github-crawler

Crawl GitHub repositories to retrieve file contents and READMEs.

2|Updated Jan 7, 2026
One-click install
npx skills add https://github.com/yuma588/skill-gallery --skill github-crawler
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: github-crawler
Source: https://github.com/yuma588/skill-gallery/tree/main/skills/github-crawler
Command: npx skills add https://github.com/yuma588/skill-gallery --skill github-crawler

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

GitHub Crawler provides a reliable way to fetch file contents and repository READMEs from GitHub, eliminating manual scraping and speeding up data collection workflows.

Core Features & Use Cases

  • Retrieve arbitrary file content from a repository by URL and path, enabling quick access to code snippets and configurations.
  • Fetch repository READMEs to surface project documentation and overviews without manual browsing.
  • Support for public repos by default and private repos via token authentication, with robust retry and error handling.

Quick Start

Request a file or README by providing the repository URL (and file path if fetching a specific file).

Frequently Asked Questions about github-crawler

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I fetch file contents and READMEs from GitHub repositories?

Yes, you can crawl private GitHub repositories by providing token authentication. This grants the necessary permissions to extract file contents and READMEs from restricted repositories securely.

Do I need a token to crawl private GitHub repositories?

Yes, crawling private GitHub repositories requires token authentication. Public repositories are accessible by default, but a token is necessary to fetch file contents and READMEs from private sources.

What is the best way to extract code snippets from GitHub repos without manual scraping?

The best way to extract code snippets without manual scraping is using a dedicated crawler. It retrieves arbitrary file contents and repository READMEs by URL and path, automating data collection workflows reliably.

Does the GitHub crawler handle errors when fetching files from unavailable paths?

Yes, the GitHub crawler handles errors resiliently when fetching files. It implements robust retry logic and raw-content fallback mechanisms to ensure reliable extraction operations even when paths are unavailable.

Can I retrieve documentation overviews from multiple GitHub repositories automatically?

You can retrieve documentation overviews from multiple GitHub repositories automatically by fetching READMEs. This surfaces project documentation quickly without manual browsing, streamlining data collection workflows.