next-qa

Run one unattended iteration of the QUALITY-ASSURANCE loop — steward any in-flight QA PR, then build ONE queued `qa` issue (test infrastructure, unit tests, regression tests for known bugs) on a branch off auto-qa and open a PR that squash-merges on green CI. Adds tests and tooling only; never edits product source. Use when the user says "QAタスク", "next qa", "テストを進めて", or wants autonomous progress on the quality track.

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%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 tightly written, highly actionable autonomous-loop skill with explicit sequencing, validation checkpoints, and error-recovery feedback loops. The only real weakness is mild repetition of the scope boundary and merge logic, which slightly inflates length without adding clarity.

Suggestions

Consolidate the 'never edit packages/*/src' rule: state it once in the scope-boundary section and reference it briefly elsewhere rather than re-deriving it three times.

The squash-merge-on-green-CI preference list appears in both the step-0 guard and step-3 build sections; factor it into one place and cross-reference to remove redundancy.

Consider moving the 'value bar for a QA task' checklist into a short reference file so the main loop body stays a lean overview.

Dimension	Reasoning	Score
Conciseness	Dense, competent prose that assumes Claude's intelligence (no explaining what tests/CI are), but the scope boundary 'never edits packages/*/src' and the squash-merge-on-green-CI logic are each restated several times and could be tightened.	4 / 5
Actionability	Fully executable guidance throughout — `gh pr list --base auto-qa --state open`, `git checkout -b claude/qa-<slug> origin/auto-qa`, `pnpm build && pnpm check && pnpm test`, `gh pr merge <num> --squash --auto` — copy-paste ready commands covering the common cases.	5 / 5
Workflow Clarity	Clear serial sequence (guard → interrupts → pick issue → build & record) with explicit validation checkpoints — re-verify before building, quality gates, squash-merge on green CI only — and a feedback loop for red CI (fix/re-push, 3-attempt limit, then label needs-attention).	5 / 5
Progressive Disclosure	Well-organized into clearly headed sections (scope, guard, interrupts, pick, build, boundaries) in a single self-contained file with no bundle references; minor gap in that some content (value bar, boundaries) is inline rather than split out, but no nested or buried references.	4 / 5
	Total	18 / 20 Passed

Description

100%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 that concretely states what the skill does and when to invoke it, with natural multilingual trigger phrases and a crisp scope boundary that distinguishes it from the feature loop. No fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'steward any in-flight QA PR', 'build ONE queued qa issue', 'open a PR that squash-merges on green CI', 'Adds tests and tooling only; never edits product source' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (run one QA loop iteration: steward a PR then build one queued issue) and 'when' (a 'Use when...' clause with concrete trigger phrases).	5 / 5
Trigger Term Quality	Provides natural trigger phrases users would actually say — 'QAタスク', 'next qa', 'テストを進めて' — plus the broader 'autonomous progress on the quality track', covering synonyms in both English and Japanese.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (QA test/tooling loop on the auto-qa branch) with a sharp scope boundary — 'Adds tests and tooling only; never edits product source' — minimizing overlap with the sibling feature loop.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: breaking-brake/cc-wf-studio
Path: .claude/skills/next-qa/SKILL.md
Commit: a7bf24a

Reviewed: 5 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.