["color"].lstrip("#") + if len(color_hex) == 6: + r = int(color_hex[0:2], 16) + g = int(color_hex[2:4], 16) + b = int(color_hex[4:6], 16) + run.font.color.rgb = RGBColor(r, g, b) + elif "theme_color" in para_data: + # Get theme color by name (e.g., "DARK_1", "ACCENT_1") + theme_name = para_data["theme_color"] + try: + run.font.color.theme_color = getattr(MSO_THEME_COLOR, theme_name) + except AttributeError: + print(f" WARNING: Unknown theme color name '{theme_name}'") + + +def detect_frame_overflow(inventory: InventoryData) -> Dict[str, Dict[str, float]]: + """Detect text overflow in shapes (text exceeding shape bounds). + + Returns dict of slide_key -> shape_key -> overflow_inches. + Only includes shapes that have text overflow. + """ + overflow_map = {} + + for slide_key, shapes_dict in inventory.items(): + for shape_key, shape_data in shapes_dict.items(): + # Check for frame overflow (text exceeding shape bounds) + if shape_data.frame_overflow_bottom is not None: + if slide_key not in overflow_map: + overflow_map[slide_key] = {} + overflow_map[slide_key][shape_key] = shape_data.frame_overflow_bottom + + return overflow_map + + +def validate_replacements(inventory: InventoryData, replacements: Dict) -> List[str]: + """Validate that all shapes in replacements exist in inventory. + + Returns list of error messages. + """ + errors = [] + + for slide_key, shapes_data in replacements.items(): + if not slide_key.startswith("slide-"): + continue + + # Check if slide exists + if slide_key not in inventory: + errors.append(f"Slide '{slide_key}' not found in inventory") + continue + + # Check each shape + for shape_key in shapes_data.keys(): + if shape_key not in inventory[slide_key]: + # Find shapes without replacements defined and show their content + unused_with_content = [] + for k in inventory[slide_key].keys(): + if k not in shapes_data: + shape_data = inventory[slide_key][k] + # Get text from paragraphs as preview + paragraphs = shape_data.paragraphs + if paragraphs and paragraphs[0].text: + first_text = paragraphs[0].text[:50] + if len(paragraphs[0].text) > 50: + first_text += "..." + unused_with_content.append(f"{k} ('{first_text}')") + else: + unused_with_content.append(k) + + errors.append( + f"Shape '{shape_key}' not found on '{slide_key}'. " + f"Shapes without replacements: {', '.join(sorted(unused_with_content)) if unused_with_content else 'none'}" + ) + + return errors + + +def check_duplicate_keys(pairs): + """Check for duplicate keys when loading JSON.""" + result = {} + for key, value in pairs: + if key in result: + raise ValueError(f"Duplicate key found in JSON: '{key}'") + result[key] = value + return result + + +def apply_replacements(pptx_file: str, json_file: str, output_file: str): + """Apply text replacements from JSON to PowerPoint presentation.""" + + # Load presentation + prs = Presentation(pptx_file) + + # Get inventory of all text shapes (returns ShapeData objects) + # Pass prs to use same Presentation instance + inventory = extract_text_inventory(Path(pptx_file), prs) + + # Detect text overflow in original presentation + original_overflow = detect_frame_overflow(inventory) + + # Load replacement data with duplicate key detection + with open(json_file, "r") as f: + replacements = json.load(f, object_pairs_hook=check_duplicate_keys) + + # Validate replacements + errors = validate_replacements(inventory, replacements) + if errors: + print("ERROR: Invalid shapes in replacement JSON:") + for error in errors: + print(f" - {error}") + print("\nPlease check the inventory and update your replacement JSON.") + print( + "You can regenerate the inventory with: python inventory.py " + ) + raise ValueError(f"Found {len(errors)} validation error(s)") + + # Track statistics + shapes_processed = 0 + shapes_cleared = 0 + shapes_replaced = 0 + + # Process each slide from inventory + for slide_key, shapes_dict in inventory.items(): + if not slide_key.startswith("slide-"): + continue + + slide_index = int(slide_key.split("-")[1]) + + if slide_index >= len(prs.slides): + print(f"Warning: Slide {slide_index} not found") + continue + + # Process each shape from inventory + for shape_key, shape_data in shapes_dict.items(): + shapes_processed += 1 + + # Get the shape directly from ShapeData + shape = shape_data.shape + if not shape: + print(f"Warning: {shape_key} has no shape reference") + continue + + # ShapeData already validates text_frame in __init__ + text_frame = shape.text_frame # type: ignore + + text_frame.clear() # type: ignore + shapes_cleared += 1 + + # Check for replacement paragraphs + replacement_shape_data = replacements.get(slide_key, {}).get(shape_key, {}) + if "paragraphs" not in replacement_shape_data: + continue + + shapes_replaced += 1 + + # Add replacement paragraphs + for i, para_data in enumerate(replacement_shape_data["paragraphs"]): + if i == 0: + p = text_frame.paragraphs[0] # type: ignore + else: + p = text_frame.add_paragraph() # type: ignore + + apply_paragraph_properties(p, para_data) + + # Check for issues after replacements + # Save to a temporary file and reload to avoid modifying the presentation during inventory + # (extract_text_inventory accesses font.color which adds empty elements) + import tempfile + + with tempfile.NamedTemporaryFile(suffix=".pptx", delete=False) as tmp: + tmp_path = Path(tmp.name) + prs.save(str(tmp_path)) + + try: + updated_inventory = extract_text_inventory(tmp_path) + updated_overflow = detect_frame_overflow(updated_inventory) + finally: + tmp_path.unlink() # Clean up temp file + + # Check if any text overflow got worse + overflow_errors = [] + for slide_key, shape_overflows in updated_overflow.items(): + for shape_key, new_overflow in shape_overflows.items(): + # Get original overflow (0 if there was no overflow before) + original = original_overflow.get(slide_key, {}).get(shape_key, 0.0) + + # Error if overflow increased + if new_overflow > original + 0.01: # Small tolerance for rounding + increase = new_overflow - original + overflow_errors.append( + f'{slide_key}/{shape_key}: overflow worsened by {increase:.2f}" ' + f'(was {original:.2f}", now {new_overflow:.2f}")' + ) + + # Collect warnings from updated shapes + warnings = [] + for slide_key, shapes_dict in updated_inventory.items(): + for shape_key, shape_data in shapes_dict.items(): + if shape_data.warnings: + for warning in shape_data.warnings: + warnings.append(f"{slide_key}/{shape_key}: {warning}") + + # Fail if there are any issues + if overflow_errors or warnings: + print("\nERROR: Issues detected in replacement output:") + if overflow_errors: + print("\nText overflow worsened:") + for error in overflow_errors: + print(f" - {error}") + if warnings: + print("\nFormatting warnings:") + for warning in warnings: + print(f" - {warning}") + print("\nPlease fix these issues before saving.") + raise ValueError( + f"Found {len(overflow_errors)} overflow error(s) and {len(warnings)} warning(s)" + ) + + # Save the presentation + prs.save(output_file) + + # Report results + print(f"Saved updated presentation to: {output_file}") + print(f"Processed {len(prs.slides)} slides") + print(f" - Shapes processed: {shapes_processed}") + print(f" - Shapes cleared: {shapes_cleared}") + print(f" - Shapes replaced: {shapes_replaced}") + + +def main(): + """Main entry point for command-line usage.""" + if len(sys.argv) != 4: + print(__doc__) + sys.exit(1) + + input_pptx = Path(sys.argv[1]) + replacements_json = Path(sys.argv[2]) + output_pptx = Path(sys.argv[3]) + + if not input_pptx.exists(): + print(f"Error: Input file '{input_pptx}' not found") + sys.exit(1) + + if not replacements_json.exists(): + print(f"Error: Replacements JSON file '{replacements_json}' not found") + sys.exit(1) + + try: + apply_replacements(str(input_pptx), str(replacements_json), str(output_pptx)) + except Exception as e: + print(f"Error applying replacements: {e}") + import traceback + + traceback.print_exc() + sys.exit(1) + + +if __name__ == "__main__": + main() diff --git a/skills/pptx/scripts/thumbnail.py b/skills/pptx/scripts/thumbnail.py new file mode 100755 index 0000000..5c7fdf1 --- /dev/null +++ b/skills/pptx/scripts/thumbnail.py @@ -0,0 +1,450 @@ +#!/usr/bin/env python3 +""" +Create thumbnail grids from PowerPoint presentation slides. + +Creates a grid layout of slide thumbnails with configurable columns (max 6). +Each grid contains up to cols×(cols+1) images. For presentations with more +slides, multiple numbered grid files are created automatically. + +The program outputs the names of all files created. + +Output: +- Single grid: {prefix}.jpg (if slides fit in one grid) +- Multiple grids: {prefix}-1.jpg, {prefix}-2.jpg, etc. + +Grid limits by column count: +- 3 cols: max 12 slides per grid (3×4) +- 4 cols: max 20 slides per grid (4×5) +- 5 cols: max 30 slides per grid (5×6) [default] +- 6 cols: max 42 slides per grid (6×7) + +Usage: + python thumbnail.py input.pptx [output_prefix] [--cols N] [--outline-placeholders] + +Examples: + python thumbnail.py presentation.pptx + # Creates: thumbnails.jpg (using default prefix) + # Outputs: + # Created 1 grid(s): + # - thumbnails.jpg + + python thumbnail.py large-deck.pptx grid --cols 4 + # Creates: grid-1.jpg, grid-2.jpg, grid-3.jpg + # Outputs: + # Created 3 grid(s): + # - grid-1.jpg + # - grid-2.jpg + # - grid-3.jpg + + python thumbnail.py template.pptx analysis --outline-placeholders + # Creates thumbnail grids with red outlines around text placeholders +""" + +import argparse +import subprocess +import sys +import tempfile +from pathlib import Path + +from inventory import extract_text_inventory +from PIL import Image, ImageDraw, ImageFont +from pptx import Presentation + +# Constants +THUMBNAIL_WIDTH = 300 # Fixed thumbnail width in pixels +CONVERSION_DPI = 100 # DPI for PDF to image conversion +MAX_COLS = 6 # Maximum number of columns +DEFAULT_COLS = 5 # Default number of columns +JPEG_QUALITY = 95 # JPEG compression quality + +# Grid layout constants +GRID_PADDING = 20 # Padding between thumbnails +BORDER_WIDTH = 2 # Border width around thumbnails +FONT_SIZE_RATIO = 0.12 # Font size as fraction of thumbnail width +LABEL_PADDING_RATIO = 0.4 # Label padding as fraction of font size + + +def main(): + parser = argparse.ArgumentParser( + description="Create thumbnail grids from PowerPoint slides." + ) + parser.add_argument("input", help="Input PowerPoint file (.pptx)") + parser.add_argument( + "output_prefix", + nargs="?", + default="thumbnails", + help="Output prefix for image files (default: thumbnails, will create prefix.jpg or prefix-N.jpg)", + ) + parser.add_argument( + "--cols", + type=int, + default=DEFAULT_COLS, + help=f"Number of columns (default: {DEFAULT_COLS}, max: {MAX_COLS})", + ) + parser.add_argument( + "--outline-placeholders", + action="store_true", + help="Outline text placeholders with a colored border", + ) + + args = parser.parse_args() + + # Validate columns + cols = min(args.cols, MAX_COLS) + if args.cols > MAX_COLS: + print(f"Warning: Columns limited to {MAX_COLS} (requested {args.cols})") + + # Validate input + input_path = Path(args.input) + if not input_path.exists() or input_path.suffix.lower() != ".pptx": + print(f"Error: Invalid PowerPoint file: {args.input}") + sys.exit(1) + + # Construct output path (always JPG) + output_path = Path(f"{args.output_prefix}.jpg") + + print(f"Processing: {args.input}") + + try: + with tempfile.TemporaryDirectory() as temp_dir: + # Get placeholder regions if outlining is enabled + placeholder_regions = None + slide_dimensions = None + if args.outline_placeholders: + print("Extracting placeholder regions...") + placeholder_regions, slide_dimensions = get_placeholder_regions( + input_path + ) + if placeholder_regions: + print(f"Found placeholders on {len(placeholder_regions)} slides") + + # Convert slides to images + slide_images = convert_to_images(input_path, Path(temp_dir), CONVERSION_DPI) + if not slide_images: + print("Error: No slides found") + sys.exit(1) + + print(f"Found {len(slide_images)} slides") + + # Create grids (max cols×(cols+1) images per grid) + grid_files = create_grids( + slide_images, + cols, + THUMBNAIL_WIDTH, + output_path, + placeholder_regions, + slide_dimensions, + ) + + # Print saved files + print(f"Created {len(grid_files)} grid(s):") + for grid_file in grid_files: + print(f" - {grid_file}") + + except Exception as e: + print(f"Error: {e}") + sys.exit(1) + + +def create_hidden_slide_placeholder(size): + """Create placeholder image for hidden slides.""" + img = Image.new("RGB", size, color="#F0F0F0") + draw = ImageDraw.Draw(img) + line_width = max(5, min(size) // 100) + draw.line([(0, 0), size], fill="#CCCCCC", width=line_width) + draw.line([(size[0], 0), (0, size[1])], fill="#CCCCCC", width=line_width) + return img + + +def get_placeholder_regions(pptx_path): + """Extract ALL text regions from the presentation. + + Returns a tuple of (placeholder_regions, slide_dimensions). + text_regions is a dict mapping slide indices to lists of text regions. + Each region is a dict with 'left', 'top', 'width', 'height' in inches. + slide_dimensions is a tuple of (width_inches, height_inches). + """ + prs = Presentation(str(pptx_path)) + inventory = extract_text_inventory(pptx_path, prs) + placeholder_regions = {} + + # Get actual slide dimensions in inches (EMU to inches conversion) + slide_width_inches = (prs.slide_width or 9144000) / 914400.0 + slide_height_inches = (prs.slide_height or 5143500) / 914400.0 + + for slide_key, shapes in inventory.items(): + # Extract slide index from "slide-N" format + slide_idx = int(slide_key.split("-")[1]) + regions = [] + + for shape_key, shape_data in shapes.items(): + # The inventory only contains shapes with text, so all shapes should be highlighted + regions.append( + { + "left": shape_data.left, + "top": shape_data.top, + "width": shape_data.width, + "height": shape_data.height, + } + ) + + if regions: + placeholder_regions[slide_idx] = regions + + return placeholder_regions, (slide_width_inches, slide_height_inches) + + +def convert_to_images(pptx_path, temp_dir, dpi): + """Convert PowerPoint to images via PDF, handling hidden slides.""" + # Detect hidden slides + print("Analyzing presentation...") + prs = Presentation(str(pptx_path)) + total_slides = len(prs.slides) + + # Find hidden slides (1-based indexing for display) + hidden_slides = { + idx + 1 + for idx, slide in enumerate(prs.slides) + if slide.element.get("show") == "0" + } + + print(f"Total slides: {total_slides}") + if hidden_slides: + print(f"Hidden slides: {sorted(hidden_slides)}") + + pdf_path = temp_dir / f"{pptx_path.stem}.pdf" + + # Convert to PDF + print("Converting to PDF...") + result = subprocess.run( + [ + "soffice", + "--headless", + "--convert-to", + "pdf", + "--outdir", + str(temp_dir), + str(pptx_path), + ], + capture_output=True, + text=True, + ) + if result.returncode != 0 or not pdf_path.exists(): + raise RuntimeError("PDF conversion failed") + + # Convert PDF to images + print(f"Converting to images at {dpi} DPI...") + result = subprocess.run( + ["pdftoppm", "-jpeg", "-r", str(dpi), str(pdf_path), str(temp_dir / "slide")], + capture_output=True, + text=True, + ) + if result.returncode != 0: + raise RuntimeError("Image conversion failed") + + visible_images = sorted(temp_dir.glob("slide-*.jpg")) + + # Create full list with placeholders for hidden slides + all_images = [] + visible_idx = 0 + + # Get placeholder dimensions from first visible slide + if visible_images: + with Image.open(visible_images[0]) as img: + placeholder_size = img.size + else: + placeholder_size = (1920, 1080) + + for slide_num in range(1, total_slides + 1): + if slide_num in hidden_slides: + # Create placeholder image for hidden slide + placeholder_path = temp_dir / f"hidden-{slide_num:03d}.jpg" + placeholder_img = create_hidden_slide_placeholder(placeholder_size) + placeholder_img.save(placeholder_path, "JPEG") + all_images.append(placeholder_path) + else: + # Use the actual visible slide image + if visible_idx < len(visible_images): + all_images.append(visible_images[visible_idx]) + visible_idx += 1 + + return all_images + + +def create_grids( + image_paths, + cols, + width, + output_path, + placeholder_regions=None, + slide_dimensions=None, +): + """Create multiple thumbnail grids from slide images, max cols×(cols+1) images per grid.""" + # Maximum images per grid is cols × (cols + 1) for better proportions + max_images_per_grid = cols * (cols + 1) + grid_files = [] + + print( + f"Creating grids with {cols} columns (max {max_images_per_grid} images per grid)" + ) + + # Split images into chunks + for chunk_idx, start_idx in enumerate( + range(0, len(image_paths), max_images_per_grid) + ): + end_idx = min(start_idx + max_images_per_grid, len(image_paths)) + chunk_images = image_paths[start_idx:end_idx] + + # Create grid for this chunk + grid = create_grid( + chunk_images, cols, width, start_idx, placeholder_regions, slide_dimensions + ) + + # Generate output filename + if len(image_paths) <= max_images_per_grid: + # Single grid - use base filename without suffix + grid_filename = output_path + else: + # Multiple grids - insert index before extension with dash + stem = output_path.stem + suffix = output_path.suffix + grid_filename = output_path.parent / f"{stem}-{chunk_idx + 1}{suffix}" + + # Save grid + grid_filename.parent.mkdir(parents=True, exist_ok=True) + grid.save(str(grid_filename), quality=JPEG_QUALITY) + grid_files.append(str(grid_filename)) + + return grid_files + + +def create_grid( + image_paths, + cols, + width, + start_slide_num=0, + placeholder_regions=None, + slide_dimensions=None, +): + """Create thumbnail grid from slide images with optional placeholder outlining.""" + font_size = int(width * FONT_SIZE_RATIO) + label_padding = int(font_size * LABEL_PADDING_RATIO) + + # Get dimensions + with Image.open(image_paths[0]) as img: + aspect = img.height / img.width + height = int(width * aspect) + + # Calculate grid size + rows = (len(image_paths) + cols - 1) // cols + grid_w = cols * width + (cols + 1) * GRID_PADDING + grid_h = rows * (height + font_size + label_padding * 2) + (rows + 1) * GRID_PADDING + + # Create grid + grid = Image.new("RGB", (grid_w, grid_h), "white") + draw = ImageDraw.Draw(grid) + + # Load font with size based on thumbnail width + try: + # Use Pillow's default font with size + font = ImageFont.load_default(size=font_size) + except Exception: + # Fall back to basic default font if size parameter not supported + font = ImageFont.load_default() + + # Place thumbnails + for i, img_path in enumerate(image_paths): + row, col = i // cols, i % cols + x = col * width + (col + 1) * GRID_PADDING + y_base = ( + row * (height + font_size + label_padding * 2) + (row + 1) * GRID_PADDING + ) + + # Add label with actual slide number + label = f"{start_slide_num + i}" + bbox = draw.textbbox((0, 0), label, font=font) + text_w = bbox[2] - bbox[0] + draw.text( + (x + (width - text_w) // 2, y_base + label_padding), + label, + fill="black", + font=font, + ) + + # Add thumbnail below label with proportional spacing + y_thumbnail = y_base + label_padding + font_size + label_padding + + with Image.open(img_path) as img: + # Get original dimensions before thumbnail + orig_w, orig_h = img.size + + # Apply placeholder outlines if enabled + if placeholder_regions and (start_slide_num + i) in placeholder_regions: + # Convert to RGBA for transparency support + if img.mode != "RGBA": + img = img.convert("RGBA") + + # Get the regions for this slide + regions = placeholder_regions[start_slide_num + i] + + # Calculate scale factors using actual slide dimensions + if slide_dimensions: + slide_width_inches, slide_height_inches = slide_dimensions + else: + # Fallback: estimate from image size at CONVERSION_DPI + slide_width_inches = orig_w / CONVERSION_DPI + slide_height_inches = orig_h / CONVERSION_DPI + + x_scale = orig_w / slide_width_inches + y_scale = orig_h / slide_height_inches + + # Create a highlight overlay + overlay = Image.new("RGBA", img.size, (255, 255, 255, 0)) + overlay_draw = ImageDraw.Draw(overlay) + + # Highlight each placeholder region + for region in regions: + # Convert from inches to pixels in the original image + px_left = int(region["left"] * x_scale) + px_top = int(region["top"] * y_scale) + px_width = int(region["width"] * x_scale) + px_height = int(region["height"] * y_scale) + + # Draw highlight outline with red color and thick stroke + # Using a bright red outline instead of fill + stroke_width = max( + 5, min(orig_w, orig_h) // 150 + ) # Thicker proportional stroke width + overlay_draw.rectangle( + [(px_left, px_top), (px_left + px_width, px_top + px_height)], + outline=(255, 0, 0, 255), # Bright red, fully opaque + width=stroke_width, + ) + + # Composite the overlay onto the image using alpha blending + img = Image.alpha_composite(img, overlay) + # Convert back to RGB for JPEG saving + img = img.convert("RGB") + + img.thumbnail((width, height), Image.Resampling.LANCZOS) + w, h = img.size + tx = x + (width - w) // 2 + ty = y_thumbnail + (height - h) // 2 + grid.paste(img, (tx, ty)) + + # Add border + if BORDER_WIDTH > 0: + draw.rectangle( + [ + (tx - BORDER_WIDTH, ty - BORDER_WIDTH), + (tx + w + BORDER_WIDTH - 1, ty + h + BORDER_WIDTH - 1), + ], + outline="gray", + width=BORDER_WIDTH, + ) + + return grid + + +if __name__ == "__main__": + main() diff --git a/skills/skill-creator/LICENSE.txt b/skills/skill-creator/LICENSE.txt new file mode 100644 index 0000000..7a4a3ea --- /dev/null +++ b/skills/skill-creator/LICENSE.txt @@ -0,0 +1,202 @@ + + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [yyyy] [name of copyright owner] + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. \ No newline at end of file diff --git a/skills/skill-creator/SKILL.md b/skills/skill-creator/SKILL.md new file mode 100644 index 0000000..b7f8659 --- /dev/null +++ b/skills/skill-creator/SKILL.md @@ -0,0 +1,356 @@ +--- +name: skill-creator +description: Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. +license: Complete terms in LICENSE.txt +--- + +# Skill Creator + +This skill provides guidance for creating effective skills. + +## About Skills + +Skills are modular, self-contained packages that extend Claude's capabilities by providing +specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific +domains or tasks—they transform Claude from a general-purpose agent into a specialized agent +equipped with procedural knowledge that no model can fully possess. + +### What Skills Provide + +1. Specialized workflows - Multi-step procedures for specific domains +2. Tool integrations - Instructions for working with specific file formats or APIs +3. Domain expertise - Company-specific knowledge, schemas, business logic +4. Bundled resources - Scripts, references, and assets for complex and repetitive tasks + +## Core Principles + +### Concise is Key + +The context window is a public good. Skills share the context window with everything else Claude needs: system prompt, conversation history, other Skills' metadata, and the actual user request. + +**Default assumption: Claude is already very smart.** Only add context Claude doesn't already have. Challenge each piece of information: "Does Claude really need this explanation?" and "Does this paragraph justify its token cost?" + +Prefer concise examples over verbose explanations. + +### Set Appropriate Degrees of Freedom + +Match the level of specificity to the task's fragility and variability: + +**High freedom (text-based instructions)**: Use when multiple approaches are valid, decisions depend on context, or heuristics guide the approach. + +**Medium freedom (pseudocode or scripts with parameters)**: Use when a preferred pattern exists, some variation is acceptable, or configuration affects behavior. + +**Low freedom (specific scripts, few parameters)**: Use when operations are fragile and error-prone, consistency is critical, or a specific sequence must be followed. + +Think of Claude as exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom). + +### Anatomy of a Skill + +Every skill consists of a required SKILL.md file and optional bundled resources: + +``` +skill-name/ +├── SKILL.md (required) +│ ├── YAML frontmatter metadata (required) +│ │ ├── name: (required) +│ │ └── description: (required) +│ └── Markdown instructions (required) +└── Bundled Resources (optional) + ├── scripts/ - Executable code (Python/Bash/etc.) + ├── references/ - Documentation intended to be loaded into context as needed + └── assets/ - Files used in output (templates, icons, fonts, etc.) +``` + +#### SKILL.md (required) + +Every SKILL.md consists of: + +- **Frontmatter** (YAML): Contains `name` and `description` fields. These are the only fields that Claude reads to determine when the skill gets used, thus it is very important to be clear and comprehensive in describing what the skill is, and when it should be used. +- **Body** (Markdown): Instructions and guidance for using the skill. Only loaded AFTER the skill triggers (if at all). + +#### Bundled Resources (optional) + +##### Scripts (`scripts/`) + +Executable code (Python/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten. + +- **When to include**: When the same code is being rewritten repeatedly or deterministic reliability is needed +- **Example**: `scripts/rotate_pdf.py` for PDF rotation tasks +- **Benefits**: Token efficient, deterministic, may be executed without loading into context +- **Note**: Scripts may still need to be read by Claude for patching or environment-specific adjustments + +##### References (`references/`) + +Documentation and reference material intended to be loaded as needed into context to inform Claude's process and thinking. + +- **When to include**: For documentation that Claude should reference while working +- **Examples**: `references/finance.md` for financial schemas, `references/mnda.md` for company NDA template, `references/policies.md` for company policies, `references/api_docs.md` for API specifications +- **Use cases**: Database schemas, API documentation, domain knowledge, company policies, detailed workflow guides +- **Benefits**: Keeps SKILL.md lean, loaded only when Claude determines it's needed +- **Best practice**: If files are large (>10k words), include grep search patterns in SKILL.md +- **Avoid duplication**: Information should live in either SKILL.md or references files, not both. Prefer references files for detailed information unless it's truly core to the skill—this keeps SKILL.md lean while making information discoverable without hogging the context window. Keep only essential procedural instructions and workflow guidance in SKILL.md; move detailed reference material, schemas, and examples to references files. + +##### Assets (`assets/`) + +Files not intended to be loaded into context, but rather used within the output Claude produces. + +- **When to include**: When the skill needs files that will be used in the final output +- **Examples**: `assets/logo.png` for brand assets, `assets/slides.pptx` for PowerPoint templates, `assets/frontend-template/` for HTML/React boilerplate, `assets/font.ttf` for typography +- **Use cases**: Templates, images, icons, boilerplate code, fonts, sample documents that get copied or modified +- **Benefits**: Separates output resources from documentation, enables Claude to use files without loading them into context + +#### What to Not Include in a Skill + +A skill should only contain essential files that directly support its functionality. Do NOT create extraneous documentation or auxiliary files, including: + +- README.md +- INSTALLATION_GUIDE.md +- QUICK_REFERENCE.md +- CHANGELOG.md +- etc. + +The skill should only contain the information needed for an AI agent to do the job at hand. It should not contain auxilary context about the process that went into creating it, setup and testing procedures, user-facing documentation, etc. Creating additional documentation files just adds clutter and confusion. + +### Progressive Disclosure Design Principle + +Skills use a three-level loading system to manage context efficiently: + +1. **Metadata (name + description)** - Always in context (~100 words) +2. **SKILL.md body** - When skill triggers (<5k words) +3. **Bundled resources** - As needed by Claude (Unlimited because scripts can be executed without reading into context window) + +#### Progressive Disclosure Patterns + +Keep SKILL.md body to the essentials and under 500 lines to minimize context bloat. Split content into separate files when approaching this limit. When splitting out content into other files, it is very important to reference them from SKILL.md and describe clearly when to read them, to ensure the reader of the skill knows they exist and when to use them. + +**Key principle:** When a skill supports multiple variations, frameworks, or options, keep only the core workflow and selection guidance in SKILL.md. Move variant-specific details (patterns, examples, configuration) into separate reference files. + +**Pattern 1: High-level guide with references** + +```markdown +# PDF Processing + +## Quick start + +Extract text with pdfplumber: +[code example] + +## Advanced features + +- **Form filling**: See [FORMS.md](FORMS.md) for complete guide +- **API reference**: See [REFERENCE.md](REFERENCE.md) for all methods +- **Examples**: See [EXAMPLES.md](EXAMPLES.md) for common patterns +``` + +Claude loads FORMS.md, REFERENCE.md, or EXAMPLES.md only when needed. + +**Pattern 2: Domain-specific organization** + +For Skills with multiple domains, organize content by domain to avoid loading irrelevant context: + +``` +bigquery-skill/ +├── SKILL.md (overview and navigation) +└── reference/ + ├── finance.md (revenue, billing metrics) + ├── sales.md (opportunities, pipeline) + ├── product.md (API usage, features) + └── marketing.md (campaigns, attribution) +``` + +When a user asks about sales metrics, Claude only reads sales.md. + +Similarly, for skills supporting multiple frameworks or variants, organize by variant: + +``` +cloud-deploy/ +├── SKILL.md (workflow + provider selection) +└── references/ + ├── aws.md (AWS deployment patterns) + ├── gcp.md (GCP deployment patterns) + └── azure.md (Azure deployment patterns) +``` + +When the user chooses AWS, Claude only reads aws.md. + +**Pattern 3: Conditional details** + +Show basic content, link to advanced content: + +```markdown +# DOCX Processing + +## Creating documents + +Use docx-js for new documents. See [DOCX-JS.md](DOCX-JS.md). + +## Editing documents + +For simple edits, modify the XML directly. + +**For tracked changes**: See [REDLINING.md](REDLINING.md) +**For OOXML details**: See [OOXML.md](OOXML.md) +``` + +Claude reads REDLINING.md or OOXML.md only when the user needs those features. + +**Important guidelines:** + +- **Avoid deeply nested references** - Keep references one level deep from SKILL.md. All reference files should link directly from SKILL.md. +- **Structure longer reference files** - For files longer than 100 lines, include a table of contents at the top so Claude can see the full scope when previewing. + +## Skill Creation Process + +Skill creation involves these steps: + +1. Understand the skill with concrete examples +2. Plan reusable skill contents (scripts, references, assets) +3. Initialize the skill (run init_skill.py) +4. Edit the skill (implement resources and write SKILL.md) +5. Package the skill (run package_skill.py) +6. Iterate based on real usage + +Follow these steps in order, skipping only if there is a clear reason why they are not applicable. + +### Step 1: Understanding the Skill with Concrete Examples + +Skip this step only when the skill's usage patterns are already clearly understood. It remains valuable even when working with an existing skill. + +To create an effective skill, clearly understand concrete examples of how the skill will be used. This understanding can come from either direct user examples or generated examples that are validated with user feedback. + +For example, when building an image-editor skill, relevant questions include: + +- "What functionality should the image-editor skill support? Editing, rotating, anything else?" +- "Can you give some examples of how this skill would be used?" +- "I can imagine users asking for things like 'Remove the red-eye from this image' or 'Rotate this image'. Are there other ways you imagine this skill being used?" +- "What would a user say that should trigger this skill?" + +To avoid overwhelming users, avoid asking too many questions in a single message. Start with the most important questions and follow up as needed for better effectiveness. + +Conclude this step when there is a clear sense of the functionality the skill should support. + +### Step 2: Planning the Reusable Skill Contents + +To turn concrete examples into an effective skill, analyze each example by: + +1. Considering how to execute on the example from scratch +2. Identifying what scripts, references, and assets would be helpful when executing these workflows repeatedly + +Example: When building a `pdf-editor` skill to handle queries like "Help me rotate this PDF," the analysis shows: + +1. Rotating a PDF requires re-writing the same code each time +2. A `scripts/rotate_pdf.py` script would be helpful to store in the skill + +Example: When designing a `frontend-webapp-builder` skill for queries like "Build me a todo app" or "Build me a dashboard to track my steps," the analysis shows: + +1. Writing a frontend webapp requires the same boilerplate HTML/React each time +2. An `assets/hello-world/` template containing the boilerplate HTML/React project files would be helpful to store in the skill + +Example: When building a `big-query` skill to handle queries like "How many users have logged in today?" the analysis shows: + +1. Querying BigQuery requires re-discovering the table schemas and relationships each time +2. A `references/schema.md` file documenting the table schemas would be helpful to store in the skill + +To establish the skill's contents, analyze each concrete example to create a list of the reusable resources to include: scripts, references, and assets. + +### Step 3: Initializing the Skill + +At this point, it is time to actually create the skill. + +Skip this step only if the skill being developed already exists, and iteration or packaging is needed. In this case, continue to the next step. + +When creating a new skill from scratch, always run the `init_skill.py` script. The script conveniently generates a new template skill directory that automatically includes everything a skill requires, making the skill creation process much more efficient and reliable. + +Usage: + +```bash +scripts/init_skill.py --path +``` + +The script: + +- Creates the skill directory at the specified path +- Generates a SKILL.md template with proper frontmatter and TODO placeholders +- Creates example resource directories: `scripts/`, `references/`, and `assets/` +- Adds example files in each directory that can be customized or deleted + +After initialization, customize or remove the generated SKILL.md and example files as needed. + +### Step 4: Edit the Skill + +When editing the (newly-generated or existing) skill, remember that the skill is being created for another instance of Claude to use. Include information that would be beneficial and non-obvious to Claude. Consider what procedural knowledge, domain-specific details, or reusable assets would help another Claude instance execute these tasks more effectively. + +#### Learn Proven Design Patterns + +Consult these helpful guides based on your skill's needs: + +- **Multi-step processes**: See references/workflows.md for sequential workflows and conditional logic +- **Specific output formats or quality standards**: See references/output-patterns.md for template and example patterns + +These files contain established best practices for effective skill design. + +#### Start with Reusable Skill Contents + +To begin implementation, start with the reusable resources identified above: `scripts/`, `references/`, and `assets/` files. Note that this step may require user input. For example, when implementing a `brand-guidelines` skill, the user may need to provide brand assets or templates to store in `assets/`, or documentation to store in `references/`. + +Added scripts must be tested by actually running them to ensure there are no bugs and that the output matches what is expected. If there are many similar scripts, only a representative sample needs to be tested to ensure confidence that they all work while balancing time to completion. + +Any example files and directories not needed for the skill should be deleted. The initialization script creates example files in `scripts/`, `references/`, and `assets/` to demonstrate structure, but