co-creation-storytelling

把跨时间、多人或人机共创的真实经历讲清楚，保留各方行动与变化。 Use when: 长故事要压成一页/短讲、成长经历散在聊天与文档、追问人和 AI 各做了什么，或故事只剩履历、成果和能力口号。Not for: 已锁定叙事的排版/出图、虚构剧情、纯技术论证或启动能力进化项目。Output: 事实与贡献图、因果分镜、载体交接稿；授权时落盘。 GOTCHA: 时间线不等于因果线；写在素材里的能力，不等于已经在画面里讲清。

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./cat-cafe-skills/co-creation-storytelling/SKILL.md

Quality

Content

71%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 tightly written, well-structured instructional skill with strong actionability and an explicit review/feedback checklist. The main defect is progressive disclosure: two referenced files (failure-patterns, pressure-cases) do not exist in the bundle, leaving broken links.

Suggestions

Create the missing refs/failure-patterns.md and refs/pressure-cases.md (or fix the link paths to point at the existing references/ directory) so the signaled references resolve.

Consider moving the §4 translation-example list into the story-map asset or a reference file to slim the main body further.

Make the §6 review checklist an explicit validate→fix→re-check loop (e.g., bullet the re-check as a mandatory final step) to push workflow clarity to the top anchor.

Dimension	Reasoning	Score
Conciseness	Dense, competence-assuming guidance with no padding about what storytelling is; every section carries actionable rules. A few illustrative lists in §4 could be trimmed slightly without loss.	4 / 5
Actionability	Gives concrete reusable structures — the causal chain '当时卡在哪 → 谁采取了什么行动 → …', the '行动者 + 动词 + 对象 + 可见变化' formula, translation examples, and a six-item review checklist — but it is instruction-only guidance rather than copy-paste commands.	4 / 5
Workflow Clarity	A clear numbered sequence §1–§6 with an explicit validation checklist in §6 and a re-check feedback loop ('修后复看全图，防止另一处被悄悄改写'), plus a pressure-check step; minor validation gaps keep it just below the top anchor.	4 / 5
Progressive Disclosure	Well-sectioned body with one real bundle asset (assets/story-map-template.md), but two signaled references (refs/failure-patterns.md, refs/pressure-cases.md) point to a refs/ directory that does not exist in the bundle, so navigation is partly broken.	3 / 5
	Total	15 / 20 Passed

Description

87%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 well-constructed description that crisply states what the skill does, when to use it, what not to use it for, and what it outputs, with a useful GOTCHA. The only minor weakness is that the capability phrasing is somewhat abstract despite naming concrete deliverables.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete deliverables — '事实与贡献图、因果分镜、载体交接稿' — plus the action of preserving each party's actions and changes, but the phrasing stays moderately abstract rather than enumerating every output.	4 / 5
Completeness	Explicitly answers both what ('把跨时间、多人或人机共创的真实经历讲清楚，保留各方行动与变化') and when ('Use when: …'), plus a 'Not for' boundary and concrete 'Output' deliverables — matching the anchor for clearly and explicitly answering both with concrete trigger phrases.	5 / 5
Trigger Term Quality	The 'Use when' clause and triggers list natural phrases users would say ('长故事要压成一页', '人和 AI 各做了什么', '故事只剩履历') with good synonym coverage, though a few common variations are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche (real co-creation storytelling) with explicit 'Not for' exclusions (虚构剧情、纯技术论证、启动能力进化项目) and routing to concept-demo-design, giving distinct triggers and minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 missing, 2 suspicious	Warning

	Total	14 / 16 Passed

Repository: zts212653/clowder-ai
Path: cat-cafe-skills/co-creation-storytelling/SKILL.md
Commit: 61389cc

Reviewed: 1 hour 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.