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

79%

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

Fix and improve this skill with Tessl

tessl review fix ./cat-cafe-skills/collaborative-thinking/SKILL.md

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.

The content is a well-structured, highly actionable instruction skill with clear multi-phase workflows, explicit gating/checklists, and concrete templates and file paths. Its main weakness is mild redundancy and embedded time-sensitive saga detail that slightly inflates token use.

Suggestions

Consolidate the Mode B Phase rules so the 严格档 section references the standard 6-phase process instead of restating overlapping principles, reducing redundancy.

Move the 2026-06-16 roundtable saga provenance and dated ADR-031 detail into the shared reference files, keeping only the operating principles inline to cut time-sensitive tokens.

Add an explicit validation checkpoint to Mode A (e.g., confirm spec coverage of architecture/components/data-flow/errors/tests before handing off) to match the gating rigor of Mode B/C.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (tables, terse bullets, no generic concept explanations), but the Mode B 严格档 restates Phase rules and embeds time-sensitive saga references, leaving minor over-explanation that could be trimmed.	4 / 5
Actionability	Provides concrete artifacts and paths (feature-specs/feature-discussions file templates, an exact commit message format, a copy-paste 收敛检查 checklist, and a meeting-notes template), with minor gaps because core multi-cat mechanics are referenced via tools rather than spelled out.	4 / 5
Workflow Clarity	Mode B is a clearly sequenced 6-phase process with explicit trigger conditions and hard gates (Phase 5 review, forced 三件套 checklist), but Mode A's checkpointing is lighter, so minor validation gaps remain relative to anchor 5.	4 / 5
Progressive Disclosure	Well-organized into logical sections with one-level-deep, clearly signaled cross-skill references (shared-rules.md §13, decision-matrix.md, feat-lifecycle, writing-plans); the inlined 严格档 principles could arguably live in a separate reference, a minor organization gap.	4 / 5
	Total	16 / 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 specific and complete, clearly stating what it does, when to use it, when not to, and what to output, with a solid set of natural triggers. Its main limitation is that the core actions are abstract thinking modes rather than concrete mechanical operations.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('创意探索', '独立思考', '讨论收敛') and an explicit Output ('收敛报告（共识/分歧/行动项）+ 三件套沉淀检查'), but the actions are relatively abstract thinking modes rather than mechanical operations, leaving minor coverage gaps relative to anchor 5.	4 / 5
Completeness	Explicitly answers what (exploration, independent thinking, convergence with a stated Output), when (a concrete 'Use when' clause), and adds a 'Not for' negative-scope, matching the anchor 5 example of clearly answering both what AND when with concrete trigger phrases.	5 / 5
Trigger Term Quality	The 'Use when' clause plus the 6-entry triggers list covers natural phrases like 'brainstorm', '多猫独立思考', and '讨论结束需要收敛', giving good keyword coverage, though a few common synonyms are missing to reach anchor 5.	4 / 5
Distinctiveness Conflict Risk	The multi-cat independent-thinking and convergence niche with specific triggers is mostly distinct, and the body explicitly disambiguates from feat-lifecycle; minor overlap with generic brainstorming skills keeps it at anchor 4 rather than 5.	4 / 5
	Total	17 / 20 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: 730c37b

Reviewed: 3 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.