most skills won't need all of them. + +#### Update SKILL.md + +**Writing Guidelines:** Always use imperative/infinitive form. + +##### Frontmatter + +Write the YAML frontmatter with `name` and `description`: + +- `name`: The skill name +- `description`: This is the primary triggering mechanism for your skill, and helps Claude understand when to use the skill. + - Include both what the Skill does and specific triggers/contexts for when to use it. + - Include all "when to use" information here - Not in the body. The body is only loaded after triggering, so "When to Use This Skill" sections in the body are not helpful to Claude. + - Example description for a `docx` skill: "Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. Use when Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks" + +Do not include any other fields in YAML frontmatter. + +##### Body + +Write instructions for using the skill and its bundled resources. + +### Step 5: Packaging a Skill + +Once development of the skill is complete, it must be packaged into a distributable .skill file that gets shared with the user. The packaging process automatically validates the skill first to ensure it meets all requirements: + +```bash +scripts/package_skill.py +``` + +Optional output directory specification: + +```bash +scripts/package_skill.py ./dist +``` + +The packaging script will: + +1. **Validate** the skill automatically, checking: + + - YAML frontmatter format and required fields + - Skill naming conventions and directory structure + - Description completeness and quality + - File organization and resource references + +2. **Package** the skill if validation passes, creating a .skill file named after the skill (e.g., `my-skill.skill`) that includes all files and maintains the proper directory structure for distribution. The .skill file is a zip file with a .skill extension. + +If validation fails, the script will report the errors and exit without creating a package. Fix any validation errors and run the packaging command again. + +### Step 6: Iterate + +After testing the skill, users may request improvements. Often this happens right after using the skill, with fresh context of how the skill performed. + +**Iteration workflow:** + +1. Use the skill on real tasks +2. Notice struggles or inefficiencies +3. Identify how SKILL.md or bundled resources should be updated +4. Implement changes and test again diff --git a/skills/skill-creator/references/output-patterns.md b/skills/skill-creator/references/output-patterns.md new file mode 100644 index 0000000..073ddda --- /dev/null +++ b/skills/skill-creator/references/output-patterns.md @@ -0,0 +1,82 @@ +# Output Patterns + +Use these patterns when skills need to produce consistent, high-quality output. + +## Template Pattern + +Provide templates for output format. Match the level of strictness to your needs. + +**For strict requirements (like API responses or data formats):** + +```markdown +## Report structure + +ALWAYS use this exact template structure: + +# [Analysis Title] + +## Executive summary +[One-paragraph overview of key findings] + +## Key findings +- Finding 1 with supporting data +- Finding 2 with supporting data +- Finding 3 with supporting data + +## Recommendations +1. Specific actionable recommendation +2. Specific actionable recommendation +``` + +**For flexible guidance (when adaptation is useful):** + +```markdown +## Report structure + +Here is a sensible default format, but use your best judgment: + +# [Analysis Title] + +## Executive summary +[Overview] + +## Key findings +[Adapt sections based on what you discover] + +## Recommendations +[Tailor to the specific context] + +Adjust sections as needed for the specific analysis type. +``` + +## Examples Pattern + +For skills where output quality depends on seeing examples, provide input/output pairs: + +```markdown +## Commit message format + +Generate commit messages following these examples: + +**Example 1:** +Input: Added user authentication with JWT tokens +Output: +``` +feat(auth): implement JWT-based authentication + +Add login endpoint and token validation middleware +``` + +**Example 2:** +Input: Fixed bug where dates displayed incorrectly in reports +Output: +``` +fix(reports): correct date formatting in timezone conversion + +Use UTC timestamps consistently across report generation +``` + +Follow this style: type(scope): brief description, then detailed explanation. +``` + +Examples help Claude understand the desired style and level of detail more clearly than descriptions alone. diff --git a/skills/skill-creator/references/workflows.md b/skills/skill-creator/references/workflows.md new file mode 100644 index 0000000..a350c3c --- /dev/null +++ b/skills/skill-creator/references/workflows.md @@ -0,0 +1,28 @@ +# Workflow Patterns + +## Sequential Workflows + +For complex tasks, break operations into clear, sequential steps. It is often helpful to give Claude an overview of the process towards the beginning of SKILL.md: + +```markdown +Filling a PDF form involves these steps: + +1. Analyze the form (run analyze_form.py) +2. Create field mapping (edit fields.json) +3. Validate mapping (run validate_fields.py) +4. Fill the form (run fill_form.py) +5. Verify output (run verify_output.py) +``` + +## Conditional Workflows + +For tasks with branching logic, guide Claude through decision points: + +```markdown +1. Determine the modification type: + **Creating new content?** → Follow "Creation workflow" below + **Editing existing content?** → Follow "Editing workflow" below + +2. Creation workflow: [steps] +3. Editing workflow: [steps] +``` \ No newline at end of file diff --git a/skills/skill-creator/scripts/init_skill.py b/skills/skill-creator/scripts/init_skill.py new file mode 100755 index 0000000..329ad4e --- /dev/null +++ b/skills/skill-creator/scripts/init_skill.py @@ -0,0 +1,303 @@ +#!/usr/bin/env python3 +""" +Skill Initializer - Creates a new skill from template + +Usage: + init_skill.py --path + +Examples: + init_skill.py my-new-skill --path skills/public + init_skill.py my-api-helper --path skills/private + init_skill.py custom-skill --path /custom/location +""" + +import sys +from pathlib import Path + + +SKILL_TEMPLATE = """--- +name: {skill_name} +description: [TODO: Complete and informative explanation of what the skill does and when to use it. Include WHEN to use this skill - specific scenarios, file types, or tasks that trigger it.] +--- + +# {skill_title} + +## Overview + +[TODO: 1-2 sentences explaining what this skill enables] + +## Structuring This Skill + +[TODO: Choose the structure that best fits this skill's purpose. Common patterns: + +**1. Workflow-Based** (best for sequential processes) +- Works well when there are clear step-by-step procedures +- Example: DOCX skill with "Workflow Decision Tree" → "Reading" → "Creating" → "Editing" +- Structure: ## Overview → ## Workflow Decision Tree → ## Step 1 → ## Step 2... + +**2. Task-Based** (best for tool collections) +- Works well when the skill offers different operations/capabilities +- Example: PDF skill with "Quick Start" → "Merge PDFs" → "Split PDFs" → "Extract Text" +- Structure: ## Overview → ## Quick Start → ## Task Category 1 → ## Task Category 2... + +**3. Reference/Guidelines** (best for standards or specifications) +- Works well for brand guidelines, coding standards, or requirements +- Example: Brand styling with "Brand Guidelines" → "Colors" → "Typography" → "Features" +- Structure: ## Overview → ## Guidelines → ## Specifications → ## Usage... + +**4. Capabilities-Based** (best for integrated systems) +- Works well when the skill provides multiple interrelated features +- Example: Product Management with "Core Capabilities" → numbered capability list +- Structure: ## Overview → ## Core Capabilities → ### 1. Feature → ### 2. Feature... + +Patterns can be mixed and matched as needed. Most skills combine patterns (e.g., start with task-based, add workflow for complex operations). + +Delete this entire "Structuring This Skill" section when done - it's just guidance.] + +## [TODO: Replace with the first main section based on chosen structure] + +[TODO: Add content here. See examples in existing skills: +- Code samples for technical skills +- Decision trees for complex workflows +- Concrete examples with realistic user requests +- References to scripts/templates/references as needed] + +## Resources + +This skill includes example resource directories that demonstrate how to organize different types of bundled resources: + +### scripts/ +Executable code (Python/Bash/etc.) that can be run directly to perform specific operations. + +**Examples from other skills:** +- PDF skill: `fill_fillable_fields.py`, `extract_form_field_info.py` - utilities for PDF manipulation +- DOCX skill: `document.py`, `utilities.py` - Python modules for document processing + +**Appropriate for:** Python scripts, shell scripts, or any executable code that performs automation, data processing, or specific operations. + +**Note:** Scripts may be executed without loading into context, but can still be read by Claude for patching or environment adjustments. + +### references/ +Documentation and reference material intended to be loaded into context to inform Claude's process and thinking. + +**Examples from other skills:** +- Product management: `communication.md`, `context_building.md` - detailed workflow guides +- BigQuery: API reference documentation and query examples +- Finance: Schema documentation, company policies + +**Appropriate for:** In-depth documentation, API references, database schemas, comprehensive guides, or any detailed information that Claude should reference while working. + +### assets/ +Files not intended to be loaded into context, but rather used within the output Claude produces. + +**Examples from other skills:** +- Brand styling: PowerPoint template files (.pptx), logo files +- Frontend builder: HTML/React boilerplate project directories +- Typography: Font files (.ttf, .woff2) + +**Appropriate for:** Templates, boilerplate code, document templates, images, icons, fonts, or any files meant to be copied or used in the final output. + +--- + +**Any unneeded directories can be deleted.** Not every skill requires all three types of resources. +""" + +EXAMPLE_SCRIPT = '''#!/usr/bin/env python3 +""" +Example helper script for {skill_name} + +This is a placeholder script that can be executed directly. +Replace with actual implementation or delete if not needed. + +Example real scripts from other skills: +- pdf/scripts/fill_fillable_fields.py - Fills PDF form fields +- pdf/scripts/convert_pdf_to_images.py - Converts PDF pages to images +""" + +def main(): + print("This is an example script for {skill_name}") + # TODO: Add actual script logic here + # This could be data processing, file conversion, API calls, etc. + +if __name__ == "__main__": + main() +''' + +EXAMPLE_REFERENCE = """# Reference Documentation for {skill_title} + +This is a placeholder for detailed reference documentation. +Replace with actual reference content or delete if not needed. + +Example real reference docs from other skills: +- product-management/references/communication.md - Comprehensive guide for status updates +- product-management/references/context_building.md - Deep-dive on gathering context +- bigquery/references/ - API references and query examples + +## When Reference Docs Are Useful + +Reference docs are ideal for: +- Comprehensive API documentation +- Detailed workflow guides +- Complex multi-step processes +- Information too lengthy for main SKILL.md +- Content that's only needed for specific use cases + +## Structure Suggestions + +### API Reference Example +- Overview +- Authentication +- Endpoints with examples +- Error codes +- Rate limits + +### Workflow Guide Example +- Prerequisites +- Step-by-step instructions +- Common patterns +- Troubleshooting +- Best practices +""" + +EXAMPLE_ASSET = """# Example Asset File + +This placeholder represents where asset files would be stored. +Replace with actual asset files (templates, images, fonts, etc.) or delete if not needed. + +Asset files are NOT intended to be loaded into context, but rather used within +the output Claude produces. + +Example asset files from other skills: +- Brand guidelines: logo.png, slides_template.pptx +- Frontend builder: hello-world/ directory with HTML/React boilerplate +- Typography: custom-font.ttf, font-family.woff2 +- Data: sample_data.csv, test_dataset.json + +## Common Asset Types + +- Templates: .pptx, .docx, boilerplate directories +- Images: .png, .jpg, .svg, .gif +- Fonts: .ttf, .otf, .woff, .woff2 +- Boilerplate code: Project directories, starter files +- Icons: .ico, .svg +- Data files: .csv, .json, .xml, .yaml + +Note: This is a text placeholder. Actual assets can be any file type. +""" + + +def title_case_skill_name(skill_name): + """Convert hyphenated skill name to Title Case for display.""" + return ' '.join(word.capitalize() for word in skill_name.split('-')) + + +def init_skill(skill_name, path): + """ + Initialize a new skill directory with template SKILL.md. + + Args: + skill_name: Name of the skill + path: Path where the skill directory should be created + + Returns: + Path to created skill directory, or None if error + """ + # Determine skill directory path + skill_dir = Path(path).resolve() / skill_name + + # Check if directory already exists + if skill_dir.exists(): + print(f"❌ Error: Skill directory already exists: {skill_dir}") + return None + + # Create skill directory + try: + skill_dir.mkdir(parents=True, exist_ok=False) + print(f"✅ Created skill directory: {skill_dir}") + except Exception as e: + print(f"❌ Error creating directory: {e}") + return None + + # Create SKILL.md from template + skill_title = title_case_skill_name(skill_name) + skill_content = SKILL_TEMPLATE.format( + skill_name=skill_name, + skill_title=skill_title + ) + + skill_md_path = skill_dir / 'SKILL.md' + try: + skill_md_path.write_text(skill_content) + print("✅ Created SKILL.md") + except Exception as e: + print(f"❌ Error creating SKILL.md: {e}") + return None + + # Create resource directories with example files + try: + # Create scripts/ directory with example script + scripts_dir = skill_dir / 'scripts' + scripts_dir.mkdir(exist_ok=True) + example_script = scripts_dir / 'example.py' + example_script.write_text(EXAMPLE_SCRIPT.format(skill_name=skill_name)) + example_script.chmod(0o755) + print("✅ Created scripts/example.py") + + # Create references/ directory with example reference doc + references_dir = skill_dir / 'references' + references_dir.mkdir(exist_ok=True) + example_reference = references_dir / 'api_reference.md' + example_reference.write_text(EXAMPLE_REFERENCE.format(skill_title=skill_title)) + print("✅ Created references/api_reference.md") + + # Create assets/ directory with example asset placeholder + assets_dir = skill_dir / 'assets' + assets_dir.mkdir(exist_ok=True) + example_asset = assets_dir / 'example_asset.txt' + example_asset.write_text(EXAMPLE_ASSET) + print("✅ Created assets/example_asset.txt") + except Exception as e: + print(f"❌ Error creating resource directories: {e}") + return None + + # Print next steps + print(f"\n✅ Skill '{skill_name}' initialized successfully at {skill_dir}") + print("\nNext steps:") + print("1. Edit SKILL.md to complete the TODO items and update the description") + print("2. Customize or delete the example files in scripts/, references/, and assets/") + print("3. Run the validator when ready to check the skill structure") + + return skill_dir + + +def main(): + if len(sys.argv) < 4 or sys.argv[2] != '--path': + print("Usage: init_skill.py --path ") + print("\nSkill name requirements:") + print(" - Hyphen-case identifier (e.g., 'data-analyzer')") + print(" - Lowercase letters, digits, and hyphens only") + print(" - Max 40 characters") + print(" - Must match directory name exactly") + print("\nExamples:") + print(" init_skill.py my-new-skill --path skills/public") + print(" init_skill.py my-api-helper --path skills/private") + print(" init_skill.py custom-skill --path /custom/location") + sys.exit(1) + + skill_name = sys.argv[1] + path = sys.argv[3] + + print(f"🚀 Initializing skill: {skill_name}") + print(f" Location: {path}") + print() + + result = init_skill(skill_name, path) + + if result: + sys.exit(0) + else: + sys.exit(1) + + +if __name__ == "__main__": + main() diff --git a/skills/skill-creator/scripts/package_skill.py b/skills/skill-creator/scripts/package_skill.py new file mode 100755 index 0000000..5cd36cb --- /dev/null +++ b/skills/skill-creator/scripts/package_skill.py @@ -0,0 +1,110 @@ +#!/usr/bin/env python3 +""" +Skill Packager - Creates a distributable .skill file of a skill folder + +Usage: + python utils/package_skill.py [output-directory] + +Example: + python utils/package_skill.py skills/public/my-skill + python utils/package_skill.py skills/public/my-skill ./dist +""" + +import sys +import zipfile +from pathlib import Path +from quick_validate import validate_skill + + +def package_skill(skill_path, output_dir=None): + """ + Package a skill folder into a .skill file. + + Args: + skill_path: Path to the skill folder + output_dir: Optional output directory for the .skill file (defaults to current directory) + + Returns: + Path to the created .skill file, or None if error + """ + skill_path = Path(skill_path).resolve() + + # Validate skill folder exists + if not skill_path.exists(): + print(f"❌ Error: Skill folder not found: {skill_path}") + return None + + if not skill_path.is_dir(): + print(f"❌ Error: Path is not a directory: {skill_path}") + return None + + # Validate SKILL.md exists + skill_md = skill_path / "SKILL.md" + if not skill_md.exists(): + print(f"❌ Error: SKILL.md not found in {skill_path}") + return None + + # Run validation before packaging + print("🔍 Validating skill...") + valid, message = validate_skill(skill_path) + if not valid: + print(f"❌ Validation failed: {message}") + print(" Please fix the validation errors before packaging.") + return None + print(f"✅ {message}\n") + + # Determine output location + skill_name = skill_path.name + if output_dir: + output_path = Path(output_dir).resolve() + output_path.mkdir(parents=True, exist_ok=True) + else: + output_path = Path.cwd() + + skill_filename = output_path / f"{skill_name}.skill" + + # Create the .skill file (zip format) + try: + with zipfile.ZipFile(skill_filename, 'w', zipfile.ZIP_DEFLATED) as zipf: + # Walk through the skill directory + for file_path in skill_path.rglob('*'): + if file_path.is_file(): + # Calculate the relative path within the zip + arcname = file_path.relative_to(skill_path.parent) + zipf.write(file_path, arcname) + print(f" Added: {arcname}") + + print(f"\n✅ Successfully packaged skill to: {skill_filename}") + return skill_filename + + except Exception as e: + print(f"❌ Error creating .skill file: {e}") + return None + + +def main(): + if len(sys.argv) < 2: + print("Usage: python utils/package_skill.py [output-directory]") + print("\nExample:") + print(" python utils/package_skill.py skills/public/my-skill") + print(" python utils/package_skill.py skills/public/my-skill ./dist") + sys.exit(1) + + skill_path = sys.argv[1] + output_dir = sys.argv[2] if len(sys.argv) > 2 else None + + print(f"📦 Packaging skill: {skill_path}") + if output_dir: + print(f" Output directory: {output_dir}") + print() + + result = package_skill(skill_path, output_dir) + + if result: + sys.exit(0) + else: + sys.exit(1) + + +if __name__ == "__main__": + main() diff --git a/skills/skill-creator/scripts/quick_validate.py b/skills/skill-creator/scripts/quick_validate.py new file mode 100755 index 0000000..d9fbeb7 --- /dev/null +++ b/skills/skill-creator/scripts/quick_validate.py @@ -0,0 +1,95 @@ +#!