guide-authoring

标准引导流程设计 SOP：场景识别 → YAML 编排 → 标签标注 → 注册发现 → 测试验证。 Use when: 新建引导流程、添加场景引导、维护 Guide Catalog、编写引导 YAML。 Not for: 使用引导（用户侧）、Guide Engine 代码实现（用 tdd）、视觉设计（用 pencil-design）。 Output: Flow YAML + tag-manifest 更新 + registry 注册 + CI 校验通过。

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-sequenced, highly actionable SOP with strong validation checkpoints; its main weaknesses are mild redundancy across skill-boundary sections and everything being inline with no extracted reference files.

Suggestions

Consolidate the three boundary/direction sections ("Not for", "和其他 Skill 的区别", "下一步") into one to remove redundancy.

Extract the Flow YAML template and tag-manifest/registry examples into reference files under references/ and link to them, keeping SKILL.md as an overview.

Dimension	Reasoning	Score
Conciseness	Largely efficient — tables and templates assume competence and lean on codes (F155, KD-9, AC-S3) without explaining them — but skill boundaries are restated across "Not for", "和其他 Skill 的区别", and "下一步", which could be consolidated.	2 / 3
Actionability	Provides copy-paste-ready artifacts: scene-card YAML, Flow YAML template, data-guide-id tag examples, registry.yaml entry, and a CI checklist — all concrete and executable.	3 / 3
Workflow Clarity	Six clearly sequenced steps with explicit validation checkpoints (Step 5 CI gate checklist, Step 6 E2E including abnormal-path and refresh/missing-target feedback loops).	3 / 3
Progressive Disclosure	No bundle files exist, so all content is inline in SKILL.md (~180 lines); large templates and registry examples that could live in separate references are kept inline, matching the 'content that should be separate is inline' anchor.	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 states concrete actions, an explicit Use-when trigger set, and clear boundaries against sibling skills, all in third-person voice.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "场景识别 → YAML 编排 → 标签标注 → 注册发现 → 测试验证" plus an explicit Output ("Flow YAML + tag-manifest 更新 + registry 注册 + CI 校验通过").	3 / 3
Completeness	Explicitly answers both what (the SOP pipeline) and when ("Use when: 新建引导流程、添加场景引导..."), with an explicit "Not for" boundary too.	3 / 3
Trigger Term Quality	The "Use when" clause and trigger list cover natural phrasings users would say: "新建引导流程", "添加场景引导", "写引导流程", "guide authoring", "引导 YAML".	3 / 3
Distinctiveness Conflict Risk	Clear niche (authoring guide flows) with explicit "Not for" redirects to guide-interaction, tdd, and pencil-design, 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/guide-authoring/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.