agentleFS
espressifespressif/esp-claw-skills-lab/skills/github_repo_star/SKILL.md

github_repo_star

Skill37 starsChanged 33 days agoMITView on GitHub

Use this skill when the user asks for the star count of a GitHub repository. Run the bundled Lua script once with lua_run_script. The script uses the Lua capability module from lua_module_call_capability to call the registered http_request capability, then extracts stargazers_count from the GitHub REST API response. By default it fetches: The configured search_http_allowlist must allow api.github.com or use *. If both repo and url are provided, repo takes precedence. Default action: Fetch a specific repository: The script prints a…

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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. Distinctive:

    Use this skill when the user asks for the star count of a GitHub repository.

    line 17
  2. Very specific:

    Run the bundled Lua script once with lua_run_script.

    line 19
  3. Very specific:

    If both repo and url are provided, repo takes precedence.

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 Star

Use this skill when the user asks for the star count of a GitHub repository.

Run the bundled Lua script once with lua_run_script. The script uses the Lua capability module from lua_module_call_capability to call the registered http_request capability, then extracts stargazers_count from the GitHub REST API response.

By default it fetches:

https://github.com/espressif/esp-claw

The configured search_http_allowlist must allow api.github.com or use *.

Script Args Schema

{
  "type": "object",
  "properties": {
    "repo": {
      "type": "string",
      "description": "Optional GitHub repository as owner/name, for example espressif/esp-claw."
    },
    "url": {
      "type": "string",
      "description": "Optional GitHub repository URL, for example https://github.com/espressif/esp-claw."
    },
    "timeout_ms": {
      "type": "integer",
      "description": "Optional HTTP timeout in milliseconds. Defaults to 15000."
    },
    "session_id": {
      "type": "string",
      "description": "Optional session id passed to capability.call opts."
    },
    "source_cap": {
      "type": "string",
      "description": "Optional source capability name. Defaults to github_repo_star."
    }
  }
}

If both repo and url are provided, repo takes precedence.

Tool Call Inputs

Default action:

{
  "path": "{CUR_SKILL_DIR}/scripts/github_repo_star.lua",
  "args": {}
}

Fetch a specific repository:

{
  "path": "{CUR_SKILL_DIR}/scripts/github_repo_star.lua",
  "args": {
    "repo": "espressif/esp-idf"
  }
}

Behavior

The script prints a human-readable line and a compact JSON result:

[github_repo_star] espressif/esp-claw stars=12345 url=https://github.com/espressif/esp-claw
{"ok":true,"owner":"espressif","repo":"esp-claw","full_name":"espressif/esp-claw","stars":12345,"url":"https://github.com/espressif/esp-claw"}

Report the stars value to the user. If the script errors, report the error message directly.

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.