/usr/bin/env python3 +""" +Quick validation script for skills - minimal version +""" + +import sys +import os +import re +import yaml +from pathlib import Path + +def validate_skill(skill_path): + """Basic validation of a skill""" + skill_path = Path(skill_path) + + # Check SKILL.md exists + skill_md = skill_path / 'SKILL.md' + if not skill_md.exists(): + return False, "SKILL.md not found" + + # Read and validate frontmatter + content = skill_md.read_text() + if not content.startswith('---'): + return False, "No YAML frontmatter found" + + # Extract frontmatter + match = re.match(r'^---\n(.*?)\n---', content, re.DOTALL) + if not match: + return False, "Invalid frontmatter format" + + frontmatter_text = match.group(1) + + # Parse YAML frontmatter + try: + frontmatter = yaml.safe_load(frontmatter_text) + if not isinstance(frontmatter, dict): + return False, "Frontmatter must be a YAML dictionary" + except yaml.YAMLError as e: + return False, f"Invalid YAML in frontmatter: {e}" + + # Define allowed properties + ALLOWED_PROPERTIES = {'name', 'description', 'license', 'allowed-tools', 'metadata'} + + # Check for unexpected properties (excluding nested keys under metadata) + unexpected_keys = set(frontmatter.keys()) - ALLOWED_PROPERTIES + if unexpected_keys: + return False, ( + f"Unexpected key(s) in SKILL.md frontmatter: {', '.join(sorted(unexpected_keys))}. " + f"Allowed properties are: {', '.join(sorted(ALLOWED_PROPERTIES))}" + ) + + # Check required fields + if 'name' not in frontmatter: + return False, "Missing 'name' in frontmatter" + if 'description' not in frontmatter: + return False, "Missing 'description' in frontmatter" + + # Extract name for validation + name = frontmatter.get('name', '') + if not isinstance(name, str): + return False, f"Name must be a string, got {type(name).__name__}" + name = name.strip() + if name: + # Check naming convention (hyphen-case: lowercase with hyphens) + if not re.match(r'^[a-z0-9-]+$', name): + return False, f"Name '{name}' should be hyphen-case (lowercase letters, digits, and hyphens only)" + if name.startswith('-') or name.endswith('-') or '--' in name: + return False, f"Name '{name}' cannot start/end with hyphen or contain consecutive hyphens" + # Check name length (max 64 characters per spec) + if len(name) > 64: + return False, f"Name is too long ({len(name)} characters). Maximum is 64 characters." + + # Extract and validate description + description = frontmatter.get('description', '') + if not isinstance(description, str): + return False, f"Description must be a string, got {type(description).__name__}" + description = description.strip() + if description: + # Check for angle brackets + if '<' in description or '>' in description: + return False, "Description cannot contain angle brackets (< or >)" + # Check description length (max 1024 characters per spec) + if len(description) > 1024: + return False, f"Description is too long ({len(description)} characters). Maximum is 1024 characters." + + return True, "Skill is valid!" + +if __name__ == "__main__": + if len(sys.argv) != 2: + print("Usage: python quick_validate.py ") + sys.exit(1) + + valid, message = validate_skill(sys.argv[1]) + print(message) + sys.exit(0 if valid else 1) \ No newline at end of file diff --git a/skills/slack-gif-creator/LICENSE.txt b/skills/slack-gif-creator/LICENSE.txt new file mode 100644 index 0000000..7a4a3ea --- /dev/null +++ b/skills/slack-gif-creator/LICENSE.txt @@ -0,0 +1,202 @@ + + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [yyyy] [name of copyright owner] + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. \ No newline at end of file diff --git a/skills/slack-gif-creator/SKILL.md b/skills/slack-gif-creator/SKILL.md new file mode 100644 index 0000000..16660d8 --- /dev/null +++ b/skills/slack-gif-creator/SKILL.md @@ -0,0 +1,254 @@ +--- +name: slack-gif-creator +description: Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." +license: Complete terms in LICENSE.txt +--- + +# Slack GIF Creator + +A toolkit providing utilities and knowledge for creating animated GIFs optimized for Slack. + +## Slack Requirements + +**Dimensions:** +- Emoji GIFs: 128x128 (recommended) +- Message GIFs: 480x480 + +**Parameters:** +- FPS: 10-30 (lower is smaller file size) +- Colors: 48-128 (fewer = smaller file size) +- Duration: Keep under 3 seconds for emoji GIFs + +## Core Workflow + +```python +from core.gif_builder import GIFBuilder +from PIL import Image, ImageDraw + +# 1. Create builder +builder = GIFBuilder(width=128, height=128, fps=10) + +# 2. Generate frames +for i in range(12): + frame = Image.new('RGB', (128, 128), (240, 248, 255)) + draw = ImageDraw.Draw(frame) + + # Draw your animation using PIL primitives + # (circles, polygons, lines, etc.) + + builder.add_frame(frame) + +# 3. Save with optimization +builder.save('output.gif', num_colors=48, optimize_for_emoji=True) +``` + +## Drawing Graphics + +### Working with User-Uploaded Images +If a user uploads an image, consider whether they want to: +- **Use it directly** (e.g., "animate this", "split this into frames") +- **Use it as inspiration** (e.g., "make something like this") + +Load and work with images using PIL: +```python +from PIL import Image + +uploaded = Image.open('file.png') +# Use directly, or just as reference for colors/style +``` + +### Drawing from Scratch +When drawing graphics from scratch, use PIL ImageDraw primitives: + +```python +from PIL import ImageDraw + +draw = ImageDraw.Draw(frame) + +# Circles/ovals +draw.ellipse([x1, y1, x2, y2], fill=(r, g, b), outline=(r, g, b), width=3) + +# Stars, triangles, any polygon +points = [(x1, y1), (x2, y2), (x3, y3), ...] +draw.polygon(points, fill=(r, g, b), outline=(r, g, b), width=3) + +# Lines +draw.line([(x1, y1), (x2, y2)], fill=(r, g, b), width=5) + +# Rectangles +draw.rectangle([x1, y1, x2, y2], fill=(r, g, b), outline=(r, g, b), width=3) +``` + +**Don't use:** Emoji fonts (unreliable across platforms) or assume pre-packaged graphics exist in this skill. + +### Making Graphics Look Good + +Graphics should look polished and creative, not basic. Here's how: + +**Use thicker lines** - Always set `width=2` or higher for outlines and lines. Thin lines (width=1) look choppy and amateurish. + +**Add visual depth**: +- Use gradients for backgrounds (`create_gradient_background`) +- Layer multiple shapes for complexity (e.g., a star with a smaller star inside) + +**Make shapes more interesting**: +- Don't just draw a plain circle - add highlights, rings, or patterns +- Stars can have glows (draw larger, semi-transparent versions behind) +- Combine multiple shapes (stars + sparkles, circles + rings) + +**Pay attention to colors**: +- Use vibrant, complementary colors +- Add contrast (dark outlines on light shapes, light outlines on dark shapes) +- Consider the overall composition + +**For complex shapes** (hearts, snowflakes, etc.): +- Use combinations of polygons and ellipses +- Calculate points carefully for symmetry +- Add details (a heart can have a highlight curve, snowflakes have intricate branches) + +Be creative and detailed! A good Slack GIF should look polished, not like placeholder graphics. + +## Available Utilities + +### GIFBuilder (`core.gif_builder`) +Assembles frames and optimizes for Slack: +```python +builder = GIFBuilder(width=128, height=128, fps=10) +builder.add_frame(frame) # Add PIL Image +builder.add_frames(frames) # Add list of frames +builder.save('out.gif', num_colors=48, optimize_for_emoji=True, remove_duplicates=True) +``` + +### Validators (`core.validators`) +Check if GIF meets Slack requirements: +```python +from core.validators import validate_gif, is_slack_ready + +# Detailed validation +passes, info = validate_gif('my.gif', is_emoji=True, verbose=True) + +# Quick check +if is_slack_ready('my.gif'): + print("Ready!") +``` + +### Easing Functions (`core.easing`) +Smooth motion instead of linear: +```python +from core.easing import interpolate + +# Progress from 0.0 to 1.0 +t = i / (num_frames - 1) + +# Apply easing +y = interpolate(start=0, end=400, t=t, easing='ease_out') + +# Available: linear, ease_in, ease_out, ease_in_out, +# bounce_out, elastic_out, back_out +``` + +### Frame Helpers (`core.frame_composer`) +Convenience functions for common needs: +```python +from core.frame_composer import ( + create_blank_frame, # Solid color background + create_gradient_background, # Vertical gradient + draw_circle, # Helper for circles + draw_text, # Simple text rendering + draw_star # 5-pointed star +) +``` + +## Animation Concepts + +### Shake/Vibrate +Offset object position with oscillation: +- Use `math.sin()` or `math.cos()` with frame index +- Add small random variations for natural feel +- Apply to x and/or y position + +### Pulse/Heartbeat +Scale object size rhythmically: +- Use `math.sin(t * frequency * 2 * math.pi)` for smooth pulse +- For heartbeat: two quick pulses then pause (adjust sine wave) +- Scale between 0.8 and 1.2 of base size + +### Bounce +Object falls and bounces: +- Use `interpolate()` with `easing='bounce_out'` for landing +- Use `easing='ease_in'` for falling (accelerating) +- Apply gravity by increasing y velocity each frame + +### Spin/Rotate +Rotate object around center: +- PIL: `image.rotate(angle, resample=Image.BICUBIC)` +- For wobble: use sine wave for angle instead of linear + +### Fade In/Out +Gradually appear or disappear: +- Create RGBA image, adjust alpha channel +- Or use `Image.blend(image1, image2, alpha)` +- Fade in: alpha from 0 to 1 +- Fade out: alpha from 1 to 0 + +### Slide +Move object from off-screen to position: +- Start position: outside frame bounds +- End position: target location +- Use `interpolate()` with `easing='ease_out'` for smooth stop +- For overshoot: use `easing='back_out'` + +### Zoom +Scale and position for zoom effect: +- Zoom in: scale from 0.1 to 2.0, crop center +- Zoom out: scale from 2.0 to 1.0 +- Can add motion blur for drama (PIL filter) + +### Explode/Particle Burst +Create particles radiating outward: +- Generate particles with random angles and velocities +- Update each particle: `x += vx`, `y += vy` +- Add gravity: `vy += gravity_constant` +- Fade out particles over time (reduce alpha) + +## Optimization Strategies + +Only when asked to make the file size smaller, implement a few of the following methods: + +1. **Fewer frames** - Lower FPS (10 instead of 20) or shorter duration +2. **Fewer colors** - `num_colors=48` instead of 128 +3. **Smaller dimensions** - 128x128 instead of 480x480 +4. **Remove duplicates** - `remove_duplicates=True` in save() +5. **Emoji mode** - `optimize_for_emoji=True` auto-optimizes + +```python +# Maximum optimization for emoji +builder.save( + 'emoji.gif', + num_colors=48, + optimize_for_emoji=True, + remove_duplicates=True +) +``` + +## Philosophy + +This skill provides: +- **Knowledge**: Slack's requirements and animation concepts +- **Utilities**: GIFBuilder, validators, easing functions +- **Flexibility**: Create the animation logic using PIL primitives + +It does NOT provide: +- Rigid animation templates or pre-made functions +- Emoji font rendering (unreliable across platforms) +- A library of pre-packaged graphics built into the skill + +**Note on user uploads**: This skill doesn't include pre-built graphics, but if a user uploads an image, use PIL to load and work with it - interpret based on their request whether they want it used directly or just as inspiration. + +Be creative! Combine concepts (bouncing + rotating, pulsing + sliding, etc.) and use PIL's full capabilities. + +## Dependencies + +```bash +pip install pillow imageio numpy +``` diff --git a/skills/slack-gif-creator/core/easing.py b/skills/slack-gif-creator/core/easing.py new file mode 100755 index 0000000..772fa83 --- /dev/null +++ b/skills/slack-gif-creator/core/easing.py @@ -0,0 +1,234 @@ +#!/usr/bin/env python3 +""" +Easing Functions - Timing functions for smooth animations. + +Provides various easing functions for natural motion and timing. +All functions take a value t (0.0 to 1.0) and return eased value (0.0 to 1.0). +""" + +import math + + +def linear(t: float) -> float: + """Linear interpolation (no easing).""" + return t + + +def ease_in_quad(t: float) -> float: + """Quadratic ease-in (slow start, accelerating).""" + return t * t + + +def ease_out_quad(t: float) -> float: + """Quadratic ease-out (fast start, decelerating).""" + return t * (2 - t) + + +def ease_in_out_quad(t: float) -> float: + """Quadratic ease-in-out (slow start and end).""" + if t < 0.5: + return 2 * t * t + return -1 + (4 - 2 * t) * t + + +def ease_in_cubic(t: float) -> float: + """Cubic ease-in (slow start).""" + return t * t * t + + +def ease_out_cubic(t: float) -> float: + """Cubic ease-out (fast start).""" + return (t - 1) * (t - 1) * (t - 1) + 1 + + +def ease_in_out_cubic(t: float) -> float: + """Cubic ease-in-out.""" + if t < 0.5: + return 4 * t * t * t + return (t - 1) * (2 * t - 2) * (2 * t - 2) + 1 + + +def ease_in_bounce(t: float) -> float: + """Bounce ease-in (bouncy start).""" + return 1 - ease_out_bounce(1 - t) + + +def ease_out_bounce(t: float) -> float: + """Bounce ease-out (bouncy end).""" + if t < 1 / 2.75: + return 7.5625 * t * t + elif t < 2 / 2.75: + t -= 1.5 / 2.75 + return 7.5625 * t * t + 0.75 + elif t < 2.5 / 2.75: + t -= 2.25 / 2.75 + return 7.5625 * t * t + 0.9375 + else: + t -= 2.625 / 2.75 + return 7.5625 * t * t + 0.984375 + + +def ease_in_out_bounce(t: float) -> float: + """Bounce ease-in-out.""" + if t < 0.5: + return ease_in_bounce(t * 2) * 0.5 + return ease_out_bounce(t * 2 - 1) * 0.5 + 0.5 + + +def ease_in_elastic(t: float) -> float: + """Elastic ease-in (spring effect).""" + if t == 0 or t == 1: + return t + return -math.pow(2, 10 * (t - 1)) * math.sin((t - 1.1) * 5 * math.pi) + + +def ease_out_elastic(t: float) -> float: + """Elastic ease-out (spring effect).""" + if t == 0 or t == 1: + return t + return math.pow(2, -10 * t) * math.sin((t - 0.1) * 5 * math.pi) + 1 + + +def ease_in_out_elastic(t: float) -> float: + """Elastic ease-in-out.""" + if t == 0 or t == 1: + return t + t = t * 2 - 1 + if t < 0: + return -0.5 * math.pow(2, 10 * t) * math.sin((t - 0.1) * 5 * math.pi) + return math.pow(2, -10 * t) * math.sin((t - 0.1) * 5 * math.pi) * 0.5 + 1 + + +# Convenience mapping +EASING_FUNCTIONS = { + "linear": linear, + "ease_in": ease_in_quad, + "ease_out": ease_out_quad, + "ease_in_out": ease_in_out_quad, + "bounce_in": ease_in_bounce, + "bounce_out": ease_out_bounce, + "bounce": ease_in_out_bounce, + "elastic_in": ease_in_elastic, + "elastic_out": ease_out_elastic, + "elastic": ease_in_out_elastic, +} + + +def get_easing(name: str = "linear"): + """Get easing function by name.""" + return EASING_FUNCTIONS.get(name, linear) + + +def interpolate(start: float, end: float, t: float, easing: str = "linear") -> float: + """ + Interpolate between two values with easing. + + Args: + start: Start value + end: End value + t: Progress from 0.0 to 1.0 + easing: Name of easing function + + Returns: + Interpolated value + """ + ease_func = get_easing(easing) + eased_t = ease_func(t) + return start + (end - start) * eased_t + + +def ease_back_in(t: float) -> float: + """Back ease-in (slight overshoot backward before forward motion).""" + c1 = 1.70158 + c3 = c1 + 1 + return c3 * t * t * t - c1 * t * t + + +def ease_back_out(t: float) -> float: + """Back ease-out (overshoot forward then settle back).""" + c1 = 1.70158 + c3 = c1 + 1 + return 1 + c3 * pow(t - 1, 3) + c1 * pow(t - 1, 2) + + +def ease_back_in_out(t: float) -> float: + """Back ease-in-out (overshoot at both ends).""" + c1 = 1.70158 + c2 = c1 * 1.525 + if t < 0.5: + return (pow(2 * t, 2) * ((c2 + 1) * 2 * t - c2)) / 2 + return (pow(2 * t - 2, 2) * ((c2 + 1) * (t * 2 - 2) + c2) + 2) / 2 + + +def apply_squash_stretch( + base_scale: tuple[float, float], intensity: float, direction: str = "vertical" +) -> tuple[float, float]: + """ + Calculate squash and stretch scales for more dynamic animation. + + Args: + base_scale: (width_scale, height_scale) base scales + intensity: Squash/stretch intensity (0.0-1.0) + direction: 'vertical', 'horizontal', or 'both' + + Returns: + (width_scale, height_scale) with squash/stretch applied + """ + width_scale, height_scale = base_scale + + if direction == "vertical": + # Compress vertically, expand horizontally (preserve volume) + height_scale *= 1 - intensity * 0.5 + width_scale *= 1 + intensity * 0.5 + elif direction == "horizontal": + # Compress horizontally, expand vertically + width_scale *= 1 - intensity * 0.5 + height_scale *= 1 + intensity * 0.5 + elif direction == "both": + # General squash (both dimensions) + width_scale *= 1 - intensity * 0.3 + height_scale *= 1 - intensity * 0.3 + + return (width_scale, height_scale) + + +def calculate_arc_motion( + start: tuple[float, float], end: tuple[float, float], height: float, t: float +) -> tuple[float, float]: + """ + Calculate position along a parabolic arc (natural motion path). + + Args: + start: (x, y) starting position + end: (x, y) ending position + height: Arc height at midpoint (positive = upward) + t: Progress (0.0-1.0) + + Returns: + (x, y) position along arc + """ + x1, y1 = start + x2, y2 = end + + # Linear interpolation for x + x = x1 + (x2 - x1) * t + + # Parabolic interpolation for y + # y = start + progress * (end - start) + arc_offset + # Arc offset peaks at t=0.5 + arc_offset = 4 * height * t * (1 - t) + y = y1 + (y2 - y1) * t - arc_offset + + return (x, y) + + +# Add new easing functions to the convenience mapping +EASING_FUNCTIONS.update( + { + "back_in": ease_back_in, + "back_out": ease_back_out, + "back_in_out": ease_back_in_out, + "anticipate": ease_back_in, # Alias + "overshoot": ease_back_out, # Alias + } +) diff --git a/skills/slack-gif-creator/core/frame_composer.py b/skills/slack-gif-creator/core/frame_composer.py new file mode 100755 index 0000000..1afe434 --- /dev/null +++ b/skills/slack-gif-creator/core/frame_composer.py @@ -0,0 +1,176 @@ +#!