CtrlK
BlogDocsLog inGet started
Tessl Logo

cross-cat-handoff

跨猫交接与 review 双路由。Use when: 交接、exact-HEAD external PR review task 或 PR tracking。Not for: 自己任务。Output: 五件套 + formal/advisory 分类 + provenance 路由。

63

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

67%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 is a dense, domain-specific instruction skill with strong actionability and a clear validating workflow, but it carries notable repetition of the 五件套 frame and re-states rules across tables and examples. Splitting the heavier routing sections into reference files would improve both conciseness and progressive disclosure.

Suggestions

Deduplicate the 五件套: keep the definition table and one full example, and have the checklist and 交接类型 section reference it rather than re-list all five items.

Move the long Action Successor Single-Flight / External Review Verdict Delivery Custody / Local Cat Review Return Route sections into a reference file, leaving the body as overview + the 检查流程.

Collapse the 常见错误 table into the rules it restates, or keep only the rows that add a non-obvious correct action not already stated above.

DimensionReasoningScore

Conciseness

Mostly efficient but the 五件套 is restated four times (definition table, full pass example, checklist, 交接类型 section) and the 常见错误 table largely restates rules from above; could be tightened without losing clarity.

3 / 5

Actionability

Gives concrete, executable guidance — exact route primitives (post_message, cross_post_message, multi_mention), required fields (clientMessageId, localReviewVerdict, reviewedHeadSha), and precise custody conditions; minor gaps only.

4 / 5

Workflow Clarity

The 检查流程 (SCAN/MISSING/BLOCK/PASS) gives a clear sequenced workflow with an explicit validation checkpoint and feedback loop (block → supplement → resend), backed by a self-check checklist; a few edge-case transitions are only implicit.

4 / 5

Progressive Disclosure

Well-organized with clear section headers and one-level-deep signaled references (../.cat-cafe-shared-refs/shared-rules.md, decision-matrix.md, review-notes/); no bundle files exist, and some inline routing detail could arguably live in a reference file.

4 / 5

Total

15

/

20

Passed

Description

83%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.

The description is concise, third-person, and explicitly covers what, when, and not-for with concrete output artifacts. Its main weakness is reliance on domain jargon (五件套, provenance 路由) that may be opaque without the body.

Suggestions

Gloss the jargon inline (e.g. "五件套 (What/Why/Tradeoff/Open Questions/Next Action)") so the description is self-contained.

Soften technical trigger terms like "exact-HEAD" and "advisory_read_only" toward phrasings a user would naturally say.

DimensionReasoningScore

Specificity

Names the domain and several concrete outputs — "五件套", "formal/advisory 分类", "provenance 路由", "exact-HEAD external PR review" — listing multiple specific actions with only minor coverage gaps.

4 / 5

Completeness

Explicitly answers both what ("跨猫交接与 review 双路由... Output: 五件套 + formal/advisory 分类 + provenance 路由") and when ("Use when: 交接、exact-HEAD external PR review task 或 PR tracking") plus a clear Not-for boundary.

5 / 5

Trigger Term Quality

Good keyword coverage including natural synonyms (交接/传话/handoff/下一棒) plus "PR tracking"; a few common phrasings are missing and some terms (exact-HEAD, advisory_read_only) lean technical.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (cross-cat handoff + review dual-routing) with distinct triggers; minor overlap risk with sibling review skills, but the routing/classification framing keeps it mostly distinguishable.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
zts212653/clowder-ai
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.