engineer-expertise-extractor

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Engineer Expertise Extractor

工程师专业技能提取器

Extract and document an engineer's coding expertise by analyzing their GitHub contributions, creating a structured knowledge base that captures their coding style, patterns, best practices, and architectural decisions.

通过分析工程师的GitHub贡献，提取并归档其编码专业技能，创建结构化的知识库，收录其编码风格、模式、最佳实践和架构决策。

What This Skill Does

该技能的作用

Researches an engineer's work to create a "digital mentor" by:

Analyzing Pull Requests - Extract code patterns, review style, decisions
Extracting Coding Style - Document their preferences and conventions
Identifying Patterns - Common solutions and approaches they use
Capturing Best Practices - Their quality standards and guidelines
Organizing Examples - Real code samples from their work
Documenting Decisions - Architectural choices and reasoning

通过以下方式调研工程师的工作成果，打造「数字导师」：

分析Pull Request - 提取代码模式、评审风格、决策逻辑
提取编码风格 - 记录其偏好和编码规范
识别编码模式 - 他们常用的通用解决方案和实现思路
收录最佳实践 - 他们的质量标准和开发准则
整理示例代码 - 来自其实际工作的真实代码样例
归档决策逻辑 - 架构选择背后的原因和考量

Why This Matters

应用价值

Knowledge Preservation:

Capture expert knowledge before they leave
Document tribal knowledge
Create mentorship materials
Onboard new engineers faster

Consistency:

Align team coding standards
Replicate expert approaches
Maintain code quality
Scale expertise across team

Learning:

Learn from senior engineers
Understand decision-making
See real-world patterns
Improve code quality

知识留存：

在专家离职前留存其核心知识
归档团队隐性知识
制作导师培训材料
加快新工程师上手速度

一致性保障：

对齐团队编码标准
复现专家的实现思路
维持代码质量
让专家经验在全团队复用

学习提升：

向资深工程师学习
理解决策逻辑
学习真实业务场景下的编码模式
提升代码质量

How It Works

工作原理

1. Research Phase

1. 调研阶段

Using GitHub CLI (

gh

), the skill:

Fetches engineer's pull requests
Analyzes code changes
Reviews their comments and feedback
Extracts patterns and conventions
Identifies their expertise areas

该技能通过GitHub CLI（

gh

）完成以下操作：

拉取工程师提交的Pull Request
分析代码变更
梳理其提交的评论和反馈
提取编码模式和规范
识别其擅长的技术领域

2. Analysis Phase

2. 分析阶段

Categorizes findings into:

Coding Style - Formatting, naming, structure
Patterns - Common solutions and approaches
Best Practices - Quality guidelines
Architecture - Design decisions
Testing - Testing approaches
Code Review - Feedback patterns
Documentation - Doc style and practices

将分析结果归类为以下维度：

编码风格 - 格式化、命名、代码结构
编码模式 - 通用解决方案和实现思路
最佳实践 - 质量准则
架构设计 - 设计决策
测试策略 - 测试实现思路
Code Review - 反馈模式
文档规范 - 文档风格和实践

3. Organization Phase

3. 整理阶段

Creates structured folders:

engineer_profiles/
└── [engineer_name]/
    ├── README.md (overview)
    ├── coding_style/
    │   ├── languages/
    │   ├── naming_conventions.md
    │   ├── code_structure.md
    │   └── formatting_preferences.md
    ├── patterns/
    │   ├── common_solutions.md
    │   ├── design_patterns.md
    │   └── code_examples/
    ├── best_practices/
    │   ├── code_quality.md
    │   ├── testing_approach.md
    │   ├── performance.md
    │   └── security.md
    ├── architecture/
    │   ├── design_decisions.md
    │   ├── tech_choices.md
    │   └── trade_offs.md
    ├── code_review/
    │   ├── feedback_style.md
    │   ├── common_suggestions.md
    │   └── review_examples.md
    └── examples/
        ├── by_language/
        ├── by_pattern/
        └── notable_prs/

