deep-wiki
通过DeepWiki访问GitHub仓库的AI生成文档和见解。当探索不熟悉的代码库、理解仓库架构、查找实现模式或询问GitHub项目如何运作时,应使用此技能。支持任何公共GitHub仓库。
📖 中文导读:通过DeepWiki访问GitHub仓库的AI生成文档和见解。当探索不熟悉的代码库、理解仓库架构、查找实现模式或询问GitHub项目如何运作时,应使用此技能。支持任何公共GitHub仓库。 以下正文为该技能的原始 SKILL.md 内容(英文),上方安装命令可直接使用。
name: deep-wiki description: Access AI-generated documentation and insights for GitHub repositories via DeepWiki. This skill should be used when exploring unfamiliar codebases, understanding repository architecture, finding implementation patterns, or asking questions about how a GitHub project works. Supports any public GitHub repository.
DeepWiki
Base directory for this skill: /home/hazeruno/.config/opencode/skills/deep-wiki
DeepWiki provides AI-generated documentation and Q&A for GitHub repositories. Use it to quickly understand codebases, explore architecture, and get answers about how projects work.
When to Use
- Exploring an unfamiliar GitHub repository
- Understanding project architecture and structure
- Finding how specific features are implemented
- Getting quick answers about a codebase without reading all source code
- Learning about dependencies, patterns, and design decisions
Quick Start
Run the CLI script with bun (use absolute path):
bun /home/hazeruno/.config/opencode/skills/deep-wiki/scripts/deepwiki.ts <command> [options]
Available Commands
read-wiki-structure
Get a list of documentation topics available for a repository.
bun /home/hazeruno/.config/opencode/skills/deep-wiki/scripts/deepwiki.ts read-wiki-structure --repo-name "facebook/react"
read-wiki-contents
View the full AI-generated documentation for a repository.
bun /home/hazeruno/.config/opencode/skills/deep-wiki/scripts/deepwiki.ts read-wiki-contents --repo-name "vercel/next.js"
ask-question
Ask any question about a repository and get an AI-generated answer.
bun /home/hazeruno/.config/opencode/skills/deep-wiki/scripts/deepwiki.ts ask-question \
--repo-name "prisma/prisma" --question "How does the query engine work?"
Global Options
-t, --timeout <ms>: Call timeout (default: 30000)-o, --output <format>: Output format:text|markdown|json|raw
Requirements
- Bun runtime
mcporterpackage (embedded in script)
References
See references/api_reference.md for detailed API documentation.