CtrlK
BlogDocsLog inGet started
Tessl Logo

guide-interaction

场景引导交互模式:当用户在询问某项功能的使用/配置流程时, 先判断该直接解释还是进入交互引导;当系统已注入 Guide Matched / Guide Pending / Guide Selection / Guide Active / Guide Completed 时, 按状态驱动回复并使用对应 guide MCP 工具。 Use when: 系统注入了 Guide Matched / Guide Pending / Guide Selection / Guide Active / Guide Completed,或用户明确在问某项功能怎么操作。 Not for: 普通闲聊、代码实现、没有流程诉求的概念讨论。

79

Quality

100%

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

100%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 body is a tight, well-organized orchestration guide: it names specific tools with parameters, lays out a clear state-driven workflow with guardrails, and avoids verbosity and redundant concept explanations. As an instruction-only skill its lack of code is not a defect since the guidance is actionable.

DimensionReasoningScore

Conciseness

The body is lean: it avoids explaining concepts Claude already knows, uses a compact tool-reference table and short bullets, and every section (角色, 边界, 注入格式, 工作流) earns its place without padding.

3 / 3

Actionability

Guidance is concrete and executable for an instruction-only skill — specific MCP tool names with real parameters (e.g. status='offered', action='exit') and per-state sequencing, not vague direction.

3 / 3

Workflow Clarity

The workflow is clearly sequenced across six guide states with explicit branch guardrails ('没有合适候选时,直接回答,不要伪造 guide', '不要重新用关键词匹配一次 guide', exit control), which function as validation checkpoints for this non-destructive orchestration flow.

3 / 3

Progressive Disclosure

The skill is self-contained with well-organized sections and no bundle files or nested references; nothing here would benefit from being split into a separate file, so the well-organized-sections standard is met.

3 / 3

Total

12

/

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.

A strong, well-structured description that clearly states capabilities, gives explicit Use when/Not for triggers using natural user language, and occupies a distinct niche. It is concise without over-claiming and uses appropriate third-person declarative voice.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — '先判断该直接解释还是进入交互引导', '按状态驱动回复并使用对应 guide MCP 工具' — and names the five specific guide states, matching the multiple-specific-actions anchor rather than the partial domain-only anchor at 2.

3 / 3

Completeness

It explicitly answers both what ('场景引导交互模式...按状态驱动回复并使用对应 guide MCP 工具') and when (explicit 'Use when:' and 'Not for:' clauses), matching the clearly-answers-both anchor.

3 / 3

Trigger Term Quality

Natural user-facing trigger terms are present ('怎么操作', '怎么配置', '引导流程') alongside an explicit 'Use when:' clause, giving good coverage of phrases users would actually say; not merely technical jargon like the score-1 anchor.

3 / 3

Distinctiveness Conflict Risk

The niche is tightly bound to specific injected guide states and cat_cafe_* MCP tools, with explicit 'Not for' exclusions (普通闲聊、代码实现、概念讨论), making conflict 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.