agentleFS
Cogni-AI-OUCogni-AI-OU/cogni-ai-agent-skills/github-topics/SKILL.md

github-topics

Skill4 starsChanged 6 months agoMITView on GitHub

Search GitHub repositories by topics and keywords. You MUST load this skill when searching for relevant tools, libraries, or curated resources.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 10 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈10

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search GitHub repositories using topics and keywords to discover relevant software and resources.

    line 12
  2. Distinctive:

    When searching for curated "awesome lists" to find community-approved resources.

    line 17
  3. Distinctive:

    If the user asks for recommendations on how to solve a specific technical problem and you need to find open-source solutions.

    line 18
  4. Very specific:

    When searching for specific code snippets or implementations inside a single repository (use gh search code instead).

    line 22
  5. Distinctive:

    When looking up official documentation that is better found via a direct web search.

    line 24
  6. Very specific:

    Identify Repositories: Use gh search repos to find repositories matching specific topics or keywords.

    line 34
  7. Very specific:

    Leverage CLI: Use the GitHub CLI (gh) for efficient searching and data retrieval.

    line 40
  8. Distinctive:

    Contextual Filtering: Always filter results for relevance to the current task or environment.

    line 42
  9. Distinctive:

    Search for curated "awesome" lists by topic:

    line 46
  10. Distinctive:

    Search for specific tools within a topic:

    line 50
  11. Distinctive:

    Use these popular GitHub topics to find high-quality resources and projects:

    line 61
  12. Distinctive:

    Avoid broad, unfiltered searches that return too many irrelevant results.

    line 82
  13. Distinctive:

    Avoid relying on interactive web scraping when CLI tools are available.

    line 83

≈ “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

Skill: github-topics

<!-- markdownlint-disable MD013 MD023 MD031 MD032 -->

Search GitHub repositories using topics and keywords to discover relevant software and resources.

When to Use

  • To discover new tools, libraries, or frameworks that match the project's technology stack.
  • When searching for curated "awesome lists" to find community-approved resources.
  • If the user asks for recommendations on how to solve a specific technical problem and you need to find open-source solutions.

When Not to Use

  • When searching for specific code snippets or implementations inside a single repository (use gh search code instead).
  • To find issues or PRs (use gh issue list or gh pr list).
  • When looking up official documentation that is better found via a direct web search.

Common Pitfalls

  • Overly Broad Queries: Searching for generic terms like "javascript" without adding specific topic filters, resulting in millions of useless hits.
  • Ignoring Star Counts: Blindly adopting the first repository found without checking its star count, recent activity, or maintenance status.
  • Failing to Read the README: Recommending a tool based solely on its topic tags without fetching and verifying its README to ensure it actually does what the user needs.

Core Process

  1. Identify Repositories: Use gh search repos to find repositories matching specific topics or keywords.
  2. Extract Resources: Fetch README content or API data to understand the repository's purpose and contents.
  3. Filter and Format: Select the most relevant repositories or tools based on the current project's stack or user constraints.

Core Principles

  • Leverage CLI: Use the GitHub CLI (gh) for efficient searching and data retrieval.
  • Topic Precision: Combine keyword searches with --topic filters to narrow down results.
  • Contextual Filtering: Always filter results for relevance to the current task or environment.

Commands / Usage Patterns

  • Search for curated "awesome" lists by topic:
    gh search repos "awesome python" --topic awesome --limit 10
  • Search for specific tools within a topic:
    gh search repos "ansible" --topic python --limit 10
  • Fetch the README of a repository to extract more details:
    gh api -H "Accept: application/vnd.github.v3.raw" repos/<owner>/<repo>/readme

Featured Topics

Use these popular GitHub topics to find high-quality resources and projects:

  • awesome: Curated lists of awesome things.
  • chrome: Projects related to the Chrome browser.
  • code-quality: Tools for style, quality, security, and test-coverage.
  • compiler: Software for translating programming languages.
  • css: Cascading Style Sheets projects and libraries.
  • database: Structured sets of data and database management systems.
  • frontend: User interface programming and layout.
  • javascript: Projects using the JavaScript programming language.
  • nodejs: JavaScript runtime environments and tools.
  • npm: Package management for JavaScript.
  • project-management: Tools for scope and goal execution.
  • python: Projects using the Python programming language.
  • react: JavaScript libraries for designing user interfaces.
  • react-native: Mobile frameworks for iOS and Android.
  • scala: Projects using the Scala programming language.
  • typescript: Typed supersets of JavaScript.

What to Avoid

  • Avoid broad, unfiltered searches that return too many irrelevant results.
  • Avoid relying on interactive web scraping when CLI tools are available.

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.