agentleFS
Sign inStart free
parvez-ahammedparvez-ahammed/shipkit/_template/SKILL.md

my-skill-name

Skill0 starsChanged 24 days agoMITView on GitHub

One or two sentences: WHAT this skill does AND WHEN it should trigger. This is the only signal Claude uses to decide whether to load the skill, so be specific and a little pushy. Name the contexts and the kinds of phrases a user would actually type ("use this whenever the user wants to X, mentions Y, or is debugging Z - even if they don't say 'skill'"). List concrete trigger examples. Avoid vague verbs. End with the neighbour skill to use instead ("Not for X (use other-skill)"). Keep it under 1,024 characters (portable Agent Skills limit; Claude Code truncates description + when_to_use at 1,536 in the skill listing).

10 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Don't use when: ... (point at the better tool/skill for those cases)

    line 30

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “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 title

One paragraph on what this skill is for and the value it delivers (especially any non-obvious, hard-won knowledge it encodes - that's what makes a skill worth more than the model improvising).

When to use / not use

  • Use when: ...
  • Don't use when: ... (point at the better tool/skill for those cases)

Workflow

Imperative steps. Explain the WHY behind anything non-obvious - smart models follow reasoning better than rigid rules.

  1. ...
  2. ...

Gotchas

The traps that produce silent failures or "looks fine but isn't" states. This section is often the real value.

  • ...

Reference map (optional - for larger skills)

  • references/<topic>.md - read when ...
  • assets/<file> - copy/adapt for ...
  • scripts/<file> - run to ...

Reference bundled files as ${CLAUDE_SKILL_DIR}/scripts/<file> so the path works whether the skill is installed as a plugin or copied into ~/.claude/skills. Keep SKILL.md under ~500 lines; move detail into references/ (one level deep) and say when to read each file.

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