创建结构化的目录存储结果：

engineer_profiles/
└── [engineer_name]/
    ├── README.md (overview)
    ├── coding_style/
    │   ├── languages/
    │   ├── naming_conventions.md
    │   ├── code_structure.md
    │   └── formatting_preferences.md
    ├── patterns/
    │   ├── common_solutions.md
    │   ├── design_patterns.md
    │   └── code_examples/
    ├── best_practices/
    │   ├── code_quality.md
    │   ├── testing_approach.md
    │   ├── performance.md
    │   └── security.md
    ├── architecture/
    │   ├── design_decisions.md
    │   ├── tech_choices.md
    │   └── trade_offs.md
    ├── code_review/
    │   ├── feedback_style.md
    │   ├── common_suggestions.md
    │   └── review_examples.md
    └── examples/
        ├── by_language/
        ├── by_pattern/
        └── notable_prs/

Output Structure

输出结构

Engineer Profile README

工程师档案README

Contains:

Engineer overview
Areas of expertise
Languages and technologies
Key contributions
Coding philosophy
How to use this profile

包含内容：

工程师基本介绍
擅长的技术领域
掌握的语言和技术栈
核心贡献
编码理念
该档案的使用说明

Coding Style Documentation

编码风格文档

Captures:

Naming conventions (variables, functions, classes)
Code structure preferences
File organization
Comment style
Formatting preferences
Language-specific idioms

Example:

markdown

undefined

收录内容：

命名规范（变量、函数、类）
代码结构偏好
文件组织方式
注释风格
格式化偏好
特定语言的惯用写法

示例：

markdown

undefined

Coding Style: [Engineer Name]

Naming Conventions

Variables

Use descriptive names:
```
userAuthentication
```
not
```
ua
```
Boolean variables:
```
isActive
```
,
```
hasPermission
```
,
```
canEdit
```
Collections: plural names
```
users
```
,
```
items
```
,
```
transactions
```

Use descriptive names:
```
userAuthentication
```
not
```
ua
```
Boolean variables:
```
isActive
```
,
```
hasPermission
```
,
```
canEdit
```
Collections: plural names
```
users
```
,
```
items
```
,
```
transactions
```

Functions

Verb-first:
```
getUserById
```
,
```
validateInput
```
,
```
calculateTotal
```
Pure functions preferred
Single responsibility

Verb-first:
```
getUserById
```
,
```
validateInput
```
,
```
calculateTotal
```
Pure functions preferred
Single responsibility

Classes

PascalCase:
```
UserService
```
,
```
PaymentProcessor
```
Interface prefix:
```
IUserRepository
```
Concrete implementations:
```
MongoUserRepository
```

PascalCase:
```
UserService
```
,
```
PaymentProcessor
```
Interface prefix:
```
IUserRepository
```
Concrete implementations:
```
MongoUserRepository
```

Code Structure

File Organization

One class per file
Related functions grouped together
Tests alongside implementation
Clear separation of concerns

One class per file
Related functions grouped together
Tests alongside implementation
Clear separation of concerns

Function Length

Max 20-30 lines preferred
Extract helper functions
Single level of abstraction

undefined

Max 20-30 lines preferred
Extract helper functions
Single level of abstraction

undefined

Patterns Documentation

编码模式文档

Captures:

Recurring solutions
Design patterns used
Architectural patterns
Problem-solving approaches

Example:

markdown

undefined

收录内容：

反复出现的解决方案
使用的设计模式
架构模式
问题解决思路

示例：

markdown

undefined

Common Patterns: [Engineer Name]

Dependency Injection

Used consistently across services:

```typescript // Pattern: Constructor injection class UserService { constructor( private readonly userRepo: IUserRepository, private readonly logger: ILogger ) {} } ```

Why: Testability, loose coupling, clear dependencies

Used consistently across services:

```typescript // Pattern: Constructor injection class UserService { constructor( private readonly userRepo: IUserRepository, private readonly logger: ILogger ) {} } ```

Why: Testability, loose coupling, clear dependencies

Error Handling

Consistent error handling approach:

```typescript // Pattern: Custom error types + global handler class ValidationError extends Error { constructor(message: string) { super(message); this.name = 'ValidationError'; } }

// Usage if (!isValid(input)) { throw new ValidationError('Invalid input format'); } ```

Why: Type-safe errors, centralized handling, clear debugging

undefined

Consistent error handling approach:

```typescript // Pattern: Custom error types + global handler class ValidationError extends Error { constructor(message: string) { super(message); this.name = 'ValidationError'; } }

