agentleFS
Sign inStart free
HenryQWHenryQW/skills/gh/SKILL.md

gh

Skill1 starsChanged 4 months agoApache-2.0View on GitHub

Look up exact GitHub CLI commands, arguments, flags, examples, and behavior from a versioned local manual. Use when asked how to use `gh` or when exact `gh` syntax or options must be checked.

  • Commits and pushes

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 4 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the bundled manual instead of recalling GitHub CLI syntax.

    line 8
  2. Distinctive:

    Read only the deepest known command README.md.

    line 14
  3. Very specific:

    Read only the needed linked facet: details.md for arguments or constraints, or examples.md for examples.

    line 15
  4. Very specific:

    Read sibling help.txt only when compact files do not settle the answer or source wording is required.

    line 16
  5. Very specific:

    Every command accepts --help.

    line 22
  6. Distinctive:

    Never invent flags, output fields, defaults, or behavior.

    line 24
  7. Very specific:

    Check references/snapshot.txt when version matters.

    line 25
  8. Distinctive:

    Update the root README's displayed version to exactly match the snapshot.

    line 33
  9. Very specific:

    Run python3 <skill>/scripts/test_compact.py, python3 <skill>/scripts/test_topics.py, then python3 <repo>/scripts/validate.py.

    line 34

≈ “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

gh

Use the bundled manual instead of recalling GitHub CLI syntax.

Load progressively

Mirror command words under references/commands/; for example, gh pr create maps to pr/create/.

  1. Read only the deepest known command README.md. It contains purpose, usage, aliases, child routes, and every command-specific option.
  2. Read only the needed linked facet: details.md for arguments or constraints, or examples.md for examples.
  3. Read sibling help.txt only when compact files do not settle the answer or source wording is required.

If the command path is uncertain, start at the nearest known parent README and follow one child. Never load sibling directories or the whole manual. Shared topics live in references/topics/; read only the needed compact topic. Use command routes instead of the omitted redundant actions topic; telemetry controls are in environment.md.

Use the manual

  • Every command accepts --help; it is intentionally omitted from command references.
  • Answer with the shortest valid command and only relevant caveats. Do not execute it unless requested.
  • Never invent flags, output fields, defaults, or behavior.
  • Check references/snapshot.txt when version matters. If installed gh differs, the command is absent, or current behavior is required, run gh help <command path> and trust live help.

Local aliases and extensions may not exist elsewhere.

Update the snapshot

  1. Install/select the intended gh version and run python3 <skill>/scripts/generate.py. Never hand-edit generated command or topic references.
  2. Inspect references/snapshot.txt, command/topic source diffs, and added or removed paths. If a topic's structure changed, update its deterministic renderer in scripts/topics.py; its shape checks fail rather than silently dropping new content.
  3. Update the root README's displayed version to exactly match the snapshot.
  4. Run python3 <skill>/scripts/test_compact.py, python3 <skill>/scripts/test_topics.py, then python3 <repo>/scripts/validate.py.

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