agentleFS
CharleneTStrainCharleneTStrain/product-ops-skills/AGENTS.md

product-ops-skills

AGENTS.md0 starsChanged 17 days agoMITView on GitHub

Guidelines for AI agents working in this repository. Product Ops Skills — Agent Skills for product operations, following the Agent Skills spec. The repo is also a Claude Code plugin marketplace through .claude-plugin/marketplace.json. Skills are content only; there's no build. Run ./validate-skills.sh after any change. It checks that:

The file

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

5 rules. About 0 are common, 1 is distinctive, and 4 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.

  • 4

    Very specific

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

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

    every skill except product-ops-context has the context check

    line 40
  2. Very specific:

    every skill has a ## Related skills section, and every skill it names exists

    line 41
  3. Very specific:

    If you add, remove, or rename a skill, update the README tables, the "how skills work together" diagram, and VERSIONS.md, and bump the …

    line 46
  4. Very specific:

    If you add, remove, or rename a skill, also update the skill data inside site/index.html.

    line 47
  5. Distinctive:

    Keep the library's rules (see CONTRIBUTING.md): one named owner per open item, decided vs.

    line 48

≈ “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

AGENTS.md

Guidelines for AI agents working in this repository.

What this is

Product Ops Skills — Agent Skills for product operations, following the Agent Skills spec. The repo is also a Claude Code plugin marketplace through .claude-plugin/marketplace.json.

Layout

product-ops-skills/
├── .claude-plugin/
│   ├── marketplace.json     # plugin marketplace manifest
│   └── plugin.json          # plugin manifest, points at ./skills
├── skills/
│   ├── product-ops-context/ # foundation skill, read by all others
│   └── skill-name/
│       ├── SKILL.md         # instructions the agent follows
│       └── README.md        # what it solves, for people
├── site/                  # the library website (index.html), published to GitHub Pages
├── validate-skills.sh
├── VERSIONS.md
├── CONTRIBUTING.md
└── README.md

Checks

Skills are content only; there's no build. Run ./validate-skills.sh after any change. It checks that:

  • front matter starts the file and has name and description
  • name matches the folder and is lowercase with hyphens, 64 characters max
  • description is 1–1024 characters and says when to use the skill
  • SKILL.md is under 500 lines
  • every skill except product-ops-context has the context check
  • every skill has a ## Related skills section, and every skill it names exists

When you change something

  • Bump the skill's metadata.version.
  • If you add, remove, or rename a skill, update the README tables, the "how skills work together" diagram, and VERSIONS.md, and bump the version in both files under .claude-plugin/.
  • If you add, remove, or rename a skill, also update the skill data inside site/index.html.
  • Keep the library's rules (see CONTRIBUTING.md): one named owner per open item, decided vs. discussed kept separate, nothing invented, plain words.

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.