rename-to-match-folder
Skill1 starsChanged 3 months agoApache-2.0View on GitHub
One sentence on what this does, then when to use it with natural trigger phrases a user would actually say. Lead with the key use case. Lean slightly pushy - skills under-trigger. Max 1024 characters.
In this repository24 other files it gives its agents.
- audit-fixSkill
- auditSkill
- commitSkill
- deps-auditSkill
- digestSkill
- flowchartSkill
- git-undoSkill
- handoffSkill
- hone-skillSkill
- kickoffSkill
- math-researchSkill
- new-skillSkill
- next-stepsSkill
- prompt-engineerSkill
- prune-test-suiteSkill
- release-notesSkill
- repo-adoptSkill
- repo-issue-scoutSkill
- resolve-tester-bugsSkill
- scaffold-auditSkill
- session-reportSkill
- sidebarSkill
- sync-profile-readmeSkill
- worktree-cleanupSkill
The file
Files
<Skill title>
Brief statement of the single job this skill does. (One clear job — if it does two things, split it.)
Instructions
State what to do, imperatively. The body stays in context across turns once invoked, so every line is recurring token cost — say what to do, not why.
- First step.
- Second step.
- Output format / what to return.
Notes (optional)
- Edge cases, "if the input is empty, say X", etc.
- Move long reference material to
references/and link it: see reference.md. - Reference bundled scripts portably with
${CLAUDE_SKILL_DIR}/scripts/foo.py.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.