review-a-skill

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

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an exemplary lean workflow skill: every step is executable, destructive operations are gated by dry-run and dependency checks, and the Gotchas section supplies genuinely non-obvious operational knowledge. No weaknesses found.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout: every section carries non-obvious information (vendored-vs-upstream preview behavior, validate's scope limits, dependency-graph risks) with zero explanation of concepts Claude already knows. Matches the 'every token earns its place' anchor.	5 / 5
Actionability	All five workflow steps give fully executable, copy-paste-ready commands with concrete flags (e.g. 'npx ai-agent-skills info <skill-name> --format json --fields name,description,tags,collections,dependencies' and 'curate ... --verify --dry-run'). Matches the 'fully executable; copy-paste ready' anchor.	5 / 5
Workflow Clarity	Clear 5-step sequence with explicit validation for the destructive operations ('Always use --dry-run before curating or removing', dependency check before removal) and conditional error guidance ('if it flags sanitization, investigate before proceeding'). The destructive-operation cap at 3 does not apply since validation steps are explicitly present.	5 / 5
Progressive Disclosure	A single compact, well-sectioned file (Goal, Guardrails, Workflow, Decision Criteria, Gotchas) with no content that belongs in separate bundle files and no nested references — the simple-skill case where organized sections alone merit full credit.	5 / 5
	Total	20 / 20 Passed

Description

67%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description answers both what and when explicitly and names several concrete actions with a clear niche. Its main weakness is trigger-term coverage: it misses the natural synonyms ('review', 'audit', 'prune') a user would most likely say when needing this skill.

Suggestions

Add natural trigger synonyms to the when-clause, e.g. 'Use when reviewing, auditing, or pruning skills in a library, or deciding whether to keep, curate, or remove one.'

Slightly expand the what-clause with concrete outcomes (e.g. 'inspect content and metadata, check dependencies') to push specificity toward comprehensive coverage.

Mention the dependency-check step in the description to further differentiate from generic skill-validation skills.

Dimension	Reasoning	Score
Specificity	Lists four named actions ('Preview content, check frontmatter, validate structure, and decide whether to keep, curate, or remove'), matching the 'several specific actions; minor gaps' anchor. Not 5 because the actions are named at a high level without comprehensive detail; not 3 because it goes well beyond 1-2 concrete actions.	4 / 5
Completeness	Has an explicit when-clause ('Use when evaluating whether a skill belongs in a library') and a clear what (preview, check, validate, decide), satisfying both. Not 5 because the when offers a single trigger condition rather than multiple concrete trigger phrases; not 3 because the when is explicit, not implied.	4 / 5
Trigger Term Quality	Contains some natural keywords ('skill', 'library', 'evaluating', 'keep, curate, or remove') but misses the most common user phrasings like 'review a skill', 'audit', or 'prune skills'. Fits the 'some relevant keywords but missing common variations or synonyms' anchor.	3 / 5
Distinctiveness Conflict Risk	The keep/curate/remove library-membership decision is a clear niche, but 'check frontmatter, validate structure' overlaps with skill-authoring/validation skills. Fits 'mostly distinct; minor overlap risk with closely related skills'; not 5 because of that overlap, not 3 because the core trigger is well differentiated.	4 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: MoizIbnYousaf/ai-agent-skills
Path: skills/review-a-skill/SKILL.md
Commit: 6d95c78

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.