Back to Details

engineer-skill-creator

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Engineer Skill Creator

工程师Skill创建器

Transform extracted engineer profiles into ready-to-use skills with progressive disclosure, enabling AI agents to efficiently find and apply the right expertise for any coding task.
将提取的工程师资料转化为可直接使用的Skill，借助渐进式披露功能，让AI Agent能够高效地为任意编码任务找到并应用合适的专业知识。

What This Skill Does

本Skill的功能

Takes the output from engineer-expertise-extractor and creates a structured, queryable skill that:
  • Organizes expertise by task type - Find relevant patterns quickly
  • Uses progressive disclosure - Show only what's needed for current task
  • Provides contextual examples - Real code samples for specific scenarios
  • Guides agents intelligently - Help find the right expertise at the right time
  • Enables task-specific queries - "How would they handle authentication?"
接收engineer-expertise-extractor的输出，创建一个结构化、可查询的Skill，具备以下特性：
  • 按任务类型组织专业知识 - 快速找到相关模式
  • 采用渐进式披露 - 仅展示当前任务所需的内容
  • 提供上下文示例 - 针对特定场景的真实代码样本
  • 智能引导Agent - 帮助在合适的时机找到合适的专业知识
  • 支持任务特定查询 - 例如“他们会如何处理身份验证？”

The Two-Step Process

两步流程

Step 1: Extract (engineer-expertise-extractor)

步骤1：提取（engineer-expertise-extractor）

bash
./extract_engineer.sh senior_dev
bash
./extract_engineer.sh senior_dev

Output: engineer_profiles/senior_dev/

Output: engineer_profiles/senior_dev/

undefined
undefined

Step 2: Create Skill (THIS SKILL)

步骤2：创建Skill（本工具）

bash
./create_expert_skill.sh senior_dev
bash
./create_expert_skill.sh senior_dev

Output: expert-skills/senior-dev-mentor/

Output: expert-skills/senior-dev-mentor/


**Result:** A ready-to-use skill that agents can query for specific guidance.

**结果：** 一个可直接使用的Skill，Agent可通过它查询特定指导内容。

Why Progressive Disclosure Matters

渐进式披露的重要性

Without progressive disclosure:
  • Agent gets all expertise at once (overwhelming)
  • Hard to find relevant information
  • Context limits reached quickly
  • Inefficient and slow
With progressive disclosure:
  • Agent asks specific question
  • Gets only relevant expertise
  • Focused, actionable guidance
  • Efficient use of context
  • Faster, better results
无渐进式披露的情况：
  • Agent一次性获取所有专业知识（信息过载）
  • 难以找到相关信息
  • 很快达到上下文限制
  • 低效且缓慢
有渐进式披露的情况：
  • Agent提出具体问题
  • 仅获取相关专业知识
  • 聚焦于可执行的指导内容
  • 高效利用上下文
  • 更快获得更优结果

Output Structure

输出结构

When you create a skill from an engineer profile, you get:
expert-skills/
└── [engineer-name]-mentor/
    ├── SKILL.md (skill documentation)
    ├── query_expertise.sh (interactive query tool)
    ├── expertise/
    │   ├── by_task/
    │   │   ├── authentication.md
    │   │   ├── api_design.md
    │   │   ├── database_design.md
    │   │   ├── error_handling.md
    │   │   └── testing.md
    │   ├── by_language/
    │   │   ├── typescript.md
    │   │   ├── python.md
    │   │   └── go.md
    │   ├── by_pattern/
    │   │   ├── dependency_injection.md
    │   │   ├── repository_pattern.md
    │   │   └── factory_pattern.md
    │   └── quick_reference/
    │       ├── coding_style.md
    │       ├── naming_conventions.md
    │       └── best_practices.md
    └── examples/
        ├── authentication_service.ts
        ├── api_controller.ts
        └── test_example.spec.ts
从工程师资料创建Skill后，你将得到如下结构：
expert-skills/
└── [engineer-name]-mentor/
    ├── SKILL.md (skill documentation)
    ├── query_expertise.sh (interactive query tool)
    ├── expertise/
    │   ├── by_task/
    │   │   ├── authentication.md
    │   │   ├── api_design.md
    │   │   ├── database_design.md
    │   │   ├── error_handling.md
    │   │   └── testing.md
    │   ├── by_language/
    │   │   ├── typescript.md
    │   │   ├── python.md
    │   │   └── go.md
    │   ├── by_pattern/
    │   │   ├── dependency_injection.md
    │   │   ├── repository_pattern.md
    │   │   └── factory_pattern.md
    │   └── quick_reference/
    │       ├── coding_style.md
    │       ├── naming_conventions.md
    │       └── best_practices.md
    └── examples/
        ├── authentication_service.ts
        ├── api_controller.ts
        └── test_example.spec.ts

