Rea
Reverse engineer anything with agents, from app behavior down to native binaries.
Anthropic's official Claude Skills for working with document formats — fill, merge, and extract data from PDFs, Word files, PowerPoint decks, and Excel spreadsheets inside agent workflows.
Each skill is a folder of instructions plus Python scripts that Claude loads on demand. When a task touches a document format, the agent pulls in the skill's instructions and invokes its scripts to parse or produce files, keeping heavy parsing out of the context window.
High-throughput parsing of complex documents (PDFs, Word docs, spreadsheets, presentations)
Structured table, key-value, and metadata extraction directly into agent memory buffers
Automated report generation and document synthesis from multi-source repositories
{
"mcpServers": {
"claude-document-skills": {
"command": "python",
"args": [
"-m",
"claude_document_skills"
]
}
}
}
Paste into your client configuration file (e.g. ~/Library/Application Support/Claude/claude_desktop_config.json on macOS or %APPDATA%/Claude/claude_desktop_config.json on Windows).
Install the Claude Code CLI or use Claude Desktop with skills enabled
Copy the document-skills folder into your project's .claude/skills/ directory
Ensure Python 3.10+ with the skill's requirements (pip install -r requirements.txt) is available
Ask Claude to process a document (e.g. 'extract all invoices from this PDF folder')
Keeps heavy parsing and raw file structures external to the LLM. Only sanitized excerpts and structured returns are injected into agent memory turns.
Enforce explicit directory allowlists and permission scopes in client configuration to ensure autonomous tool calls never breach system boundaries.
Executes in an isolated local child process communicating strictly over JSON-RPC via stdio with explicit process timeouts.
Anthropic Document Skills (PDF, DOCX, PPTX, XLSX) is an open-source document capability designed for AI clients and autonomous agents. Anthropic's official Claude Skills for working with document formats — fill, merge, and extract data from PDFs, Word files, PowerPoint decks, and Excel spreadsheets inside agent workflows.
Follow the step-by-step installation: 1) Verify your runtime (Python 3.10+), 2) Add the configuration snippet into your AI client settings (e.g. claude_desktop_config.json), 3) Restart the client to initialize tool execution.
Anthropic Document Skills (PDF, DOCX, PPTX, XLSX) is compatible with all AI tools supporting tool-calling and the Model Context Protocol (MCP), including Claude Desktop, Cursor, Claude Code CLI, Windsurf, OpenCode, and custom agent runtimes.
Anthropic Document Skills (PDF, DOCX, PPTX, XLSX) executes locally with strict directory allowlists and permission scopes. Heavy parsing and raw file structures stay external to the LLM context window to prevent memory saturation and unauthorized access.
Yes, Anthropic Document Skills (PDF, DOCX, PPTX, XLSX) is published under the MIT open-source license. You can inspect the source code and contribute on GitHub at https://github.com/anthropics/skills.
Explore open-source implementation code, license, and community releases.
Reverse engineer anything with agents, from app behavior down to native binaries.
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 deterministic AST parsing, every edge explained, no vector store.
An Agno agentic system that provides expert software architecture analysis and recommendations using a dual-model approach combining DeepSeek R1's Reasoning and Claude. The system provides detailed technical analysis, implementation...
Advanced AI AgentsA reference implementation demonstrating how to build a multi-agent pipeline that aggregates technical signals from multiple sources, scores them for relevance, assesses risks, and synthesizes an actionable intelligence digest.
Advanced AI AgentsA multi-agent app built on EvoAgentX that turns a single natural-language goal into a working program. It automatically generates a.