my-skill
Skill6 starsChanged 53 days agoMITView on GitHub
What this does, then when to use it. The description is the only thing Claude reads when deciding whether to load the skill, so write the trigger conditions into it — including the words a user would actually say. Aim for 1-3 sentences.
18 other projects use a version of this.
Adopted by
Most recently taken up by
- Osipchuk/agent-skillstheir own version, first seen Nov 8, 2026
- TheMarnix/agent-config-kittheir own version, first seen Nov 1, 2026
- elastic/clients-team-automationstheir own version, first seen Oct 25, 2026
- kzndotsh/skillstheir own version, first seen Oct 17, 2026
- nakane1chome/claude-skillstheir own version, first seen Oct 15, 2026
- PurasAI/skillpack-templatetheir own version, first seen Oct 11, 2026
Other versions18 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 18
- PaperDebugger/paperdebugger★ 1.5ksame name
- microsoft/GHCP-Lab★ 45same name
- FoneClaw-AI/foneclaw-android★ 21same name
- chuckyatsuk/acidtest★ 8same name
- sigpanic/goink-skills★ 8same name
- Osipchuk/agent-skills★ 5same name
- kzndotsh/skills★ 2same name
- sarveshtalele/mcp-skills-registry★ 2same name
- sumulige/sumulige-claude★ 2same name
- elastic/clients-team-automations★ 1same name
8 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repositoryOne other file it gives its agents.
- CLAUDE.mdCLAUDE.md
The file
Files
My skill — one line on what it's for
Why this exists
The problem, and why the obvious approach doesn't solve it. Keep this short; it's context, not content. If you can't name a concrete failure this skill prevents, the skill probably isn't worth writing.
Procedure
1. First step
Numbered, ordered steps with the actual commands. A skill that says "be careful about X" changes nothing — say what to run and what to look for.
# real, runnable commands2. Second step
Discover, don't assume. If the step depends on the repo's setup, say where to look for it rather than hard-coding what your repo happens to use.
Rules
- Constraints that apply throughout, not just at one step.
- What this skill must never do.
- What it does not cover, so nobody trusts it in a situation it can't handle.
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
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.