Progressive Disclosure System

渐进式披露系统

Query by Task

按任务查询

Agent asks: "How would they implement user authentication?"
Skill provides:
  1. Relevant patterns from 
    by_task/authentication.md
  2. Code examples from their auth PRs
  3. Their testing approach for auth
  4. Security considerations they use
  5. Related best practices
NOT provided (yet):
  • Unrelated patterns
  • Database design details
  • Payment processing approach
  • Everything else
Agent提问： "他们会如何实现用户身份验证？"
Skill提供：
  1. by_task/authentication.md
    中的相关模式
  2. 来自他们PR的身份验证代码示例
  3. 他们针对身份验证的测试方法
  4. 他们遵循的安全注意事项
  5. 相关最佳实践
暂不提供：
  • 无关模式
  • 数据库设计细节
  • 支付处理方案
  • 其他所有不相关内容

Query by Language

按语言查询

Agent asks: "Show me their TypeScript coding style"
Skill provides:
  1. TypeScript-specific conventions
  2. Type usage patterns
  3. Interface design approach
  4. Error handling in TS
  5. Real TS examples
Agent提问： "展示他们的TypeScript编码风格"
Skill提供：
  1. TypeScript特定约定
  2. 类型使用模式
  3. 接口设计方法
  4. TS中的错误处理方式
  5. 真实TS示例

Query by Pattern

按模式查询

Agent asks: "How do they implement dependency injection?"
Skill provides:
  1. DI pattern from their code
  2. Constructor injection examples
  3. IoC container setup
  4. Testing with DI
  5. When they use it vs when they don't
Agent提问： "他们会如何实现依赖注入？"
Skill提供：
  1. 他们代码中的DI模式
  2. 构造函数注入示例
  3. IoC容器设置
  4. 基于DI的测试
  5. 他们使用和不使用DI的场景

Skill Usage by Agents

Agent对Skill的使用方式

Basic Query

基础查询

"Using the skill expert-skills/senior-dev-mentor/, show me how to
implement authentication"
Skill responds with:
  • Authentication patterns they use
  • Real code examples
  • Testing approach
  • Security practices
  • Step-by-step guidance
"使用expert-skills/senior-dev-mentor/ Skill，展示如何实现身份验证"
Skill回复：
  • 他们使用的身份验证模式
  • 真实代码示例
  • 测试方法
  • 安全实践
  • 分步指导

Language-Specific Query

特定语言查询

"Using expert-skills/senior-dev-mentor/, write a TypeScript service
following their style"
Skill provides:
  • TypeScript coding conventions
  • Class structure patterns
  • Type definitions approach
  • Import organization
  • Testing patterns for services
"使用expert-skills/senior-dev-mentor/ Skill，按照他们的风格编写一个TypeScript服务"
Skill提供：
  • TypeScript编码约定
  • 类结构模式
  • 类型定义方法
  • 导入组织方式
  • 服务的测试模式

Pattern-Specific Query

特定模式查询

"Using expert-skills/senior-dev-mentor/, implement the repository
pattern as they would"
Skill provides:
  • Their repository pattern implementation
  • Interface definitions
  • Concrete implementation example
  • Testing approach
  • When to use this pattern
"使用expert-skills/senior-dev-mentor/ Skill，按照他们的方式实现仓库模式"
Skill提供：
  • 他们的仓库模式实现方案
  • 接口定义
  • 具体实现示例
  • 测试方法
  • 该模式的适用场景

