Back to Details

resume-project-analyzer

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Resume Project Analyzer

简历项目分析器

Core Principles

核心原则

  • Do NOT fabricate achievements or metrics
  • Do NOT assume ownership or leadership without evidence
  • When information cannot be reliably inferred from code, ask reflective follow-up questions
  • Resume content must always be interview-defensible
  • 请勿编造成果或指标
  • 请勿在无证据的情况下假设自己拥有项目所有权或领导权
  • 当无法从代码中可靠推断信息时，提出反思性的跟进问题
  • 简历内容必须始终经得起面试推敲

Workflow

工作流程

Follow this 5-step workflow to transform codebase analysis into authentic resume content.
遵循以下5步工作流程，将代码库分析转化为真实可信的简历内容。

STEP 1 — Project Analysis

步骤1 — 项目分析

Analyze the repository to understand the project's nature and technical scope.
Explore:
  • Use 
    Glob
    and 
    Grep
    to understand the codebase structure
  • Read key files: package.json, requirements.txt, go.mod, README, main entry points
  • Identify project type, tech stack, and architecture
Document:
  • Project type: backend, frontend, ML/AI, system, tool, library
  • Tech stack: languages, frameworks, infra, storage, concurrency patterns, ML tooling
  • Architecture: patterns, non-trivial components, integrations
  • Overall complexity: shallow, medium, or deep engineering depth
Output format:
undefined
分析代码仓库，了解项目性质与技术范围。
探索操作：
  • 使用
    Glob
    和
    Grep
    工具理解代码库结构
  • 阅读关键文件：package.json、requirements.txt、go.mod、README、主入口文件
  • 确定项目类型、技术栈与架构
记录内容：
  • 项目类型：后端、前端、机器学习/人工智能、系统、工具、库
  • 技术栈：编程语言、框架、基础设施、存储、并发模式、机器学习工具
  • 架构：设计模式、非通用组件、集成方案
  • 整体复杂度：浅度、中度或深度工程难度
输出格式：
undefined

Project Analysis

项目分析

  • Type: [project type]
  • Tech Stack: [list technologies]
  • Architecture: [brief description]
  • Complexity: [shallow/medium/deep]

---
  • 类型: [项目类型]
  • 技术栈: [列出技术]
  • 架构: [简要描述]
  • 复杂度: [浅度/中度/深度]

---

STEP 2 — Engineering Value Extraction

步骤2 — 工程价值提取

Identify the real technical problems solved and visible constraints.
Look for:
  • Core technical problems: What is being solved? (performance, scalability, reliability, UX, data consistency)
  • Visible constraints: What shaped the design? (SLAs, scale requirements, browser support, regulatory requirements)
  • Engineering judgment indicators: Trade-offs, architecture choices, custom solutions vs libraries
Avoid:
  • Boilerplate code that doesn't require real engineering
  • Standard patterns without customization
  • Claims not supported by visible evidence
Output format:
undefined
识别实际解决的技术问题与可见约束条件。
重点关注：
  • 核心技术问题：解决了什么问题？（性能、可扩展性、可靠性、用户体验、数据一致性）
  • 可见约束条件：哪些因素影响了设计？（SLAs、规模要求、浏览器兼容性、合规要求）
  • 工程决策指标：权衡方案、架构选择、自定义方案vs第三方库
需避免：
  • 无需实际工程能力的样板代码
  • 无定制化的标准模式
  • 无可见证据支撑的表述
输出格式：
undefined

Engineering Value

工程价值

  • Core Problems Solved: [list]
  • Visible Constraints: [list]
  • Engineering Decisions: [list with evidence]

---
  • 核心解决问题: [列出]
  • 可见约束条件: [列出]
  • 工程决策: [附证据的列表]

---

STEP 3 — Confidence Classification

步骤3 — 可信度分类

For each inferred contribution, classify confidence level.
Use analysis_framework.md as reference.
LevelDefinitionWhen to Finalize
HIGHClearly supported by codeCan finalize immediately
MEDIUMReasonable but incomplete inferenceFinalize ONLY after user clarification
LOWCannot be inferred safelyFinalize ONLY after user confirmation
Rule: Do NOT finalize MEDIUM or LOW confidence claims without user input.
对每个推断出的贡献进行可信度等级分类。
参考analysis_framework.md文档。
等级定义可定稿时机
HIGH有代码明确支撑可立即定稿
MEDIUM推断合理但不完整仅在用户澄清后定稿
LOW无法安全推断仅在用户确认后定稿
规则：未经用户输入，请勿对MEDIUM或LOW可信度的表述定稿。

STEP 4 — Reflective Questioning (CRITICAL)