// Usage if (!isValid(input)) { throw new ValidationError('Invalid input format'); } ```

Why: Type-safe errors, centralized handling, clear debugging

undefined

Best Practices Documentation

最佳实践文档

Captures:

Quality standards
Testing approaches
Performance guidelines
Security practices
Documentation standards

Example:

markdown

undefined

收录内容：

质量标准
测试策略
性能准则
安全实践
文档标准

示例：

markdown

undefined

Best Practices: [Engineer Name]

Testing

Unit Test Structure

AAA pattern (Arrange, Act, Assert)
One assertion per test preferred
Test names describe behavior
Mock external dependencies

```typescript describe('UserService', () => { describe('createUser', () => { it('should create user with valid data', async () => { // Arrange const userData = { email: 'test@example.com', name: 'Test' }; const mockRepo = createMockRepository();

  // Act
  const result = await userService.createUser(userData);

  // Assert
  expect(result.id).toBeDefined();
  expect(result.email).toBe(userData.email);
});

}); }); ```

AAA pattern (Arrange, Act, Assert)
One assertion per test preferred
Test names describe behavior
Mock external dependencies

  // Act
  const result = await userService.createUser(userData);

  // Assert
  expect(result.id).toBeDefined();
  expect(result.email).toBe(userData.email);
});

}); }); ```

Test Coverage

Aim for 80%+ coverage
100% coverage for critical paths
Integration tests for APIs
E2E tests for user flows

Aim for 80%+ coverage
100% coverage for critical paths
Integration tests for APIs
E2E tests for user flows

Code Review Standards

What to Check

Tests included and passing
No console.logs remaining
Error handling present
Comments explain "why" not "what"
No hardcoded values
Security considerations addressed

undefined

Tests included and passing
No console.logs remaining
Error handling present
Comments explain "why" not "what"
No hardcoded values
Security considerations addressed

undefined

Architecture Documentation

架构设计文档

Captures:

Design decisions
Technology choices
Trade-offs made
System design approaches

Example:

markdown

undefined

收录内容：

设计决策
技术选型
权衡考量
系统设计思路

示例：

markdown

undefined

Architectural Decisions: [Engineer Name]

Decision: Microservices vs Monolith

Context: Scaling user service Decision: Start monolith, extract services when needed Reasoning:

Team size: 5 engineers
Product stage: MVP
Premature optimization risk
Easier debugging and deployment

Trade-offs:

Monolith pros: Simpler, faster development
Monolith cons: Harder to scale later
Decision: Optimize for current needs, refactor when hitting limits

Context: Scaling user service Decision: Start monolith, extract services when needed Reasoning:

Team size: 5 engineers
Product stage: MVP
Premature optimization risk
Easier debugging and deployment

Trade-offs:

Monolith pros: Simpler, faster development
Monolith cons: Harder to scale later
Decision: Optimize for current needs, refactor when hitting limits

Decision: REST vs GraphQL

Context: API design for mobile app Decision: REST with versioning Reasoning:

Team familiar with REST
Simple use cases
Caching easier
Over-fetching not a problem yet

When to reconsider: If frontend needs complex queries

undefined

Context: API design for mobile app Decision: REST with versioning Reasoning:

Team familiar with REST
Simple use cases
Caching easier
Over-fetching not a problem yet

When to reconsider: If frontend needs complex queries

undefined

Code Review Documentation

Code Review文档

Captures:

Feedback patterns
Review approach
Common suggestions
Communication style

Example:

markdown

undefined

收录内容：

反馈模式
评审思路
常见建议
沟通风格

示例：

markdown

undefined

Code Review Style: [Engineer Name]

Review Approach

Priority Order

Security vulnerabilities
Logic errors