/usr/bin/env python3 +""" +Frame Composer - Utilities for composing visual elements into frames. + +Provides functions for drawing shapes, text, emojis, and compositing elements +together to create animation frames. +""" + +from typing import Optional + +import numpy as np +from PIL import Image, ImageDraw, ImageFont + + +def create_blank_frame( + width: int, height: int, color: tuple[int, int, int] = (255, 255, 255) +) -> Image.Image: + """ + Create a blank frame with solid color background. + + Args: + width: Frame width + height: Frame height + color: RGB color tuple (default: white) + + Returns: + PIL Image + """ + return Image.new("RGB", (width, height), color) + + +def draw_circle( + frame: Image.Image, + center: tuple[int, int], + radius: int, + fill_color: Optional[tuple[int, int, int]] = None, + outline_color: Optional[tuple[int, int, int]] = None, + outline_width: int = 1, +) -> Image.Image: + """ + Draw a circle on a frame. + + Args: + frame: PIL Image to draw on + center: (x, y) center position + radius: Circle radius + fill_color: RGB fill color (None for no fill) + outline_color: RGB outline color (None for no outline) + outline_width: Outline width in pixels + + Returns: + Modified frame + """ + draw = ImageDraw.Draw(frame) + x, y = center + bbox = [x - radius, y - radius, x + radius, y + radius] + draw.ellipse(bbox, fill=fill_color, outline=outline_color, width=outline_width) + return frame + + +def draw_text( + frame: Image.Image, + text: str, + position: tuple[int, int], + color: tuple[int, int, int] = (0, 0, 0), + centered: bool = False, +) -> Image.Image: + """ + Draw text on a frame. + + Args: + frame: PIL Image to draw on + text: Text to draw + position: (x, y) position (top-left unless centered=True) + color: RGB text color + centered: If True, center text at position + + Returns: + Modified frame + """ + draw = ImageDraw.Draw(frame) + + # Uses Pillow's default font. + # If the font should be changed for the emoji, add additional logic here. + font = ImageFont.load_default() + + if centered: + bbox = draw.textbbox((0, 0), text, font=font) + text_width = bbox[2] - bbox[0] + text_height = bbox[3] - bbox[1] + x = position[0] - text_width // 2 + y = position[1] - text_height // 2 + position = (x, y) + + draw.text(position, text, fill=color, font=font) + return frame + + +def create_gradient_background( + width: int, + height: int, + top_color: tuple[int, int, int], + bottom_color: tuple[int, int, int], +) -> Image.Image: + """ + Create a vertical gradient background. + + Args: + width: Frame width + height: Frame height + top_color: RGB color at top + bottom_color: RGB color at bottom + + Returns: + PIL Image with gradient + """ + frame = Image.new("RGB", (width, height)) + draw = ImageDraw.Draw(frame) + + # Calculate color step for each row + r1, g1, b1 = top_color + r2, g2, b2 = bottom_color + + for y in range(height): + # Interpolate color + ratio = y / height + r = int(r1 * (1 - ratio) + r2 * ratio) + g = int(g1 * (1 - ratio) + g2 * ratio) + b = int(b1 * (1 - ratio) + b2 * ratio) + + # Draw horizontal line + draw.line([(0, y), (width, y)], fill=(r, g, b)) + + return frame + + +def draw_star( + frame: Image.Image, + center: tuple[int, int], + size: int, + fill_color: tuple[int, int, int], + outline_color: Optional[tuple[int, int, int]] = None, + outline_width: int = 1, +) -> Image.Image: + """ + Draw a 5-pointed star. + + Args: + frame: PIL Image to draw on + center: (x, y) center position + size: Star size (outer radius) + fill_color: RGB fill color + outline_color: RGB outline color (None for no outline) + outline_width: Outline width + + Returns: + Modified frame + """ + import math + + draw = ImageDraw.Draw(frame) + x, y = center + + # Calculate star points + points = [] + for i in range(10): + angle = (i * 36 - 90) * math.pi / 180 # 36 degrees per point, start at top + radius = size if i % 2 == 0 else size * 0.4 # Alternate between outer and inner + px = x + radius * math.cos(angle) + py = y + radius * math.sin(angle) + points.append((px, py)) + + # Draw star + draw.polygon(points, fill=fill_color, outline=outline_color, width=outline_width) + + return frame diff --git a/skills/slack-gif-creator/core/gif_builder.py b/skills/slack-gif-creator/core/gif_builder.py new file mode 100755 index 0000000..5759f14 --- /dev/null +++ b/skills/slack-gif-creator/core/gif_builder.py @@ -0,0 +1,269 @@ +#!/usr/bin/env python3 +""" +GIF Builder - Core module for assembling frames into GIFs optimized for Slack. + +This module provides the main interface for creating GIFs from programmatically +generated frames, with automatic optimization for Slack's requirements. +""" + +from pathlib import Path +from typing import Optional + +import imageio.v3 as imageio +import numpy as np +from PIL import Image + + +class GIFBuilder: + """Builder for creating optimized GIFs from frames.""" + + def __init__(self, width: int = 480, height: int = 480, fps: int = 15): + """ + Initialize GIF builder. + + Args: + width: Frame width in pixels + height: Frame height in pixels + fps: Frames per second + """ + self.width = width + self.height = height + self.fps = fps + self.frames: list[np.ndarray] = [] + + def add_frame(self, frame: np.ndarray | Image.Image): + """ + Add a frame to the GIF. + + Args: + frame: Frame as numpy array or PIL Image (will be converted to RGB) + """ + if isinstance(frame, Image.Image): + frame = np.array(frame.convert("RGB")) + + # Ensure frame is correct size + if frame.shape[:2] != (self.height, self.width): + pil_frame = Image.fromarray(frame) + pil_frame = pil_frame.resize( + (self.width, self.height), Image.Resampling.LANCZOS + ) + frame = np.array(pil_frame) + + self.frames.append(frame) + + def add_frames(self, frames: list[np.ndarray | Image.Image]): + """Add multiple frames at once.""" + for frame in frames: + self.add_frame(frame) + + def optimize_colors( + self, num_colors: int = 128, use_global_palette: bool = True + ) -> list[np.ndarray]: + """ + Reduce colors in all frames using quantization. + + Args: + num_colors: Target number of colors (8-256) + use_global_palette: Use a single palette for all frames (better compression) + + Returns: + List of color-optimized frames + """ + optimized = [] + + if use_global_palette and len(self.frames) > 1: + # Create a global palette from all frames + # Sample frames to build palette + sample_size = min(5, len(self.frames)) + sample_indices = [ + int(i * len(self.frames) / sample_size) for i in range(sample_size) + ] + sample_frames = [self.frames[i] for i in sample_indices] + + # Combine sample frames into a single image for palette generation + # Flatten each frame to get all pixels, then stack them + all_pixels = np.vstack( + [f.reshape(-1, 3) for f in sample_frames] + ) # (total_pixels, 3) + + # Create a properly-shaped RGB image from the pixel data + # We'll make a roughly square image from all the pixels + total_pixels = len(all_pixels) + width = min(512, int(np.sqrt(total_pixels))) # Reasonable width, max 512 + height = (total_pixels + width - 1) // width # Ceiling division + + # Pad if necessary to fill the rectangle + pixels_needed = width * height + if pixels_needed > total_pixels: + padding = np.zeros((pixels_needed - total_pixels, 3), dtype=np.uint8) + all_pixels = np.vstack([all_pixels, padding]) + + # Reshape to proper RGB image format (H, W, 3) + img_array = ( + all_pixels[:pixels_needed].reshape(height, width, 3).astype(np.uint8) + ) + combined_img = Image.fromarray(img_array, mode="RGB") + + # Generate global palette + global_palette = combined_img.quantize(colors=num_colors, method=2) + + # Apply global palette to all frames + for frame in self.frames: + pil_frame = Image.fromarray(frame) + quantized = pil_frame.quantize(palette=global_palette, dither=1) + optimized.append(np.array(quantized.convert("RGB"))) + else: + # Use per-frame quantization + for frame in self.frames: + pil_frame = Image.fromarray(frame) + quantized = pil_frame.quantize(colors=num_colors, method=2, dither=1) + optimized.append(np.array(quantized.convert("RGB"))) + + return optimized + + def deduplicate_frames(self, threshold: float = 0.9995) -> int: + """ + Remove duplicate or near-duplicate consecutive frames. + + Args: + threshold: Similarity threshold (0.0-1.0). Higher = more strict (0.9995 = nearly identical). + Use 0.9995+ to preserve subtle animations, 0.98 for aggressive removal. + + Returns: + Number of frames removed + """ + if len(self.frames) < 2: + return 0 + + deduplicated = [self.frames[0]] + removed_count = 0 + + for i in range(1, len(self.frames)): + # Compare with previous frame + prev_frame = np.array(deduplicated[-1], dtype=np.float32) + curr_frame = np.array(self.frames[i], dtype=np.float32) + + # Calculate similarity (normalized) + diff = np.abs(prev_frame - curr_frame) + similarity = 1.0 - (np.mean(diff) / 255.0) + + # Keep frame if sufficiently different + # High threshold (0.9995+) means only remove nearly identical frames + if similarity < threshold: + deduplicated.append(self.frames[i]) + else: + removed_count += 1 + + self.frames = deduplicated + return removed_count + + def save( + self, + output_path: str | Path, + num_colors: int = 128, + optimize_for_emoji: bool = False, + remove_duplicates: bool = False, + ) -> dict: + """ + Save frames as optimized GIF for Slack. + + Args: + output_path: Where to save the GIF + num_colors: Number of colors to use (fewer = smaller file) + optimize_for_emoji: If True, optimize for emoji size (128x128, fewer colors) + remove_duplicates: If True, remove duplicate consecutive frames (opt-in) + + Returns: + Dictionary with file info (path, size, dimensions, frame_count) + """ + if not self.frames: + raise ValueError("No frames to save. Add frames with add_frame() first.") + + output_path = Path(output_path) + + # Remove duplicate frames to reduce file size + if remove_duplicates: + removed = self.deduplicate_frames(threshold=0.9995) + if removed > 0: + print( + f" Removed {removed} nearly identical frames (preserved subtle animations)" + ) + + # Optimize for emoji if requested + if optimize_for_emoji: + if self.width > 128 or self.height > 128: + print( + f" Resizing from {self.width}x{self.height} to 128x128 for emoji" + ) + self.width = 128 + self.height = 128 + # Resize all frames + resized_frames = [] + for frame in self.frames: + pil_frame = Image.fromarray(frame) + pil_frame = pil_frame.resize((128, 128), Image.Resampling.LANCZOS) + resized_frames.append(np.array(pil_frame)) + self.frames = resized_frames + num_colors = min(num_colors, 48) # More aggressive color limit for emoji + + # More aggressive FPS reduction for emoji + if len(self.frames) > 12: + print( + f" Reducing frames from {len(self.frames)} to ~12 for emoji size" + ) + # Keep every nth frame to get close to 12 frames + keep_every = max(1, len(self.frames) // 12) + self.frames = [ + self.frames[i] for i in range(0, len(self.frames), keep_every) + ] + + # Optimize colors with global palette + optimized_frames = self.optimize_colors(num_colors, use_global_palette=True) + + # Calculate frame duration in milliseconds + frame_duration = 1000 / self.fps + + # Save GIF + imageio.imwrite( + output_path, + optimized_frames, + duration=frame_duration, + loop=0, # Infinite loop + ) + + # Get file info + file_size_kb = output_path.stat().st_size / 1024 + file_size_mb = file_size_kb / 1024 + + info = { + "path": str(output_path), + "size_kb": file_size_kb, + "size_mb": file_size_mb, + "dimensions": f"{self.width}x{self.height}", + "frame_count": len(optimized_frames), + "fps": self.fps, + "duration_seconds": len(optimized_frames) / self.fps, + "colors": num_colors, + } + + # Print info + print(f"\n✓ GIF created successfully!") + print(f" Path: {output_path}") + print(f" Size: {file_size_kb:.1f} KB ({file_size_mb:.2f} MB)") + print(f" Dimensions: {self.width}x{self.height}") + print(f" Frames: {len(optimized_frames)} @ {self.fps} fps") + print(f" Duration: {info['duration_seconds']:.1f}s") + print(f" Colors: {num_colors}") + + # Size info + if optimize_for_emoji: + print(f" Optimized for emoji (128x128, reduced colors)") + if file_size_mb > 1.0: + print(f"\n Note: Large file size ({file_size_kb:.1f} KB)") + print(" Consider: fewer frames, smaller dimensions, or fewer colors") + + return info + + def clear(self): + """Clear all frames (useful for creating multiple GIFs).""" + self.frames = [] diff --git a/skills/slack-gif-creator/core/validators.py b/skills/slack-gif-creator/core/validators.py new file mode 100755 index 0000000..a6f5bdf --- /dev/null +++ b/skills/slack-gif-creator/core/validators.py @@ -0,0 +1,136 @@ +#!/usr/bin/env python3 +""" +Validators - Check if GIFs meet Slack's requirements. + +These validators help ensure your GIFs meet Slack's size and dimension constraints. +""" + +from pathlib import Path + + +def validate_gif( + gif_path: str | Path, is_emoji: bool = True, verbose: bool = True +) -> tuple[bool, dict]: + """ + Validate GIF for Slack (dimensions, size, frame count). + + Args: + gif_path: Path to GIF file + is_emoji: True for emoji (128x128 recommended), False for message GIF + verbose: Print validation details + + Returns: + Tuple of (passes: bool, results: dict with all details) + """ + from PIL import Image + + gif_path = Path(gif_path) + + if not gif_path.exists(): + return False, {"error": f"File not found: {gif_path}"} + + # Get file size + size_bytes = gif_path.stat().st_size + size_kb = size_bytes / 1024 + size_mb = size_kb / 1024 + + # Get dimensions and frame info + try: + with Image.open(gif_path) as img: + width, height = img.size + + # Count frames + frame_count = 0 + try: + while True: + img.seek(frame_count) + frame_count += 1 + except EOFError: + pass + + # Get duration + try: + duration_ms = img.info.get("duration", 100) + total_duration = (duration_ms * frame_count) / 1000 + fps = frame_count / total_duration if total_duration > 0 else 0 + except: + total_duration = None + fps = None + + except Exception as e: + return False, {"error": f"Failed to read GIF: {e}"} + + # Validate dimensions + if is_emoji: + optimal = width == height == 128 + acceptable = width == height and 64 <= width <= 128 + dim_pass = acceptable + else: + aspect_ratio = ( + max(width, height) / min(width, height) + if min(width, height) > 0 + else float("inf") + ) + dim_pass = aspect_ratio <= 2.0 and 320 <= min(width, height) <= 640 + + results = { + "file": str(gif_path), + "passes": dim_pass, + "width": width, + "height": height, + "size_kb": size_kb, + "size_mb": size_mb, + "frame_count": frame_count, + "duration_seconds": total_duration, + "fps": fps, + "is_emoji": is_emoji, + "optimal": optimal if is_emoji else None, + } + + # Print if verbose + if verbose: + print(f"\nValidating {gif_path.name}:") + print( + f" Dimensions: {width}x{height}" + + ( + f" ({'optimal' if optimal else 'acceptable'})" + if is_emoji and acceptable + else "" + ) + ) + print( + f" Size: {size_kb:.1f} KB" + + (f" ({size_mb:.2f} MB)" if size_mb >= 1.0 else "") + ) + print( + f" Frames: {frame_count}" + + (f" @ {fps:.1f} fps ({total_duration:.1f}s)" if fps else "") + ) + + if not dim_pass: + print( + f" Note: {'Emoji should be 128x128' if is_emoji else 'Unusual dimensions for Slack'}" + ) + + if size_mb > 5.0: + print(f" Note: Large file size - consider fewer frames/colors") + + return dim_pass, results + + +def is_slack_ready( + gif_path: str | Path, is_emoji: bool = True, verbose: bool = True +) -> bool: + """ + Quick check if GIF is ready for Slack. + + Args: + gif_path: Path to GIF file + is_emoji: True for emoji GIF, False for message GIF + verbose: Print feedback + + Returns: + True if dimensions are acceptable + """ + passes, _ = validate_gif(gif_path, is_emoji, verbose) + return passes diff --git a/skills/slack-gif-creator/requirements.txt b/skills/slack-gif-creator/requirements.txt new file mode 100644 index 0000000..8bc4493 --- /dev/null +++ b/skills/slack-gif-creator/requirements.txt @@ -0,0 +1,4 @@ +pillow>=10.0.0 +imageio>=2.31.0 +imageio-ffmpeg>=0.4.9 +numpy>=1.24.0 \ No newline at end of file diff --git a/skills/theme-factory/LICENSE.txt b/skills/theme-factory/LICENSE.txt new file mode 100644 index 0000000..7a4a3ea --- /dev/null +++ b/skills/theme-factory/LICENSE.txt @@ -0,0 +1,202 @@ + + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [yyyy] [name of copyright owner] + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. \ No newline at end of file diff --git a/skills/theme-factory/SKILL.md b/skills/theme-factory/SKILL.md new file mode 100644 index 0000000..90dfcea --- /dev/null +++ b/skills/theme-factory/SKILL.md @@ -0,0 +1,59 @@ +--- +name: theme-factory +description: Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly. +license: Complete terms in LICENSE.txt +--- + + +# Theme Factory Skill + +This skill provides a curated collection of professional font and color themes themes, each with carefully selected color palettes and font pairings. Once a theme is chosen, it can be applied to any artifact. + +## Purpose + +To apply consistent, professional styling to presentation slide decks, use this skill. Each theme includes: +- A cohesive color palette with hex codes +- Complementary font pairings for headers and body text +- A distinct visual identity suitable for different contexts and audiences + +## Usage Instructions + +To apply styling to a slide deck or other artifact: + +1. **Show the theme showcase**: Display the `theme-showcase.pdf` file