agentleFS
kidowkidow/skills/find-github-repo/SKILL.md

find-github-repo

Skill2 starsChanged 6 months agoMITView on GitHub

Search GitHub repositories by functionality using gh CLI, iteratively refining the query until the user finds the right one. Use when user wants to find a GitHub repository, library, or tool for a specific purpose, or says things like "is there a repo that does X", "find me a library for Y", or "recommend a tool for Z".

The file

Files
SKILL.md

GitHub Repository Finder

Quick Start

Extract 2–4 keywords from user's description, then search:

gh search repos "<keywords>" --sort stars --limit 10 \
  --json name,description,url,stargazerCount,updatedAt

Workflow

  1. Extract keywords — pick nouns/verbs most specific to the desired functionality
  2. Search with gh search repos
  3. Present results as list (see Output Format)
  4. Ask with choices:

    "Did any of these match? A) Wrong language or runtime B) Too generic — need something more specific C) Wrong category (library / CLI / framework) D) Let me describe what I need E) Show more results"

  5. Refine based on answer → repeat from step 2
  6. No limit on rounds — keep going until user confirms they found it

Refinement Strategy

ChoiceAction
AAdd --language <lang> filter, ask which language
BAdd more specific terms to query
CAppend "library" / "cli" / "framework" to query
DRe-extract keywords from user's new description
ERe-run with --limit 20, show next 10 results

gh Search Options

# Basic
gh search repos "<query>" --sort stars --limit 10

# With language filter
gh search repos "<query>" --language typescript --sort stars --limit 10

# More results
gh search repos "<query>" --sort stars --limit 20

# Full JSON output
gh search repos "<query>" --sort stars --limit 10 \
  --json name,description,url,stargazerCount,updatedAt

Output Format

Present results as:

Sort by star count descending. If description is empty, note "(no description)". Format updatedAt as YYYY-MM (year and month only).

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.