Deep Wiki
插件 已验证 活跃AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
To automate the creation of high-quality, browsable documentation for code repositories, making projects more accessible and understandable.
功能
- AI-powered wiki generation from code
- Comprehensive documentation including diagrams and citations
- VitePress site generation with dark theme
- Audience-tailored onboarding guides
- Multiple commands for specific documentation tasks (changelog, research, Q&A)
使用场景
- Generating onboarding documentation for new team members
- Creating a browsable technical wiki for a large codebase
- Documenting specific components or systems with deep code analysis
- Understanding a repository's architecture and data flow
非目标
- Replacing IDEs or code editors
- Generating non-technical content
- Acting as a general-purpose AI assistant outside of documentation tasks
工作流
- Resolve source repository context
- Scan repository structure and identify key components
- Generate wiki pages with diagrams and citations
- Create onboarding guides for different audiences
- Package wiki into a VitePress site
- Generate AGENTS.md and llms.txt for LLM integration
- Optionally generate GitHub Actions for deployment
实践
- Code analysis depth
- Evidence-based writing
- Visual communication (diagrams)
- Dark-mode design
先决条件
- Git repository context (remote URL or local)
- Claude Code CLI
安装
请先添加 Marketplace
/plugin marketplace add microsoft/skills/plugin install deep-wiki@skills包含 10 个扩展
Skill (10)
Converts VitePress/GFM wiki markdown to Azure DevOps Wiki-compatible format. Generates a Node.js build script that transforms Mermaid syntax, strips front matter, fixes links, and outputs ADO-compatible copies to dist/ado-wiki/.
Generates AGENTS.md files for repository folders — coding agent context files with build commands, testing instructions, code style, project structure, and boundaries. Only generates where AGENTS.md is missing.
Analyzes code repositories and generates hierarchical documentation structures with onboarding guides. Use when the user wants to create a wiki, generate documentation, map a codebase structure, or understand a project's architecture at a high level.
Analyzes git commit history and generates structured changelogs categorized by change type. Use when the user asks about recent changes, wants a changelog, or needs to understand what changed in the repository.
Generates llms.txt and llms-full.txt files for LLM-friendly project documentation following the llms.txt specification. Use when the user wants to create LLM-readable summaries, llms.txt files, or make their wiki accessible to language models.
Generates four audience-tailored onboarding guides in an onboarding/ folder — Contributor, Staff Engineer, Executive, and Product Manager. Use when the user wants onboarding documentation for a codebase.
Generates rich technical documentation pages with dark-mode Mermaid diagrams, source code citations, and first-principles depth. Use when writing documentation, generating wiki pages, creating technical deep-dives, or documenting specific components or systems.
Answers questions about a code repository using source file analysis. Use when the user asks a question about how something works, wants to understand a component, or needs help navigating the codebase.
Conducts multi-turn iterative deep research on specific topics within a codebase with zero tolerance for shallow analysis. Use when the user wants an in-depth investigation, needs to understand how something works across multiple files, or asks for comprehensive analysis of a specific system or pattern.
Packages generated wiki Markdown into a VitePress static site with dark theme, dark-mode Mermaid diagrams with click-to-zoom, and production build output. Use when the user wants to create a browsable website from generated wiki pages.
质量评分
已验证类似扩展
Unslop
100使助手输出听起来更人性化。去除 AI 术语(谄媚、陈词滥调、敷衍的说法、连用的破折号),营造自然的爆发力,恢复语音。保留代码、URL 和技术准确性。
Hugging Face Papers
100Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata like authors, linked models, datasets, Spaces, and media URLs when needed.
Cypress
100创建、更新和修复 Cypress 测试。连接到 Cypress Cloud 以查看测试结果并利用数据来管理您的测试套件。
Claude AI Music Skills
100AI music generation workflow for Suno - album concepts, lyrics, prompts, mastering, release
Context7 Plugin
100Upstash Context7 MCP 服务器,用于查找最新文档。直接从源代码存储库将特定版本的文档和代码示例拉取到您的 LLM 上下文中。
Performance Testing Review
99Performance analysis, test coverage review, and AI-powered code quality assessment