Back to Details

interview-master

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Interview Master - Comprehensive Career & Interview Assistant

Interview Master - 全方位职业与面试助手

Purpose

用途

Interview Master is a specialized skill that provides end-to-end support for technical interview preparation and career development. It serves both job seekers preparing for interviews and interviewers designing effective assessments. The skill's unique capability is generating professional resumes by analyzing git commit history to extract technical skills, project impact, and contributions.
Interview Master是一款为技术面试准备和职业发展提供端到端支持的专业Skill。它既服务于准备面试的求职者，也服务于设计有效评估方案的面试官。该Skill的独特功能是通过分析Git提交历史，提取技术技能、项目影响力和贡献，生成专业简历。

When to Use This Skill

适用场景

Use this skill when:
  • Generating interview questions for specific roles or seniority levels
  • Preparing for technical interviews (algorithms, system design, behavioral)
  • Optimizing or reviewing resume content
  • Conducting mock interviews with realistic scenarios
  • Analyzing git repositories to generate resume content
  • Extracting technical expertise and project contributions from code history
  • Creating interview preparation roadmaps
  • Evaluating candidate technical skills through code analysis
在以下场景中使用本Skill：
  • 为特定岗位或职级生成面试问题
  • 准备技术面试（算法、系统设计、行为面试）
  • 优化或评审简历内容
  • 开展贴近真实场景的模拟面试
  • 分析Git仓库以生成简历内容
  • 从代码历史中提取技术能力和项目贡献
  • 制定面试准备路线图
  • 通过代码分析评估候选人的技术能力

Core Capabilities

核心能力

1. Interview Question Generation

1. 面试问题生成

Generate role-specific interview questions tailored to position requirements, seniority level, and technical stack.
Process:
  1. Identify target role, seniority (junior/mid/senior/staff), and tech stack
  2. Consult 
    references/interview-questions-bank.md
    for question patterns
  3. Generate questions across categories:
    • Technical fundamentals
    • Problem-solving and algorithms
    • System design (for senior+ roles)
    • Behavioral and situational
    • Role-specific deep dives
  4. Include follow-up questions and evaluation criteria
  5. Provide answer guidelines for interviewers
Typical output includes 10-15 questions with difficulty ratings, estimated time, and evaluation rubrics.
根据岗位要求、职级和技术栈生成针对性的面试问题。
流程：
  1. 确定目标岗位、职级（初级/中级/高级/资深）和技术栈
  2. 参考
    references/interview-questions-bank.md
    中的问题模板
  3. 生成多类问题：
    • 技术基础知识
    • 问题解决与算法
    • 系统设计（面向资深及以上职级）
    • 行为与情景类
    • 岗位深度挖掘类
  4. 包含跟进问题和评估标准
  5. 为面试官提供答题指导
典型输出包含10-15个带有难度评级、预计时长和评估细则的问题。

2. Resume Optimization

2. 简历优化

Analyze and improve resume content for technical roles with actionable feedback.
Process:
  1. Review resume structure, formatting, and content
  2. Reference 
    references/resume-best-practices.md
    for industry standards
  3. Evaluate:
    • Technical skills presentation
    • Project descriptions and impact metrics
    • Achievement quantification
    • ATS (Applicant Tracking System) compatibility
    • Keyword optimization for target roles
  4. Provide specific improvement suggestions with before/after examples
  5. Check for common mistakes (typos, inconsistent formatting, vague descriptions)
Consult 
examples/good-resume-examples.md
for reference patterns.
分析并改进技术岗位的简历内容，提供可落地的反馈建议。
流程：
  1. 审核简历结构、格式和内容
  2. 参考
    references/resume-best-practices.md
    中的行业标准
  3. 评估维度：
    • 技术技能呈现方式
    • 项目描述与影响力指标
    • 成果量化程度
    • ATS（Applicant Tracking System，求职者跟踪系统）兼容性
    • 目标岗位的关键词优化
  4. 提供具体的改进建议及前后对比示例
  5. 检查常见问题（拼写错误、格式不一致、描述模糊）
可参考
examples/good-resume-examples.md
中的模板。

