resume-tailoring

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Resume Tailoring Skill

简历定制技能

Overview

概述

Generates high-quality, tailored resumes optimized for specific job descriptions while maintaining factual integrity. Builds resumes around the holistic person by surfacing undocumented experiences through conversational discovery.

Core Principle: Truth-preserving optimization - maximize fit while maintaining factual integrity. Never fabricate experience, but intelligently reframe and emphasize relevant aspects.

Mission: A person's ability to get a job should be based on their experiences and capabilities, not on their resume writing skills.

生成高质量、贴合特定职位描述的定制化简历，同时严格保持事实准确性。通过对话式挖掘发掘未记录的经历，围绕求职者的整体背景打造简历。

核心原则： 保真优化——在保持事实准确的前提下最大化简历与职位的匹配度。绝不编造经历，但可智能重构并突出相关内容。

使命： 求职者获得工作的能力应基于自身的经历与能力，而非简历撰写技巧。

When to Use

适用场景

Use this skill when:

User provides a job description and wants a tailored resume
User has multiple existing resumes in markdown format
User wants to optimize their application for a specific role/company
User needs help surfacing and articulating undocumented experiences

DO NOT use for:

Generic resume writing from scratch (user needs existing resume library)
Cover letters (different skill)
LinkedIn profile optimization (different skill)

在以下场景使用本技能：

用户提供职位描述，需要定制化简历
用户拥有多份Markdown格式的现有简历
用户希望针对特定职位/公司优化求职申请材料
用户需要帮助发掘并表述未记录的经历

禁止用于：

从零开始撰写通用简历（用户需已有简历库）
求职信撰写（对应其他技能）
LinkedIn档案优化（对应其他技能）

Quick Start

快速开始

Required from user:

Job description (text or URL)
Resume library location (defaults to
```
resumes/
```
in current directory)

Workflow:

Build library from existing resumes
Research company/role
Create template (with user checkpoint)
Optional: Branching experience discovery
Match content with confidence scoring
Generate MD + DOCX + PDF + Report
User review → Optional library update

需用户提供：

职位描述（文本或URL）
简历库位置（默认当前目录下的
```
resumes/
```
文件夹）

工作流程：

基于现有简历构建简历库
研究目标公司/职位
创建简历模板（需用户确认）
可选：分支式经历挖掘
内容匹配并给出置信度评分
生成MD + DOCX + PDF + 报告格式的文件
用户审核 → 可选更新简历库

Implementation

实现细节

See supporting files:

```
research-prompts.md
```
- Structured prompts for company/role research
```
matching-strategies.md
```
- Content matching algorithms and scoring
```
branching-questions.md
```
- Experience discovery conversation patterns

参考支持文件：

```
research-prompts.md
```
- 用于公司/职位研究的结构化提示词
```
matching-strategies.md
```
- 内容匹配算法与评分规则
```
branching-questions.md
```
- 经历挖掘的对话模式

Workflow Details

工作流程详情

Multi-Job Detection

多职位检测

Triggers when user provides:

Multiple JD URLs (comma or newline separated)
Phrases: "multiple jobs", "several positions", "batch", "3 jobs"
List of companies/roles: "Microsoft PM, Google TPM, AWS PM"

Detection Logic:

python

undefined

触发条件：用户提供以下内容时

多个JD URL（逗号或换行分隔）
相关表述："multiple jobs"、"several positions"、"batch"、"3 jobs"
公司/职位列表："Microsoft PM, Google TPM, AWS PM"

检测逻辑：

python

undefined

Pseudo-code

伪代码

def detect_multi_job(user_input): indicators = [ len(extract_urls(user_input)) > 1, any(phrase in user_input.lower() for phrase in ["multiple jobs", "several positions", "batch of", "3 jobs", "5 jobs"]), count_company_mentions(user_input) > 1 ] return any(indicators)


**If detected:**

"I see you have multiple job applications. Would you like to use multi-job mode?

BENEFITS:

Shared experience discovery (faster - ask questions once for all jobs)
Batch processing with progress tracking
Incremental additions (add more jobs later)

TIME COMPARISON (3 similar jobs):

Sequential single-job: ~45 minutes (15 min × 3)
Multi-job mode: ~40 minutes (15 min discovery + 8 min per job)

Use multi-job mode? (Y/N)"


**If user confirms Y:**
- Use multi-job workflow (see multi-job-workflow.md)

**If user confirms N or single job detected:**
- Use existing single-job workflow (Phase 0 onwards)

**Backward Compatibility:** Single-job workflow completely unchanged.

**Multi-Job Workflow:**

When multi-job mode is activated, see `multi-job-workflow.md` for complete workflow.

