Skip to content
Back to search

repo-analyzer

MarketplaceWorks with Claude CodeGitHub

Deep architectural analysis of open-source projects with professional reports

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/yzddmr6--repo-analyzer/badge.svg)](/listings/yzddmr6--repo-analyzer)

HTML

<a href="/listings/yzddmr6--repo-analyzer"><img src="/api/listings/yzddmr6--repo-analyzer/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

**npx (Recommended)**

npx skills add yzddmr6/repo-analyzer

**Plugin Marketplace**

/plugin marketplace add yzddmr6/repo-analyzer
/plugin install repo-analyzer@repo-analyzer

**Manual (Git Clone)**

# macOS / Linux
git clone https://github.com/yzddmr6/repo-analyzer.git ~/.claude/skills/repo-analyzer

# Windows
git clone https://github.com/yzddmr6/repo-analyzer.git %USERPROFILE%\.claude\skills\repo-analyzer

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 18 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "repo-analyzer",
  3. "description": "Deep architectural analysis of open-source projects with professional reports",
  4. "owner": {
  5. "name": "yzddmr6"
  6. },
  7. "plugins": [
  8. {
  9. "name": "repo-analyzer",
  10. "description": "Deep architectural analysis of open-source projects with professional reports",
  11. "version": "1.0.0",
  12. "source": "./",
  13. "author": {
  14. "name": "yzddmr6"
  15. }
  16. }
  17. ]
  18. }
README.md · README · 145 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Repo Analyzer
  2. An AI coding agent skill for deep architectural analysis of open-source projects. Generates professional-grade architecture reports with design insights, trade-off analysis, and Mermaid diagrams.
  3. Compatible with [Claude Code](https://claude.ai/claude-code), [Codex](https://github.com/openai/codex), [OpenClaw](https://github.com/anthropics/openclaw), and any AI coding agent that supports the skills format.
  4. **[中文文档](README.zh.md)**
  5. ## Related Articles
  6. - [一键生成专业级分析报告:迭代20多轮的深度架构分析Skill,我决定开源了](https://mp.weixin.qq.com/s/sOPHFaNS8pIkhB4F-FysTQ)
  7. - [Claude Code 源码深度架构分析](https://mp.weixin.qq.com/s/GjZ-tFBVwfJwK11F1lP5TQ)
  8. ## Quick Install
  9. **npx (Recommended)**
  10. ```bash
  11. npx skills add yzddmr6/repo-analyzer
  12. ```
  13. **Plugin Marketplace**
  14. ```
  15. /plugin marketplace add yzddmr6/repo-analyzer
  16. /plugin install repo-analyzer@repo-analyzer
  17. ```
  18. **Manual (Git Clone)**
  19. ```bash
  20. # macOS / Linux
  21. git clone https://github.com/yzddmr6/repo-analyzer.git ~/.claude/skills/repo-analyzer
  22. # Windows
  23. git clone https://github.com/yzddmr6/repo-analyzer.git %USERPROFILE%\.claude\skills\repo-analyzer
  24. ```
  25. ## Features
  26. - **Architecture-level analysis** — Focuses on *why* things are designed the way they are, not just *what* the code does
  27. - **Adaptive report structure** — No fixed template; chapters are designed based on each project's unique characteristics
  28. - **Parallel subagent analysis** — Spawns multiple agents to analyze core modules concurrently for large codebases
  29. - **Competitive positioning** — Compares design philosophy and technical trade-offs against similar projects
  30. - **Mermaid diagrams** — Architecture overviews, data flows, and per-module sequence diagrams throughout the report
  31. - **Interactive workflow** — Asks targeted questions based on project traits before diving into analysis
  32. ## Usage
  33. Simply ask Claude Code to analyze a project:
  34. ```
  35. 分析项目 https://github.com/astral-sh/ruff
  36. ```
  37. ```
  38. 分析一下 ollama/ollama 这个仓库的架构
  39. ```
  40. ```
  41. 对比分析 express 和 fastify
  42. ```
  43. The skill also accepts `owner/repo` shorthand, full GitHub/GitLab/Gitee URLs, or local paths.