Test coverage
Code structure
Naming and style

Security vulnerabilities
Logic errors
Test coverage
Code structure
Naming and style

Feedback Style

Specific and constructive
Explains "why" behind suggestions
Provides examples
Asks questions to understand reasoning

Specific and constructive
Explains "why" behind suggestions
Provides examples
Asks questions to understand reasoning

Common Suggestions

Security:

"Consider input validation here"
"This query is vulnerable to SQL injection"
"Should we rate-limit this endpoint?"

Performance:

"This N+1 query could be optimized with a join"
"Consider caching this expensive operation"
"Memoize this pure function"

Testing:

"Can we add a test for the error case?"
"What happens if the API returns null?"
"Let's test the boundary conditions"

Code Quality:

"Can we extract this into a helper function?"
"This function is doing too many things"
"Consider a more descriptive variable name"

undefined

Security:

"Consider input validation here"
"This query is vulnerable to SQL injection"
"Should we rate-limit this endpoint?"

Performance:

"This N+1 query could be optimized with a join"
"Consider caching this expensive operation"
"Memoize this pure function"

Testing:

"Can we add a test for the error case?"
"What happens if the API returns null?"
"Let's test the boundary conditions"

Code Quality:

"Can we extract this into a helper function?"
"This function is doing too many things"
"Consider a more descriptive variable name"

undefined

Using This Skill

如何使用该技能

Extract Engineer Profile

提取工程师档案

bash

./scripts/extract_engineer.sh [github-username]

Interactive workflow:

Enter GitHub username
Select repository scope (all/specific org)
Choose analysis depth (last N PRs)
Specify focus areas (languages, topics)
Extract and organize findings

Output: Structured profile in

engineer_profiles/[username]/

bash

./scripts/extract_engineer.sh [github-username]

交互式工作流：

输入GitHub用户名
选择仓库范围（全部/指定组织）
选择分析深度（最近N个PR）
指定重点分析领域（语言、主题）
提取并整理分析结果

输出： 结构化档案存储在

engineer_profiles/[username]/

目录下

Analyze Specific Repository

分析指定仓库

bash

./scripts/analyze_repo.sh [repo-url] [engineer-username]

Focuses analysis on specific repository contributions.

bash

./scripts/analyze_repo.sh [repo-url] [engineer-username]

仅分析工程师在指定仓库的贡献。

Update Existing Profile

更新已有档案

bash

./scripts/update_profile.sh [engineer-username]

Adds new PRs and updates existing profile.

bash

./scripts/update_profile.sh [engineer-username]

拉取新的PR并更新已有档案。

Research Sources

数据来源

GitHub CLI Queries

GitHub CLI 查询

Pull Requests:

bash

gh pr list --author [username] --limit 100 --state all
gh pr view [pr-number] --json title,body,files,reviews,comments

Code Changes:

bash

gh pr diff [pr-number]
gh api repos/{owner}/{repo}/pulls/{pr}/files

Reviews:

bash

gh pr view [pr-number] --comments
gh api repos/{owner}/{repo}/pulls/{pr}/reviews

Commits:

bash

gh api search/commits --author [username]

Pull Request:

bash

gh pr list --author [username] --limit 100 --state all
gh pr view [pr-number] --json title,body,files,reviews,comments

代码变更:

bash

gh pr diff [pr-number]
gh api repos/{owner}/{repo}/pulls/{pr}/files

评审内容:

bash

gh pr view [pr-number] --comments
gh api repos/{owner}/{repo}/pulls/{pr}/reviews

提交记录:

bash

gh api search/commits --author [username]

Analysis Techniques

分析技术

Pattern Recognition:

Identify recurring code structures
Extract common solutions
Detect naming patterns
Find architectural choices

Style Extraction:

Analyze formatting consistency
Extract naming conventions
Identify comment patterns
Detect structural preferences

Best Practice Identification:

Look for testing patterns
Find error handling approaches
Identify security practices
Extract performance optimizations

模式识别:

