knowledge-engineering

猫猫指导外部项目文档重构 — AI FDE 知识工程方法论。 Use when: 猫猫部署到外部项目、用户项目缺少结构化文档、需要知识工程指导、冷启动理解业务。 Not for: cat-cafe 项目自身开发、已有完善 docs/ 结构的项目（直接用 CatCafeScanner）。 Output: 文档现状诊断 + 路径选择 + 三层知识注入建议 + 文档骨架模板。

Quality

81%

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 thorough, actionable methodology with a clear phased workflow and concrete templates, scoring well on actionability and workflow clarity. It is let down by inline template bulk that would benefit from reference-file extraction and by a few verbose explanatory passages.

Suggestions

Move the four document skeleton templates (Phase 4) into separate reference files (e.g. references/template-domain-glossary.md) and link to them from the body so SKILL.md stays a lean overview — this lifts progressive_disclosure.

Trim the opening '核心认知' rationale and the long quoted '向用户说明的要点' speech to one line each; the phased workflow already conveys the same intent, improving conciseness.

Collapse the repeated '猫的指导步骤' numbered scaffolding across P0a/P0b/P0c into a single shared step template referenced by each deliverable to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	Most content earns its place (phases, scenario table, templates, checklist), but the opening rationale paragraph, the long quoted '向用户说明的要点' speech, and repeated '猫的指导步骤' scaffolding could be tightened; it does not explain concepts Claude already knows, so it stays above 1.	2 / 3
Actionability	Concrete deliverable paths (project-research/domain-glossary.md), copy-paste markdown template skeletons with frontmatter and table schemas, and example search_evidence(...) calls give specific, fillable guidance rather than vague direction.	3 / 3
Workflow Clarity	A clear Phase 1→4 sequence with numbered steps, explicit user-confirmation feedback loops inside Phase 3, a path-switching escape ('如果理解不足建议切到 Guided'), and a completion checklist provide explicit checkpoints and error recovery.	3 / 3
Progressive Disclosure	There are no bundle files and top-level sections are well organized, but ~90 lines of inline template scaffolding (templates 1–4) and the special-scenario detail could live in one-level-deep reference files, leaving the body a leaner overview.	2 / 3
	Total	10 / 12 Passed

Description

85%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.

A well-structured description that states concrete deliverables, an explicit Use-when trigger, and a Not-for guard for distinctiveness. Its only weakness is trigger-term naturalness: the description leans on technical phrasing while the most user-natural term is parked in the triggers field.

Dimension	Reasoning	Score
Specificity	The 'Output:' clause lists four concrete deliverables — 文档现状诊断, 路径选择, 三层知识注入建议, 文档骨架模板 — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It explicitly answers 'what' (Output: ...骨架模板) and 'when' (an explicit 'Use when:' clause), plus a 'Not for:' guard, satisfying both halves with explicit triggers.	3 / 3
Trigger Term Quality	The 'Use when:' clause carries relevant terms (冷启动, 知识工程, 缺少结构化文档) but they lean technical; the most natural user phrasing ('帮我整理文档') sits in the separate triggers field rather than the description itself, so common variation coverage is incomplete.	2 / 3
Distinctiveness Conflict Risk	A clear niche (external-project knowledge engineering) with an explicit 'Not for: ...直接用 CatCafeScanner' disambiguation makes conflict with sibling skills unlikely.	3 / 3
	Total	11 / 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/knowledge-engineering/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.