Compdf Skills
ComPDF Skills are AI-agent-ready PDF processing skills for Claude Code, Cursor, Copilot, OpenCode, and 39+ coding agents to convert, edit, split, insert, compare, compress…
Install
npx skills add https://github.com/ComPDFKit/compdf-skills -yclaude mcp add compdf-skills -- npx skills add https://github.com/ComPDFKit/compdf-skills -y{
"mcpServers": {
"compdf-skills": {
"command": "npx",
"args": [
"skills",
"add",
"https://github.com/ComPDFKit/compdf-skills",
"-y"
]
}
}
}Install command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →ComPDF Skills
ComPDF Skills provide PDF and image parsing, data extraction, document format conversion, and PDF processing capabilities for AI agents, helping them build complete automated document workflows. Before large-model reasoning begins, ComPDF Skills can handle document parsing, OCR, data extraction, and structured preprocessing, turning unstructured files into data that AI can directly understand. This means only the necessary content is passed to the model, reducing token usage, lowering model cost, and significantly improving both document-processing efficiency and answer quality in agent workflows.
- If ComPDF Skills help your workflow, we'd love your ⭐ Star on GitHub.
- If you have questions, suggestions, or integration ideas, feel free to reach out through Issues and Discussions.
Why ComPDF Skills • Supported Features • License & Free Access • Installation • Use Cases • Support
Why ComPDF Skills
Professional AI document-processing capabilities: support PDF and image parsing, OCR, data extraction, format conversion, and page-level processing, turning unstructured documents into structured data that AI agents can directly understand and use more accurately.
More efficient, lower-cost AI workflows: complete document parsing and preprocessing before model reasoning, and pass only the necessary content to the LLM to reduce token usage, lower model cost, and improve both response speed and workflow efficiency.
Broad output format support: support Word, Excel, PowerPoint, HTML, Markdown, JSON, CSV, RTF, TXT, image, and other output formats to meet data exchange needs across agent workflows and business systems.
Free to start and easy to validate: include free monthly document-processing credits so teams can verify value quickly in day-to-day workflows.
Supported Features
ComPDF Skills provide document conversion, PDF operations, and intelligent parsing and data extraction for agents, as detailed below:
1. PDF Parsing and Data Extraction
| Capability | Description |
|---|---|
| Image Parsing and Data Extraction | Extract text, tables, fields, and structured content from image files for downstream AI workflows and automation. |
| PDF Parsing and Data Extraction | Extract text, tables, fields, and structured content from PDF files for downstream AI workflows and automation. |
2. PDF and Image Conversion
Similar plugs
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local…
Why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
Production-grade engineering skills for AI coding agents.
The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create prototypes, websites, apps, dashboards, presentations, images, and videos with your team…