Created Skill Features

创建的Skill特性

1. Task-Based Navigation

1. 基于任务的导航

Expertise organized by common development tasks:
  • Authentication & Authorization
  • API Design
  • Database Design
  • Error Handling
  • Testing Strategies
  • Performance Optimization
  • Security Practices
  • Code Review Guidelines
专业知识按常见开发任务组织：
  • 身份验证与授权
  • API设计
  • 数据库设计
  • 错误处理
  • 测试策略
  • 性能优化
  • 安全实践
  • 代码评审指南

2. Language-Specific Guidance

2. 特定语言指导

Separate docs for each language they use:
  • Naming conventions per language
  • Language-specific patterns
  • Idiomatic code examples
  • Framework preferences
为他们使用的每种语言单独提供文档：
  • 各语言的命名约定
  • 特定语言的模式
  • 符合语言习惯的代码示例
  • 框架偏好

3. Pattern Library

3. 模式库

Design patterns they commonly use:
  • When to apply each pattern
  • Implementation examples
  • Testing approach
  • Common pitfalls to avoid
他们常用的设计模式：
  • 每种模式的适用场景
  • 实现示例
  • 测试方法
  • 需避免的常见陷阱

4. Quick Reference

4. 快速参考

Fast access to essentials:
  • Coding style at a glance
  • Naming conventions cheat sheet
  • Common commands/snippets
  • Review checklist
快速访问核心内容：
  • 概览编码风格
  • 命名约定速查表
  • 常用命令/代码片段
  • 评审检查清单

5. Interactive Query Tool

5. 交互式查询工具

Script that helps find expertise:
bash
./query_expertise.sh

What are you working on?
1) Authentication
2) API Design
3) Database
4) Testing
5) Custom query

Select: 1

=== Authentication Expertise ===

[Shows relevant patterns, examples, best practices]
用于查找专业知识的脚本：
bash
./query_expertise.sh

What are you working on?
1) Authentication
2) API Design
3) Database
4) Testing
5) Custom query

Select: 1

=== Authentication Expertise ===

[Shows relevant patterns, examples, best practices]

How Skills Are Created

Skill的创建流程

Input

输入

Engineer profile from extractor:
engineer_profiles/senior_dev/
├── coding_style/
├── patterns/
├── best_practices/
├── architecture/
├── code_review/
└── examples/
来自提取工具的工程师资料：
engineer_profiles/senior_dev/
├── coding_style/
├── patterns/
├── best_practices/
├── architecture/
├── code_review/
└── examples/

Process

流程

  1. Analyze profile structure
  2. Categorize by task - Group related expertise
  3. Extract examples - Pull relevant code samples
  4. Create navigation - Build progressive disclosure system
  5. Generate queries - Create query tool
  6. Package skill - Ready-to-use skill structure
  1. 分析资料结构
  2. 按任务分类 - 分组相关专业知识
  3. 提取示例 - 提取相关代码样本
  4. 创建导航系统 - 构建渐进式披露系统
  5. 生成查询工具 - 创建查询系统
  6. 打包Skill - 生成可直接使用的Skill结构

Output

输出

Skill with progressive disclosure:
expert-skills/senior-dev-mentor/
├── SKILL.md
├── query_expertise.sh
├── expertise/
│   ├── by_task/
│   ├── by_language/
│   ├── by_pattern/
│   └── quick_reference/
└── examples/
具备渐进式披露功能的Skill：
expert-skills/senior-dev-mentor/
├── SKILL.md
├── query_expertise.sh
├── expertise/
│   ├── by_task/
│   ├── by_language/
│   ├── by_pattern/
│   └── quick_reference/
└── examples/

Example Created Skill

已创建Skill示例

Authentication Task Doc

身份验证任务文档

File: 
expertise/by_task/authentication.md
markdown
undefined
文件： 
expertise/by_task/authentication.md
markdown
undefined

Authentication - Senior Dev's Approach

Authentication - Senior Dev's Approach

Overview

Overview

How senior_dev implements authentication based on 15 PRs analyzed.
How senior_dev implements authentication based on 15 PRs analyzed.

