agentleFS
GoogleKnown publishergoogle-gemini/gemini-managed-agents-templates/repo-maintainer/skills/github-researcher/SKILL.md

github-researcher

Skill99 starsChanged 6 months agoApache-2.0View on GitHub

Guides the agent on how to read and search GitHub issues to understand the repository's problems.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If you need to fetch specific issue details or comments, you can query the GitHub REST API directly using curl (since api.github.com is in …

    line 25
  2. Distinctive:

    Read the README: Check the top-level README.md in the cloned repo.

    line 39
  3. Very specific:

    Scan the directory tree: Use find . -maxdepth 2 to understand the structure.

    line 40
  4. Distinctive:

    Summarize issues: Read the fetched issues and identify themes, recurring complaints, or critical bugs.

    line 41

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

GitHub Researcher Skill

This skill helps the agent find and understand issues in a specified GitHub repository, and gain a deep understanding of the codebase.

[!WARNING] GitHub CLI (gh) is NOT installed in this environment. Do NOT attempt to run gh commands. Always use the provided fetch_issues.py script to batch fetch open issues, and use curl with the GitHub REST API to fetch specific issue details or comments.

Workflow

1. Fetching Issues

You can fetch issues using the provided Python script (works without auth for public repos):

python skills/github-researcher/scripts/fetch_issues.py --repo <owner>/<repo> --workspace ./workspace

Output: {workspace}/data/github-issues.md

If you need to fetch specific issue details or comments, you can query the GitHub REST API directly using curl (since api.github.com is in the network allowlist):

Fetch Specific Issue Details:

curl -s -H "User-Agent: Repo-Maintainer/1.0" https://api.github.com/repos/<owner>/<repo>/issues/<issue_number>

Fetch Comments on a Specific Issue:

curl -s -H "User-Agent: Repo-Maintainer/1.0" https://api.github.com/repos/<owner>/<repo>/issues/<issue_number>/comments

3. Understanding the Repo

To answer questions like "What are my biggest issues?" or understand the project deeply:

  1. Read the README: Check the top-level README.md in the cloned repo.
  2. Scan the directory tree: Use find . -maxdepth 2 to understand the structure.
  3. Summarize issues: Read the fetched issues and identify themes, recurring complaints, or critical bugs.

Output

Produce a summary of the top issues and codebase structure to answer the user's high-level questions.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.