to allow users to see all available themes visually. Do not make any modifications to it; simply show the file for viewing. +2. **Ask for their choice**: Ask which theme to apply to the deck +3. **Wait for selection**: Get explicit confirmation about the chosen theme +4. **Apply the theme**: Once a theme has been chosen, apply the selected theme's colors and fonts to the deck/artifact + +## Themes Available + +The following 10 themes are available, each showcased in `theme-showcase.pdf`: + +1. **Ocean Depths** - Professional and calming maritime theme +2. **Sunset Boulevard** - Warm and vibrant sunset colors +3. **Forest Canopy** - Natural and grounded earth tones +4. **Modern Minimalist** - Clean and contemporary grayscale +5. **Golden Hour** - Rich and warm autumnal palette +6. **Arctic Frost** - Cool and crisp winter-inspired theme +7. **Desert Rose** - Soft and sophisticated dusty tones +8. **Tech Innovation** - Bold and modern tech aesthetic +9. **Botanical Garden** - Fresh and organic garden colors +10. **Midnight Galaxy** - Dramatic and cosmic deep tones + +## Theme Details + +Each theme is defined in the `themes/` directory with complete specifications including: +- Cohesive color palette with hex codes +- Complementary font pairings for headers and body text +- Distinct visual identity suitable for different contexts and audiences + +## Application Process + +After a preferred theme is selected: +1. Read the corresponding theme file from the `themes/` directory +2. Apply the specified colors and fonts consistently throughout the deck +3. Ensure proper contrast and readability +4. Maintain the theme's visual identity across all slides + +## Create your Own Theme +To handle cases where none of the existing themes work for an artifact, create a custom theme. Based on provided inputs, generate a new theme similar to the ones above. Give the theme a similar name describing what the font/color combinations represent. Use any basic description provided to choose appropriate colors/fonts. After generating the theme, show it for review and verification. Following that, apply the theme as described above. diff --git a/skills/theme-factory/theme-showcase.pdf b/skills/theme-factory/theme-showcase.pdf new file mode 100644 index 0000000..24495d1 Binary files /dev/null and b/skills/theme-factory/theme-showcase.pdf differ diff --git a/skills/theme-factory/themes/arctic-frost.md b/skills/theme-factory/themes/arctic-frost.md new file mode 100644 index 0000000..e9f1eb0 --- /dev/null +++ b/skills/theme-factory/themes/arctic-frost.md @@ -0,0 +1,19 @@ +# Arctic Frost + +A cool and crisp winter-inspired theme that conveys clarity, precision, and professionalism. + +## Color Palette + +- **Ice Blue**: `#d4e4f7` - Light backgrounds and highlights +- **Steel Blue**: `#4a6fa5` - Primary accent color +- **Silver**: `#c0c0c0` - Metallic accent elements +- **Crisp White**: `#fafafa` - Clean backgrounds and text + +## Typography + +- **Headers**: DejaVu Sans Bold +- **Body Text**: DejaVu Sans + +## Best Used For + +Healthcare presentations, technology solutions, winter sports, clean tech, pharmaceutical content. diff --git a/skills/theme-factory/themes/botanical-garden.md b/skills/theme-factory/themes/botanical-garden.md new file mode 100644 index 0000000..0c95bf7 --- /dev/null +++ b/skills/theme-factory/themes/botanical-garden.md @@ -0,0 +1,19 @@ +# Botanical Garden + +A fresh and organic theme featuring vibrant garden-inspired colors for lively presentations. + +## Color Palette + +- **Fern Green**: `#4a7c59` - Rich natural green +- **Marigold**: `#f9a620` - Bright floral accent +- **Terracotta**: `#b7472a` - Earthy warm tone +- **Cream**: `#f5f3ed` - Soft neutral backgrounds + +## Typography + +- **Headers**: DejaVu Serif Bold +- **Body Text**: DejaVu Sans + +## Best Used For + +Garden centers, food presentations, farm-to-table content, botanical brands, natural products. diff --git a/skills/theme-factory/themes/desert-rose.md b/skills/theme-factory/themes/desert-rose.md new file mode 100644 index 0000000..ea7c74e --- /dev/null +++ b/skills/theme-factory/themes/desert-rose.md @@ -0,0 +1,19 @@ +# Desert Rose + +A soft and sophisticated theme with dusty, muted tones perfect for elegant presentations. + +## Color Palette + +- **Dusty Rose**: `#d4a5a5` - Soft primary color +- **Clay**: `#b87d6d` - Earthy accent +- **Sand**: `#e8d5c4` - Warm neutral backgrounds +- **Deep Burgundy**: `#5d2e46` - Rich dark contrast + +## Typography + +- **Headers**: FreeSans Bold +- **Body Text**: FreeSans + +## Best Used For + +Fashion presentations, beauty brands, wedding planning, interior design, boutique businesses. diff --git a/skills/theme-factory/themes/forest-canopy.md b/skills/theme-factory/themes/forest-canopy.md new file mode 100644 index 0000000..90c2b26 --- /dev/null +++ b/skills/theme-factory/themes/forest-canopy.md @@ -0,0 +1,19 @@ +# Forest Canopy + +A natural and grounded theme featuring earth tones inspired by dense forest environments. + +## Color Palette + +- **Forest Green**: `#2d4a2b` - Primary dark green +- **Sage**: `#7d8471` - Muted green accent +- **Olive**: `#a4ac86` - Light accent color +- **Ivory**: `#faf9f6` - Backgrounds and text + +## Typography + +- **Headers**: FreeSerif Bold +- **Body Text**: FreeSans + +## Best Used For + +Environmental presentations, sustainability reports, outdoor brands, wellness content, organic products. diff --git a/skills/theme-factory/themes/golden-hour.md b/skills/theme-factory/themes/golden-hour.md new file mode 100644 index 0000000..ed8fc25 --- /dev/null +++ b/skills/theme-factory/themes/golden-hour.md @@ -0,0 +1,19 @@ +# Golden Hour + +A rich and warm autumnal palette that creates an inviting and sophisticated atmosphere. + +## Color Palette + +- **Mustard Yellow**: `#f4a900` - Bold primary accent +- **Terracotta**: `#c1666b` - Warm secondary color +- **Warm Beige**: `#d4b896` - Neutral backgrounds +- **Chocolate Brown**: `#4a403a` - Dark text and anchors + +## Typography + +- **Headers**: FreeSans Bold +- **Body Text**: FreeSans + +## Best Used For + +Restaurant presentations, hospitality brands, fall campaigns, cozy lifestyle content, artisan products. diff --git a/skills/theme-factory/themes/midnight-galaxy.md b/skills/theme-factory/themes/midnight-galaxy.md new file mode 100644 index 0000000..97e1c5f --- /dev/null +++ b/skills/theme-factory/themes/midnight-galaxy.md @@ -0,0 +1,19 @@ +# Midnight Galaxy + +A dramatic and cosmic theme with deep purples and mystical tones for impactful presentations. + +## Color Palette + +- **Deep Purple**: `#2b1e3e` - Rich dark base +- **Cosmic Blue**: `#4a4e8f` - Mystical mid-tone +- **Lavender**: `#a490c2` - Soft accent color +- **Silver**: `#e6e6fa` - Light highlights and text + +## Typography + +- **Headers**: FreeSans Bold +- **Body Text**: FreeSans + +## Best Used For + +Entertainment industry, gaming presentations, nightlife venues, luxury brands, creative agencies. diff --git a/skills/theme-factory/themes/modern-minimalist.md b/skills/theme-factory/themes/modern-minimalist.md new file mode 100644 index 0000000..6bd26a2 --- /dev/null +++ b/skills/theme-factory/themes/modern-minimalist.md @@ -0,0 +1,19 @@ +# Modern Minimalist + +A clean and contemporary theme with a sophisticated grayscale palette for maximum versatility. + +## Color Palette + +- **Charcoal**: `#36454f` - Primary dark color +- **Slate Gray**: `#708090` - Medium gray for accents +- **Light Gray**: `#d3d3d3` - Backgrounds and dividers +- **White**: `#ffffff` - Text and clean backgrounds + +## Typography + +- **Headers**: DejaVu Sans Bold +- **Body Text**: DejaVu Sans + +## Best Used For + +Tech presentations, architecture portfolios, design showcases, modern business proposals, data visualization. diff --git a/skills/theme-factory/themes/ocean-depths.md b/skills/theme-factory/themes/ocean-depths.md new file mode 100644 index 0000000..b675126 --- /dev/null +++ b/skills/theme-factory/themes/ocean-depths.md @@ -0,0 +1,19 @@ +# Ocean Depths + +A professional and calming maritime theme that evokes the serenity of deep ocean waters. + +## Color Palette + +- **Deep Navy**: `#1a2332` - Primary background color +- **Teal**: `#2d8b8b` - Accent color for highlights and emphasis +- **Seafoam**: `#a8dadc` - Secondary accent for lighter elements +- **Cream**: `#f1faee` - Text and light backgrounds + +## Typography + +- **Headers**: DejaVu Sans Bold +- **Body Text**: DejaVu Sans + +## Best Used For + +Corporate presentations, financial reports, professional consulting decks, trust-building content. diff --git a/skills/theme-factory/themes/sunset-boulevard.md b/skills/theme-factory/themes/sunset-boulevard.md new file mode 100644 index 0000000..df799a0 --- /dev/null +++ b/skills/theme-factory/themes/sunset-boulevard.md @@ -0,0 +1,19 @@ +# Sunset Boulevard + +A warm and vibrant theme inspired by golden hour sunsets, perfect for energetic and creative presentations. + +## Color Palette + +- **Burnt Orange**: `#e76f51` - Primary accent color +- **Coral**: `#f4a261` - Secondary warm accent +- **Warm Sand**: `#e9c46a` - Highlighting and backgrounds +- **Deep Purple**: `#264653` - Dark contrast and text + +## Typography + +- **Headers**: DejaVu Serif Bold +- **Body Text**: DejaVu Sans + +## Best Used For + +Creative pitches, marketing presentations, lifestyle brands, event promotions, inspirational content. diff --git a/skills/theme-factory/themes/tech-innovation.md b/skills/theme-factory/themes/tech-innovation.md new file mode 100644 index 0000000..e029a43 --- /dev/null +++ b/skills/theme-factory/themes/tech-innovation.md @@ -0,0 +1,19 @@ +# Tech Innovation + +A bold and modern theme with high-contrast colors perfect for cutting-edge technology presentations. + +## Color Palette + +- **Electric Blue**: `#0066ff` - Vibrant primary accent +- **Neon Cyan**: `#00ffff` - Bright highlight color +- **Dark Gray**: `#1e1e1e` - Deep backgrounds +- **White**: `#ffffff` - Clean text and contrast + +## Typography + +- **Headers**: DejaVu Sans Bold +- **Body Text**: DejaVu Sans + +## Best Used For + +Tech startups, software launches, innovation showcases, AI/ML presentations, digital transformation content. diff --git a/skills/web-artifacts-builder/LICENSE.txt b/skills/web-artifacts-builder/LICENSE.txt new file mode 100644 index 0000000..7a4a3ea --- /dev/null +++ b/skills/web-artifacts-builder/LICENSE.txt @@ -0,0 +1,202 @@ + + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [yyyy] [name of copyright owner] + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. \ No newline at end of file diff --git a/skills/web-artifacts-builder/SKILL.md b/skills/web-artifacts-builder/SKILL.md new file mode 100644 index 0000000..8b39b19 --- /dev/null +++ b/skills/web-artifacts-builder/SKILL.md @@ -0,0 +1,74 @@ +--- +name: web-artifacts-builder +description: Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts. +license: Complete terms in LICENSE.txt +--- + +# Web Artifacts Builder + +To build powerful frontend claude.ai artifacts, follow these steps: +1. Initialize the frontend repo using `scripts/init-artifact.sh` +2. Develop your artifact by editing the generated code +3. Bundle all code into a single HTML file using `scripts/bundle-artifact.sh` +4. Display artifact to user +5. (Optional) Test the artifact + +**Stack**: React 18 + TypeScript + Vite + Parcel (bundling) + Tailwind CSS + shadcn/ui + +## Design & Style Guidelines + +VERY IMPORTANT: To avoid what is often referred to as "AI slop", avoid using excessive centered layouts, purple gradients, uniform rounded corners, and Inter font. + +## Quick Start + +### Step 1: Initialize Project + +Run the initialization script to create a new React project: +```bash +bash scripts/init-artifact.sh +cd +``` + +This creates a fully configured project with: +- ✅ React + TypeScript (via Vite) +- ✅ Tailwind CSS 3.4.1 with shadcn/ui theming system +- ✅ Path aliases (`@/`) configured +- ✅ 40+ shadcn/ui components pre-installed +- ✅ All Radix UI dependencies included +- ✅ Parcel configured for bundling (via .parcelrc) +- ✅ Node 18+ compatibility (auto-detects and pins Vite version) + +### Step 2: Develop Your Artifact + +To build the artifact, edit the generated files. See **Common Development Tasks** below for guidance. + +### Step 3: Bundle to Single HTML File + +To bundle the React app into a single HTML artifact: +```bash +bash scripts/bundle-artifact.sh +``` + +This creates `bundle.html` - a self-contained artifact with all JavaScript, CSS, and dependencies inlined. This file can be directly shared in Claude conversations as an artifact. + +**Requirements**: Your project must have an `index.html` in the root directory. + +**What the script does**: +- Installs bundling dependencies (parcel, @parcel/config-default, parcel-resolver-tspaths, html-inline) +- Creates `.parcelrc` config with path alias support +- Builds with Parcel (no source maps) +- Inlines all assets into single HTML using html-inline + +### Step 4: Share Artifact with User + +Finally, share the bundled HTML file in conversation with the user so they can view it as an artifact. + +### Step 5: Testing/Visualizing the Artifact (Optional) + +Note: This is a completely optional step. Only perform if necessary or requested. + +To test/visualize the artifact, use available tools (including other Skills or built-in tools like Playwright or Puppeteer). In general, avoid testing the artifact upfront as it adds latency between the request and when the finished artifact can be seen. Test later, after presenting the artifact, if requested or if issues arise. + +## Reference + +- **shadcn/ui components**: https://ui.shadcn.com/docs/components \ No newline at end of file diff --git a/skills/web-artifacts-builder/scripts/bundle-artifact.sh b/skills/web-artifacts-builder/scripts/bundle-artifact.sh new file mode 100755 index 0000000..c13d229 --- /dev/null +++ b/skills/web-artifacts-builder/scripts/bundle-artifact.sh @@ -0,0 +1,54 @@ +#!/bin/bash +set -e + +echo "📦 Bundling React app to single HTML artifact..." + +# Check if we're in a project directory +if [ ! -f "package.json" ]; then + echo "❌ Error: No package.json found. Run this script from your project root." + exit 1 +fi + +# Check if index.html exists +if [ ! -f "index.html" ]; then + echo "❌ Error: No index.html found in project root." + echo " This script requires an index.html entry point." + exit 1 +fi + +# Install bundling dependencies +echo "📦 Installing bundling dependencies..." +pnpm add -D parcel @parcel/config-default parcel-resolver-tspaths html-inline + +# Create Parcel config with tspaths resolver +if [ ! -f ".parcelrc" ]; then + echo "🔧 Creating Parcel configuration with path alias support..." + cat > .parcelrc << 'EOF' +{ + "extends": "@parcel/config-default", + "resolvers": ["parcel-resolver-tspaths", "..."] +} +EOF +fi + +# Clean previous build +echo "🧹 Cleaning previous build..." +rm -rf dist bundle.html + +# Build with Parcel +echo "🔨 Building with Parcel..." +pnpm exec parcel build index.html --dist-dir dist --no-source-maps + +# Inline everything into single HTML +echo "🎯 Inlining all assets into single HTML file..." +pnpm exec html-inline dist/index.html > bundle.html + +# Get file size +FILE_SIZE=$(du -h bundle.html | cut -f1) + +echo "" +echo "✅ Bundle complete!" +echo "📄 Output: bundle.html ($FILE_SIZE)" +echo "" +echo "You can now use this single HTML file as an artifact in Claude conversations." +echo "To test locally: open bundle.html in your browser" \ No newline at end of file diff --git a/skills/web-artifacts-builder/scripts/init-artifact.sh b/skills/web-artifacts-builder/scripts/init-artifact.sh new file mode 100755 index 0000000..7d1022d --- /dev/null +++ b/skills/web-artifacts-builder/scripts/init-artifact.sh @@ -0,0 +1,322 @@ +#!/bin/bash + +# Exit on error +set -e + +# Detect Node version +NODE_VERSION=$(node -v | cut -d'v' -f2 | cut -d'.' -f1) + +echo "🔍 Detected Node.js version: $NODE_VERSION" + +if [ "$NODE_VERSION" -lt 18 ]; then + echo "❌ Error: Node.js 18 or higher is required" + echo " Current version: $(node -v)" + exit 1 +fi + +# Set Vite version based on Node version +if [ "$NODE_VERSION" -ge 20 ]; then + VITE_VERSION="latest" + echo "✅ Using Vite latest (Node 20+)" +else + VITE_VERSION="5.4.11" + echo "✅ Using Vite $VITE_VERSION (Node 18 compatible)" +fi + +# Detect OS and set sed syntax +if [[ "$OSTYPE" == "darwin"* ]]; then + SED_INPLACE="sed -i ''" +else + SED_INPLACE="sed -i" +fi + +# Check if pnpm is installed +if ! command -v pnpm &> /dev/null; then + echo "📦 pnpm not found. Installing pnpm..." + npm install -g pnpm +fi + +# Check if project name is provided +if [ -z "$1" ]; then + echo "❌ Usage: ./create-react-shadcn-complete.sh " + exit 1 +fi + +PROJECT_NAME="$1" +SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" +COMPONENTS_TARBALL="$SCRIPT_DIR/shadcn-components.tar.gz" + +# Check if components tarball exists +if [ ! -f "$COMPONENTS_TARBALL" ]; then + echo "❌ Error: shadcn-components.tar.gz not found in script directory" + echo " Expected location: $COMPONENTS_TARBALL" + exit 1 +fi + +echo "🚀 Creating new React + Vite project: $PROJECT_NAME" + +# Create new Vite project (always use latest create-vite, pin vite version later) +pnpm create vite "$PROJECT_NAME" --template react-ts + +# Navigate into project directory +cd "$PROJECT_NAME" + +echo "🧹 Cleaning up Vite template..." +$SED_INPLACE '/.*<\/title>/'"$PROJECT_NAME"'<\/title>/' index.html + +echo "📦 Installing base dependencies..." +pnpm install + +# Pin Vite version for Node 18 +if [ "$NODE_VERSION" -lt 20 ]; then + echo "📌 Pinning Vite to $VITE_VERSION for Node 18 compatibility..." + pnpm add -D vite@$VITE_VERSION +fi + +echo "📦 Installing Tailwind CSS and dependencies..." +pnpm install -D tailwindcss@3.4.1 postcss autoprefixer @types/node tailwindcss-animate +pnpm install class-variance-authority clsx tailwind-merge lucide-react next-themes + +echo "⚙️ Creating Tailwind and PostCSS configuration..." +cat > postcss.config.js << 'EOF' +export default { + plugins: { + tailwindcss: {}, + autoprefixer: {}, + }, +} +EOF + +echo "📝 Configuring Tailwind with shadcn theme..." +cat > tailwind.config.js << 'EOF' +/** @type {import('tailwindcss').Config} */ +module.exports = { + darkMode: ["class"], + content: [ + "./index.html", + "./src/**/*.