skill-curator
Skill2 starsChanged 2 months agoMITView on GitHub
Audit a skill library for duplicated guidance, contradictions, bloat, dead references, and defects. Use when cleaning, consolidating, or de-duplicating a skills tree.
9 other projects use a version of this.
Adopted by
Most recently taken up by
- skdfndh/better-skill-managertheir own version, first seen Nov 1, 2026
- cskwork/skill-curatortheir own version, first seen Nov 1, 2026
- SHYXIN/skillstheir own version, first seen Oct 11, 2026
- sakuruamayday-ops/enterprise-project-application-assistanttheir own version, first seen Oct 9, 2026
- LarrySequino/skillstheir own version, first seen Oct 5, 2026
- creanlab/agent-genome-labtheir own version, first seen Jul 10, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- laolaoshiren/claude-code-skills-zh★ 907same name
- lexielin99-code/skill-curator★ 9same name
- SHYXIN/skills★ 6same name
- Shino-zzz/skill-curator★ 4same name
- creanlab/agent-genome-lab★ 2same name
- sakuruamayday-ops/enterprise-project-application-assistant★ 2same name
- cskwork/skill-curator★ 1same name
- LarrySequino/skills★ 1same name
- skdfndh/better-skill-manager★ 0same name
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 repository27 other files it gives its agents.
- agent-guardrailsSkill
- benchmark-checklistSkill
- blast-radiusSkill
- blog-reviewSkill
- code-reviewSkill
- create-verification-skillSkill
- datavizSkill
- grill-meSkill
- grok-repoSkill
- hammerspoonSkill
- html-lessonSkill
- karpathy-planningSkill
- mechanism-vizSkill
- obsidian-captureSkill
- obsidian-searchSkill
- paper-searchSkill
- readbackSkill
- repo-evalSkill
- route-skillSkill
- sherlockSkill
- show-meSkill
- sketch-conceptSkill
- test-writingSkill
- tla-modelSkill
- web-recapSkill
- write-docsSkill
- write-skillSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
2
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
- Distinctive: line 16
Fix and verify: Don't commit unless asked.
- Distinctive: line 30
Read every claimed defect before asserting it — heuristics misfire on code blocks and intentional parallel structures.
“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.
Files
skill-curator
Workflow
- Inventory —
for d in <root>/*/*/; do grep -E '^(name|description):' "$d/SKILL.md"; done - Cluster — group by topic; flag pairs whose descriptions overlap or triggers could both fire.
- Read suspects — never classify from description or regex alone.
- Classify against taxonomy below.
- Surface findings + recommended fix — get direction before multi-file refactor; small isolated fixes can proceed.
- Fix and verify. Don't commit unless asked.
Taxonomy
- Forked script — same script copied across skills. Diff for drift. One owner; the other points to it.
- Contradiction — conflicting instructions for the same artifact. Pick owner; other defers.
- Restatement — one skill re-derives another's content. Replace with a one-line pointer.
- Bloat — frequently-loaded file carrying rare detail. Externalize to
references/; keep quick-fixes inline. - Unused or over budget — a skill no session log has read, or descriptions that together exceed the harness's list budget (Codex: 2% of context, then equal truncation). steipete/agent-scripts skill-cleaner measures both for Codex; elsewhere, sum description bytes by hand.
- Internal defect — duplicate headers/numbering, dead path refs, dead code.
- Smell — a single skill that fails on its own. From a 238-skill survey (arXiv 2607.01456), the ones worth flagging: stepless workflow; option buffet (choices with no decision rule); rationalization loophole ("usually", "if needed"); buried gotchas (traps mid-paragraph instead of in Notes); confusing description (what, when, and keywords blurred into one sentence); time-sensitive claims; non-third-person description; XML or backslash paths in frontmatter.
Rules
- Read every claimed defect before asserting it — heuristics misfire on code blocks and intentional parallel structures.
- One owner per capability; the other references it by explicit path.
- Progressive disclosure: description → SKILL.md (terse) →
references/REFERENCE.md(deep). Terseness scales with load frequency. - Fix the defect only — no adjacent refactoring, no extra cross-links.
See also
write-skill— author one new skill.
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.