CtrlK
BlogDocsLog inGet started
Tessl Logo

cross-cat-handoff

跨猫传话/交接的五件套结构(What/Why/Tradeoff/Open/Next)。 Use when: 交接工作给其他猫、传话、写 review 信。 Not for: 自己的任务、不涉及其他猫的工作。 Output: 结构化交接信。

72

Quality

88%

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

SKILL.md
Quality
Evals
Security

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 highly actionable, well-sequenced instruction skill with a clear validation workflow and concrete templates. Its main weaknesses are repetition of the five-piece structure across multiple sections and dangling references to non-existent bundle files.

Suggestions

Consolidate the five-piece definition so it is stated once in the table and only referenced (not restated) in the block scenarios, handoff-type emphasis, and common-errors table to reduce token redundancy.

Either create the referenced `refs/decision-matrix.md` and `refs/shared-rules.md` files or remove/inline those citations, since the paths currently resolve to nothing.

Move the full worked handoff example (the 通过场景 block) into a reference file and link to it, keeping SKILL.md as a concise overview that points one level deep.

DimensionReasoningScore

Conciseness

Mostly efficient but the five-piece structure is re-explained several times — the definition table, two block scenarios, a full worked example, the per-type emphasis, the common-errors table, and the checklist all restate the same items, which could be tightened.

2 / 3

Actionability

Gives concrete executable guidance: a five-piece template with per-item examples, a SCAN/MISSING/BLOCK/PASS check flow, exact block-message templates, a full model handoff, and a copy-paste self-check checklist.

3 / 3

Workflow Clarity

The 检查流程 is a clear sequence with an explicit validation checkpoint (BLOCK on missing items → prompt to supplement → re-check), and the checklist provides a feedback loop for error recovery.

3 / 3

Progressive Disclosure

Sections are well organized, but referenced paths (`refs/decision-matrix.md`, `refs/shared-rules.md`, `review-notes/`) point to bundle files that do not exist, and large inline blocks (the full worked example, handoff-type emphasis) could live in separate reference files.

2 / 3

Total

10

/

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-structured description: it states a concrete five-piece structure, gives explicit 'Use when'/'Not for' triggers, and is clearly distinguishable from adjacent skills. It avoids fluff and uses third-person fragment voice throughout.

DimensionReasoningScore

Specificity

Names a concrete five-piece structure — "What/Why/Tradeoff/Open/Next" — listing multiple specific concrete actions rather than vague capability claims.

3 / 3

Completeness

Explicitly answers both what (跨猫传话/交接的五件套结构) and when (the 'Use when:' clause), and further bounds scope with 'Not for:' and an 'Output:' line.

3 / 3

Trigger Term Quality

Includes natural terms users would say ("交接", "传话", "handoff") plus a 'Use when' clause naming 交接工作、传话、写 review 信, giving good coverage of common phrasings.

3 / 3

Distinctiveness Conflict Risk

The cross-cat handoff/传话 niche is clearly bounded by the 'Not for:' clause (own tasks, work not involving other cats), making it unlikely to trigger for the wrong skill.

3 / 3

Total

12

/

12

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.