read-github
Read GitHub repos the RIGHT way - via gitmcp.io instead of raw scraping. Why this beats web search: (1) Semantic search across docs, not just keyword matching, (2) Smart code navigation with accurate file structure - zero hallucinations on repo layout, (3) Proper markdown output optimized for LLMs, not raw HTML/JSON garbage, (4) Aggregates README + /docs + code in one clean interface, (5) Respects rate limits and robots.txt. Stop pasting raw GitHub URLs - use this instead.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/am-will/read-githubWhat This Skill Does
The read-github skill integrates your OpenClaw agent with gitmcp.io to revolutionize how you interact with GitHub repositories. Unlike traditional web search or simple raw page scraping, this tool utilizes the Model Context Protocol (MCP) to access repositories as structured data. It provides semantic search capabilities, accurate file system navigation, and LLM-optimized documentation formatting. By acting as an interface between your agent and the gitmcp.io service, it eliminates hallucinations regarding folder structures and ensures that the information retrieved is clean, consistent, and respectful of web standards like robots.txt.
Installation
To integrate this skill into your environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/am-will/read-github
Ensure that your OpenClaw configuration allows the agent to execute the provided scripts/gitmcp.py utility to enable the underlying tool calls.
Use Cases
- Project Onboarding: Quickly parse README files and documentation to understand how to contribute to a new open-source codebase.
- Technical Research: Perform semantic searches across complex documentation sets to find specific architectural decisions or API definitions.
- Code Debugging: Use exact-match code searching to locate where specific functions are defined or implemented within a target repository.
- External Reference Tracking: Seamlessly follow and fetch external links cited within project docs without manual context switching.
Example Prompts
- "Read the documentation for facebook/react and explain the core lifecycle methods described in their guides."
- "Search the documentation for 'useMemo' in the facebook/react repository to see how it should be implemented in modern components."
- "Look through the codebase of karpathy/llm-council for the implementation of the main loop and summarize how it handles input tokens."
Tips & Limitations
- Tip: Always run
fetch-docsas your first step for any new repository. This populates the agent's knowledge base with the project's high-level architecture. - Tip: Use
search-codeonly when you need an exact implementation match; otherwise, rely onsearch-docsfor more nuanced, semantic insights. - Limitation: The skill depends on the gitmcp.io service; if the service is unreachable, the tool will return a connection error.
- Limitation: While semantic search is highly effective, large repositories may yield many matches; refine your queries with specific keywords to improve result relevancy.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-am-will-read-github": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, external-api
Related Skills
remotion-best-practices
Best practices for Remotion - Video creation in React
gemini-computer-use
Build and run Gemini 2.5 Computer Use browser-control agents with Playwright. Use when a user wants to automate web browser tasks via the Gemini Computer Use model, needs an agent loop (screenshot → function_call → action → function_response), or asks to integrate safety confirmation for risky UI actions.
morning-email-rollup
Daily morning rollup of important emails and calendar events at 8am with AI-generated summaries
openai-docs-skill
Query the OpenAI developer documentation via the OpenAI Docs MCP server using CLI (curl/jq). Use whenever a task involves the OpenAI API (Responses, Chat Completions, Realtime, etc.), OpenAI SDKs, ChatGPT Apps SDK, Codex, MCP integrations, endpoint schemas, parameters, limits, or migrations and you need up-to-date official guidance.
remotion-best-practices
Best practices for Remotion - Video creation in React