3. Mock Interview Simulation

3. 模拟面试仿真

Conduct realistic mock interviews with real-time feedback and performance evaluation.
Process:
  1. Establish interview context (role, company type, interview stage)
  2. Reference 
    references/interview-flow.md
    for realistic pacing
  3. Ask questions progressively, adapting difficulty based on responses
  4. Provide hints if candidate struggles
  5. Evaluate responses on:
    • Technical accuracy
    • Communication clarity
    • Problem-solving approach
    • Time management
  6. Deliver constructive feedback with improvement areas
See 
examples/mock-interview-dialogue.md
for interaction patterns.
开展贴近真实的模拟面试，提供实时反馈和表现评估。
流程：
  1. 确定面试背景（岗位、公司类型、面试阶段）
  2. 参考
    references/interview-flow.md
    中的真实面试节奏
  3. 逐步提出问题，根据回答调整难度
  4. 当候选人遇到困难时提供提示
  5. 从以下维度评估回答：
    • 技术准确性
    • 表达清晰度
    • 问题解决思路
    • 时间管理能力
  6. 提供带有改进方向的建设性反馈
可查看
examples/mock-interview-dialogue.md
中的交互示例。

4. Git-Based Resume Generation (Signature Feature)

4. 基于Git的简历生成（核心特色功能）

Analyze git commit history to automatically generate resume content highlighting technical contributions and project impact.
Workflow:
Step 1: Collect Repository Information
  • Identify target repository path
  • Determine author name/email to analyze
  • Specify time range (optional, default: all history)
Step 2: Execute Analysis Scripts
Use the following scripts in sequence:
  1. scripts/analyze-commits.sh
     - Extract commit history
    bash
    ./scripts/analyze-commits.sh <author> <repo-path> [start-date] [end-date]
    Output: Commit count, frequency, file change patterns
  2. scripts/extract-tech-stack.sh
     - Identify technologies
    bash
    ./scripts/extract-tech-stack.sh <repo-path> <author>
    Output: Programming languages, frameworks, tools detected from code changes Reference: 
    references/tech-stack-keywords.md
    for keyword matching
  3. scripts/calculate-impact.py
     - Quantify contributions
    bash
    python scripts/calculate-impact.py <repo-path> <author>
    Output: Lines added/removed, files modified, feature-critical commits Reference: 
    references/project-impact-metrics.md
    for impact calculation
  4. scripts/generate-resume-data.sh
     - Aggregate results
    bash
    ./scripts/generate-resume-data.sh <author> <repo-path>
    Output: Structured JSON with resume-ready content
Step 3: Generate Resume Content
Transform analysis into professional resume sections:
  1. Technical Skills Section
    • Group technologies by category (languages, frameworks, tools, databases)
    • Prioritize by usage frequency and recency
  2. Project Experience Section
    • Identify major features/modules from commit messages
    • Quantify impact (e.g., "Developed authentication system handling 10K+ daily users")
    • Highlight technical challenges solved
    • Use action verbs: "Architected", "Implemented", "Optimized", "Refactored"
  3. Key Achievements
    • Extract notable contributions (large refactors, performance improvements, critical bug fixes)
