MoizIbnYousafMoizIbnYousaf/Ai-Agent-Skills/skills/review-a-skill/SKILL.md

review-a-skill

Skill1.1k starsChanged 8 months agoMITView on GitHub

Use when evaluating whether a skill belongs in a library. Preview content, check frontmatter, validate structure, and decide whether to keep, curate, or remove.

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 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.
4
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Always use --format json for machine-readable output in automated pipelines.
line 16
Very specific:
Always use --fields to limit output size when inspecting catalog entries.
line 17
Very specific:
Always use --dry-run before curating or removing a skill.
line 18
Very specific:
Never remove a skill without first checking if other skills depend on it via info --format json dependencies.
line 19
Distinctive:
If the skill needs curation (notes, collections, verification):
line 43
Distinctive:
If the skill should be removed:
line 50

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Review A Skill

Goal

Evaluate a single skill's quality, relevance, and safety before it enters or stays in a library.

Guardrails

Always use --format json for machine-readable output in automated pipelines.
Always use --fields to limit output size when inspecting catalog entries.
Always use --dry-run before curating or removing a skill.
Never remove a skill without first checking if other skills depend on it via info --format json dependencies.

Workflow

Preview the skill content to check for quality and safety.

npx ai-agent-skills preview <skill-name>

The preview command sanitizes content — if it flags sanitization, investigate before proceeding.

Inspect the catalog entry for metadata completeness.

npx ai-agent-skills info <skill-name> --format json --fields name,description,tags,collections,dependencies

Validate the skill's SKILL.md structure.

npx ai-agent-skills validate <skill-name>

If the skill needs curation (notes, collections, verification):

npx ai-agent-skills curate <skill-name> --notes "Reviewed: solid patterns" --verify --dry-run
npx ai-agent-skills curate <skill-name> --notes "Reviewed: solid patterns" --verify

If the skill should be removed:

npx ai-agent-skills curate <skill-name> --remove --dry-run
npx ai-agent-skills curate <skill-name> --remove --yes

Decision Criteria

Keep: Clear description, valid frontmatter, useful to the library's audience, no injection patterns.
Curate: Needs better whyHere, collection placement, or verification status.
Remove: Duplicate, outdated, broken source, or contains suspicious content.

Gotchas

The preview command only works for vendored (house) skills. Upstream skills show description and whyHere only.
The validate command checks frontmatter structure but not content quality — that requires human or agent judgment.
Removing a skill that other skills depend on will break the dependency graph. Always check dependencies.usedBy first.

Download now (ZIP)

Other versions3 projects use a version of this.
Word for word · 2
skillcreatorai/Ai-Agent-Skills★ 1.1k100% same
MoizIbnYousaf/ai-agent-skills★ 1.1k100% same
Edited · 0
None found.
Wrote their own version · 1
dafaalz/agent-skills★ 2same 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 repository17 other files it gives its agents.
- ask-questions-if-underspecifiedSkill
- audit-library-healthSkill
- backend-developmentSkill
- best-practicesSkill
- browse-and-evaluateSkill
- build-workspace-docsSkill
- changelog-generatorSkill
- code-documentationSkill
- content-research-writerSkill
- curate-a-team-librarySkill
- database-designSkill
- install-from-remote-librarySkill
- llm-application-devSkill
- migrate-skills-between-librariesSkill
- share-a-librarySkill
- update-installed-skillsSkill
- verification-agentSkill

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.

Check your setup, free