request-review

向跨家族 peer-reviewer 发送 review 请求（含五件套）。 Use when: 自检通过后准备请其他猫 review。 Not for: 收到 review 结果（用 receive-review）、自检（用 quality-gate）。 Output: Review 请求信（存档到 review-notes/）。

Quality

76%

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/request-review/SKILL.md

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.

A dense, highly actionable workflow body with strong sequencing and validation checkpoints, grounded in real project lessons. The main gaps are broken reference files and inline time-sensitive case narrative that hurts token efficiency.

Suggestions

Create the referenced refs/ files (review-request-template.md, decision-matrix.md, opensource-ops-inbound-pr.md) or remove the broken references so navigation is not dead-ended.

Move the dated case-study narrative (cat-cafe#2357/#2359, 2026-06-17) into a concise lesson anchor or a refs/ file rather than inline prose.

Fix the duplicated step numbering (5 and 5.5) in the BEFORE flow for a cleaner sequence.

Dimension	Reasoning	Score
Conciseness	Most content is genuinely non-obvious project lore (apply_patch worktree trap, shared-GH-account self-approve trap) that earns its tokens, but inline time-sensitive narrative ('cat-cafe#2357 / #2359（2026-06-17...）— 47 撞了两次') could be trimmed or moved to a lessons section.	2 / 3
Actionability	Provides concrete, copy-paste-ready commands: 'git status', 'git status --short \| rg ...', 'git diff --name-only origin/main...HEAD \| rg ...', 'pnpm review:start', 'gh pr comment {N} --repo … --body-file <verdict.md>', plus concrete sandbox paths and ID derivation rules.	3 / 3
Workflow Clarity	The BEFORE flow is a numbered 1–8 sequence with explicit validation checkpoints (gate report, tests green, git status clean, root-artifact gate) and dedicated Block scenarios with BLOCKED messages and recovery guidance.	3 / 3
Progressive Disclosure	References are clearly signaled and intended one-level-deep ('refs/review-request-template.md', 'refs/decision-matrix.md', 'refs/opensource-ops-inbound-pr.md'), but no refs/ directory exists so the links are broken, and some content (the verdict-landing case studies) is inline rather than split out.	2 / 3
	Total	10 / 12 Passed

Description

75%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 well-structured description that clearly states purpose, timing, and boundaries, with explicit Use-when/Not-for guidance and third-person voice. Weaker only on specificity (un-enumerated '五件套') and limited trigger variation coverage.

Suggestions

Enumerate the '五件套' (five-piece set) in the description so the action list is concrete rather than a label.

Add a couple more natural trigger variations (e.g. '帮我看下这版', 'review 一下我的改动') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions ('发送 review 请求（含五件套）', '存档到 review-notes/'), but '五件套' is referenced without being enumerated, so the action list is not comprehensive.	2 / 3
Completeness	Explicitly answers what ('发送 review 请求...存档到 review-notes/') and when ('Use when: 自检通过后准备请其他猫 review'), plus a 'Not for' clause, satisfying both what and when with explicit trigger guidance.	3 / 3
Trigger Term Quality	Triggers '请 review', '帮我看看', 'request review' are natural phrases a user might say, but coverage of variations is limited to three near-synonymous phrases across two languages.	2 / 3
Distinctiveness Conflict Risk	The 'Not for: 收到 review 结果（用 receive-review）、自检（用 quality-gate）' clause carves out a clear niche and actively prevents overlap with sibling skills.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

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