    • Convert git data to business impact when possible
    • Include metrics from 
      references/project-impact-metrics.md
Step 4: Format and Review
  • Apply 
    assets/resume-template.md
    structure
  • Ensure ATS compatibility (plain text format, standard section headings)
  • Cross-reference with 
    examples/good-resume-examples.md
    for quality standards
  • Validate technical terminology accuracy
Example Usage:
User: "Analyze my commits in this repository and generate resume content"
Assistant:
1. Runs analyze-commits.sh to get 247 commits over 18 months
2. Extracts tech stack: React, TypeScript, Node.js, PostgreSQL, Docker
3. Calculates impact: 15K lines added, 12 major features
4. Generates resume section:
   "Software Engineer | E-commerce Platform (Jan 2023 - Present)
   - Architected and implemented user authentication system using JWT and OAuth 2.0, serving 50K+ daily active users
   - Developed RESTful API with Node.js and Express, improving response time by 40% through query optimization
   - Built responsive admin dashboard with React and TypeScript, reducing content management time by 60%
   - Containerized application with Docker, enabling consistent deployment across 3 environments"
分析Git提交历史，自动生成突出技术贡献和项目影响力的简历内容。
工作流：
步骤1：收集仓库信息
  • 确定目标仓库路径
  • 指定要分析的作者姓名/邮箱
  • 设置时间范围（可选，默认：全部历史）
步骤2：执行分析脚本
按顺序使用以下脚本：
  1. scripts/analyze-commits.sh
     - 提取提交历史
    bash
    ./scripts/analyze-commits.sh <author> <repo-path> [start-date] [end-date]
    输出：提交数量、频率、文件变更模式
  2. scripts/extract-tech-stack.sh
     - 识别技术栈
    bash
    ./scripts/extract-tech-stack.sh <repo-path> <author>
    输出：从代码变更中检测到的编程语言、框架、工具 参考：
    references/tech-stack-keywords.md
    中的关键词匹配规则
  3. scripts/calculate-impact.py
     - 量化贡献值
    bash
    python scripts/calculate-impact.py <repo-path> <author>
    输出：新增/删除代码行数、修改文件数、核心功能提交 参考：
    references/project-impact-metrics.md
    中的影响力计算标准
  4. scripts/generate-resume-data.sh
     - 聚合分析结果
    bash
    ./scripts/generate-resume-data.sh <author> <repo-path>
    输出：符合简历格式的结构化JSON数据
步骤3：生成简历内容
将分析结果转换为专业的简历模块：
  1. 技术技能模块
    • 按类别分组技术栈（语言、框架、工具、数据库）
    • 根据使用频率和时效性排序
  2. 项目经验模块
    • 从提交信息中识别主要功能/模块
    • 量化影响力（例如：「基于JWT和OAuth 2.0实现用户认证系统，服务5万+日活跃用户」）
    • 突出解决的技术难题
    • 使用动作动词：「架构设计」「实现开发」「性能优化」「代码重构」
  3. 核心成就模块
    • 提取显著贡献（大型重构、性能提升、关键Bug修复）
    • 尽可能将Git数据转化为业务价值
    • 参考
      references/project-impact-metrics.md
      中的指标
步骤4：格式调整与审核
  • 应用
    assets/resume-template.md
    的结构
  • 确保ATS兼容性（纯文本格式、标准模块标题）
  • 对照
    examples/good-resume-examples.md
    的质量标准
  • 验证技术术语的准确性
使用示例：
用户：「分析我在这个仓库的提交记录并生成简历内容」
助手：
1. 运行analyze-commits.sh获取18个月内的247条提交记录
2. 提取技术栈：React、TypeScript、Node.js、PostgreSQL、Docker
3. 计算影响力：新增1.5万行代码、完成12个核心功能
4. 生成简历模块：
   "软件工程师 | 电商平台（2023年1月 - 至今）
   - 基于JWT和OAuth 2.0架构并实现用户认证系统，服务5万+日活跃用户
   - 使用Node.js和Express开发RESTful API，通过查询优化将响应时间提升40%
   - 基于React和TypeScript构建响应式管理后台，将内容管理时间缩短60%
   - 使用Docker容器化应用，实现3个环境的一致部署"

