receive-review

处理 reviewer 反馈：Red→Green 修复 + 按 engagement mode 收口。Use when: 收到 review 结果或 P1/P2。Not for: 发 review 请求、自检。Output: 按 iterative / one-shot 契约闭环。

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./cat-cafe-skills/receive-review/SKILL.md

Quality

Content

77%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.

The body delivers a well-sequenced, highly actionable review-response workflow with explicit validation gates and honest scoping of optional material. Its main weaknesses are length with some internal-reference noise and a monolithic structure with no progressive disclosure into bundle files.

Suggestions

Split self-contained modules — Reviewer Delta Annotation (F253), TAKEOVER rules, and the sandbox lifecycle — into reference files under references/ and link them from a lean overview, instead of inlining everything in SKILL.md.

Ship or inline the fallback-layer check: either include scripts/check-fallback-layers.mjs in the bundle or replace the bare `node scripts/...` invocation with the actual detection criteria so the step is executable standalone.

Trim repeated guidance and internal ticket IDs: the Common Mistakes table restates 必须做到 and AUDIT points verbatim, and F-codes (F140, F177, F229, KD-13) add tokens without aiding execution for a fresh reader.

Dimension	Reasoning	Score
Conciseness	The body is dense operational guidance with no beginner-concept padding, but ~275 lines include some repetition (Common Mistakes restates 必须做到 and audit points) and many internal ticket IDs (F140, F253, F177, F229) that could be trimmed — efficient with minor over-explanation, matching 4 rather than 5.	4 / 5
Actionability	Concrete and executable throughout: the READ→CLOSE pipeline, three VERIFY gates with decision branches, pushback criteria, a copy-paste confirmation-letter template, and a per-source action table. Minor gaps keep it at 4 — it invokes `node scripts/check-fallback-layers.mjs` which is absent from the bundle, and resolves key procedures to external references (shared-rules §16e, §18).	4 / 5
Workflow Clarity	The WHEN block gives a clear 7-step sequence with explicit validation checkpoints (Spec/Mechanism/Feature gates, AUDIT-before-FIX with rationale, mandatory fallback-layer analysis in the report) and error-recovery loops (rollback on broken user path, manual reproducible steps when automation is unstable), matching the 5 anchor.	5 / 5
Progressive Disclosure	No bundle files exist; all content is inlined in one ~275-line file with decent headers and tables, but self-contained modules (Reviewer Delta Annotation, TAKEOVER rules, sandbox lifecycle) clearly belong in separate reference files, and external references (`../.cat-cafe-shared-refs/pr-signals.md`, the script path) are unverifiable outside the bundle — matching the 3 anchor.	3 / 5
	Total	16 / 20 Passed

Description

82%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 description: it states concrete actions, explicit use-when triggers, an explicit not-for boundary against sibling skills, and an output contract, all concisely. The only weakness is a thin action list that leans on workflow jargon rather than enumerating capabilities.

Dimension	Reasoning	Score
Specificity	The description names the domain ("处理 reviewer 反馈") with 1-2 concrete actions ("Red→Green 修复 + 按 engagement mode 收口") plus explicit exclusions, but the action list is brief and not comprehensive, matching the 3 anchor rather than 4's 'several specific actions'.	3 / 5
Completeness	It explicitly answers what ("Red→Green 修复 + 按 engagement mode 收口"), when ("Use when: 收到 review 结果或 P1/P2"), and adds explicit not-for and output clauses with concrete trigger phrases, matching the 5 anchor exactly.	5 / 5
Trigger Term Quality	"收到 review 结果或 P1/P2", "reviewer 反馈", "发 review 请求", "自检" give good natural-phrase coverage of this domain, though common variations reviewers actually use (e.g. "changes requested", "LGTM") are missing, fitting 4 rather than the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	"Not for: 发 review 请求、自检" explicitly separates the sibling skills (request-review, quality-gate), giving a clear niche with minimal conflict risk.	5 / 5
	Total	17 / 20 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: 61389cc

Reviewed: 3 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.