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

80%

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

82%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 curation workflow that respects the token budget and validates its own output before finishing. Its main gaps are the absence of a complete example mutation command and of an error-recovery loop around the sanity check.

Suggestions

Add one full copy-paste example of a mutation command, e.g. `npx ai-agent-skills add <skill> --area mobile --branch "React Native / UI" --why "Covers React Native testing so the mobile shelf has a real device-validation option."`

Extend the Sanity Check with a short feedback loop: what to fix and re-run if the shelf mix no longer matches the user's stack or `build-docs` output looks wrong.

Dimension	Reasoning	Score
Conciseness	The body is lean and entirely CLI-specific — no concept explanations, no padding; even the good/bad examples for branch names and `whyHere` carry real discrimination value. Every token earns its place.	5 / 5
Actionability	Concrete, executable commands appear throughout (`npx ai-agent-skills init-library`, `list --area`, `search`, `collections`, `build-docs`) with specific good/bad examples. The mutation commands (`add`/`catalog`/`vendor`) name their flags (`--area`, `--branch`, `--why`) but never show one complete example invocation, leaving a minor gap.	4 / 5
Workflow Clarity	A clear sequence runs First Move → Shelf System → Discovery Loop → Mutation Rules → Collections → Sanity Check → Finish, with an explicit validation checkpoint (Sanity Check runs `list --area`, `collections`, `build-docs` and confirms the shelf mix). It stops short of anchor 5 because there is no error-recovery feedback loop (e.g., what to do when the shelf mix or build-docs output is wrong).	4 / 5
Progressive Disclosure	No bundle files exist and the ~130-line body is well organized into clear sections with nothing mis-placed or buried. It does not reach 5 because the skill exceeds the simple-skill (<50 lines) exception and inline material like the shelf taxonomy or good/bad examples could live in a one-level-deep reference.	4 / 5
	Total	17 / 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 description that explicitly states both what the skill does and when to use it, in a distinctive niche. Its main room for improvement is broader trigger coverage and slightly fuller capability coverage.

Suggestions

Broaden the when-clause with a second natural trigger, e.g. "Use when building or curating a team skills library, or when the user asks to organize or catalog shared skills."

Add one or two downstream capability terms (e.g., installing skills for teammates, publishing a shareable library) to tighten capability coverage and trigger-term synonyms.

Dimension	Reasoning	Score
Specificity	The description lists four concrete actions ("Map work to shelves, browse before curating, write meaningful `whyHere` notes, and create a starter pack") with only minor coverage gaps. It is not 5 because the headline action "building a managed team skills library" is somewhat abstract and downstream capabilities like installing or sharing are unmentioned.	4 / 5
Completeness	Both parts are explicit: the what is the action list and the when is "Use when building a managed team skills library for a real stack". It falls short of anchor 5 because the when-clause covers a single scenario without additional concrete trigger phrasings (e.g., "or when the user asks to organize or curate team skills").	4 / 5
Trigger Term Quality	Good natural keyword coverage: "team skills library", "curating", "starter pack", "shelf" are phrases a user would plausibly say. A few natural terms are missing (e.g., "skill catalog", "skill registry", "organize team skills"), keeping it below the comprehensive-synonym level of anchor 5.	4 / 5
Distinctiveness Conflict Risk	The description occupies a clear niche — shelves, `whyHere` curator notes, and starter packs via a library CLI — with distinct triggers and minimal risk of firing for an unrelated skill.	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: 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.