CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

collaborative-thinking

单人或多猫的创意探索、独立思考、讨论收敛。 Use when: 有目标但不知道怎么做、已有方向反复不满意、brainstorm、多猫独立思考、讨论收敛或方向性问题需要多视角。 Not for: 已有明确 spec 直接写代码、单猫执行已定方案。 Output: 共同理解、反例、取舍或结论;需要留存且已获授权时形成设计或讨论记录。

Quality

80%

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/collaborative-thinking/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 well-structured instruction-only process skill: concise tabulated knowledge, concrete mechanisms and templates, and clearly sequenced multi-phase workflows with review gates and checklists. Its weaknesses are minor — some cross-section repetition, and key formats (Decision Packet, Stateful Object Gate) delegated to shared-reference files that are not part of this bundle.

DimensionReasoningScore

Conciseness

The body is dense and token-efficient — decision tables for 核心知识/Quick Reference/Common Mistakes, no explanation of concepts Claude already knows — with only minor repetition (the anti-"演戏" warning and 分歧保留 rules each reappear across the strict-mode section, Phase rules, and mistakes table). Efficient with small trims possible: anchor 4, short of anchor 5's every-token-earns-its-place.

4 / 5

Actionability

Concrete, executable guidance throughout: "routeParallel() 或operator分别 @ 各猫", the 2-3 轮 debate cap, the Phase 4 must-include synthesis list, a copy-paste meeting-notes template with path "feature-discussions/YYYY-MM-DD-{topic}-meeting-notes.md", and a reversibility-based escalation rule. The minor gap is that the Decision Packet format and Stateful Object Gate are delegated to referenced files not present in this bundle.

4 / 5

Workflow Clarity

Multi-step processes are clearly sequenced: Mode A steps 1-4, Mode B's 6 phases with explicit Phase 2 trigger conditions ("各方基本一致 → 跳过;存在明显分歧 → 需要(限 2-3 轮)"), a Phase 5 review gate (升为硬门 in strict mode), and Mode C's reversibility check before escalation. Validation checkpoints and checklists are present; it falls just short of anchor 5 because per-phase detail is compressed into a code block and the census gate is undefined inline.

4 / 5

Progressive Disclosure

The single file (~128 lines) is well organized with an overview table, per-mode sections, Quick Reference, and Common Mistakes, and its external references ("../.cat-cafe-shared-refs/decision-matrix.md", "shared-rules.md §13") are clearly signaled and one level deep. However, the bundle contains no reference files and the cited paths resolve outside it, leaving minor organization gaps consistent with anchor 4 rather than 5.

4 / 5

Total

16

/

20

Passed

Description

78%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 that explicitly covers what, when, when-not, and expected output with natural trigger phrases. Its main weakness is that the capability verbs (探索/思考/收敛) describe modes of thinking at a generic level rather than concrete, distinguishable actions.

DimensionReasoningScore

Specificity

The description names the domain and enumerates three modes ("单人或多猫的创意探索、独立思考、讨论收敛") plus concrete output types ("共同理解、反例、取舍或结论"), but the verbs remain process-generic rather than operationally concrete. It is more informative than anchor 2's minimal actions, yet lacks the specific concrete actions anchor 4 requires.

3 / 5

Completeness

It explicitly answers both 'what' (creative exploration, independent multi-cat thinking, discussion convergence) and 'when' with concrete trigger phrases in the "Use when:" clause, and goes further with "Not for:" exclusions and an "Output:" clause. This matches the anchor 5 pattern of clearly and explicitly answering what AND when with concrete triggers.

5 / 5

Trigger Term Quality

Natural trigger phrases are present — "brainstorm", "有目标但不知道怎么做", "已有方向反复不满意", "方向性问题需要多视角" — phrased the way a user would actually say them. A few common variants (e.g., "想不出方案", "卡住了") are missing, so it falls short of anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The "Not for: 已有明确 spec 直接写代码、单猫执行已定方案" clause carves a clear niche distinct from implementation skills, but broad trigger terms like "讨论" and "收敛" create minor overlap risk with general discussion or documentation skills. Mostly distinct with minor overlap — anchor 4, not 5.

4 / 5

Total

16

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository

zts212653/clowder-ai

Path

cat-cafe-skills/collaborative-thinking/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.