识别反复出现的代码结构
提取通用解决方案
检测命名模式
提取架构选择

风格提取:

分析格式一致性
提取命名规范
识别注释模式
检测代码结构偏好

最佳实践识别:

查找测试模式
提取错误处理思路
识别安全实践
提取性能优化方案

Use Cases

使用场景

1. Onboarding New Engineers

1. 新工程师入职培训

Problem: New engineer needs to learn team standards Solution: Provide senior engineer's profile as reference

Benefits:

Real examples from codebase
Understand team conventions
See decision-making process
Learn best practices

问题： 新工程师需要学习团队标准 解决方案： 提供资深工程师的档案作为参考

收益：

来自代码库的真实示例
理解团队规范
了解决策流程
学习最佳实践

2. Code Review Training

2. Code Review培训

Problem: Teaching good code review skills Solution: Study experienced reviewer's feedback patterns

Benefits:

Learn what to look for
Understand feedback style
See common issues
Improve review quality

问题： 需要教授良好的Code Review技能 解决方案： 学习资深评审人员的反馈模式

收益：

了解评审时需要关注的点
理解反馈风格
认识常见问题
提升评审质量

3. Knowledge Transfer

3. 知识迁移

Problem: Senior engineer leaving, knowledge lost Solution: Extract their expertise before departure

Benefits:

Preserve tribal knowledge
Document decisions
Maintain code quality
Reduce bus factor

问题： 资深工程师离职会导致知识流失 解决方案： 在其离职前提取专业技能

收益：

留存团队隐性知识
归档决策逻辑
维持代码质量
降低bus factor

4. Establishing Team Standards

4. 建立团队标准

Problem: Inconsistent coding styles across team Solution: Extract patterns from best engineers, create standards

Benefits:

Evidence-based standards
Real-world examples
Buy-in from team
Consistent codebase

问题： 团队编码风格不统一 解决方案： 提取优秀工程师的编码模式，制定团队标准

收益：

基于实际案例的标准
真实场景示例
获得团队认可
代码库风格统一

5. AI Agent Training

5. AI Agent训练

Problem: Agent needs to code like specific engineer Solution: Provide extracted profile to agent

Benefits:

Match expert's style
Follow their patterns
Apply their best practices
Maintain consistency

问题： 需要Agent按照特定工程师的风格编码 解决方案： 为Agent提供提取好的工程师档案

收益：

匹配专家的编码风格
遵循其编码模式
应用其最佳实践
维持编码一致性

Profile Usage by Agents

Agent对档案的使用

When an agent has access to an engineer profile, it can:

Code Generation:

Follow extracted naming conventions
Use identified patterns
Apply documented best practices
Match architectural style

Code Review:

Provide feedback in engineer's style
Check for common issues they'd catch
Apply their quality standards
Match their priorities

Problem Solving:

Use their common solutions
Follow their architectural approach
Apply their design patterns
Consider their trade-offs

Example Agent Prompt:

"Using the profile at engineer_profiles/senior_dev/, write a user service
following their coding style, patterns, and best practices. Pay special
attention to their error handling approach and testing standards."

当Agent可以访问工程师档案时，它可以完成以下操作：

代码生成：

遵循提取的命名规范
使用识别到的编码模式
应用归档的最佳实践
匹配架构设计风格

Code Review：

按照工程师的风格提供反馈
检查专家通常会发现的常见问题
应用其质量标准
匹配其评审优先级

问题解决：

使用专家的通用解决方案
遵循其架构设计思路
应用其设计模式
参考其权衡考量

Agent提示词示例：

"Using the profile at engineer_profiles/senior_dev/, write a user service
following their coding style, patterns, and best practices. Pay special
attention to their error handling approach and testing standards."

Best Practices

使用最佳实践

Research Ethics

调研伦理

DO:

✅ Get permission before extracting
✅ Focus on public contributions
✅ Respect privacy
✅ Use for learning and improvement

DON'T:

❌ Extract without permission
❌ Share profiles externally
❌ Include sensitive information
❌ Use for performance reviews

允许的行为：

✅ 提取前获得许可
✅ 仅分析公开贡献
✅ 尊重隐私
✅ 用于学习和提升

禁止的行为：

❌ 未经许可提取
❌ 对外分享档案
❌ 包含敏感信息
❌ 用于绩效评估

Profile Maintenance

档案维护

Regular Updates:

Refresh every quarter
Add new significant PRs
Update with latest patterns
Archive outdated practices

Quality Control:

Verify extracted patterns
Review examples for relevance
Update documentation
Remove deprecated practices

定期更新：

每季度刷新一次
添加新的重要PR
更新最新的编码模式
归档过时的实践

质量控制：

验证提取的模式
检查示例的相关性
更新文档
移除已废弃的实践

Effective Usage

高效使用

For Learning:

Study patterns with context
Understand reasoning behind choices
