← 返回 Skills 市场
aiwithabidi

Github Intel

作者 aiwithabidi · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
333
总下载
0
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install 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's purpose and code are largely coherent (it fetches and analyzes public GitHub data), but the documentation falsely claims 'stdlib only' while the scripts require the third-party 'requests' library. Before installing or running: 1) ensure your agent environment has the 'requests' package or update the skill to include an install step; 2) if you provide a GITHUB_TOKEN, use a least-privilege token (or a public_repo/read-only token) and treat it like any secret; 3) review the scripts yourself (they fetch full file contents and include them in outputs) if you have concerns about pulling large or sensitive files from repositories; 4) run the tool in an isolated environment/venv to avoid dependency conflicts. If the README claim of 'stdlib only' is intentional, ask the author to either remove the 'requests' import or add an explicit install step so the dependency mismatch is resolved.
功能分析
Type: OpenClaw Skill Name: github-intel Version: 1.0.0 The OpenClaw AgentSkills skill bundle 'github-intel' is classified as benign. The Python scripts (`repo_analyzer.py`, `repo_to_markdown.py`) perform read-only analysis of public GitHub repositories by making API calls to `api.github.com` and `raw.githubusercontent.com`, which is aligned with the stated purpose. They do not execute code from repositories, exfiltrate data, or attempt to establish persistence. The `SKILL.md` instructions are clear and do not contain any prompt injection attempts. A minor documentation inaccuracy exists in `SKILL.md` claiming 'Python stdlib only, no dependencies', while both Python scripts import the `requests` library, but this is not a security vulnerability or indicator of malice.
能力评估
Purpose & Capability
Name and description match the code and required credential: this is a GitHub analysis tool and declaring GITHUB_TOKEN (optional) as the primary credential is appropriate. Nothing in the scripts requests unrelated cloud or system credentials.
Instruction Scope
Runtime instructions and scripts are limited to read-only GitHub API and raw.githubusercontent requests, tree parsing, README inclusion, and text extraction. The code does not execute repo code or run build steps; it prints analysis and fetches file contents (with size limits).
Install Mechanism
SKILL.md claims 'Python stdlib only — no dependencies', but both scripts import the third-party 'requests' library. There is no install spec provided, so an environment lacking 'requests' will fail. This mismatch is a material incoherence (missing dependency/install instructions).
Credentials
Requesting an optional GITHUB_TOKEN to increase rate limits is proportionate to the stated purpose. No other secrets, unrelated env vars, or config paths are requested.
Persistence & Privilege
The skill is not always-on, does not modify other skills or system-wide config, and does not request persistent elevated privileges. It performs network reads only.
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 github-intel
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /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
github-intel 1.0.0 - Initial public release of github-intel. - Analyze any GitHub repository in a read-only, AI-friendly format. - Generate repo structure trees, language breakdowns, and architecture diagrams using Mermaid. - Convert entire repositories to single markdown documents. - Includes GitHub URL tricks, API shortcuts, and advanced search techniques. - Python standard library only; no dependencies.
元数据
Slug github-intel
版本 1.0.0
许可证
累计安装 2
当前安装数 2
历史版本数 1
常见问题

Github Intel 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 333 次。

如何安装 Github Intel?

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

Github Intel 是免费的吗?

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

Github Intel 支持哪些平台?

Github Intel 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 Intel?

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

💬 留言讨论