Back to Details

skill-router

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Skill Router

Skill Router

An intelligent router that analyzes user requests and recommends the most appropriate Claude Code skill for the task.
这是一款智能路由器，可分析用户请求并为任务推荐最合适的Claude Code Skill。

When This Skill Activates

本Skill的激活场景

This skill activates when you:
  • Ask "which skill should I use?" or "what skill can help with...?"
  • Say "use a skill" without specifying which one
  • Express a need but aren't sure which skill fits
  • Mention "skill router" or "help me find a skill"
当你出现以下情况时，本Skill会激活：
  • 询问“我应该使用哪个skill？”或“哪个skill可以帮助我完成...？”
  • 说“使用一个skill”但未指定具体是哪一个
  • 表达了需求但不确定哪个Skill适用
  • 提及“skill router”或“帮我找一个skill”

Available Skills Catalog

可用技能目录

Core Development

核心开发

SkillBest For
commit-helper
Writing Git commit messages, formatting commits
code-reviewer
Reviewing PRs, code changes, quality checks
debugger
Diagnosing bugs, errors, unexpected behavior
refactoring-specialist
Improving code structure, reducing technical debt
Skill适用场景
commit-helper
编写Git提交信息、格式化提交内容
code-reviewer
审核PR、代码变更、质量检查
debugger
诊断Bug、错误、异常行为
refactoring-specialist
优化代码结构、减少技术债务

Design & UX

设计与UX

SkillBest For
figma-designer
Analyzing Figma designs and producing implementation-ready visual specs/PRDs
Skill适用场景
figma-designer
分析Figma设计并生成可直接用于开发的视觉规范/PRD

Documentation & Testing

文档与测试

SkillBest For
documentation-engineer
Writing README, technical docs, code documentation
api-documenter
Creating OpenAPI/Swagger specifications
test-automator
Writing tests, setting up test frameworks
qa-expert
Test strategy, quality gates, QA processes
Skill适用场景
documentation-engineer
编写README、技术文档、代码注释
api-documenter
创建OpenAPI/Swagger规范
test-automator
编写测试用例、搭建测试框架
qa-expert
测试策略、质量门禁、QA流程

Architecture & DevOps

架构与DevOps

SkillBest For
api-designer
Designing REST/GraphQL APIs, API architecture
security-auditor
Security audits, vulnerability reviews, OWASP Top 10
performance-engineer
Performance optimization, speed analysis
deployment-engineer
CI/CD pipelines, deployment automation
Skill适用场景
api-designer
设计REST/GraphQL API、API架构
security-auditor
安全审计、漏洞排查、OWASP Top 10
performance-engineer
性能优化、速度分析
deployment-engineer
CI/CD流水线、部署自动化

Planning & Analysis

规划与分析

SkillBest For
architecting-solutions
Creating PRDs, solution design, requirements analysis
planning-with-files
Multi-step task planning, persistent file-based organization
self-improving-agent
Universal self-improvement that learns from all skill experiences
Skill适用场景
architecting-solutions
创建PRD、解决方案设计、需求分析
planning-with-files
多步骤任务规划、基于持久化文件的组织管理
self-improving-agent
通用自我提升，可从所有Skill使用经验中学习

Routing Process

路由流程

Step 1: Intent Analysis

步骤1：意图分析

Analyze the user's request to identify:
  • Task Type: What does the user want to accomplish?
  • Context: What is the working domain (web, mobile, data, etc.)?
  • Complexity: Is this a simple task or complex workflow?
分析用户请求以明确：
  • 任务类型：用户想要完成什么？
  • 上下文：工作领域是什么（Web、移动、数据等）？
  • 复杂度：这是简单任务还是复杂工作流？

Step 2: Skill Matching

步骤2：Skill匹配

Match the identified intent to the most relevant skill(s) using:
  • Keyword matching: Compare request keywords with skill descriptions
  • Semantic similarity: Understand the meaning behind the request
  • Context awareness: Consider project state and previous actions
通过以下方式将识别出的意图与最相关的Skill进行匹配：
  • 关键词匹配：将请求关键词与Skill描述对比
  • 语义相似度：理解请求背后的含义
  • 上下文感知：考虑项目状态和之前的操作

Step 3: Interactive Clarification

步骤3：交互式澄清

If the request is ambiguous, guide the user with targeted questions:
  • What is the primary goal?
  • What type of output is expected?
  • Are there specific constraints or preferences?
如果请求模糊不清，通过针对性问题引导用户：
  • 主要目标是什么？
  • 期望的输出类型是什么？
  • 是否有特定的约束或偏好？

Step 4: Recommendation & Execution

步骤4：推荐与执行

Present the recommended skill with:
  • Skill name and brief description
  • Why it fits the current request
  • Option to proceed or ask for alternatives
向用户呈现推荐的Skill，包括：
  • Skill名称和简要描述
  • 为何它适合当前请求
  • 继续使用或查看其他选项的选择

Routing Examples

路由示例

Example 1: Clear Intent

示例1：意图明确

User: "I need to review this pull request"
Router Analysis:
  • Keywords: "review", "pull request"
  • Intent: Code review
  • Recommendation: 
    code-reviewer
用户: "我需要审核这个拉取请求"
路由器分析:
  • 关键词："review"、"pull request"
  • 意图：代码审核
  • 推荐: 
    code-reviewer

Example 2: Ambiguous Intent

示例2：意图模糊

User: "Use a skill to help with my project"
Router Questions:
  1. What type of task are you working on?
  2. Are you designing, coding, testing, or documenting?
Based on answers → Recommend appropriate skill
用户: "用一个Skill来帮助我的项目"
路由器问题:
  1. 你正在处理什么类型的任务？
  2. 你是在设计、编码、测试还是编写文档？
根据回答 → 推荐合适的Skill

