CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

63%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.

A rich, evidence-driven feedback-handling procedure with concrete decision gates, explicit validation loops, and ready-to-use templates. Its main costs are a monolithic single-file structure that inlines reviewer-side and lifecycle content with a dangling script reference, and repeated restatement of the same closure rules across sections that inflates the token budget.

Suggestions

Split reviewer-side material out of the body — the F253 Delta Annotation table, TAKEOVER 降级, and 沙盒生命周期 sections — into a reference file (or back into request-review/shared-rules), keeping SKILL.md as the author-side feedback loop.

Consolidate the thrice-repeated closure/合入门禁 rules into one authoritative section and cross-reference it, cutting redundancy between 必须做到, 修复后确认, and the cloud-path guidance.

Ship the referenced script (or fix the path) so 'node scripts/check-fallback-layers.mjs' is executable as written, and add a one-line note on where it lives.

DimensionReasoningScore

Conciseness

The ~290-line body is dense with domain-specific policy rather than concepts Claude already knows, so it is far from anchor 2's padded explanations. But the same closure rules are stated three or more times ('不得自称通过未满足的合入门禁' recurs in 必须做到, the engagement section, and the cloud section), and sections like the Reviewer Delta Annotation (F253) table and 沙盒生命周期 address the reviewer's workflow, not the feedback receiver this skill targets — it 'could be tightened' to anchor 3 rather than the trimmable-minor-excess of anchor 4.

3 / 5

Actionability

Guidance is largely executable for an instruction-only skill: a stepwise READ→CLASSIFY→…→CLOSE flow, three decision gates with explicit branches ('冲突 → pushback,附 AC 原文'), a fill-in confirmation-letter template, concrete bash commands ('pnpm worktree:finish /tmp/cat-cafe-review/{review-target-id}/{reviewer-handle} --source-ref {review-subject-ref}'), and a browser-verification checklist. It is not anchor 5 because several directives defer to external contracts not in the bundle (request-review's carrier/verdict state machine, shared-rules §16e/§18) and the audit step's 'grep 本 PR diff 里所有同类位置' leaves the search itself to the model.

4 / 5

Workflow Clarity

The optional 处理顺序 block gives a clear 7-step sequence with named checkpoints, and validation is explicit throughout: RED must be saved before GREEN ('有则运行并保存 RED'), fixed paths are re-verified, the Feature Gate mandates rollback ('功能死了 → 回滚'), and the UX section has a literal 验证清单. It misses anchor 5 because the definitive sequence is explicitly labeled '可选参考' amid many parallel sections, and the mixed author/reviewer roles (TAKEOVER, sandbox cleanup) make the primary path harder to follow without re-reading.

4 / 5

Progressive Disclosure

Section headers exist and external references are clearly signaled ('详见 ../.cat-cafe-shared-refs/pr-signals.md'), but there is no bundle at all — no references/, scripts/, or assets/ — while the body inlines ~290 lines that clearly belong in separate files (delta-annotation spec for reviewers, sandbox lifecycle mechanics, confirmation-letter formats), matching 'content that should be separate is inline'. It also cites 'node scripts/check-fallback-layers.mjs', a script that does not exist in this bundle, which is below anchor 4's 'references mostly clear' reliability.

3 / 5

Total

14

/

20

Passed

Description

66%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 compact, third-person description with an explicit Use-when, Not-for, and Output contract, giving it strong distinctiveness within its skill family. Its weaknesses are thin trigger-term coverage (only two trigger phrases, with natural variants relegated to the triggers list) and a jargon-compressed statement of what the skill does.

Suggestions

Fold 1-2 natural trigger phrasings into the description itself (e.g. '收到 review 结果、review 意见或 P1/P2 finding 时'), instead of leaving variants like 'review 意见' and 'fix these' only in the triggers frontmatter.

Expand the 'what' with one or two more concrete actions (e.g. VERIFY findings against evidence, sweep for same failure-mode defects) to lift specificity beyond a two-verb summary.

Briefly gloss the engagement terms ('按 iterative / one-shot 契约闭环') so the description is parseable without loading the body.

DimensionReasoningScore

Specificity

The description names its domain and 1-2 concrete actions — '处理 reviewer 反馈:Red→Green 修复 + 按 engagement mode 收口' — but coverage is not comprehensive (no mention of VERIFY/push-back, failure-mode audit, or UX verification), and the actions are compressed into jargon ('收口', 'iterative / one-shot 契约'). It sits above anchor 2 (which would name only the domain) but does not list the several specific actions of anchor 4.

3 / 5

Completeness

It explicitly answers both: what ('处理 reviewer 反馈:Red→Green 修复 + 按 engagement mode 收口') and when ('Use when: 收到 review 结果或 P1/P2'), plus a 'Not for' exclusion and an 'Output' contract. It falls short of anchor 5 because the trigger clause covers only two conditions (e.g. it omits approved/LGTM handling and 'review 意见'-style phrasings) and the 'what' leans on unexplained contract jargon — 'when' could be more explicit and specific.

4 / 5

Trigger Term Quality

'Use when: 收到 review 结果或 P1/P2' gives two relevant natural phrases, but common variations a user would actually say are missing — e.g. 'review 意见', 'reviewer 反馈', 'fix these comments', 'changes_requested' (these appear only in the separate triggers list, not the description). This matches 'some relevant keywords but missing common variations or synonyms' rather than anchor 4's 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

'Not for: 发 review 请求、自检' explicitly disambiguates the two most confusable sibling skills (request-review, quality-gate), and the trigger '收到 review 结果或 P1/P2' is the receive-side counterpart to the excluded '发 review 请求' — a clear niche with minimal conflict risk. It is not anchor 4 because that anchor still assumes 'minor overlap risk' and this description actively neutralizes the overlap via the exclusion clause.

5 / 5

Total

15

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 suspicious

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

13

/

16

Passed

Repository

zts212653/clowder-ai

Path

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

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.