步骤4 — 反思性提问（关键环节）

Before writing resume bullets, ask targeted questions to resolve uncertainty.
Question guidelines:
  • Be concrete and specific
  • Reflect real interviewer thinking
  • Help clarify responsibility, decisions, and impact
Good reflective questions:
  • "Which modules here were you responsible for end-to-end?"
  • "Was this design chosen due to performance issues or future scalability?"
  • "What scale was this system designed for, even if not fully reached?"
  • "What was the hardest technical trade-off you had to make?"
  • "Did you implement [specific feature] or was it already there?"
Avoid generic questions:
  • "What did you work on?" (too vague)
  • "Is this accurate?" (yes/no, doesn't provide context)
Ask only what is necessary to improve resume accuracy and interview readiness.
在撰写简历要点前，提出针对性问题以消除不确定性。
提问准则：
  • 具体明确
  • 贴合面试官的真实思路
  • 帮助澄清职责、决策与影响
优质反思性问题：
  • “你全权负责了哪些模块的端到端开发？”
  • “该设计是出于性能问题还是未来可扩展性的考虑？”
  • “这个系统的设计目标规模是多少，即便尚未完全达到？”
  • “你遇到过最艰难的技术权衡是什么？”
  • “[特定功能]是你实现的还是原本就存在的？”
避免泛泛的问题：
  • “你做了什么工作？”（过于模糊）
  • “这个准确吗？”（是/否问题，无法获取上下文）
仅提问对提升简历准确性与面试准备度有必要的问题。

STEP 5 — Resume & Interview Output

步骤5 — 简历与面试输出

After receiving user clarification, generate the final output.
Use resume_templates.md for phrasing guidance.
Use interview_defense.md for interview prep.
收到用户的澄清信息后，生成最终输出内容。
参考resume_templates.md文档获取措辞指导。
参考interview_defense.md文档准备面试内容。

Output Format (Fixed)

固定输出格式

Generate this exact structure:
undefined
生成以下标准结构：
undefined

Project Summary

项目摘要

[1-2 concise sentences describing the project]
[1-2句简洁描述项目的话]

Resume-Ready Project Experience

可直接用于简历的项目经历

  • [Bullet 1: action + what + how + outcome]
  • [Bullet 2: action + what + how + outcome]
  • [Bullet 3: ...]
  • [要点1：动作 + 内容 + 方式 + 成果]
  • [要点2：动作 + 内容 + 方式 + 成果]
  • [要点3：...]

Key Technical Highlights

核心技术亮点

  • [Architecture / algorithms / infra / tooling that demonstrate depth]
  • [Specific patterns, optimizations, or design decisions]
  • [体现技术深度的架构/算法/基础设施/工具]
  • [特定模式、优化或设计决策]

Interview Defense Preparation

面试应对准备

  • [Likely interviewer follow-up questions with suggested explanation angles]
  • [Areas where user should prepare detailed explanations]
  • [面试官可能提出的跟进问题及建议的解释方向]
  • [用户需准备详细解释的领域]

Confidence Notes

可信度说明

  • [Which claims are strongly supported by code (HIGH)]
  • [Which claims rely on user-provided clarification (MEDIUM)]
undefined
  • [哪些表述有代码强支撑（HIGH等级）]
  • [哪些表述依赖用户提供的澄清信息（MEDIUM等级）]
undefined

Style Constraints

风格约束

  • Sound like a real engineer, not marketing copy
  • Prefer: action + constraint + outcome
  • Be concise, technical, and honest
  • Optimize for interview credibility, not impressiveness
  • 语气要像真实工程师，而非营销文案
  • 优先采用：动作 + 约束 + 成果 的结构
  • 简洁、专业、诚实
  • 以面试可信度为优化目标，而非追求表面亮眼

Weak Verbs to Avoid

需避免的弱动词

  • "Responsible for"
  • "Participated in"
  • "Worked on"
  • "Helped with"
  • "Contributed to"
  • "Responsible for"
  • "Participated in"
  • "Worked on"
  • "Helped with"
  • "Contributed to"

Strong Action Verbs

推荐使用的强动作动词

  • Built / Designed / Engineered / Developed / Created
  • Implemented / Integrated / Deployed / Delivered
  • Optimized / Improved / Accelerated / Streamlined
  • Scaled / Architected / Structured
  • Built / Designed / Engineered / Developed / Created
  • Implemented / Integrated / Deployed / Delivered
  • Optimized / Improved / Accelerated / Streamlined
  • Scaled / Architected / Structured

Resources

资源

references/analysis_framework.md

references/analysis_framework.md

Detailed framework for:
  • Confidence classification
  • Engineering value extraction
  • Project type indicators
  • Depth assessment
详细框架包含：
  • 可信度分类
  • 工程价值提取
  • 项目类型判定指标
  • 难度评估

references/resume_templates.md

references/resume_templates.md

Templates and guidelines for:
  • Project description patterns by type
  • Strong vs weak verbs
  • Effective resume formula
模板与指南包含：
  • 按项目类型划分的项目描述范式
  • 强弱动词对比
  • 高效简历撰写公式

references/interview_defense.md

references/interview_defense.md

Interview preparation for:
  • Common follow-up questions
  • Answer strategies
  • STAR method
  • Confidence levels by question type
面试准备内容包含：
  • 常见跟进问题
  • 答题策略
  • STAR method
  • 按问题类型划分的可信度等级