codew-release-qa-sweep

Use before claiming CodeWhale release work is done: run the full gate sweep and list the manual QA targets.

Quality

88%

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%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced, token-efficient release QA skill with explicit validation and reporting guardrails. Its single weakness is progressive disclosure: all content lives inline in one long file rather than being split into clearly signaled reference files.

Suggestions

Split the detailed Manual QA target reproduction steps into a referenced file (e.g. references/manual-qa.md) and keep SKILL.md as a lean overview pointing to it, improving progressive_disclosure toward 3.

Consider moving the longer Red flags / don't guardrails into a references file as well, signaling them one level deep so the main body stays a navigable overview.

Verify any referenced paths (e.g. ./scripts/release/check-versions.sh) are project scripts not skill bundle files; if bundle references are added, link them as clearly signaled one-level-deep references.

Dimension	Reasoning	Score
Conciseness	Lean and task-specific throughout — ordered cargo/git commands and terse QA targets with no explanation of concepts Claude already knows; every section earns its place, so it is not the padded 2-anchor case.	3 / 3
Actionability	Provides a copy-paste-ready ordered command block (cargo fmt/test/build, check-versions.sh, --version smoke) plus concrete per-target manual QA steps citing issue numbers; not 2 because the guidance is fully executable rather than pseudocode or abstract.	3 / 3
Workflow Clarity	Sequenced steps 0–8 with "Stop on the first failure and report it", a check-versions.sh verdict, and an explicit reporting checklist requiring pass/fail per command; validation and feedback are present, so it is not capped at 2.	3 / 3
Progressive Disclosure	Sections are well-organized with clear headers, but the body is a single 110-line monolithic file with no overview→reference split — detailed reproduction steps and guardrails are all inline rather than split into one-level-deep reference files; the 3 anchor requires well-signaled external references, which are absent.	2 / 3
	Total	11 / 12 Passed

Description

85%

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 specific, well-triggered, distinctive description that clearly states both what it does and when to use it. Its only weakness is trigger-term breadth, which relies on project-specific jargon rather than the varied natural phrases a user might say.

Suggestions

Broaden the trigger terms beyond project jargon — add natural variations a user might say such as "release QA", "ship readiness", or "is the release done".

Keep the explicit "Use before..." trigger; consider mirroring one or two common phrasings of the release-readiness question to improve trigger_term_quality toward 3.

Dimension	Reasoning	Score
Specificity	Names concrete actions — "run the full gate sweep and list the manual QA targets" — matching the anchor for multiple specific concrete actions; not reduced to 2 because it lists more than a single domain+action.	3 / 3
Completeness	Answers both what ("run the full gate sweep and list the manual QA targets") and when with an explicit trigger ("Use before claiming CodeWhale release work is done"); not 2 because the when-clause is explicit rather than implied.	3 / 3
Trigger Term Quality	The phrase "CodeWhale release work is done" is a natural trigger, but coverage is narrow and leans on project jargon ("gate sweep", "manual QA targets"); falls short of the broad natural-term variation the 3 anchor requires.	2 / 3
Distinctiveness Conflict Risk	Scoped to a single project's release ritual (CodeWhale release work), making it a clear niche unlikely to trigger for unrelated skills; not 2 because the trigger is highly specific rather than broadly overlapping.	3 / 3
	Total	11 / 12 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: Hmbown/CodeWhale
Path: docs/skills/codew-release-qa-sweep/SKILL.md
Commit: f018d3e

Reviewed: about 13 hours 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.