{js,ts,jsx,tsx}", + ], + theme: { + extend: { + colors: { + border: "hsl(var(--border))", + input: "hsl(var(--input))", + ring: "hsl(var(--ring))", + background: "hsl(var(--background))", + foreground: "hsl(var(--foreground))", + primary: { + DEFAULT: "hsl(var(--primary))", + foreground: "hsl(var(--primary-foreground))", + }, + secondary: { + DEFAULT: "hsl(var(--secondary))", + foreground: "hsl(var(--secondary-foreground))", + }, + destructive: { + DEFAULT: "hsl(var(--destructive))", + foreground: "hsl(var(--destructive-foreground))", + }, + muted: { + DEFAULT: "hsl(var(--muted))", + foreground: "hsl(var(--muted-foreground))", + }, + accent: { + DEFAULT: "hsl(var(--accent))", + foreground: "hsl(var(--accent-foreground))", + }, + popover: { + DEFAULT: "hsl(var(--popover))", + foreground: "hsl(var(--popover-foreground))", + }, + card: { + DEFAULT: "hsl(var(--card))", + foreground: "hsl(var(--card-foreground))", + }, + }, + borderRadius: { + lg: "var(--radius)", + md: "calc(var(--radius) - 2px)", + sm: "calc(var(--radius) - 4px)", + }, + keyframes: { + "accordion-down": { + from: { height: "0" }, + to: { height: "var(--radix-accordion-content-height)" }, + }, + "accordion-up": { + from: { height: "var(--radix-accordion-content-height)" }, + to: { height: "0" }, + }, + }, + animation: { + "accordion-down": "accordion-down 0.2s ease-out", + "accordion-up": "accordion-up 0.2s ease-out", + }, + }, + }, + plugins: [require("tailwindcss-animate")], +} +EOF + +# Add Tailwind directives and CSS variables to index.css +echo "🎨 Adding Tailwind directives and CSS variables..." +cat > src/index.css << 'EOF' +@tailwind base; +@tailwind components; +@tailwind utilities; + +@layer base { + :root { + --background: 0 0% 100%; + --foreground: 0 0% 3.9%; + --card: 0 0% 100%; + --card-foreground: 0 0% 3.9%; + --popover: 0 0% 100%; + --popover-foreground: 0 0% 3.9%; + --primary: 0 0% 9%; + --primary-foreground: 0 0% 98%; + --secondary: 0 0% 96.1%; + --secondary-foreground: 0 0% 9%; + --muted: 0 0% 96.1%; + --muted-foreground: 0 0% 45.1%; + --accent: 0 0% 96.1%; + --accent-foreground: 0 0% 9%; + --destructive: 0 84.2% 60.2%; + --destructive-foreground: 0 0% 98%; + --border: 0 0% 89.8%; + --input: 0 0% 89.8%; + --ring: 0 0% 3.9%; + --radius: 0.5rem; + } + + .dark { + --background: 0 0% 3.9%; + --foreground: 0 0% 98%; + --card: 0 0% 3.9%; + --card-foreground: 0 0% 98%; + --popover: 0 0% 3.9%; + --popover-foreground: 0 0% 98%; + --primary: 0 0% 98%; + --primary-foreground: 0 0% 9%; + --secondary: 0 0% 14.9%; + --secondary-foreground: 0 0% 98%; + --muted: 0 0% 14.9%; + --muted-foreground: 0 0% 63.9%; + --accent: 0 0% 14.9%; + --accent-foreground: 0 0% 98%; + --destructive: 0 62.8% 30.6%; + --destructive-foreground: 0 0% 98%; + --border: 0 0% 14.9%; + --input: 0 0% 14.9%; + --ring: 0 0% 83.1%; + } +} + +@layer base { + * { + @apply border-border; + } + body { + @apply bg-background text-foreground; + } +} +EOF + +# Add path aliases to tsconfig.json +echo "🔧 Adding path aliases to tsconfig.json..." +node -e " +const fs = require('fs'); +const config = JSON.parse(fs.readFileSync('tsconfig.json', 'utf8')); +config.compilerOptions = config.compilerOptions || {}; +config.compilerOptions.baseUrl = '.'; +config.compilerOptions.paths = { '@/*': ['./src/*'] }; +fs.writeFileSync('tsconfig.json', JSON.stringify(config, null, 2)); +" + +# Add path aliases to tsconfig.app.json +echo "🔧 Adding path aliases to tsconfig.app.json..." +node -e " +const fs = require('fs'); +const path = 'tsconfig.app.json'; +const content = fs.readFileSync(path, 'utf8'); +// Remove comments manually +const lines = content.split('\n').filter(line => !line.trim().startsWith('//')); +const jsonContent = lines.join('\n'); +const config = JSON.parse(jsonContent.replace(/\/\*[\s\S]*?\*\//g, '').replace(/,(\s*[}\]])/g, '\$1')); +config.compilerOptions = config.compilerOptions || {}; +config.compilerOptions.baseUrl = '.'; +config.compilerOptions.paths = { '@/*': ['./src/*'] }; +fs.writeFileSync(path, JSON.stringify(config, null, 2)); +" + +# Update vite.config.ts +echo "⚙️ Updating Vite configuration..." +cat > vite.config.ts << 'EOF' +import path from "path"; +import react from "@vitejs/plugin-react"; +import { defineConfig } from "vite"; + +export default defineConfig({ + plugins: [react()], + resolve: { + alias: { + "@": path.resolve(__dirname, "./src"), + }, + }, +}); +EOF + +# Install all shadcn/ui dependencies +echo "📦 Installing shadcn/ui dependencies..." +pnpm install @radix-ui/react-accordion @radix-ui/react-aspect-ratio @radix-ui/react-avatar @radix-ui/react-checkbox @radix-ui/react-collapsible @radix-ui/react-context-menu @radix-ui/react-dialog @radix-ui/react-dropdown-menu @radix-ui/react-hover-card @radix-ui/react-label @radix-ui/react-menubar @radix-ui/react-navigation-menu @radix-ui/react-popover @radix-ui/react-progress @radix-ui/react-radio-group @radix-ui/react-scroll-area @radix-ui/react-select @radix-ui/react-separator @radix-ui/react-slider @radix-ui/react-slot @radix-ui/react-switch @radix-ui/react-tabs @radix-ui/react-toast @radix-ui/react-toggle @radix-ui/react-toggle-group @radix-ui/react-tooltip +pnpm install sonner cmdk vaul embla-carousel-react react-day-picker react-resizable-panels date-fns react-hook-form @hookform/resolvers zod + +# Extract shadcn components from tarball +echo "📦 Extracting shadcn/ui components..." +tar -xzf "$COMPONENTS_TARBALL" -C src/ + +# Create components.json for reference +echo "📝 Creating components.json config..." +cat > components.json << 'EOF' +{ + "$schema": "https://ui.shadcn.com/schema.json", + "style": "default", + "rsc": false, + "tsx": true, + "tailwind": { + "config": "tailwind.config.js", + "css": "src/index.css", + "baseColor": "slate", + "cssVariables": true, + "prefix": "" + }, + "aliases": { + "components": "@/components", + "utils": "@/lib/utils", + "ui": "@/components/ui", + "lib": "@/lib", + "hooks": "@/hooks" + } +} +EOF + +echo "✅ Setup complete! You can now use Tailwind CSS and shadcn/ui in your project." +echo "" +echo "📦 Included components (40+ total):" +echo " - accordion, alert, aspect-ratio, avatar, badge, breadcrumb" +echo " - button, calendar, card, carousel, checkbox, collapsible" +echo " - command, context-menu, dialog, drawer, dropdown-menu" +echo " - form, hover-card, input, label, menubar, navigation-menu" +echo " - popover, progress, radio-group, resizable, scroll-area" +echo " - select, separator, sheet, skeleton, slider, sonner" +echo " - switch, table, tabs, textarea, toast, toggle, toggle-group, tooltip" +echo "" +echo "To start developing:" +echo " cd $PROJECT_NAME" +echo " pnpm dev" +echo "" +echo "📚 Import components like:" +echo " import { Button } from '@/components/ui/button'" +echo " import { Card, CardHeader, CardTitle, CardContent } from '@/components/ui/card'" +echo " import { Dialog, DialogContent, DialogTrigger } from '@/components/ui/dialog'" diff --git a/skills/web-artifacts-builder/scripts/shadcn-components.tar.gz b/skills/web-artifacts-builder/scripts/shadcn-components.tar.gz new file mode 100644 index 0000000..cdbe7cd Binary files /dev/null and b/skills/web-artifacts-builder/scripts/shadcn-components.tar.gz differ diff --git a/skills/webapp-testing/LICENSE.txt b/skills/webapp-testing/LICENSE.txt new file mode 100644 index 0000000..7a4a3ea --- /dev/null +++ b/skills/webapp-testing/LICENSE.txt @@ -0,0 +1,202 @@ + + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [yyyy] [name of copyright owner] + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. \ No newline at end of file diff --git a/skills/webapp-testing/SKILL.md b/skills/webapp-testing/SKILL.md new file mode 100644 index 0000000..4726215 --- /dev/null +++ b/skills/webapp-testing/SKILL.md @@ -0,0 +1,96 @@ +--- +name: webapp-testing +description: Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs. +license: Complete terms in LICENSE.txt +--- + +# Web Application Testing + +To test local web applications, write native Python Playwright scripts. + +**Helper Scripts Available**: +- `scripts/with_server.py` - Manages server lifecycle (supports multiple servers) + +**Always run scripts with `--help` first** to see usage. DO NOT read the source until you try running the script first and find that a customized solution is abslutely necessary. These scripts can be very large and thus pollute your context window. They exist to be called directly as black-box scripts rather than ingested into your context window. + +## Decision Tree: Choosing Your Approach + +``` +User task → Is it static HTML? + ├─ Yes → Read HTML file directly to identify selectors + │ ├─ Success → Write Playwright script using selectors + │ └─ Fails/Incomplete → Treat as dynamic (below) + │ + └─ No (dynamic webapp) → Is the server already running? + ├─ No → Run: python scripts/with_server.py --help + │ Then use the helper + write simplified Playwright script + │ + └─ Yes → Reconnaissance-then-action: + 1. Navigate and wait for networkidle + 2. Take screenshot or inspect DOM + 3. Identify selectors from rendered state + 4. Execute actions with discovered selectors +``` + +## Example: Using with_server.py + +To start a server, run `--help` first, then use the helper: + +**Single server:** +```bash +python scripts/with_server.py --server "npm run dev" --port 5173 -- python your_automation.py +``` + +**Multiple servers (e.g., backend + frontend):** +```bash +python scripts/with_server.py \ + --server "cd backend && python server.py" --port 3000 \ + --server "cd frontend && npm run dev" --port 5173 \ + -- python your_automation.py +``` + +To create an automation script, include only Playwright logic (servers are managed automatically): +```python +from playwright.sync_api import sync_playwright + +with sync_playwright() as p: + browser = p.chromium.launch(headless=True) # Always launch chromium in headless mode + page = browser.new_page() + page.goto('http://localhost:5173') # Server already running and ready + page.wait_for_load_state('networkidle') # CRITICAL: Wait for JS to execute + # ... your automation logic + browser.close() +``` + +## Reconnaissance-Then-Action Pattern + +1. **Inspect rendered DOM**: + ```python + page.screenshot(path='/tmp/inspect.png', full_page=True) + content = page.content() + page.locator('button').all() + ``` + +2. **Identify selectors** from inspection results + +3. **Execute actions** using discovered selectors + +## Common Pitfall + +❌ **Don't** inspect the DOM before waiting for `networkidle` on dynamic apps +✅ **Do** wait for `page.wait_for_load_state('networkidle')` before inspection + +## Best Practices + +- **Use bundled scripts as black boxes** - To accomplish a task, consider whether one of the scripts available in `scripts/` can help. These scripts handle common, complex workflows reliably without cluttering the context window. Use `--help` to see usage, then invoke directly. +- Use `sync_playwright()` for synchronous scripts +- Always close the browser when done +- Use descriptive selectors: `text=`, `role=`, CSS selectors, or IDs +- Add appropriate waits: `page.wait_for_selector()` or `page.wait_for_timeout()` + +## Reference Files + +- **examples/** - Examples showing common patterns: + - `element_discovery.py` - Discovering buttons, links, and inputs on a page + - `static_html_automation.py` - Using file:// URLs for local HTML + - `console_logging.py` - Capturing console logs during automation \ No newline at end of file diff --git a/skills/webapp-testing/examples/console_logging.py b/skills/webapp-testing/examples/console_logging.py new file mode 100644 index 0000000..9329b5e --- /dev/null +++ b/skills/webapp-testing/examples/console_logging.py @@ -0,0 +1,35 @@ +from playwright.sync_api import sync_playwright + +# Example: Capturing console logs during browser automation + +url = 'http://localhost:5173' # Replace with your URL + +console_logs = [] + +with sync_playwright() as p: + browser = p.chromium.launch(headless=True) + page = browser.new_page(viewport={'width': 1920, 'height': 1080}) + + # Set up console log capture + def handle_console_message(msg): + console_logs.append(f"[{msg.type}] {msg.text}") + print(f"Console: [{msg.type}] {msg.text}") + + page.on("console", handle_console_message) + + # Navigate to page + page.goto(url) + page.wait_for_load_state('networkidle') + + # Interact with the page (triggers console logs) + page.click('text=Dashboard') + page.wait_for_timeout(1000) + + browser.close() + +# Save console logs to file +with open('/mnt/user-data/outputs/console.log', 'w') as f: + f.write('\n'.join(console_logs)) + +print(f"\nCaptured {len(console_logs)} console messages") +print(f"Logs saved to: /mnt/user-data/outputs/console.log") \ No newline at end of file diff --git a/skills/webapp-testing/examples/element_discovery.py b/skills/webapp-testing/examples/element_discovery.py new file mode 100644 index 0000000..917ba72 --- /dev/null +++ b/skills/webapp-testing/examples/element_discovery.py @@ -0,0 +1,40 @@ +from playwright.sync_api import sync_playwright + +# Example: Discovering buttons and other elements on a page + +with sync_playwright() as p: + browser = p.chromium.launch(headless=True) + page = browser.new_page() + + # Navigate to page and wait for it to fully load + page.goto('http://localhost:5173') + page.wait_for_load_state('networkidle') + + # Discover all buttons on the page + buttons = page.locator('button').all() + print(f"Found {len(buttons)} buttons:") + for i, button in enumerate(buttons): + text = button.inner_text() if button.is_visible() else "[hidden]" + print(f" [{i}] {text}") + + # Discover links + links = page.locator('a[href]').all() + print(f"\nFound {len(links)} links:") + for link in links[:5]: # Show first 5 + text = link.inner_text().strip() + href = link.get_attribute('href') + print(f" - {text} -> {href}") + + # Discover input fields + inputs = page.locator('input, textarea, select').all() + print(f"\nFound {len(inputs)} input fields:") + for input_elem in inputs: + name = input_elem.get_attribute('name') or input_elem.get_attribute('id') or "[unnamed]" + input_type = input_elem.get_attribute('type') or 'text' + print(f" - {name} ({input_type})") + + # Take screenshot for visual reference + page.screenshot(path='/tmp/page_discovery.png', full_page=True) + print("\nScreenshot saved to /tmp/page_discovery.png") + + browser.close() \ No newline at end of file diff --git a/skills/webapp-testing/examples/static_html_automation.py b/skills/webapp-testing/examples/static_html_automation.py new file mode 100644 index 0000000..90bbedc --- /dev/null +++ b/skills/webapp-testing/examples/static_html_automation.py @@ -0,0 +1,33 @@ +from playwright.sync_api import sync_playwright +import os + +# Example: Automating interaction with static HTML files using file:// URLs + +html_file_path = os.path.abspath('path/to/your/file.html') +file_url = f'file://{html_file_path}' + +with sync_playwright() as p: + browser = p.chromium.launch(headless=True) + page = browser.new_page(viewport={'width': 1920, 'height': 1080}) + + # Navigate to local HTML file + page.goto(file_url) + + # Take screenshot + page.screenshot(path='/mnt/user-data/outputs/static_page.png', full_page=True) + + # Interact with elements + page.click('text=Click Me') + page.fill('#name', 'John Doe') + page.fill('#email', 'john@example.com') + + # Submit form + page.click('button[type="submit"]') + page.wait_for_timeout(500) + + # Take final screenshot + page.screenshot(path='/mnt/user-data/outputs/after_submit.png', full_page=True) + + browser.close() + +print("Static HTML automation completed!") \ No newline at end of file diff --git a/skills/webapp-testing/scripts/with_server.py b/skills/webapp-testing/scripts/with_server.py new file mode 100755 index 0000000..431f2eb --- /dev/null +++ b/skills/webapp-testing/scripts/with_server.py @@ -0,0 +1,106 @@ +#!