test-audit

Invoke whenever writing, changing, reviewing, or sweeping Vitest tests in this repo. Authoring gate for new or changed tests, plus an audit workflow for low-value, implementation-coupled, or duplicative tests and the test-only production seams they keep alive. Use when asked to add tests, review tests, clean up tests, or when a PR touches *.test.ts.

Quality

94%

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

92%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 exceptionally dense, executable procedure: concrete commands, named files, explicit validation checkpoints, and error-recovery loops for destructive and batch operations. The only structural weakness is that all of it lives in one long SKILL.md with no reference files, which the well-organized sections only partially compensate for.

Suggestions

Split the Campaign-mode pipeline (phase definitions and campaign rules) into a references/ file (e.g. references/campaign-mode.md), keeping SKILL.md as an overview with a clearly signaled one-level-deep link.

Move the junk-pattern catalog into a references/junk-patterns.md checklist, keeping only the short summary and the link in SKILL.md.

Consider extracting the repo-specific pattern list (per-test imports, error-class re-declaration, Drizzle chain mocking, etc.) into its own reference so the shared checklist stays scannable during audits.

Dimension	Reasoning	Score
Conciseness	The body contains no concept explanations and no padding; every line is procedural or a non-obvious repo constraint ('Vitest `clearMocks` is already on', '`pnpm format:write` ignores arguments and formats the whole repository', 'Knip fails `ci:check` on the orphaned export'). It assumes Claude's competence throughout, matching the lean anchor 5 rather than 4.	5 / 5
Actionability	Copy-paste-ready commands appear at every step: 'pnpm exec vitest run <path-or-filter>', 'pnpm sync-plugin-skills', 'pnpm exec prettier --write <files>', 'pnpm ci:check', '--sequence.shuffle.tests --sequence.seed=<n>', 'git diff --numstat', plus named files and factories ('ga4-test-fixtures.ts', 'samSkills.test.ts'). The junk-pattern list is concretely checkable, matching anchor 5.	5 / 5
Workflow Clarity	A numbered Validation sequence with explicit checkpoints (owner/sibling tests, contract executable, format + ci:check, full suite, numstat inspection) plus a two-phase Campaign pipeline with feedback loops ('the applier confirms that test still exists', 'skips every risky item, listing it back for the maintainer'). Destructive and batch edits carry required validation and error-recovery loops, matching anchor 5 rather than 4.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent), so everything — the junk-pattern catalog and the full Campaign-mode pipeline — is inlined in a single ~230-line SKILL.md. Section headers and internal anchor links give good in-file navigation, but content that clearly belongs in separate reference files is inline, matching anchor 3; it is not 4 because there are no external references at all, and not 2 because the in-file structure is well organized and easy to navigate.	3 / 5
	Total	18 / 20 Passed

Description

96%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 is tightly written: it names the concrete capabilities (authoring gate, audit workflow, test-only seam detection), scopes them to Vitest in this repo, and gives explicit and varied trigger phrases including the test-file pattern. Its only weakness is slight trigger overlap with general code-review skills when a PR touches tests.

Dimension	Reasoning	Score
Specificity	Quotes: 'Authoring gate for new or changed tests', 'audit workflow for low-value, implementation-coupled, or duplicative tests', 'the test-only production seams they keep alive'. Multiple specific concrete actions (write-time gating, auditing, seam hunting) comprehensively cover the skill's scope; no minor coverage gaps, so it matches the anchor 5 rather than 4.	5 / 5
Completeness	Explicitly answers both: what ('Authoring gate for new or changed tests, plus an audit workflow...') and when ('Invoke whenever writing, changing, reviewing, or sweeping Vitest tests... Use when asked to add tests, review tests, clean up tests, or when a PR touches *.test.ts'). Concrete trigger phrases for both, matching anchor 5.	5 / 5
Trigger Term Quality	Natural user phrases appear with synonyms: 'writing, changing, reviewing, or sweeping Vitest tests' and 'add tests, review tests, clean up tests', plus the file pattern '*.test.ts'. Keyword coverage is comprehensive including synonyms and the test-file extension pattern, matching anchor 5 rather than 4.	5 / 5
Distinctiveness Conflict Risk	The niche (Vitest test-value auditing in this repo, triggered by '.test.ts') is clear and mostly distinct. However 'reviewing... tests' and 'when a PR touches .test.ts' carry minor overlap risk with general code-review and PR-review skills, placing it at anchor 4 rather than 5; it is far more specific than anchor 3.	4 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: every-app/open-seo
Path: .agents/skills/test-audit/SKILL.md
Commit: db8bde1

Reviewed: 3 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.