curate-a-team-library

Use when building a managed team skills library for a real stack. Map work to shelves, browse before curating, write meaningful `whyHere` notes, and create a starter pack once the first pass is solid.

Quality

86%

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

93%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.

A tight, highly actionable workflow skill with executable CLI commands, concrete good/bad examples, and a verification sanity-check section. Its only gap is the absence of an explicit retry-on-failure feedback loop for batch mutations.

Suggestions

Add an explicit validate→fix→retry loop in the Sanity Check or Mutation Rules section, e.g. 'If `list --area` shows a shelf that doesn't match the user's stack, remove the misplaced skill and re-run the check before finishing.'

Make the 'Sanity Check' checkpoints firmer by stating the pass condition (e.g. 'Only proceed to Finish once every primary shelf passes `list --area`').

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it never explains what skills/libraries are and every section (Shelf System, Mutation Rules, whyHere) earns its tokens, matching the score-5 lean-and-efficient anchor.	5 / 5
Actionability	Executable `npx ai-agent-skills init-library/list/search/add/catalog/vendor/build-docs` commands appear throughout, paired with concrete good/bad examples for branch names and whyHere notes, making the guidance copy-paste ready.	5 / 5
Workflow Clarity	A clear sequenced flow (First Move → Shelf System → Discovery → Mutation → Sanity Check → Finish) with a verification section that re-runs `list --area` and confirms the shelf mix still matches the stack, but it lacks an explicit validate→fix→retry feedback loop for the batch mutation operations, capping it at 4 rather than 5.	4 / 5
Progressive Disclosure	No bundle files exist and none are referenced; the single self-contained file (~130 lines) is well-organized into clearly headed sections with no nested references or monolithic walls, satisfying the simple-skill exception for a high progressive-disclosure score.	5 / 5
	Total	19 / 20 Passed

Description

78%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.

A strong, third-person description with an explicit trigger clause and a sequence of concrete curator actions. Its only weakness is that the 'when' trigger and keyword coverage are good but not exhaustive of natural synonyms.

Suggestions

Broaden trigger phrases with natural synonyms a user might say, e.g. 'team skills catalog', 'skill registry', or 'skill library for our stack'.

Tighten the 'when' clause to name the triggering situation more concretely, e.g. 'Use when a team needs a shared, installable skills library for their actual stack rather than ad-hoc skill files.'

Dimension	Reasoning	Score
Specificity	Lists several concrete curator actions — 'Map work to shelves', 'browse before curating', 'write meaningful whyHere notes', 'create a starter pack' — covering the domain well with only minor gaps, fitting the score-4 anchor rather than the comprehensive score-5.	4 / 5
Completeness	It opens with an explicit 'Use when...' trigger and pairs it with a clear 'what' (map shelves, browse, write whyHere, create a starter pack); both halves are present, but the 'when' could be slightly more specific, matching score 4 over score 5.	4 / 5
Trigger Term Quality	'building a managed team skills library for a real stack' and 'starter pack', 'curating' are natural phrases a user would say, giving good keyword coverage, though a few common synonyms (catalog, registry) are missing, keeping it below 5.	4 / 5
Distinctiveness Conflict Risk	The niche is sharp — building a managed team skills library — with distinct triggers and minimal overlap risk against other skills, matching the score-5 clear-niche anchor.	5 / 5
	Total	17 / 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/curate-a-team-library/SKILL.md
Commit: 1159592

Reviewed: 18 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.