DeepWiki is an MCP-based skill that allows AI agents to query, browse, and ask questions about public GitHub repository documentation.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install deepwiki
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install deepwiki using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is DeepWiki?
DeepWiki provides a bridge between AI coding agents and GitHub repository documentation. By leveraging the DeepWiki MCP server, this skill enables agents to look beyond source code and understand the high-level documentation, wiki pages, and architectural guides provided by repo maintainers. It is an essential addition to your Openclaw Skills library for deeper repository analysis.
Whether you need to understand specific implementation details or get a bird's-eye view of a project's structure, DeepWiki provides context-grounded responses. It eliminates the manual effort of browsing wiki tabs by allowing programmatic access to the documentation structure and content directly within your agentic workflows.
DeepWiki Use Cases
- Researching how to integrate a specific library by asking questions grounded in its official GitHub wiki.
- Mapping out the documentation structure of a large open-source project to identify key setup guides.
- Retrieving specific content from a documentation path for automated code generation context.
- Validating implementation steps against documented best practices using Openclaw Skills.
How DeepWiki Works
- The user provides a public GitHub repository owner and name to the Openclaw Skills interface.
- The skill connects to the DeepWiki Model Context Protocol (MCP) server located at https://mcp.deepwiki.com/mcp.
- For questions, the skill performs a context-aware search through the repository's wiki pages using AI.
- The skill returns a grounded response, or the specific documentation structure or content requested.
- The resulting data is formatted for use within the Openclaw Skills environment to inform the next steps of the agent.
DeepWiki Setup
Ensure you have Node.js installed to run the underlying scripts provided by Openclaw Skills. No authentication or API keys are required for accessing public repositories.
# Ask a specific question about a repository
node ./scripts/deepwiki.js ask <owner/repo> "your question"
# List the documentation structure
node ./scripts/deepwiki.js structure <owner/repo>
# Read a specific documentation page
node ./scripts/deepwiki.js contents <owner/repo> <path>
DeepWiki Data Schema & Taxonomy
The skill interacts with the DeepWiki API and returns structured Markdown or text-based outputs. Data is organized as follows:
| Component | Description |
|---|---|
| Wiki Structure | A hierarchical list of documentation topics and valid paths for the repository. |
| Wiki Contents | The raw markdown content extracted from a specific documentation path. |
| AI Response | A synthesized natural language answer grounded in the repository context. |
| MCP Endpoint | Connects via https://mcp.deepwiki.com/mcp. |
DeepWiki Advanced Features
- Context-grounded questioning for complex architectural queries using Openclaw Skills.
- Automated documentation mapping for large-scale repository analysis and indexing.
- Seamless integration with MCP-enabled AI agents to provide up-to-date documentation context.
- Support for any public repository without requiring GitHub Personal Access Tokens (PATs).
- Efficient path-based content retrieval for targeted information gathering.
SKILL.md
Loading
Related Openclaw Skills
Mia Twitter Stealth
A high-stealth Twitter/X automation tool designed to mimic human behavior and bypass bot detection mechanisms using Playwright.
Mia Polymarket Trader
An AI agent designed for autonomous market analysis and trade execution on the Polymarket prediction platform.
Mia Content Creator
An AI agent for automated content creation, multi-platform scheduling, and comprehensive revenue tracking.
Reasoning Personas
Activate specialized high-agency thinking modes to optimize AI reasoning patterns for brainstorming, review, and complex decision-making.
Gemini Deep Research
An autonomous AI research agent that decomposes complex queries, crawls the web systematically, and synthesizes multi-source findings into professional reports.
LinkedIn CLI
A terminal-based interface for LinkedIn that enables automated profile scouting, message checking, and feed summarization using session cookies.
Featured*