Preferred Approach

Preferred Approach

  • JWT-based authentication
  • Refresh token rotation
  • HttpOnly cookies for web
  • Token in headers for mobile/API
  • JWT-based authentication
  • Refresh token rotation
  • HttpOnly cookies for web
  • Token in headers for mobile/API

Implementation Pattern

Implementation Pattern

Service Structure

Service Structure

[Code example from their PR #1234]
[Code example from their PR #1234]

Token Generation

Token Generation

[Code example from their PR #5678]
[Code example from their PR #5678]

Token Validation

Token Validation

[Code example from their PR #9012]
[Code example from their PR #9012]

Testing Approach

Testing Approach

  • Unit tests for token generation
  • Integration tests for auth flow
  • Security tests for token validation
[Test examples from their code]
  • Unit tests for token generation
  • Integration tests for auth flow
  • Security tests for token validation
[Test examples from their code]

Security Considerations

Security Considerations

From their code reviews:
  • Always validate token signature
  • Check expiration
  • Implement rate limiting
  • Use secure random for secrets
From their code reviews:
  • Always validate token signature
  • Check expiration
  • Implement rate limiting
  • Use secure random for secrets

Common Pitfalls They Avoid

Common Pitfalls They Avoid

  • Storing tokens in localStorage (XSS risk)
  • Not rotating refresh tokens
  • Weak secret keys
  • Missing token expiration
  • Storing tokens in localStorage (XSS risk)
  • Not rotating refresh tokens
  • Weak secret keys
  • Missing token expiration

Related Patterns

Related Patterns

  • Error handling for auth failures
  • Middleware pattern for auth checks
  • Repository pattern for user lookup
  • Error handling for auth failures
  • Middleware pattern for auth checks
  • Repository pattern for user lookup

Examples

Examples

See: examples/authentication_service.ts
undefined
See: examples/authentication_service.ts
undefined

Use Cases

使用场景

1. Consistent Code Generation

1. 一致的代码生成

Problem: AI generates code that doesn't match team style
Solution:
"Using expert-skills/senior-dev-mentor/, write a user service"
Result: Code matching senior dev's exact style and patterns
问题： AI生成的代码与团队风格不符
解决方案：
"使用expert-skills/senior-dev-mentor/ Skill，编写一个用户服务"
结果： 符合资深工程师精确风格和模式的代码

2. Task-Specific Guidance

2. 任务特定指导

Problem: How would senior dev approach this specific problem?
Solution:
"Using expert-skills/tech-lead-mentor/, how do I handle rate limiting?"
Result: Their specific approach, examples, and reasoning
问题： 资深工程师会如何处理这个具体问题？
解决方案：
"使用expert-skills/tech-lead-mentor/ Skill，我该如何处理速率限制？"
结果： 他们的具体方案、示例和推理过程

3. Code Review Training

3. 代码评审培训

Problem: Learn what experienced engineer looks for
Solution:
"Using expert-skills/architect-mentor/, review this code"
Result: Review following their standards and priorities
问题： 学习资深工程师关注的评审要点
解决方案：
"使用expert-skills/architect-mentor/ Skill，评审这段代码"
结果： 按照他们的标准和优先级进行的评审

4. Onboarding

4. 新员工入职

Problem: New engineer needs to learn team conventions
Solution: Give them access to expert-skills
Result: Learn from real examples, specific to their tasks
问题： 新工程师需要学习团队约定
解决方案： 为他们提供expert-skills的访问权限
结果： 从真实示例中学习，内容与他们的任务紧密相关

Skill Query Examples

Skill查询示例

Example 1: Authentication

示例1：身份验证

bash
./query_expertise.sh
> Working on: Authentication
> Language: TypeScript

Output:
=== Authentication in TypeScript ===

Preferred approach: JWT with refresh tokens

[Shows specific auth pattern]
[Provides TS code example]
[Testing strategy]
[Security checklist]

Related: error_handling.md, api_design.md
bash
./query_expertise.sh
> Working on: Authentication
> Language: TypeScript

