Deep Wiki
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.
- Type
- Plugin
- Repository
- microsoft/skills
- GitHub stars
- 3.1k
- License
- MIT
- Repo last updated
- Sep 24, 2026
- Version
- 2.0.0
- Author
- thegovind
What Deep Wiki is
Deep Wiki is a plugin published in the microsoft/skills repository on GitHub, which has about 3.1k stars. The repository describes itself as: “Skills, MCP servers, Custom Agents, Agents.md for SDKs to ground Coding Agents”
A plugin is a package that bundles skills, slash commands, subagents, hooks, and MCP connectors so they install together. Plugins are plain files with a manifest at .claude-plugin/plugin.json, and they work in both Claude Code and Claude Cowork.
Installing Deep Wiki adds everything it ships in one step. Connectors inside a plugin still need to be connected separately, and hooks and subagents only run in Cowork and Claude Code, not in regular chat.
How to install Deep Wiki
Claude Code
- Add the repository as a plugin marketplace: claude plugin marketplace add microsoft/skills
- Install the plugin: claude plugin install deep-wiki@<marketplace-name>, using the marketplace name from the repository's .claude-plugin/marketplace.json.
- Restart the session if the new skills or commands don't appear straight away.
Claude Cowork
- Open Customize → Plugins and choose Add marketplace.
- Enter microsoft/skills (the owner/repo shorthand works for GitHub).
- Find Deep Wiki in the list, click Install, then connect any connectors it needs from its Connectors tab.
New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.
Inside the source file
An excerpt from .github/plugins/deep-wiki/.claude-plugin/plugin.json, shared under the repository's MIT license. Read the full file on GitHub.
AI-Powered Wiki Generator for Code Repositories — GitHub Copilot CLI Plugin
Generate comprehensive, structured, Mermaid-rich documentation wikis for any codebase — with dark-mode VitePress sites, onboarding guides, and deep research capabilities. Distilled from the prompt architectures of OpenDeepWiki and deepwiki-open.
Installation
From a marketplace
# Inside Copilot CLI, run these slash commands:
/plugin marketplace add microsoft/skills
/plugin install deep-wiki@skillscopilot --plugin-dir ./deep-wikiCommands
Agents
View available agents: /agents
Skills (Auto-Invoked)
Quick Start
# Install the plugin (slash command inside Copilot CLI)
/plugin install deep-wiki@skills
# Generate a full wiki with onboarding guides and VitePress site
/deep-wiki:generate
# Fast wiki — concise, parallelized, avoids rate limits
/deep-wiki:crisp
# Just the structure
/deep-wiki:catalogue
# Single page with dark-mode diagrams
/deep-wiki:page Authentication System
# Generate onboarding guides
/deep-wiki:onboard
…How It Works
Repository → Scan → Catalogue (JSON TOC) → Per-Section Pages → Assembled Wiki
↓
Mermaid Diagrams + Citations
↓
Onboarding Guides (Contributor, Staff Engineer, Executive, PM)
↓
VitePress Site (Dark Theme + Click-to-Zoom)
↓
AGENTS.md Files (Only If Missing)
↓
llms.txt + llms-full.txt (LLM-friendly)
↓
GitHub Pages Deployment (Optional)Design Principles
- Source-linked citations: Before any task, resolve the source repo URL (or confirm local). All citations use file:line for remote repos, (file:line) for local
- Structure-first: Always generate a TOC/catalogue before page content
- Evidence-based: Every claim cites file_path:line_number with clickable links — no hand-waving
- Diagram-rich: Minimum 3–5 dark-mode Mermaid diagrams per page using multiple diagram types, with click-to-zoom and comment blocks. More diagrams = better — use them liberally for architecture, flows, state, data models, and decisions.
- Table-driven: Prefer tables over prose for any structured information. Use summary tables, comparison tables, and always include a "Source" column with citations.
- Progressive disclosure: Big picture first, then drill into details. Every section starts with a TL;DR.