/usr/bin/env python3 +""" +Start one or more servers, wait for them to be ready, run a command, then clean up. + +Usage: + # Single server + python scripts/with_server.py --server "npm run dev" --port 5173 -- python automation.py + python scripts/with_server.py --server "npm start" --port 3000 -- python test.py + + # Multiple servers + python scripts/with_server.py \ + --server "cd backend && python server.py" --port 3000 \ + --server "cd frontend && npm run dev" --port 5173 \ + -- python test.py +""" + +import subprocess +import socket +import time +import sys +import argparse + +def is_server_ready(port, timeout=30): + """Wait for server to be ready by polling the port.""" + start_time = time.time() + while time.time() - start_time < timeout: + try: + with socket.create_connection(('localhost', port), timeout=1): + return True + except (socket.error, ConnectionRefusedError): + time.sleep(0.5) + return False + + +def main(): + parser = argparse.ArgumentParser(description='Run command with one or more servers') + parser.add_argument('--server', action='append', dest='servers', required=True, help='Server command (can be repeated)') + parser.add_argument('--port', action='append', dest='ports', type=int, required=True, help='Port for each server (must match --server count)') + parser.add_argument('--timeout', type=int, default=30, help='Timeout in seconds per server (default: 30)') + parser.add_argument('command', nargs=argparse.REMAINDER, help='Command to run after server(s) ready') + + args = parser.parse_args() + + # Remove the '--' separator if present + if args.command and args.command[0] == '--': + args.command = args.command[1:] + + if not args.command: + print("Error: No command specified to run") + sys.exit(1) + + # Parse server configurations + if len(args.servers) != len(args.ports): + print("Error: Number of --server and --port arguments must match") + sys.exit(1) + + servers = [] + for cmd, port in zip(args.servers, args.ports): + servers.append({'cmd': cmd, 'port': port}) + + server_processes = [] + + try: + # Start all servers + for i, server in enumerate(servers): + print(f"Starting server {i+1}/{len(servers)}: {server['cmd']}") + + # Use shell=True to support commands with cd and && + process = subprocess.Popen( + server['cmd'], + shell=True, + stdout=subprocess.PIPE, + stderr=subprocess.PIPE + ) + server_processes.append(process) + + # Wait for this server to be ready + print(f"Waiting for server on port {server['port']}...") + if not is_server_ready(server['port'], timeout=args.timeout): + raise RuntimeError(f"Server failed to start on port {server['port']} within {args.timeout}s") + + print(f"Server ready on port {server['port']}") + + print(f"\nAll {len(servers)} server(s) ready") + + # Run the command + print(f"Running: {' '.join(args.command)}\n") + result = subprocess.run(args.command) + sys.exit(result.returncode) + + finally: + # Clean up all servers + print(f"\nStopping {len(server_processes)} server(s)...") + for i, process in enumerate(server_processes): + try: + process.terminate() + process.wait(timeout=5) + except subprocess.TimeoutExpired: + process.kill() + process.wait() + print(f"Server {i+1} stopped") + print("All servers stopped") + + +if __name__ == '__main__': + main() \ No newline at end of file diff --git a/skills/xlsx/LICENSE.txt b/skills/xlsx/LICENSE.txt new file mode 100644 index 0000000..c55ab42 --- /dev/null +++ b/skills/xlsx/LICENSE.txt @@ -0,0 +1,30 @@ +© 2025 Anthropic, PBC. All rights reserved. + +LICENSE: Use of these materials (including all code, prompts, assets, files, +and other components of this Skill) is governed by your agreement with +Anthropic regarding use of Anthropic's services. If no separate agreement +exists, use is governed by Anthropic's Consumer Terms of Service or +Commercial Terms of Service, as applicable: +https://www.anthropic.com/legal/consumer-terms +https://www.anthropic.com/legal/commercial-terms +Your applicable agreement is referred to as the "Agreement." "Services" are +as defined in the Agreement. + +ADDITIONAL RESTRICTIONS: Notwithstanding anything in the Agreement to the +contrary, users may not: + +- Extract these materials from the Services or retain copies of these + materials outside the Services +- Reproduce or copy these materials, except for temporary copies created + automatically during authorized use of the Services +- Create derivative works based on these materials +- Distribute, sublicense, or transfer these materials to any third party +- Make, offer to sell, sell, or import any inventions embodied in these + materials +- Reverse engineer, decompile, or disassemble these materials + +The receipt, viewing, or possession of these materials does not convey or +imply any license or right beyond those expressly granted above. + +Anthropic retains all right, title, and interest in these materials, +including all copyrights, patents, and other intellectual property rights. diff --git a/skills/xlsx/SKILL.md b/skills/xlsx/SKILL.md new file mode 100644 index 0000000..22db189 --- /dev/null +++ b/skills/xlsx/SKILL.md @@ -0,0 +1,289 @@ +--- +name: xlsx +description: "Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas" +license: Proprietary. LICENSE.txt has complete terms +--- + +# Requirements for Outputs + +## All Excel files + +### Zero Formula Errors +- Every Excel model MUST be delivered with ZERO formula errors (#REF!, #DIV/0!, #VALUE!, #N/A, #NAME?) + +### Preserve Existing Templates (when updating templates) +- Study and EXACTLY match existing format, style, and conventions when modifying files +- Never impose standardized formatting on files with established patterns +- Existing template conventions ALWAYS override these guidelines + +## Financial models + +### Color Coding Standards +Unless otherwise stated by the user or existing template + +#### Industry-Standard Color Conventions +- **Blue text (RGB: 0,0,255)**: Hardcoded inputs, and numbers users will change for scenarios +- **Black text (RGB: 0,0,0)**: ALL formulas and calculations +- **Green text (RGB: 0,128,0)**: Links pulling from other worksheets within same workbook +- **Red text (RGB: 255,0,0)**: External links to other files +- **Yellow background (RGB: 255,255,0)**: Key assumptions needing attention or cells that need to be updated + +### Number Formatting Standards + +#### Required Format Rules +- **Years**: Format as text strings (e.g., "2024" not "2,024") +- **Currency**: Use $#,##0 format; ALWAYS specify units in headers ("Revenue ($mm)") +- **Zeros**: Use number formatting to make all zeros "-", including percentages (e.g., "$#,##0;($#,##0);-") +- **Percentages**: Default to 0.0% format (one decimal) +- **Multiples**: Format as 0.0x for valuation multiples (EV/EBITDA, P/E) +- **Negative numbers**: Use parentheses (123) not minus -123 + +### Formula Construction Rules + +#### Assumptions Placement +- Place ALL assumptions (growth rates, margins, multiples, etc.) in separate assumption cells +- Use cell references instead of hardcoded values in formulas +- Example: Use =B5*(1+$B$6) instead of =B5*1.05 + +#### Formula Error Prevention +- Verify all cell references are correct +- Check for off-by-one errors in ranges +- Ensure consistent formulas across all projection periods +- Test with edge cases (zero values, negative numbers) +- Verify no unintended circular references + +#### Documentation Requirements for Hardcodes +- Comment or in cells beside (if end of table). Format: "Source: [System/Document], [Date], [Specific Reference], [URL if applicable]" +- Examples: + - "Source: Company 10-K, FY2024, Page 45, Revenue Note, [SEC EDGAR URL]" + - "Source: Company 10-Q, Q2 2025, Exhibit 99.1, [SEC EDGAR URL]" + - "Source: Bloomberg Terminal, 8/15/2025, AAPL US Equity" + - "Source: FactSet, 8/20/2025, Consensus Estimates Screen" + +# XLSX creation, editing, and analysis + +## Overview + +A user may ask you to create, edit, or analyze the contents of an .xlsx file. You have different tools and workflows available for different tasks. + +## Important Requirements + +**LibreOffice Required for Formula Recalculation**: You can assume LibreOffice is installed for recalculating formula values using the `recalc.py` script. The script automatically configures LibreOffice on first run + +## Reading and analyzing data + +### Data analysis with pandas +For data analysis, visualization, and basic operations, use **pandas** which provides powerful data manipulation capabilities: + +```python +import pandas as pd + +# Read Excel +df = pd.read_excel('file.xlsx') # Default: first sheet +all_sheets = pd.read_excel('file.xlsx', sheet_name=None) # All sheets as dict + +# Analyze +df.head() # Preview data +df.info() # Column info +df.describe() # Statistics + +# Write Excel +df.to_excel('output.xlsx', index=False) +``` + +## Excel File Workflows + +## CRITICAL: Use Formulas, Not Hardcoded Values + +**Always use Excel formulas instead of calculating values in Python and hardcoding them.** This ensures the spreadsheet remains dynamic and updateable. + +### ❌ WRONG - Hardcoding Calculated Values +```python +# Bad: Calculating in Python and hardcoding result +total = df['Sales'].sum() +sheet['B10'] = total # Hardcodes 5000 + +# Bad: Computing growth rate in Python +growth = (df.iloc[-1]['Revenue'] - df.iloc[0]['Revenue']) / df.iloc[0]['Revenue'] +sheet['C5'] = growth # Hardcodes 0.15 + +# Bad: Python calculation for average +avg = sum(values) / len(values) +sheet['D20'] = avg # Hardcodes 42.5 +``` + +### ✅ CORRECT - Using Excel Formulas +```python +# Good: Let Excel calculate the sum +sheet['B10'] = '=SUM(B2:B9)' + +# Good: Growth rate as Excel formula +sheet['C5'] = '=(C4-C2)/C2' + +# Good: Average using Excel function +sheet['D20'] = '=AVERAGE(D2:D19)' +``` + +This applies to ALL calculations - totals, percentages, ratios, differences, etc. The spreadsheet should be able to recalculate when source data changes. + +## Common Workflow +1. **Choose tool**: pandas for data, openpyxl for formulas/formatting +2. **Create/Load**: Create new workbook or load existing file +3. **Modify**: Add/edit data, formulas, and formatting +4. **Save**: Write to file +5. **Recalculate formulas (MANDATORY IF USING FORMULAS)**: Use the recalc.py script + ```bash + python recalc.py output.xlsx + ``` +6. **Verify and fix any errors**: + - The script returns JSON with error details + - If `status` is `errors_found`, check `error_summary` for specific error types and locations + - Fix the identified errors and recalculate again + - Common errors to fix: + - `#REF!`: Invalid cell references + - `#DIV/0!`: Division by zero + - `#VALUE!`: Wrong data type in formula + - `#NAME?`: Unrecognized formula name + +### Creating new Excel files + +```python +# Using openpyxl for formulas and formatting +from openpyxl import Workbook +from openpyxl.styles import Font, PatternFill, Alignment + +wb = Workbook() +sheet = wb.active + +# Add data +sheet['A1'] = 'Hello' +sheet['B1'] = 'World' +sheet.append(['Row', 'of', 'data']) + +# Add formula +sheet['B2'] = '=SUM(A1:A10)' + +# Formatting +sheet['A1'].font = Font(bold=True, color='FF0000') +sheet['A1'].fill = PatternFill('solid', start_color='FFFF00') +sheet['A1'].alignment = Alignment(horizontal='center') + +# Column width +sheet.column_dimensions['A'].width = 20 + +wb.save('output.xlsx') +``` + +### Editing existing Excel files + +```python +# Using openpyxl to preserve formulas and formatting +from openpyxl import load_workbook + +# Load existing file +wb = load_workbook('existing.xlsx') +sheet = wb.active # or wb['SheetName'] for specific sheet + +# Working with multiple sheets +for sheet_name in wb.sheetnames: + sheet = wb[sheet_name] + print(f"Sheet: {sheet_name}") + +# Modify cells +sheet['A1'] = 'New Value' +sheet.insert_rows(2) # Insert row at position 2 +sheet.delete_cols(3) # Delete column 3 + +# Add new sheet +new_sheet = wb.create_sheet('NewSheet') +new_sheet['A1'] = 'Data' + +wb.save('modified.xlsx') +``` + +## Recalculating formulas + +Excel files created or modified by openpyxl contain formulas as strings but not calculated values. Use the provided `recalc.py` script to recalculate formulas: + +```bash +python recalc.py <excel_file> [timeout_seconds] +``` + +Example: +```bash +python recalc.py output.xlsx 30 +``` + +The script: +- Automatically sets up LibreOffice macro on first run +- Recalculates all formulas in all sheets +- Scans ALL cells for Excel errors (#REF!, #DIV/0!, etc.) +- Returns JSON with detailed error locations and counts +- Works on both Linux and macOS + +## Formula Verification Checklist + +Quick checks to ensure formulas work correctly: + +### Essential Verification +- [ ] **Test 2-3 sample references**: Verify they pull correct values before building full model +- [ ] **Column mapping**: Confirm Excel columns match (e.g., column 64 = BL, not BK) +- [ ] **Row offset**: Remember Excel rows are 1-indexed (DataFrame row 5 = Excel row 6) + +### Common Pitfalls +- [ ] **NaN handling**: Check for null values with `pd.notna()` +- [ ] **Far-right columns**: FY data often in columns 50+ +- [ ] **Multiple matches**: Search all occurrences, not just first +- [ ] **Division by zero**: Check denominators before using `/` in formulas (#DIV/0!) +- [ ] **Wrong references**: Verify all cell references point to intended cells (#REF!) +- [ ] **Cross-sheet references**: Use correct format (Sheet1!A1) for linking sheets + +### Formula Testing Strategy +- [ ] **Start small**: Test formulas on 2-3 cells before applying broadly +- [ ] **Verify dependencies**: Check all cells referenced in formulas exist +- [ ] **Test edge cases**: Include zero, negative, and very large values + +### Interpreting recalc.py Output +The script returns JSON with error details: +```json +{ + "status": "success", // or "errors_found" + "total_errors": 0, // Total error count + "total_formulas": 42, // Number of formulas in file + "error_summary": { // Only present if errors found + "#REF!": { + "count": 2, + "locations": ["Sheet1!B5", "Sheet1!C10"] + } + } +} +``` + +## Best Practices + +### Library Selection +- **pandas**: Best for data analysis, bulk operations, and simple data export +- **openpyxl**: Best for complex formatting, formulas, and Excel-specific features + +### Working with openpyxl +- Cell indices are 1-based (row=1, column=1 refers to cell A1) +- Use `data_only=True` to read calculated values: `load_workbook('file.xlsx', data_only=True)` +- **Warning**: If opened with `data_only=True` and saved, formulas are replaced with values and permanently lost +- For large files: Use `read_only=True` for reading or `write_only=True` for writing +- Formulas are preserved but not evaluated - use recalc.py to update values + +### Working with pandas +- Specify data types to avoid inference issues: `pd.read_excel('file.xlsx', dtype={'id': str})` +- For large files, read specific columns: `pd.read_excel('file.xlsx', usecols=['A', 'C', 'E'])` +- Handle dates properly: `pd.read_excel('file.xlsx', parse_dates=['date_column'])` + +## Code Style Guidelines +**IMPORTANT**: When generating Python code for Excel operations: +- Write minimal, concise Python code without unnecessary comments +- Avoid verbose variable names and redundant operations +- Avoid unnecessary print statements + +**For Excel files themselves**: +- Add comments to cells with complex formulas or important assumptions +- Document data sources for hardcoded values +- Include notes for key calculations and model sections \ No newline at end of file diff --git a/skills/xlsx/recalc.py b/skills/xlsx/recalc.py new file mode 100644 index 0000000..102e157 --- /dev/null +++ b/skills/xlsx/recalc.py @@ -0,0 +1,178 @@ +#!/usr/bin/env python3 +""" +Excel Formula Recalculation Script +Recalculates all formulas in an Excel file using LibreOffice +""" + +import json +import sys +import subprocess +import os +import platform +from pathlib import Path +from openpyxl import load_workbook + + +def setup_libreoffice_macro(): + """Setup LibreOffice macro for recalculation if not already configured""" + if platform.system() == 'Darwin': + macro_dir = os.path.expanduser('~/Library/Application Support/LibreOffice/4/user/basic/Standard') + else: + macro_dir = os.path.expanduser('~/.config/libreoffice/4/user/basic/Standard') + + macro_file = os.path.join(macro_dir, 'Module1.xba') + + if os.path.exists(macro_file): + with open(macro_file, 'r') as f: + if 'RecalculateAndSave' in f.read(): + return True + + if not os.path.exists(macro_dir): + subprocess.run(['soffice', '--headless', '--terminate_after_init'], + capture_output=True, timeout=10) + os.makedirs(macro_dir, exist_ok=True) + + macro_content = '''<?xml version="1.0" encoding="UTF-8"?> +<!DOCTYPE script:module PUBLIC "-//OpenOffice.org//DTD OfficeDocument 1.0//EN" "module.dtd"> +<script:module xmlns:script="http://openoffice.org/2000/script" script:name="Module1" script:language="StarBasic"> + Sub RecalculateAndSave() + ThisComponent.calculateAll() + ThisComponent.store() + ThisComponent.close(True) + End Sub +</script:module>''' + + try: + with open(macro_file, 'w') as f: + f.write(macro_content) + return True + except Exception: + return False + + +def recalc(filename, timeout=30): + """ + Recalculate formulas in Excel file and report any errors + + Args: + filename: Path to Excel file + timeout: Maximum time to wait for recalculation (seconds) + + Returns: + dict with error locations and counts + """ + if not Path(filename).exists(): + return {'error': f'File {filename} does not exist'} + + abs_path = str(Path(filename).absolute()) + + if not setup_libreoffice_macro(): + return {'error': 'Failed to setup LibreOffice macro'} + + cmd = [ + 'soffice', '--headless', '--norestore', + 'vnd.sun.star.script:Standard.Module1.RecalculateAndSave?language=Basic&location=application', + abs_path + ] + + # Handle timeout command differences between Linux and macOS + if platform.system() != 'Windows': + timeout_cmd = 'timeout' if platform.system() == 'Linux' else None + if platform.system() == 'Darwin': + # Check if gtimeout is available on macOS + try: + subprocess.run(['gtimeout', '--version'], capture_output=True, timeout=1, check=False) + timeout_cmd = 'gtimeout' + except (FileNotFoundError, subprocess.TimeoutExpired): + pass + + if timeout_cmd: + cmd = [timeout_cmd, str(timeout)] + cmd + + result = subprocess.run(cmd, capture_output=True, text=True) + + if result.returncode != 0 and result.returncode != 124: # 124 is timeout exit code + error_msg = result.stderr or 'Unknown error during recalculation' + if 'Module1' in error_msg or 'RecalculateAndSave' not in error_msg: + return {'error': 'LibreOffice macro not configured properly'} + else: + return {'error': error_msg} + + # Check for Excel errors in the recalculated file - scan ALL cells + try: + wb = load_workbook(filename, data_only=True) + + excel_errors = ['#VALUE!', '#DIV/0!', '#REF!', '#NAME?', '#NULL!', '#NUM!', '#N/A'] + error_details = {err: [] for err in excel_errors} + total_errors = 0 + + for sheet_name in wb.sheetnames: + ws = wb[sheet_name] + # Check ALL rows and columns - no limits + for row in ws.iter_rows(): + for cell in row: + if cell.value is not None and isinstance(cell.value, str): + for err in excel_errors: + if err in cell.value: + location = f"{sheet_name}!{cell.coordinate}" + error_details[err].append(location) + total_errors += 1 + break + + wb.close() + + # Build result summary + result = { + 'status': 'success' if total_errors == 0 else 'errors_found', + 'total_errors': total_errors, + 'error_summary': {} + } + + # Add non-empty error categories + for err_type, locations in error_details.items(): + if locations: + result['error_summary'][err_type] = { + 'count': len(locations), + 'locations': locations[:20] # Show up to 20 locations + } + + # Add formula count for context - also check ALL cells + wb_formulas = load_workbook(filename, data_only=False) + formula_count = 0 + for sheet_name in wb_formulas.sheetnames: + ws = wb_formulas[sheet_name] + for row in ws.iter_rows(): + for cell in row: + if cell.value and isinstance(cell.value, str) and cell.value.startswith('='): + formula_count += 1 + wb_formulas.close() + + result['total_formulas'] = formula_count + + return result + + except Exception as e: + return {'error': str(e)} + + +def main(): + if len(sys.argv) < 2: + print("Usage: python recalc.py <excel_file> [timeout_seconds]") + print("\nRecalculates all formulas in an Excel file using LibreOffice") + print("\nReturns JSON with error details:") + print(" - status: 'success' or 'errors_found'") + print(" - total_errors: Total number of Excel errors found") + print(" - total_formulas: Number of formulas in the file") + print(" - error_summary: Breakdown by error type with locations") + print(" - #VALUE!, #DIV/0!, #REF!, #NAME?, #NULL!, #NUM!, #N/A") + sys.exit(1) + + filename = sys.argv[1] + timeout = int(sys.argv[2]) if len(sys.argv) > 2 else 30 + + result = recalc(filename, timeout) + print(json.dumps(result, indent=2)) + + +if __name__ == '__main__': + main() \ No newline at end of file