receive-review

处理 reviewer 反馈：Red→Green 修复 + 技术论证（禁止表演性同意）。 Use when: 收到 review 结果、reviewer 提了 P1/P2、需要处理反馈。 Not for: 发 review 请求（用 request-review）、自检（用 quality-gate）。 Output: 逐项修复确认 + reviewer 放行。

Quality

85%

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

70%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 a richly structured, well-sequenced review-feedback workflow with strong validation checkpoints and a ready-to-use confirmation template. Its main weaknesses are verbose acronym-laden prose and references to bundle files that are not actually present, which weakens both actionability and progressive disclosure.

Suggestions

Add the missing referenced files (refs/pr-signals.md, scripts/check-fallback-layers.mjs) or remove the citations, so progressive_disclosure and actionability hold up against the actual bundle.

Trim the dense internal-jargon markers (F177/F253/F229/§16e/KD-13) and lengthy rationale paragraphs to reduce token cost without losing the core READ→CONFIRM procedure.

Consolidate the redundant push-back/escalation guidance (currently spread across 禁止表演性同意, Push Back, AUDIT ≥3轮升级, and Common Mistakes) into one section to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes competence, but ~290 lines with heavy jargon (F177, F253, F229, §16e, KD-13) and lengthy prose rationale blocks pad the body beyond what the core procedure requires.	2 / 3
Actionability	Concrete commands appear (node scripts/check-fallback-layers.mjs, cat_cafe_create_task) and the fix-confirmation letter template is copy-paste ready, but several cited artifacts (refs/pr-signals.md, scripts/check-fallback-layers.mjs, the refs/ folder) are not present in the bundle, so the guidance is partly non-executable.	2 / 3
Workflow Clarity	The READ→CLASSIFY→CLARIFY→VERIFY→AUDIT→FIX→CONFIRM flow is clearly sequenced, VERIFY has three explicit gates, and feedback loops (Red→Green, re-trigger remote review, ≥3-round escalation) cover error recovery.	3 / 3
Progressive Disclosure	Inline structure is well-sectioned, but referenced deeper materials (refs/pr-signals.md, refs/, scripts/) do not exist in the bundle, so the one-level-deep references are signaled but unfulfilled.	2 / 3
	Total	9 / 12 Passed

Description

100%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.

A tight, well-targeted description: it states concrete actions, gives explicit Use when/Not for triggers, and explicitly disambiguates from related review skills. The third-person voice is consistent (no first/second person), so it avoids the voice penalty.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — Red→Green 修复, 技术论证, 禁止表演性同意 — naming exactly what the skill does rather than vague abstractions.	3 / 3
Completeness	Both what (Red→Green 修复 + 技术论证) and when (Use when 收到 review 结果...) are explicitly stated, plus a Not for clause and an Output clause rounding out guidance.	3 / 3
Trigger Term Quality	Explicit triggers (review 结果, review 意见, reviewer 说, fix these, github-review-feedback) cover natural phrasings a user/operator would say when this skill is needed.	3 / 3
Distinctiveness Conflict Risk	The Not for clause (use request-review for review requests, quality-gate for self-check) carves out a clear niche, making it unlikely to trigger for sibling skills.	3 / 3
	Total	12 / 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: 1 missing	Warning

	Total	14 / 16 Passed

Repository: zts212653/clowder-ai
Path: cat-cafe-skills/receive-review/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.