agentleFS
Sign inStart free
BrendenKennedyBrendenKennedy/claude-for-ai-platforms/.claude/skills/_example/SKILL.md

example-skill

Skill1 starsChanged 3 months agoMITView on GitHub

REPLACE THIS. A skill auto-surfaces purely on this text, and the listing TRUNCATES it at 1,536 chars (tail first) inside a shared budget — so front-load and stay ≤1,000 chars. Formula: <domain/contract in one clause> — <what it carries: the 3–5 specifics an agent can't guess>. Load when <the tasks it covers>. Triggers: <phrases the user will actually type, SHARPEST FIRST — they must survive truncation>. Optionally end with a one-clause scope boundary (what belongs to a sibling skill instead).

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 38 edited versions we read keep these.

  • 1

    Distinctive

    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:

    Put deep knowledge WITH discovery triggers here.

    line 45
  2. Distinctive:

    Keep it refined and current.

    line 47

“Common” is measured: kept by at least 6 in 10 of the 38 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 name> — <one-line subtitle>

A skill is on-demand expertise: deep, ground-truth domain knowledge that Claude loads only when the description matches the task. Reach for it before acting in its domain — it carries the authoritative detail that the lightweight CLAUDE.md map intentionally omits.

When this applies

<The situations where this skill is the source of truth. Mirrors the description's triggers.>

The facts

<The actual knowledge: endpoints, versions, commands, gotchas, contracts, exact configs. This is what makes a skill worth having — specifics an agent can't guess and shouldn't re-derive. Use tables and code blocks freely.>

ThingValue
<key fact><value>

How to do X

# concrete, copy-pasteable commands

Gotchas

  • <the non-obvious failure mode and how to avoid it>
<!-- Authoring notes (delete in real skills): - One skill = one coherent domain. If it sprawls, split it. - The directory name and `name:` should match and be kebab-case: skills/<name>/SKILL.md. - Skills can include supporting files alongside SKILL.md (scripts, reference docs); link to them with relative paths and Claude can read them on demand. - Put deep knowledge WITH discovery triggers here. Reusable "how we do X" with no triggers → .claude/memory/reference/. What happened in a session → .claude/memory/sessions/. - Keep it refined and current. A stale skill is worse than no skill. -->

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