5. Interview Preparation Guidance

5. 面试准备指导

Create personalized preparation roadmaps for technical interviews.
Process:
  1. Assess candidate current level and target role
  2. Generate study plan covering:
    • Algorithm and data structures (reference: 
      references/algorithm-prep.md
      )
    • System design concepts (reference: 
      references/system-design-prep.md
      )
    • Behavioral interview techniques (reference: 
      references/behavioral-interview.md
      )
  3. Provide timeline-based milestones (2 weeks, 1 month, 3 months)
  4. Include practice resources and mock interview schedules
  5. Track preparation progress and adjust plan
为技术面试制定个性化的准备路线图。
流程：
  1. 评估候选人当前水平和目标岗位
  2. 生成包含以下内容的学习计划：
    • 算法与数据结构（参考：
      references/algorithm-prep.md
      ）
    • 系统设计概念（参考：
      references/system-design-prep.md
      ）
    • 行为面试技巧（参考：
      references/behavioral-interview.md
      ）
  3. 提供基于时间线的里程碑（2周、1个月、3个月）
  4. 包含练习资源和模拟面试安排
  5. 跟踪准备进度并调整计划

Workflow Integration

工作流集成

For Job Seekers

面向求职者

  1. Resume Generation: Run git analysis on personal projects → generate technical resume content
  2. Resume Optimization: Review generated/existing resume → receive improvement suggestions
  3. Interview Prep: Follow preparation roadmap → practice with mock interviews
  4. Mock Interview: Conduct simulated interview → receive feedback → iterate
  1. 简历生成：对个人项目仓库执行Git分析 → 生成技术简历内容
  2. 简历优化：评审生成/现有简历 → 获取改进建议
  3. 面试准备：遵循准备路线图 → 通过模拟面试练习
  4. 模拟面试：开展仿真面试 → 获取反馈 → 迭代提升

For Interviewers

面向面试官

  1. Question Design: Specify role requirements → generate tailored question set
  2. Evaluation Framework: Use provided rubrics → standardize candidate assessment
  3. Interview Calibration: Reference mock interview examples → align interview style
  1. 问题设计：明确岗位要求 → 生成针对性问题集
  2. 评估框架：使用提供的评分细则 → 标准化候选人评估
  3. 面试校准：参考模拟面试示例 → 统一面试风格

Additional Resources

额外资源

Reference Files

参考文件

Detailed guides and knowledge bases:
  • references/interview-questions-bank.md
     - Comprehensive question library by role and category
  • references/resume-best-practices.md
     - Industry-standard resume writing guidelines
  • references/algorithm-prep.md
     - Algorithm interview preparation roadmap
  • references/system-design-prep.md
     - System design concepts and practice problems
  • references/behavioral-interview.md
     - STAR method and behavioral question patterns
  • references/tech-stack-keywords.md
     - Technology keyword database for code analysis
  • references/project-impact-metrics.md
     - Impact quantification standards
详细指南与知识库：
  • references/interview-questions-bank.md
     - 按岗位和类别划分的全面问题库
  • references/resume-best-practices.md
     - 行业标准的简历撰写指南
  • references/algorithm-prep.md
     - 算法面试准备路线图
  • references/system-design-prep.md
     - 系统设计概念与练习题
  • references/behavioral-interview.md
     - STAR法则与行为问题模板
  • references/tech-stack-keywords.md
     - 用于代码分析的技术关键词库
  • references/project-impact-metrics.md
     - 影响力量化标准

Example Files

示例文件

Working examples and templates:
  • examples/good-resume-examples.md
     - High-quality resume samples for various roles
  • examples/interview-questions-set.md
     - Complete interview question sets
  • examples/mock-interview-dialogue.md
     - Realistic interview conversation flows
  • examples/git-analysis-output.json
     - Sample git analysis results
实用示例与模板：
  • examples/good-resume-examples.md
     - 适用于各类岗位的高质量简历样本
  • examples/interview-questions-set.md
     - 完整的面试问题集
  • examples/mock-interview-dialogue.md
     - 贴近真实的面试对话流程
  • examples/git-analysis-output.json
     - Git分析结果样本

Script Utilities

脚本工具

Automation tools for git analysis:
  • scripts/analyze-commits.sh
     - Extract commit history and patterns
  • scripts/extract-tech-stack.sh
     - Identify technologies from codebase
  • scripts/calculate-impact.py
     - Quantify code contributions and impact
  • scripts/generate-resume-data.sh
     - Aggregate analysis into resume format
用于Git分析的自动化工具：
  • scripts/analyze-commits.sh
     - 提取提交历史与模式
  • scripts/extract-tech-stack.sh
     - 从代码库中识别技术栈
  • scripts/calculate-impact.py
     - 量化代码贡献与影响力
  • scripts/generate-resume-data.sh
     - 将分析结果聚合为简历格式