Output:
=== Authentication in TypeScript ===

Preferred approach: JWT with refresh tokens

[Shows specific auth pattern]
[Provides TS code example]
[Testing strategy]
[Security checklist]

Related: error_handling.md, api_design.md

Example 2: Database Design

示例2：数据库设计

bash
./query_expertise.sh
> Working on: Database design
> Database: PostgreSQL

Output:
=== Database Design - PostgreSQL ===

Schema design approach:
- Normalized tables
- Foreign keys enforced
- Indexes on lookups
- Migrations for changes

[Shows migration example]
[Query optimization patterns]
[Testing approach]
bash
./query_expertise.sh
> Working on: Database design
> Database: PostgreSQL

Output:
=== Database Design - PostgreSQL ===

Schema design approach:
- Normalized tables
- Foreign keys enforced
- Indexes on lookups
- Migrations for changes

[Shows migration example]
[Query optimization patterns]
[Testing approach]

Example 3: Error Handling

示例3：错误处理

bash
./query_expertise.sh
> Working on: Error handling
> Language: Python

Output:
=== Error Handling in Python ===

Pattern: Custom exception classes + global handler

[Shows exception hierarchy]
[Handler implementation]
[Logging approach]
[User-facing messages]
bash
./query_expertise.sh
> Working on: Error handling
> Language: Python

Output:
=== Error Handling in Python ===

Pattern: Custom exception classes + global handler

[Shows exception hierarchy]
[Handler implementation]
[Logging approach]
[User-facing messages]

Creating a Skill

创建Skill的方法

Basic Usage

基础用法

bash
cd engineer-skill-creator
./scripts/create_expert_skill.sh [engineer-username]
bash
cd engineer-skill-creator
./scripts/create_expert_skill.sh [engineer-username]

Advanced Usage

高级用法

bash
./scripts/create_expert_skill.sh [engineer-username] --focus api,testing
Limits skill to specific focus areas.
bash
./scripts/create_expert_skill.sh [engineer-username] --focus api,testing
将Skill限制为特定的重点领域。

What Gets Generated

生成内容

Automatic categorization:
  • Groups related patterns
  • Organizes by common tasks
  • Separates by language
  • Highlights best practices
Query system:
  • Interactive CLI tool
  • Smart search
  • Related content linking
  • Example suggestions
Documentation:
  • Task-specific guides
  • Language references
  • Pattern library
  • Quick reference cards
自动分类：
  • 分组相关模式
  • 按常见任务组织
  • 按语言区分
  • 突出最佳实践
查询系统：
  • 交互式CLI工具
  • 智能搜索
  • 相关内容链接
  • 示例建议
文档：
  • 任务特定指南
  • 语言参考
  • 模式库
  • 快速参考卡片

Integration with Development Workflow

与开发工作流集成

In Claude Code

在Claude Code中使用

"Load the expert-skills/senior-dev-mentor/ skill and help me
implement this feature following their approach"
"加载expert-skills/senior-dev-mentor/ Skill，按照他们的方法帮助我实现这个功能"

In Code Review

在代码评审中使用

"Using expert-skills/tech-lead-mentor/, review this PR for:
- Code style compliance
- Pattern usage
- Best practices
- Security considerations"
"使用expert-skills/tech-lead-mentor/ Skill，从以下方面评审这个PR：
- 代码风格合规性
- 模式使用
- 最佳实践
- 安全注意事项"

In Architecture Decisions

在架构决策中使用

"Using expert-skills/architect-mentor/, how would they design
this microservice?"
"使用expert-skills/architect-mentor/ Skill，他们会如何设计这个微服务？"

Skill Maintenance

Skill维护

Updating Skills

更新Skill

When engineer profile is updated:
bash
./scripts/update_expert_skill.sh senior-dev
Re-generates skill with new expertise.
当工程师资料更新时：
bash
./scripts/update_expert_skill.sh senior-dev
重新生成包含新专业知识的Skill。

Version Control

版本控制

Each skill generation includes:
  • Source profile version
  • Generation date
  • Expertise count
  • Last PR analyzed
每次Skill生成包含：
  • 源资料版本
  • 生成日期
  • 专业知识数量
  • 最后分析的PR