Practice applying techniques
Ask questions when unclear

For Replication:

Start with style guide
Reference patterns for similar problems
Adapt to current context
Don't blindly copy

用于学习：

结合上下文学习编码模式
理解选择背后的原因
练习应用相关技术
遇到疑问时主动提问

用于复现：

从风格指南开始
参考类似问题的编码模式
适配当前场景
不要盲目复制

Limitations

局限性

What This Extracts:

✅ Coding style and conventions
✅ Common patterns and approaches
✅ Best practices and guidelines
✅ Architectural decisions
✅ Review feedback patterns

What This Doesn't Capture:

❌ Real-time problem-solving process
❌ Verbal communication style
❌ Meeting discussions
❌ Design phase thinking
❌ Interpersonal mentoring

可提取的内容：

✅ 编码风格和规范
✅ 通用编码模式和实现思路
✅ 最佳实践和开发准则
✅ 架构决策
✅ 评审反馈模式

无法提取的内容：

❌ 实时问题解决流程
❌ 口头沟通风格
❌ 会议讨论内容
❌ 设计阶段的思考
❌ 人际指导能力

Future Enhancements

未来优化方向

Potential additions:

Slack message analysis (communication style)
Design doc extraction (design thinking)
Meeting notes analysis (decision process)
Video analysis (pair programming sessions)
Code metrics tracking (evolution over time)

潜在的新增功能：

Slack消息分析（沟通风格）
设计文档提取（设计思路）
会议记录分析（决策流程）
视频分析（结对编程会话）
代码指标跟踪（能力随时间的变化）

Example Output

输出示例

engineer_profiles/
└── senior_dev/
    ├── README.md
    │   # Senior Dev - Staff Engineer
    │   Expertise: TypeScript, Node.js, System Design
    │   Focus: API design, performance optimization
    │
    ├── coding_style/
    │   ├── typescript_style.md
    │   ├── naming_conventions.md
    │   └── code_structure.md
    │
    ├── patterns/
    │   ├── dependency_injection.md
    │   ├── error_handling.md
    │   └── examples/
    │       ├── service_pattern.ts
    │       └── repository_pattern.ts
    │
    ├── best_practices/
    │   ├── testing_strategy.md
    │   ├── code_quality.md
    │   └── performance.md
    │
    ├── architecture/
    │   ├── api_design.md
    │   ├── database_design.md
    │   └── scaling_approach.md
    │
    ├── code_review/
    │   ├── feedback_examples.md
    │   └── review_checklist.md
    │
    └── examples/
        └── notable_prs/
            ├── pr_1234_auth_refactor.md
            └── pr_5678_performance_fix.md

engineer_profiles/
└── senior_dev/
    ├── README.md
    │   # Senior Dev - Staff Engineer
    │   Expertise: TypeScript, Node.js, System Design
    │   Focus: API design, performance optimization
    │
    ├── coding_style/
    │   ├── typescript_style.md
    │   ├── naming_conventions.md
    │   └── code_structure.md
    │
    ├── patterns/
    │   ├── dependency_injection.md
    │   ├── error_handling.md
    │   └── examples/
    │       ├── service_pattern.ts
    │       └── repository_pattern.ts
    │
    ├── best_practices/
    │   ├── testing_strategy.md
    │   ├── code_quality.md
    │   └── performance.md
    │
    ├── architecture/
    │   ├── api_design.md
    │   ├── database_design.md
    │   └── scaling_approach.md
    │
    ├── code_review/
    │   ├── feedback_examples.md
    │   └── review_checklist.md
    │
    └── examples/
        └── notable_prs/
            ├── pr_1234_auth_refactor.md
            └── pr_5678_performance_fix.md

Summary

总结

This skill transforms an engineer's GitHub contributions into a structured, reusable knowledge base. It captures their expertise in a format that:

Humans can learn from - Clear documentation with examples
Agents can replicate - Structured patterns and guidelines
Teams can adopt - Evidence-based best practices
Organizations can preserve - Knowledge that survives turnover

The goal: Make expertise scalable, learnable, and replicable.

"The best way to learn is from those who have already mastered it."

该技能将工程师的GitHub贡献转化为结构化、可复用的知识库。它收录的专业技能可以满足以下需求：

可供人类学习 - 带示例的清晰文档
可供Agent复现 - 结构化的模式和准则
可供团队采纳 - 基于实际案例的最佳实践
可供组织留存 - 不受人员变动影响的知识资产

目标： 让专业技能可规模化、可学习、可复现。

「最好的学习方式是向已经掌握技能的人学习。」