CtrlK
BlogDocsLog inGet started
Tessl Logo

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。

68

Quality

83%

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

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.

A well-organized, actionable SOP body with sequenced steps, validation checkpoints, and concrete templates. It is efficient rather than padded, but the central Flow YAML uses placeholders and the fix-retry loop is implicit rather than explicit.

Suggestions

Provide one fully filled Flow YAML example (e.g. for api-provider-setup) alongside the template so the central artifact is directly copy-paste runnable.

Make the validation feedback loop explicit in Step 5: 'If CI checks fail, fix the flagged target/schema issue and re-run the gate before proceeding to E2E.'

Consider splitting the Flow YAML schema and tag-naming convention into a references/ file, keeping SKILL.md as a lean overview with one-level-deep links.

DimensionReasoningScore

Conciseness

Mostly lean: tables (核心知识, advance modes, Quick Reference, Common Mistakes) and concrete YAML/code blocks convey information efficiently, with only minor prose (和其他 Skill 的区别, 下一步) that could be trimmed.

4 / 5

Actionability

Concrete, copy-paste-ready artifacts appear throughout (filled scene card, registry entry, tag-manifest, naming conventions), but the central Flow YAML template still uses {scene_id}/{scene_name}/{一句话描述} placeholders rather than a fully filled runnable example, leaving a minor gap.

4 / 5

Workflow Clarity

Six clearly sequenced steps with a CI validation checklist (Step 5) and E2E error-path testing (Step 6) provide strong checkpoints, but the explicit fix→re-run feedback loop on validation failure is only implied rather than spelled out.

4 / 5

Progressive Disclosure

A single self-contained file is well-sectioned with a Quick Reference table aiding navigation, and no bundle files exist to reference; the dense 6-step body could optionally split the YAML schema/tag conventions into reference files, leaving minor organization headroom.

4 / 5

Total

16

/

20

Passed

Description

92%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 strong, well-structured description that explicitly covers what, when, not-for, and output with concrete actions and bilingual triggers. The only minor gap is trigger-term completeness, where a few natural synonyms are absent.

DimensionReasoningScore

Specificity

Lists five concrete actions (场景识别 → YAML 编排 → 标签标注 → 注册发现 → 测试验证) plus explicit output artifacts (Flow YAML + tag-manifest 更新 + registry 注册 + CI 校验通过), giving comprehensive concrete coverage rather than vague language.

5 / 5

Completeness

Explicitly answers both what (标准引导流程设计 SOP with the action chain) and when (Use when: 新建引导流程、添加场景引导、维护 Guide Catalog、编写引导 YAML), plus Not for and Output — exceeding the what+when requirement with concrete trigger phrases.

5 / 5

Trigger Term Quality

Bilingual triggers (新建引导流程, 添加场景引导, 写引导流程, guide authoring, 引导 YAML) with synonyms are natural for users, but a few common variations (e.g. 引导文档, guide flow) are missing, so it sits just below fully comprehensive.

4 / 5

Distinctiveness Conflict Risk

A clear niche (authoring guide-flow SOPs) with an explicit Not for clause distinguishing it from guide-interaction, tdd, and pencil-design, minimizing the chance of triggering for the wrong skill.

5 / 5

Total

19

/

20

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.