Best Practices

最佳实践

When Creating Skills

创建Skill时

DO:
  • ✅ Create skills for different expertise areas
  • ✅ Update skills regularly (quarterly)
  • ✅ Test queries before deploying
  • ✅ Document what the skill covers
DON'T:
  • ❌ Create skills from insufficient data (< 20 PRs)
  • ❌ Mix multiple engineers in one skill
  • ❌ Ignore profile updates
  • ❌ Over-categorize (keep it simple)
建议：
  • ✅ 为不同专业领域创建Skill
  • ✅ 定期更新Skill（每季度）
  • ✅ 部署前测试查询功能
  • ✅ 记录Skill涵盖的内容
不建议：
  • ❌ 从不足的数据创建Skill（少于20个PR）
  • ❌ 在一个Skill中混合多个工程师的资料
  • ❌ 忽略资料更新
  • ❌ 过度分类（保持简洁）

When Using Skills

使用Skill时

DO:
  • ✅ Ask specific questions
  • ✅ Provide context (language, task)
  • ✅ Reference examples
  • ✅ Combine with your judgment
DON'T:
  • ❌ Blindly copy patterns
  • ❌ Skip understanding reasoning
  • ❌ Ignore project context
  • ❌ Treat as inflexible rules
建议：
  • ✅ 提出具体问题
  • ✅ 提供上下文（语言、任务）
  • ✅ 参考示例
  • ✅ 结合自己的判断
不建议：
  • ❌ 盲目复制模式
  • ❌ 跳过对推理过程的理解
  • ❌ 忽略项目上下文
  • ❌ 将其视为僵化的规则

Limitations

局限性

What Skills Can Do:
  • ✅ Provide proven patterns
  • ✅ Show real examples
  • ✅ Guide implementation
  • ✅ Explain reasoning
  • ✅ Surface best practices
What Skills Cannot Do:
  • ❌ Make decisions for you
  • ❌ Understand your specific context
  • ❌ Replace senior engineer judgment
  • ❌ Guarantee correctness
  • ❌ Adapt to new technologies automatically
Skill可以做到：
  • ✅ 提供经过验证的模式
  • ✅ 展示真实示例
  • ✅ 指导实现
  • ✅ 解释推理过程
  • ✅ 呈现最佳实践
Skill无法做到：
  • ❌ 为你做决策
  • ❌ 理解你的特定上下文
  • ❌ 替代资深工程师的判断
  • ❌ 保证正确性
  • ❌ 自动适应新技术

Summary

总结

The Engineer Skill Creator transforms extracted expertise into actionable, queryable skills:
Input: Engineer profile (from extractor) Process: Categorize, organize, create query system Output: Progressive disclosure skill
Benefits:
  • Find expertise fast
  • Get task-specific guidance
  • Learn from real examples
  • Maintain consistency
  • Scale knowledge
Use with agents:
"Using expert-skills/[engineer]-mentor/, [task description]"
The complete workflow:
  1. Extract expertise: 
    extract_engineer.sh username
  2. Create skill: 
    create_expert_skill.sh username
  3. Use with agents: Reference skill in prompts
  4. Get consistent, expert-level results
"Progressive disclosure: Show only what's needed, when it's needed."
工程师Skill创建器将提取的专业知识转化为可执行、可查询的Skill：
输入： 工程师资料（来自提取工具） 流程： 分类、组织、创建查询系统 输出： 具备渐进式披露功能的Skill
优势：
  • 快速找到专业知识
  • 获取任务特定指导
  • 从真实示例中学习
  • 保持一致性
  • 扩展知识范围
与Agent配合使用：
"使用expert-skills/[engineer]-mentor/ Skill，[任务描述]"
完整工作流：
  1. 提取专业知识：
    extract_engineer.sh username
  2. 创建Skill：
    create_expert_skill.sh username
  3. 与Agent配合使用：在提示词中引用Skill
  4. 获得一致的专家级结果
"渐进式披露：只在需要时展示所需内容。"