<kebab-case-skill-name>
Skill2 starsChanged 5 months agoMITView on GitHub
One paragraph — leads with "when to use" / trigger phrases. Stays ≤ 1536 chars. Example "Use when... User says... Auto-triggers on..." patterns work best.
In this repository60 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- analyzeSkill
- animation-disciplineSkill
- api-versioningSkill
- autopilotSkill
- browser-e2eSkill
- characterizeSkill
- clarifySkill
- codemodSkill
- constitution-compactSkill
- constitutionSkill
- context-budgetSkill
- creative-webSkill
- db-migrationSkill
- debugSkill
- detect-stackSkill
- dispatch-criteriaSkill
- dreamSkill
- experimentSkill
- fastapiSkill
- flag-cleanupSkill
- flag-rolloutSkill
- flask-realtimeSkill
- framework-detectorSkill
- front-end-designSkill
- grill-meSkill
- handoffSkill
- image-generationSkill
- implementSkill
- initiativeSkill
- instinctSkill
- loopSkill
- nextjsSkill
- observabilitySkill
- okr-alignSkill
- parallel-swarmSkill
- pivotSkill
- planSkill
- pr-bodySkill
- prime-disciplineSkill
- prod-observabilitySkill
- react-nodeSkill
- react-viteSkill
- release-trainSkill
- researchSkill
- reviewSkill
- security-guardSkill
- self-healSkill
- shipSkill
- skill-creatorSkill
- specifySkill
- tailwind-disciplineSkill
- tasksSkill
- tdd-loopSkill
- token-budgetSkill
- typographySkill
- verify-loopSkill
- verifySkill
- wip-checkpointSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
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
- Distinctive: line 50
If the skill modifies tone or behavior, declare when it must DISABLE itself:
- Distinctive: line 62
After save: "<one-line summary of what was done>."
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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.
Files
<Skill Title>
One-sentence summary of what this skill does. Keep it crisp.
When to use
- Specific user phrase 1
- Specific user phrase 2
- Concrete scenario 1
When NOT to use
- Scenario where another skill is better
- Scenario where this is overkill
Process
1. Read inputs from <where>
2. Do <thing>
3. Validate via <how>
4. Output to <where>
5. Hand off to <next step>Hard rules
- Rule 1 — why it matters
- Rule 2 — why it matters
- Rule 3 — why it matters
Auto-clarity escape hatch (per caveman pattern)
If the skill modifies tone or behavior, declare when it must DISABLE itself:
- Security warnings
- Irreversible action confirmations
- Multi-step sequences where fragment order matters
- Ambiguity needing clarification
Output
<path-or-artifact-this-produces>After save: "<one-line summary of what was done>."
References
- Source / inspiration:
<github URL> - Related skills:
.claude/skills/<other>/SKILL.md - Anthropic skills spec: https://code.claude.com/docs/en/skills
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.