  44. ### Trigger Keywords
  45. The skill activates automatically when you mention:
  46. `分析项目` `分析仓库` `分析 GitHub` `项目分析` `源码分析` `架构分析` `代码分析` `学习这个项目` `研究这个框架` `看看这个库怎么实现的` `对比两个项目` `项目评测` `框架评测`
  47. > **Note:** The skill outputs reports in Chinese by default. If you ask in another language, it follows your language.
  48. ## Analysis Modes
  49. After scanning the codebase, the skill asks you to choose a depth level:
  50. | Mode | Core Module Coverage | Secondary Coverage | Best For |
  51. |------|---------------------|-------------------|----------|
  52. | **Quick** | >= 30% | >= 10% | Getting a high-level overview |
  53. | **Standard** (default) | >= 60% | >= 30% | Regular architecture analysis |
  54. | **Deep** | >= 90% | >= 60% | Studying every design decision |
  55. ## How It Works
  56. 1. **Clone & Scan** — Clones the repo (or uses a local path), counts effective lines of code by module
  57. 2. **External Research** — Web searches for reviews, comparisons, and architecture discussions; crawls the official website
  58. 3. **Adaptive Q&A** — Generates targeted questions based on project characteristics, not a fixed checklist
  59. 4. **Dynamic Report Structure** — Designs chapter layout based on your answers and project traits
  60. 5. **Parallel Deep Analysis** — Spawns subagents for each core module, analyzing them concurrently
  61. 6. **Cross-Validation** — Verifies conclusions across modules, checks code read coverage
  62. 7. **Multi-Source Fusion** — Merges research, module analyses, and insights into a cohesive narrative
  63. 8. **Final Report** — Outputs a single Markdown file with Mermaid diagrams
  64. ## Report Output
  65. The final report is saved as a single Markdown file at:
  66. ```
  67. ~/repo-analyses/{project-name}-{date}/ANALYSIS_REPORT.md
  68. ```
  69. Every report includes (adapted per project):
  70. - **Problem Context** — What problem does this solve? Why do existing solutions fall short?
  71. - **Competitive Positioning** — Design philosophy differences vs. alternatives (not feature checklists)
  72. - **Project Overview** — Architecture at a glance
  73. - **Deep Module Analysis** — Why > What analysis with trade-offs and industry comparisons
  74. - **Evaluation & Takeaways** — Honest assessment of strengths, weaknesses, and lessons learned
  75. - **Architecture Diagrams** — Mermaid charts for system overview and per-module flows
  76. ## Optional Dependencies
  77. The skill works with Claude Code's built-in tools out of the box. For enhanced research capabilities, these MCP servers are optional:
  78. - [Tavily MCP](https://github.com/tavily-ai/tavily-mcp) — Website crawling via `tavily_crawl`
  79. - [Brave Search MCP](https://github.com/anthropics/anthropic-quickstarts/tree/main/brave-search-mcp) — Alternative web search provider
  80. ## File Structure
  81. ```
  82. repo-analyzer/
  83. ├── .claude-plugin/
  84. │ └── plugin.json # Plugin metadata
  85. ├── package.json # Package manifest
  86. ├── skills/
  87. │ └── repo-analyzer/
  88. │ ├── SKILL.md # Main skill definition
  89. │ └── references/
  90. │ ├── analysis-guide.md # Analysis philosophy & evaluation framework
  91. │ └── module-analysis-guide.md # Module analysis guide & subagent templates
  92. ├── README.md # English documentation
  93. ├── README.zh.md # Chinese documentation
  94. └── LICENSE # MIT License
  95. ```
  96. ## Contributing
  97. Contributions are welcome! Feel free to open issues or submit pull requests.
  98. If you'd like to improve the analysis workflow, the core logic lives in `skills/repo-analyzer/SKILL.md`. The evaluation framework and subagent templates are in the `references/` directory.
  99. ## License
  100. [MIT](LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.