- Hierarchical depth: Max 4 levels for component-level granularity
- Systems thinking: Architecture → Subsystems → Components → Methods
- Never invent: All content derived from actual code — trace real implementations
- Dark-mode native: All output designed for dark-theme rendering (VitePress)
- Depth before breadth: Trace actual code paths, never guess from file names
- Agent-discoverable: Output placed at standard paths (llms.txt at repo root, AGENTS.md in key folders) so coding agents and MCP tools find documentation automatically
Agent & MCP Integration
The generated output is designed to be discoverable by coding agents using the GitHub MCP Server or any MCP-compatible tool:
How it works with GitHub MCP:
- Agent calls get_file_contents on llms.txt → gets project summary + links to all wiki pages
- Agent calls get_file_contents on specific wiki pages → gets full documentation with source citations
- Agent calls search_code with patterns → finds relevant wiki sections across the repository
- Agent reads AGENTS.md → Documentation section points to wiki and onboarding guides
Plugin Structure
deep-wiki/
├── .claude-plugin/
│ └── plugin.json # Plugin manifest (name, version, description)
├── commands/ # Slash commands (/deep-wiki:*)
│ ├── generate.md # Full wiki generation pipeline
│ ├── crisp.md # Fast, concise wiki (rate-limit-friendly)
│ ├── catalogue.md # Wiki structure as JSON
│ ├── page.md # Single page with dark-mode diagrams
│ ├── changelog.md # Git-based changelog
│ ├── research.md # 5-iteration deep research
│ ├── ask.md # Q&A about the repo
│ ├── onboard.md # Onboarding guide generation
│ ├── agents.md # AGENTS.md generation (only if missing)
│ ├── llms.md # llms.txt generation for LLM-friendly access
│ ├── deploy.md # GitHub Pages deployment workflow generation
│ ├── ado.md # Azure DevOps Wiki export script generation
│ └── build.md # VitePress site packaging
├── skills/ # Auto-invoked based on context
…License
MIT
Before you install
- Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
- Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
- Try it in a test project or a copy of your files before pointing it at real work.
- Pin the version you tested, and review changes before updating.
- Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.
FAQ
What is Deep Wiki?
Deep Wiki is a plugin for Claude Code and Claude Cowork from the microsoft/skills repository on GitHub. 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.
How do I install Deep Wiki in Claude Code?
Add the repository as a plugin marketplace: claude plugin marketplace add microsoft/skills Install the plugin: claude plugin install deep-wiki@<marketplace-name>, using the marketplace name from the repository's .claude-plugin/marketplace.json. Restart the session if the new skills or commands don't appear straight away.
Can I use Deep Wiki in Claude Cowork?
Open Customize → Plugins and choose Add marketplace. Enter microsoft/skills (the owner/repo shorthand works for GitHub). Find Deep Wiki in the list, click Install, then connect any connectors it needs from its Connectors tab.
Is Deep Wiki safe to install?
It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.
Similar resources
- Azure Microsoft Azure MCP and Skills integration for cloud resource management, deployments, and Azure services. Manage your Azure infrastructure, monitor applications, and deploy resources directly from Claude Code. Plugin · microsoft/skills
- Azure Sdk Dotnet Azure SDK patterns and best practices for .NET developers covering AI, resource management, identity, messaging, and Key Vault libraries. Plugin · microsoft/skills
- Azure Sdk Rust Azure SDK patterns and best practices for Rust developers covering identity, Key Vault, storage, Cosmos DB, and Event Hubs. Plugin · microsoft/skills
- Backend Developer FastAPI/Python specialist for CoreAI DIY backend development with Pydantic, Cosmos DB, and Azure services Subagent · microsoft/skills
- Microsoft 365 Agents Toolkit Toolkit for building and evaluating Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, capability configuration, and eval workflows. Plugin · microsoft/skills
- Microsoft Foundry Foundry-platform fluency for any language. One orchestrator + 10 sub-skills covering hosted agents, intent-based toolboxes, multi-agent workflows, Foundry IQ knowledge bases, managed skills, long-term memory, observability and evaluations, and governance via the Foundry Control Plane. Bundles Azure MCP, Foundry MCP (mcp.ai.azure.com), and Microsoft Docs MCP for live operations and always-current… Plugin · microsoft/skills
- Azure Sdk Python Azure SDK patterns and best practices for Python developers covering AI, storage, identity, monitoring, messaging, and management libraries. Plugin · microsoft/skills
- Cloudflare Build, test, and deploy applications on Cloudflare with platform guidance Skills and the Cloudflare MCP server. Plugin · cloudflare/skills