quality-gate

开发完成后的自检门禁：愿景对照 + spec 合规 + 验证。 Use when: 开发完了准备提 review、声称完成了、准备交付。 Not for: 收到 review 反馈（用 receive-review）、merge（用 merge-gate）。 Output: Spec 合规报告（含愿景覆盖度）。

Quality

83%

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

77%Weight 40%Scale 1-3

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

The body is highly actionable with concrete commands, a clear sequenced workflow, and explicit validation gates. Its main weaknesses are verbose embedded lesson narratives and the absence of bundle files to offload the long rationale/reference material.

Suggestions

Move the dated lesson retrospectives (F041, F177, F209, F244) into a ./references/lessons.md and keep only the one-line rule in the main body, improving conciseness.

Add bundle files (e.g. ./references/report-template.md, ./references/checks.md) and reference them from the body so the report template and per-step check details live one level deep.

Tighten the Dogfood 'Why' multi-paragraph block into a single sentence pointing to a reference, since the rule itself is already stated above it.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes competence (concrete commands, terse rules), but embedded lesson narratives ('F041 教训：AC 全打勾...', 'F209 反思 2026-05-23' multi-paragraph stories) add context that could be tightened or moved to a reference.	2 / 3
Actionability	Fully executable guidance throughout: real commands ('pnpm test', 'pnpm check', 'node scripts/check-hotfix-pattern.mjs', 'git status --short \| rg ...'), exact glob patterns, and a copy-paste-ready report template.	3 / 3
Workflow Clarity	A clearly sequenced Step 0–8 flow with explicit validation checkpoints ('必须全部通过', '0 errors', 'exit 0'), BLOCK conditions, and fix/retry feedback loops for risky batch and runtime operations.	3 / 3
Progressive Disclosure	Sections are well-organized and references to external repo paths (e.g. 'cat-cafe-skills/refs/vision-evidence-workflow.md') are one level deep, but no bundle files exist in ./references/scripts/assets and substantial inline lesson/rationale content that could be split out is kept in the main body.	2 / 3
	Total	10 / 12 Passed

Description

90%Weight 40%Scale 1-3

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 well-structured: it states the purpose, gives explicit Use when/Not for guidance, and lists concrete trigger terms. Its only weakness is that the capability list is condensed rather than enumerating multiple distinct concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain and several actions ('愿景对照 + spec 合规 + 验证', 'Spec 合规报告（含愿景覆盖度）') but does not enumerate a comprehensive set of concrete distinct actions comparable to the anchor-3 multi-action example.	2 / 3
Completeness	Explicitly answers both what ('开发完成后的自检门禁：愿景对照 + spec 合规 + 验证', 'Output: Spec 合规报告') and when ('Use when: 开发完了准备提 review、声称完成了、准备交付').	3 / 3
Trigger Term Quality	The 'Use when' clause and triggers list natural phrases a user would say ('开发完了准备提 review', '声称完成了', '自检', '准备交付') with good coverage of the relevant variations.	3 / 3
Distinctiveness Conflict Risk	A clear niche is stated and an explicit 'Not for' clause distinguishes it from sibling skills ('收到 review（用 receive-review）、merge（用 merge-gate）'), minimizing wrong-skill triggering.	3 / 3
	Total	11 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: zts212653/clowder-ai
Path: cat-cafe-skills/quality-gate/SKILL.md
Commit: 80782c5

Reviewed: 11 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.