CtrlK
BlogDocsLog inGet started
Tessl Logo

release-quality-audit

发版前代码质量审查。大文件治理三道闸门(gate/near-threshold/strictReduction retained)+ tsc/cargo 全量 + 测试零新增失败对比 + Format Discipline 提交卫生 + 高风险域 pitfall 红线。只审查只报告不修复。触发场景:用户说「发版前审查」「release quality audit」「质量门禁」或准备发版/打 tag 前。

70

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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.

An exceptionally concise audit checklist with concrete commands and explicit pass/fail criteria, structured as an overview pointing to an external single-source-of-truth file. Its main weakness is that the detailed procedure and the referenced docs live outside the skill bundle, and item 6's pitfall guidance is vague.

Suggestions

Make item 6 actionable: name the specific pitfall red-line checks (commands or files) for the engine dual-forwarder / app-shell / git-history / cold-start paths instead of the generic '过对应 pitfall 红线'.

Either bring the referenced .claude/commands/release-quality-audit.md checklist into the bundle (e.g. references/release-quality-audit.md) or inline the key steps so the skill is self-contained when loaded alone.

Add a brief explicit failure-handling note per checkpoint (e.g. 'on retained/gate failure: report the offending files, do not attempt fixes') to close the workflow feedback loop.

DimensionReasoningScore

Conciseness

Lean and efficient — a terse 6-point checklist that assumes Claude's competence with no padding or explanation of concepts Claude already knows; every line earns its place.

5 / 5

Actionability

Provides concrete executable commands ('check:large-files:gate exit 0', 'npx tsc --noEmit', 'cargo check --all-targets', 'git diff --stat') with expected outcomes, but defers the full procedure to an external file and item 6 ('过对应 pitfall 红线') is vague direction rather than a command.

4 / 5

Workflow Clarity

A clearly numbered 1–6 sequence with explicit pass/fail checkpoints (exit 0, zero error, retained = 阻塞); falls short of 5 because there is no error-recovery/feedback loop describing what to do when a check fails (the skill reports rather than fixes, but the recovery guidance is implicit).

4 / 5

Progressive Disclosure

Well-signaled one-level-deep references ('执行清单见 .claude/commands/release-quality-audit.md', '以 docs/...md §0/§8 为准') with the body acting as a concise overview; held below 5 because the referenced files live outside the skill bundle (no references/scripts/assets dirs), so they may not travel with the skill.

4 / 5

Total

17

/

20

Passed

Description

87%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 specific, well-triggered description that clearly states both what the skill does and when to invoke it, with concrete natural-language trigger phrases. It is slightly jargon-dense in naming its capabilities, which keeps specificity just short of fully comprehensive.

DimensionReasoningScore

Specificity

Lists several concrete actions — '大文件治理三道闸门', 'tsc/cargo 全量', '测试零新增失败对比', 'Format Discipline 提交卫生', '高风险域 pitfall 红线' — but several are jargon references to internal gates rather than fully self-contained actions, leaving minor coverage gaps.

4 / 5

Completeness

Clearly answers 'what' (发版前代码质量审查, 只审查只报告不修复) and 'when' (触发场景 with concrete trigger phrases), matching the anchor that requires both what and when with explicit triggers.

5 / 5

Trigger Term Quality

Includes natural trigger phrases users would say ('发版前审查', 'release quality audit', '质量门禁', '准备发版/打 tag 前') with both Chinese and English variants, but a few common synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (pre-release quality gate with specific gate names and pitfall domains) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
zhukunpenglinyutong/desktop-cc-gui
Reviewed

Table of Contents

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.