Example 3: Multi-Skill Scenario

示例3：多Skill场景

User: "I'm building a new API and need help with the full workflow"
Router Recommendation: Consider using multiple skills in sequence:
  1. api-designer
    - Design the API structure
  2. api-documenter
    - Document endpoints with OpenAPI
  3. test-automator
    - Set up API tests
  4. code-reviewer
    - Review implementation
用户: "我正在构建一个新API，需要全流程帮助"
路由器推荐: 建议按顺序使用多个Skill：
  1. api-designer
    - 设计API结构
  2. api-documenter
    - 用OpenAPI文档化端点
  3. test-automator
    - 搭建API测试
  4. code-reviewer
    - 审核实现代码

Interactive Question Templates

交互式问题模板

When user intent is unclear, use these question patterns:
当用户意图不明确时，使用以下问题模板：

Goal Clarification

目标澄清

  • "What are you trying to accomplish with this task?"
  • "What would the ideal outcome look like?"
  • "你试图通过这项任务达成什么目标？"
  • "理想的结果是什么样的？"

Domain Identification

领域识别

  • "What area does this relate to: development, testing, documentation, or deployment?"
  • "Are you working on code, APIs, infrastructure, or something else?"
  • "这涉及哪个领域：开发、测试、文档还是部署？"
  • "你正在处理代码、API、基础设施还是其他内容？"

Stage Assessment

阶段评估

  • "What stage are you at: planning, implementing, testing, or maintaining?"
  • "你处于哪个阶段：规划、实现、测试还是维护？"

Preference Confirmation

偏好确认

  • "Do you want a quick solution or a comprehensive approach?"
  • "Are there specific tools or frameworks you're using?"
  • "你想要快速解决方案还是全面的方法？"
  • "你是否在使用特定的工具或框架？"

Best Practices

最佳实践

1. Start Broad, Then Narrow

1. 从宽泛到具体

  • Begin with general category questions
  • Drill down into specifics based on responses
  • 从通用类别问题开始
  • 根据回答逐步深入细节

2. Explain Your Reasoning

2. 解释推理过程

  • Tell the user why a particular skill is recommended
  • Build trust through transparency
  • 告诉用户为什么推荐某个Skill
  • 通过透明化建立信任

3. Offer Alternatives

3. 提供替代选项

  • Present the top recommendation
  • Mention 1-2 alternatives if applicable
  • 呈现首选推荐
  • 如有适用，提及1-2个替代选项

4. Handle Edge Cases

4. 处理边缘情况

  • If no skill fits perfectly, suggest the closest match
  • Offer to help without a specific skill if better
  • 如果没有完全匹配的Skill，建议最接近的选项
  • 如果更合适，提供不使用特定Skill的帮助

5. Learn from Context

5. 从上下文学习

  • Consider previous interactions
  • Remember user preferences for future routing
  • 考虑之前的交互
  • 记住用户偏好以便未来路由

Advanced Routing Patterns

高级路由模式

Semantic Routing

语义路由

Use semantic similarity when keywords don't match directly:
  • "clean up my code" → 
    refactoring-specialist
  • "make my app faster" → 
    performance-engineer
  • "check for security issues" → 
    security-auditor
当关键词不直接匹配时，使用语义相似度：
  • "清理我的代码" → 
    refactoring-specialist
  • "让我的应用更快" → 
    performance-engineer
  • "检查安全问题" → 
    security-auditor

Multi-Skill Orchestrations

多Skill编排

Suggest skill combinations for complex workflows:
  • New Feature: 
    architecting-solutions
    → 
    debugger
    → 
    code-reviewer
  • API Project: 
    api-designer
    → 
    api-documenter
    → 
    test-automator
  • Production Readiness: 
    security-auditor
    → 
    performance-engineer
    → 
    deployment-engineer
为复杂工作流建议Skill组合：
  • 新功能开发：
    architecting-solutions
    → 
    debugger
    → 
    code-reviewer
  • API项目：
    api-designer
    → 
    api-documenter
    → 
    test-automator
  • 生产就绪：
    security-auditor
    → 
    performance-engineer
    → 
    deployment-engineer

Confidence Levels

置信度等级

Indicate confidence in recommendations:
  • High: Direct keyword match, clear intent
  • Medium: Semantic similarity, reasonable inference
  • Low: Ambiguous request, clarification needed
标明推荐的置信度：
  • 高：直接关键词匹配，意图明确
  • 中：语义相似，合理推断
  • 低：请求模糊，需要澄清

Error Recovery

错误恢复

If the recommended skill doesn't fit:
  1. Acknowledge the mismatch
  2. Ask follow-up questions to refine understanding
  3. Provide alternative recommendations
  4. Fall back to general assistance if needed
如果推荐的Skill不合适：
  1. 承认匹配不当
  2. 提出后续问题以细化理解
  3. 提供替代推荐
  4. 必要时退回至通用协助

Output Format

输出格式

When recommending a skill, use this format:
markdown
undefined
当推荐Skill时，使用以下格式：
markdown
undefined

Recommended Skill: {skill-name}

推荐Skill: {skill-name}

{brief description of why this skill fits}
What it does: {one-sentence skill description}
Best for: {specific use cases}
Would you like me to activate this skill, or would you prefer to see other options?
undefined
{该Skill适合当前请求的简要说明}
功能介绍: {一句话Skill描述}
适用场景: {具体用例}
是否需要激活此Skill，还是你想查看其他选项？
undefined

References

参考资料