CtrlK
BlogDocsLog inGet started
Tessl Logo

writing-skills

创建或修改 Cat Café skill / MCP tool description 的元技能(含质量标准、范本、发布)。 Use when: 写新 skill、修改现有 skill、写/改 MCP tool description、验证 skill 质量; 或者功能实现中产出了 SKILL.md / cat-cafe-skills/ 新目录 / manifest.yaml skill 条目。 Not for: 使用 skill(直接触发对应 skill)。 Output: 新/更新的 SKILL.md + manifest 条目 + symlinks。 GOTCHA: 软硬同重——skill/MCP 质量 = 代码质量;不要写模型已知的通用教程,先过价值门禁。

74

Quality

92%

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

85%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.

The content is a strong, actionable meta-skill with a sequenced validation-gated publishing workflow and disciplined progressive disclosure. Its only weakness is conciseness: it runs longer than its own 150-line target and re-states the value-gate criteria in two places.

Suggestions

Consolidate the '价值门禁' table and the T0-0 carrier-selection table into one section to remove the duplicated value-gate material and trim body length below 150 lines.

Resolve or drop the '*(internal reference removed)*' placeholders so readers aren't left with dangling pointers in the T0-1 and 深入学习 sections.

Move the SKILL.md structure template and concept-boundary guide into a refs/ file, keeping the body as a lean overview that links out.

DimensionReasoningScore

Conciseness

The body is dense and table-driven with no generic-concept padding (it explicitly avoids teaching for-loops), but at ~185 lines it exceeds its own 150-line guidance and overlaps conceptually — the value-gate material recurs in both the '价值门禁' table and T0-0, so it could be tightened.

2 / 3

Actionability

Provides concrete executable commands ('pnpm sync:skills', 'pnpm check:skills', 'pnpm check'), exact file paths ('cat-cafe-skills/{skill-name}/SKILL.md'), a copy-paste SKILL.md structure template, and the explicit MCP five-element checklist — copy-paste ready.

3 / 3

Workflow Clarity

The 发布检查清单 is a clearly sequenced workflow (源文件→同步→注册→验证→commit) with an explicit validation checkpoint ('pnpm check:skills 全绿') and a feedback loop ('若改动涉及 API/localhost 必须 pnpm check').

3 / 3

Progressive Disclosure

The body is an overview pointing one level deep to well-signaled references (cat-cafe-skill-quality-principles.md, anthropic-best-practices.md, refs/mcp-tool-description-standard.md); no bundle dirs ship in this package, and the pointers are clean and single-level.

3 / 3

Total

11

/

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 exemplary: it states concrete actions, provides explicit Use-when/Not-for/Output triggers in natural terms, and carves out a distinct meta-skill niche. It hits the top anchor on every dimension.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '创建或修改 skill / MCP tool description', '验证 skill 质量', and an explicit 'Output: 新/更新的 SKILL.md + manifest 条目 + symlinks' — rather than vague language.

3 / 3

Completeness

Explicitly answers both what (meta-skill for authoring skills/MCP descriptions) and when via a 'Use when:' clause plus 'Not for:' and 'Output:' — matching the three-part trigger format.

3 / 3

Trigger Term Quality

Covers natural user phrasings ('写新 skill', '修改 skill', '写 MCP', 'MCP description', 'tool description') plus artifact-based triggers (SKILL.md, cat-cafe-skills/, manifest.yaml) a user would actually mention.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear meta-skill niche (authoring skills/MCP, not using them) and the 'Not for: 使用 skill' boundary plus specific file-artifact triggers make overlap with other skills unlikely.

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.