agentleFS
Sign inStart free
spf13spf13/go-skills/AGENTS.md

go-skills

AGENTS.md699 starsChanged 7 days agoMITView on GitHub

Source repository for spf13's Go Agent Skills marketplace. The skills table in README.md lists every skill. Run these before committing. CI runs the same set, plus a link check of README.md and CONTRIBUTING.md; a monthly workflow checks each skill's current through Go X.Y claim against the latest Go release (check_go_release.py, see CONTRIBUTING.md). Skills are plain directories, so a local clone can serve any agent that reads a skills directory:

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository7 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

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

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run these before committing.

    line 13
  2. Distinctive:

    If you sync skills across machines with a linking tool, re-run its sync after adding, renaming, or removing a skill so new links are …

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
AGENTS.md

Go Skills (spf13/go-skills) — Agent Instructions

Source repository for spf13's Go Agent Skills marketplace. The skills table in README.md lists every skill.

Repository Layout

  • Each top-level skill directory contains a SKILL.md with YAML frontmatter (name, description) and a .claude-plugin/plugin.json.
  • .claude-plugin/marketplace.json is the Claude Code marketplace manifest. Keep it in sync whenever a skill is added, renamed, or removed.
  • CONTRIBUTING.md lists every rule CI enforces. Read it before changing a skill or a manifest.

Checks

Run these before committing. CI runs the same set, plus a link check of README.md and CONTRIBUTING.md; a monthly workflow checks each skill's current through Go X.Y claim against the latest Go release (check_go_release.py, see CONTRIBUTING.md).

python3 -m unittest discover -s .github/scripts
python3 .github/scripts/check_invariants.py
python3 .github/scripts/validate_manifests.py
python3 .github/scripts/check_skill_code.py        # needs the latest stable Go on PATH
(cd .github/claims && go test ./...)

Using these skills from a local clone

Skills are plain directories, so a local clone can serve any agent that reads a skills directory:

  • Link each skill into the agent's skills directory (for example ~/.agents/skills/<skill>), as the README describes. Edits to a linked SKILL.md take effect immediately on that machine.
  • If you sync skills across machines with a linking tool, re-run its sync after adding, renaming, or removing a skill so new links are created and stale ones removed. Editing an existing skill needs no re-sync.
  • Other machines pick up changes with git pull --ff-only in their clone, followed by the sync step when skills were added, renamed, or removed.

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