← 返回 Skills 市场
aiwithabidi

GitHub Intelligence

作者 aiwithabidi · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
656
总下载
0
收藏
4
当前安装
1
版本数
在 OpenClaw 中安装
/install a6-github-intel
功能描述
Analyze any GitHub repository in AI-friendly format. Convert entire repos to single markdown documents, generate architecture diagrams with Mermaid, inspect...
使用说明 (SKILL.md)

🔍 GitHub Intelligence

Analyze any GitHub repository in AI-friendly format. Convert repos to markdown, generate architecture diagrams, understand structure and patterns.

Features

  • Analyze repo structure — file tree, README, language breakdown, recent activity
  • Generate architecture diagrams — Mermaid flowcharts from codebase structure
  • Convert repo to markdown — entire repository as a single AI-readable document
  • Inspect language breakdown — percentage by language with file counts
  • Track recent activity — latest commits, contributors, release history
  • GitHub URL tricks — hidden features, API shortcuts, search operators
  • Control analysis depth — configurable directory traversal depth
  • Limit file count — cap files for large repos
  • Read-only guarantee — never executes code from repositories
  • Public API access — no token needed (optional token for higher rate limits)

Requirements

Variable Required Description
GITHUB_TOKEN Optional — increases rate limit from 60 to 5000 req/hr. Get from GitHub Settings

Quick Start

PY=~/.openclaw/workspace/.venv/bin/python3

# Analyze a repository
$PY skills/github-intel/scripts/repo_analyzer.py https://github.com/anthropics/claude-code

# Convert repo to single markdown
$PY skills/github-intel/scripts/repo_to_markdown.py https://github.com/openai/openai-python

# Deep analysis
$PY skills/github-intel/scripts/repo_analyzer.py https://github.com/user/repo --depth 3

Commands

Repo Analyzer

# Basic analysis
$PY scripts/repo_analyzer.py https://github.com/owner/repo

# Deep directory traversal
$PY scripts/repo_analyzer.py https://github.com/owner/repo --depth 3

# With authentication for higher rate limits
GITHUB_TOKEN=ghp_xxx $PY scripts/repo_analyzer.py https://github.com/owner/repo

Repo to Markdown

# Convert full repo
$PY scripts/repo_to_markdown.py https://github.com/owner/repo

# Limit files for large repos
$PY scripts/repo_to_markdown.py https://github.com/owner/repo --max-files 50

# Output to file
$PY scripts/repo_to_markdown.py https://github.com/owner/repo > repo.md

Output Format (Analyzer)

# Repository: owner/repo

## Structure
├── src/
│   ├── index.ts
│   └── ...
├── README.md
└── package.json

## README
[Full README content]

## Language Breakdown
- TypeScript: 78.2%
- JavaScript: 15.1%
- Shell: 6.7%

## Architecture (Mermaid)
graph TD
  A[CLI Entry] --> B[Command Parser]
  ...

## Recent Activity
- 2 days ago: feat: add streaming support
- 5 days ago: fix: handle timeout errors

References

File Description
references/github-tricks.md URL hacks, API shortcuts, search operators

Script Reference

Script Description
{baseDir}/scripts/repo_analyzer.py Full repository analysis with diagrams
{baseDir}/scripts/repo_to_markdown.py Convert repo to single markdown document

⚠️ Security

This tool is READ-ONLY. It NEVER:

  • Executes code from repositories
  • Runs scripts, makefiles, or build commands
  • Evaluates any content from repos
  • Writes to any repository

All analysis is static file reading only.

Data Policy

This skill fetches public data from GitHub's API. No data is stored locally beyond the analysis output.


Built by M. Abidi

LinkedIn · YouTube · GitHub · Book a Call

安全使用建议
This skill appears to do what it claims (read-only GitHub repo analysis) and only asks optionally for a GitHub token, which is reasonable. However, the README claims 'stdlib only' but the scripts import the third-party 'requests' package and there is no install specification. Before installing or invoking it: 1) ask the publisher to correct the documentation (declare 'requests' as a dependency) and provide an explicit install step (e.g., requirements.txt or pip install). 2) If you must run it, prefer providing a limited-scope personal access token (or none) and run it in a sandboxed environment so that an unexpected install (pip) or network behavior is constrained. 3) If you require stronger assurance, request a version that avoids third-party packages or includes a vetted install manifest. Overall: functionally coherent, but the mismatch around dependencies and lack of install instructions is a notable risk.
功能分析
Type: OpenClaw Skill Name: a6-github-intel Version: 1.0.0 The skill bundle is benign. All scripts (`repo_analyzer.py`, `repo_to_markdown.py`) exclusively perform read-only `GET` requests to official GitHub API endpoints and `raw.githubusercontent.com` to fetch public repository data. The `GITHUB_TOKEN` is used solely for GitHub API authentication to increase rate limits, as explicitly stated. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts in `SKILL.md` or `references/github-tricks.md`. The code adheres to its 'read-only' and 'never executes code from repositories' claims.
能力评估
Purpose & Capability
Name, description, scripts, and declared primary credential (GITHUB_TOKEN, optional) align: the skill fetches and analyzes public GitHub data and converts repos to markdown/diagrams, which legitimately requires GitHub API access.
Instruction Scope
SKILL.md and the scripts are focused on read-only static analysis of GitHub repositories. The instructions and code only fetch repository metadata and file contents and do not instruct execution of repo code or exfiltration to third-party endpoints beyond GitHub.
Install Mechanism
SKILL.md asserts 'Python stdlib only, no dependencies', but both included scripts import the third-party 'requests' package. There is no install specification (no pip/requirements), so runtime may fail or require the agent to install 'requests' from PyPI — an installation step that is not declared and increases risk.
Credentials
Only an optional GITHUB_TOKEN is used (declared as primaryEnv). The token usage is proportional for raising GitHub rate limits and is consistent with the skill's purpose; no other secrets or unrelated env vars are requested or accessed.
Persistence & Privilege
Skill does not request persistent/always-on presence and does not modify other skills or system-wide settings. Default autonomy is allowed (normal) and there are no elevated privilege requests.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install a6-github-intel
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /a6-github-intel 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
- Initial release of github-intel skill for analyzing GitHub repositories in an AI-friendly format. - Features static repo structure analysis, markdown export, Mermaid architecture diagrams, and language/activity breakdowns. - Includes advanced GitHub search tips and API shortcuts; all analysis is read-only and does not execute code. - No external dependencies required; works with Python 3.10+ stdlib. - Designed for AI agents and research, with public and token-authenticated API access options.
元数据
Slug a6-github-intel
版本 1.0.0
许可证
累计安装 4
当前安装数 4
历史版本数 1
常见问题

GitHub Intelligence 是什么?

Analyze any GitHub repository in AI-friendly format. Convert entire repos to single markdown documents, generate architecture diagrams with Mermaid, inspect... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 656 次。

如何安装 GitHub Intelligence?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install a6-github-intel」即可一键安装,无需额外配置。

GitHub Intelligence 是免费的吗?

是的,GitHub Intelligence 完全免费(开源免费),可自由下载、安装和使用。

GitHub Intelligence 支持哪些平台?

GitHub Intelligence 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 GitHub Intelligence?

由 aiwithabidi(@aiwithabidi)开发并维护,当前版本 v1.0.0。

💬 留言讨论