agentleFS
Sign inStart free
wangge-aiwangge-ai/wangge-skills/skills/github-repo-dissector/SKILL.md

github-repo-dissector

Skill4 starsChanged 36 days agoMITView on GitHub

Use when the user shares a GitHub repository URL or owner/repo and wants to understand, compare, evaluate, install, run, trial, or explain the repository, including purpose, architecture, setup, recent activity, growth signals, risks, and a readable technical report.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the GitHub connector for repository facts, files, issues, releases, and activity.

    line 8
  2. Distinctive:

    When a share-ready report is requested, use the verified result and retain its sources and trial status.

    line 16
  3. Very specific:

    Use scripts/github_repo_stats.py only when connector data is insufficient or a deterministic trend calculation is requested.

    line 19

≈ “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 Repository Dissector

Use the GitHub connector for repository facts, files, issues, releases, and activity. Clone or run code only when the user asks or technical verification requires it.

Workflow

  1. Confirm whether the user wants a quick scan, deep architecture analysis, install trial, comparison, or share-ready report.
  2. Collect repository identity, purpose, license, release state, recent activity, architecture, setup path, and visible risks.
  3. Distinguish repository claims from verified behavior. Do not equate stars with quality or current growth.
  4. For a real trial, use an isolated temporary directory such as github-trials/<owner-repo> and record commands, outputs, failures, and cleanup needs.
  5. When a share-ready report is requested, use the verified result and retain its sources and trial status.
  6. Produce a concise conclusion first, then evidence, architecture, setup, suitability, risks, and next action.

Use scripts/github_repo_stats.py only when connector data is insufficient or a deterministic trend calculation is requested. Resolve the current Python runtime instead of assuming python or gh is on PATH. Read references/legacy-full-workflow.md only for advanced legacy report details.

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.

Check your setup, free