The body is highly actionable, with a clear sequenced workflow, concrete examples, decision rules, and an explicit validation step. Its main weaknesses are mild redundancy that inflates the token budget and two locally-referenced bundle files (scope-and-strategy.md, tooling.md) that are cited repeatedly but missing from the bundle, breaking progressive-disclosure navigation.

Suggestions

Create the missing `references/scope-and-strategy.md` and `references/tooling.md` files (or remove the inline references to them) so the four cited links resolve.

De-duplicate the body: the OAuth2 example and the commit-message format each appear in multiple sections — keep one canonical instance and cross-reference it.

Trim the Mindset section's restatement of basic SemVer/type mappings (which Claude already knows) and keep only the non-obvious guidance about scope vocabulary.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and on-point, but includes redundancy and some over-explanation — the `feat(auth): add OAuth2 login support` example appears twice (agent output format and Examples), the commit format is restated in multiple sections, and the Mindset section re-explains SemVer mappings Claude already knows. Could be tightened to earn its full token budget.	2 / 3
Actionability	Provides a concrete 7-step procedure, a type reference table, explicit decision rules for type ambiguities, multiple full copy-paste-ready commit examples, and runnable validation commands (`git commit --dry-run`, `npx commitlint`, `git log --format=...`).	3 / 3
Workflow Clarity	The Procedure is a clearly numbered 7-step sequence culminating in an explicit verification checkpoint (step 7: 'run git commit --dry-run or your local commitlint hook'), with ambiguity-resolution rules embedded at the decision points.	3 / 3
Progressive Disclosure	The body is well-organized and signals one-level-deep references to `references/scope-and-strategy.md` and `references/tooling.md`, but those files do not exist — no `references/` directory is present — so the signaled navigation is broken and following the links dead-ends.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 that concretely enumerates capabilities and provides explicit, natural-language trigger terms covering the main user intents. It clearly states both what the skill does and when Claude should invoke it, with minimal risk of conflicting with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Analyzes diffs or change descriptions, selects the correct type/scope, writes an imperative-mood header under 72 characters, and composes optional body and footer sections including breaking-change notation' — matching the multi-action anchor.	3 / 3
Completeness	Explicitly answers both what it does (generate/format commit messages, analyze diffs, pick type/scope, write header, compose body/footer) and when to use it via a clear 'Use when...' clause with multiple triggers.	3 / 3
Trigger Term Quality	Covers natural user phrasing — 'help writing commit messages, formatting git commits, ... staged changes, ... changelog entry, ... conventional commits, semantic versioning, or version bumps' — strong coverage of terms users would actually say.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (Conventional Commits spec) with distinct, specific triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
relative_links	Relative link issues: 6 missing	Warning
referenced_paths_exist	Referenced path issues: 6 missing	Warning

	Total	13 / 16 Passed

Reviewed

9 days ago

Table of Contents

Discovery Implementation Validation