DeepWiki

Query the DeepWiki MCP server for GitHub repository documentation, wiki structure, and AI-powered questions.

インストール
$clawhub install deepwiki

DeepWiki

Use this skill to access documentation for public GitHub repositories via the DeepWiki MCP server. You can search repository wikis, get structure, and ask complex questions grounded in the repository's documentation.

Commands

Ask Question

Ask any question about a GitHub repository and get an AI-powered, context-grounded response. bash node ./scripts/deepwiki.js ask <owner/repo> "your question"

Read Wiki Structure

Get a list of documentation topics for a GitHub repository. bash node ./scripts/deepwiki.js structure <owner/repo>

Read Wiki Contents

View documentation about a specific path in a GitHub repository's wiki. bash node ./scripts/deepwiki.js contents <owner/repo> <path>

Examples

Ask about Devin's MCP usage: bash node ./scripts/deepwiki.js ask cognitionlabs/devin "How do I use MCP?"

Get the structure for the React docs: bash node ./scripts/deepwiki.js structure facebook/react

Notes

  • Base Server: https://mcp.deepwiki.com/mcp
  • Works for public repositories only.
  • No authentication required.

詳細

バージョン
v1.0.0
ダウンロード
4,281
スター
4
ClawHub
ClawHubで見る

人気のSkills

Frontend Design Ultimate
Create distinctive, production-grade static sites with React, Tailwind CSS, and shadcn/ui — no mockups needed. Generates bold, memorable designs from plain text requirements with anti-AI-slop aesthetics, mobile-first responsive patterns, and single-file bundling. Use when building landing pages, marketing sites, portfolios, dashboards, or any static web UI. Supports both Vite (pure static) and Next.js (Vercel deploy) workflows.
Caldav Calendar
Sync and query CalDAV calendars (iCloud, Google, Fastmail, Nextcloud, etc.) using vdirsyncer + khal. Works on Linux.
Browser Use
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.