Asset Templates

资产模板

Ready-to-use templates:
  • assets/resume-template.md
     - Markdown resume template
  • assets/resume-template.json
     - Structured resume data schema
可直接使用的模板：
  • assets/resume-template.md
     - Markdown简历模板
  • assets/resume-template.json
     - 结构化简历数据 schema

Best Practices

最佳实践

  1. Resume Generation: Always validate generated content for accuracy; git commits may contain technical jargon that needs business-friendly translation
  2. Interview Questions: Adapt difficulty to candidate level; avoid questions beyond role requirements
  3. Mock Interviews: Maintain realistic pacing; provide hints before revealing answers
  4. Feedback Delivery: Be constructive and specific; focus on actionable improvements
  5. Privacy: When analyzing git history, ensure proper authorization; anonymize sensitive project details if needed
  1. 简历生成：务必验证生成内容的准确性；Git提交中可能包含技术术语，需要转化为业务友好的表述
  2. 面试问题：根据候选人水平调整难度；避免提出超出岗位要求的问题
  3. 模拟面试：保持贴近真实的节奏；在公布答案前先提供提示
  4. 反馈传递：保持建设性和针对性；聚焦可落地的改进方向
  5. 隐私保护：分析Git历史时确保获得合法授权；如有需要，匿名化敏感项目细节

Common Use Cases

常见用例

Scenario 1: Junior Developer Seeking First Role
  • Generate resume from university project repositories
  • Focus on technical skills and learning trajectory
  • Provide entry-level interview prep roadmap
Scenario 2: Senior Engineer Career Transition
  • Analyze contributions across multiple projects
  • Highlight system design and architecture work
  • Prepare for staff-level system design interviews
Scenario 3: Hiring Manager Building Interview Process
  • Generate role-specific question bank
  • Establish evaluation criteria
  • Calibrate interview difficulty
Scenario 4: Career Switcher with Limited Resume Content
  • Mine git history for hidden technical achievements
  • Quantify impact of side projects
  • Frame bootcamp/self-taught experience professionally
场景1：寻求首份工作的初级开发者
  • 从大学项目仓库生成简历
  • 聚焦技术技能和学习轨迹
  • 提供入门级面试准备路线图
场景2：寻求职业转型的资深工程师
  • 分析多个项目中的贡献
  • 突出系统设计与架构工作
  • 准备资深职级的系统设计面试
场景3：搭建面试流程的招聘经理
  • 生成岗位专属问题库
  • 建立评估标准
  • 校准面试难度
场景4：简历内容有限的转行人士
  • 从Git历史中挖掘隐藏的技术成果
  • 量化副业项目的影响力
  • 专业呈现训练营/自学经历

Technical Requirements

技术要求

  • Git access: Scripts require read access to target repositories
  • Shell environment: Bash 4.0+ for shell scripts
  • Python 3.8+: For impact calculation script
  • Git command-line: Version 2.20+ installed
  • Git访问权限：脚本需要目标仓库的读权限
  • Shell环境：Bash 4.0+（用于执行Shell脚本）
  • Python 3.8+：用于运行影响力计算脚本
  • Git命令行工具：安装2.20+版本

Limitations

局限性

  • Git analysis quality depends on commit message clarity; vague messages yield less useful insights
  • Cannot access private repositories without proper authentication
  • Project impact quantification is heuristic-based; manual validation recommended
  • Generated resume content requires human review for context and accuracy
  • Git分析质量取决于提交信息的清晰度；模糊的提交信息会降低分析价值
  • 无合法授权时无法访问私有仓库
  • 项目影响力量化基于启发式规则；建议人工验证
  • 生成的简历内容需要人工审核以确保上下文准确性