collaborative-thinking

单人或多猫的创意探索、独立思考、讨论收敛。 Use when: brainstorm、多猫独立思考、讨论结束需要收敛、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: 收敛报告（共识/分歧/行动项）+ 三件套沉淀检查。

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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 well-structured, actionable process skill with clear sequenced workflows and explicit validation checkpoints. The main weakness is progressive disclosure: several referenced files (refs/, docs/) are cited but not bundled, and the overview is somewhat long with the 严格档 section adding density that could live in a reference.

Suggestions

Provide the referenced bundle files (refs/decision-matrix.md, refs/shared-rules.md, docs/public-lessons.md) or drop the references so navigation points to real, bundled content.

Move the Mode B 严格档 five-principle block into a separate reference file and keep SKILL.md to the trigger conditions plus a one-line pointer, tightening the overview.

Trim repeated cost/仪式化 warnings (e.g. the token-cost and ceremony-devaluation notes) into a single shared caution, as the same message appears in multiple places.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and assumes competence (no concept-fluff like 'what is brainstorm'), but at ~150 lines it is long for an overview and the 严格档 principles add procedural verbosity that could be tightened or pushed to a reference.	2 / 3
Actionability	Concrete, executable guidance throughout: specific file paths ('feature-specs/YYYY-MM-DD-{topic}-design.md'), a forced '有/没有' checklist, an explicit commit-message format, and a meeting-notes template — copy-paste ready for an instruction-only skill.	3 / 3
Workflow Clarity	Modes A/B/C are clearly sequenced, Mode B has an explicit 6-phase flow, and validation checkpoints plus feedback loops are present (Phase 5 审阅, operator 反馈 + 最终确认, and the mandatory 收敛检查 format).	3 / 3
Progressive Disclosure	References are one-level-deep and clearly signaled ('refs/decision-matrix.md', 'refs/shared-rules.md', 'docs/public-lessons.md'), but the referenced bundle directories (references/, assets/, scripts/) are not present, so the navigation points to files the skill does not actually carry — structure is good but the split is incomplete.	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.

The description is specific, complete, and distinctive: it names concrete actions, includes natural trigger terms both inline and as a trigger list, and draws clear boundaries against adjacent skills. Third-person voice is maintained throughout. Strong example of a well-formed description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '创意探索、独立思考、讨论收敛' plus an explicit output '收敛报告（共识/分歧/行动项）+ 三件套沉淀检查' — matching the anchor for several specific concrete actions.	3 / 3
Completeness	Explicitly answers what it does and when to use it via a 'Use when:' clause, and adds a 'Not for:' boundary — clearly covering both what and when with explicit triggers. Voice is third person, no 'I/You' usage.	3 / 3
Trigger Term Quality	Natural terms users would say appear both inline ('brainstorm、多猫独立思考、讨论结束、总结一下') and in the dedicated triggers list, giving good coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	Clear niche carved by 'Not for: 已有明确 spec 直接写代码、单猫执行已定方案' and the body's distinction from feat-lifecycle's discussion phase, making wrong-skill triggering unlikely.	3 / 3
	Total	12 / 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/collaborative-thinking/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.