**High-Level Multi-Job Process:**

┌─────────────────────────────────────────────────────────────┐ │ PHASE 0: Intake & Batch Initialization │ │ - Collect 3-5 job descriptions │ │ - Initialize batch structure │ │ - Run library initialization (once) │ └─────────────────────────────────────────────────────────────┘ ↓ ┌─────────────────────────────────────────────────────────────┐ │ PHASE 1: Aggregate Gap Analysis │ │ - Extract requirements from all JDs │ │ - Cross-reference against library │ │ - Build unified gap map (deduplicate) │ │ - Prioritize: Critical → Important → Job-specific │ └─────────────────────────────────────────────────────────────┘ ↓ ┌─────────────────────────────────────────────────────────────┐ │ PHASE 2: Shared Experience Discovery │ │ - Single branching interview covering ALL gaps │ │ - Multi-job context for each question │ │ - Tag experiences with job relevance │ │ - Enrich library with discoveries │ └─────────────────────────────────────────────────────────────┘ ↓ ┌─────────────────────────────────────────────────────────────┐ │ PHASE 3: Per-Job Processing (Sequential) │ │ For each job: │ │ ├─ Research (company + role benchmarking) │ │ ├─ Template generation │ │ ├─ Content matching (uses enriched library) │ │ └─ Generation (MD + DOCX + Report) │ │ Interactive or Express mode │ └─────────────────────────────────────────────────────────────┘ ↓ ┌─────────────────────────────────────────────────────────────┐ │ PHASE 4: Batch Finalization │ │ - Generate batch summary │ │ - User reviews all resumes together │ │ - Approve/revise individual or batch │ │ - Update library with approved resumes │ └─────────────────────────────────────────────────────────────┘


**Time Savings:**
- 3 jobs: ~40 min (vs 45 min sequential) = 11% savings
- 5 jobs: ~55 min (vs 75 min sequential) = 27% savings

**Quality:** Same depth as single-job workflow (research, matching, generation)

**See `multi-job-workflow.md` for complete implementation details.**


**检测到多职位时：**

"我注意到你需要申请多个职位。是否要启用多职位模式？

优势：

共享经历挖掘（更高效——只需一次问答即可覆盖所有职位）
批量处理并跟踪进度
可增量添加职位（后续可补充更多职位）

时间对比（3个相似职位）：

单职位依次处理：约45分钟（15分钟/个 ×3）
多职位模式：约40分钟（15分钟挖掘 + 8分钟/个处理）

是否启用多职位模式？(Y/N)"


**用户确认Y时：**
- 使用多职位工作流程（详见multi-job-workflow.md）

**用户确认N或检测为单职位时：**
- 使用现有单职位工作流程（从第0阶段开始）

**向后兼容性：** 单职位工作流程完全保持不变。

**多职位工作流程：**

启用多职位模式后，完整流程详见`multi-job-workflow.md`。

**多职位流程概览：**

┌─────────────────────────────────────────────────────────────┐ │ 阶段0：信息收集与批次初始化 │ │ - 收集3-5份职位描述 │ │ - 初始化批次结构 │ │ - 运行简历库初始化（仅执行一次） │ └─────────────────────────────────────────────────────────────┘ ↓ ┌─────────────────────────────────────────────────────────────┐ │ 阶段1：汇总差距分析 │ │ - 提取所有JD中的要求 │ │ - 与简历库进行交叉比对 │ │ - 构建统一的差距图谱（去重） │ │ - 优先级排序：关键需求 → 重要需求 → 职位特定需求 │ └─────────────────────────────────────────────────────────────┘ ↓ ┌─────────────────────────────────────────────────────────────┐ │ 阶段2：共享经历挖掘 │ │ - 一次分支式访谈覆盖所有差距 │ │ - 每个问题结合多职位背景 │ │ - 为经历标记职位相关性 │ │ - 将发掘的经历补充到简历库中 │ └─────────────────────────────────────────────────────────────┘ ↓ ┌─────────────────────────────────────────────────────────────┐ │ 阶段3：按职位依次处理（顺序执行） │ │ 针对每个职位： │ │ ├─ 研究（公司 + 职位基准分析） │ │ ├─ 生成模板 │ │ ├─ 内容匹配（使用更新后的简历库） │ │ └─ 生成文件（MD + DOCX + 报告） │ │ 支持交互式或快速模式 │ └─────────────────────────────────────────────────────────────┘ ↓ ┌─────────────────────────────────────────────────────────────┐ │ 阶段4：批次收尾 │ │ - 生成批次汇总报告 │ │ - 用户统一审核所有简历 │ │ - 批准/修订单个或全部简历 │ │ - 将获批简历更新到简历库中 │ └─────────────────────────────────────────────────────────────┘


**时间节省：**
- 3个职位：约40分钟（vs 依次处理45分钟）= 节省11%
- 5个职位：约55分钟（vs 依次处理75分钟）= 节省27%

**质量保障：** 与单职位流程深度一致（包含研究、匹配、生成环节）

**详见`multi-job-workflow.md`获取完整实现细节。**

Phase 0: Library Initialization

阶段0：简历库初始化

Always runs first - builds fresh resume database

Process:

Locate resume directory:

User provides path OR default to ./resumes/
Validate directory exists

Scan for markdown files:

Use Glob tool: pattern="*.md" path={resume_directory}
Count files found
Announce: "Building resume library... found {N} resumes"

Parse each resume: For each resume file:
- Use Read tool to load content
- Extract sections: roles, bullets, skills, education
- Identify patterns: bullet structure, length, formatting

Build experience database structure:

json

{
  "roles": [
    {
      "role_id": "company_title_year",
      "company": "Company Name",
      "title": "Job Title",
      "dates": "YYYY-YYYY",
      "description": "Role summary",
      "bullets": [
        {
          "text": "Full bullet text",
          "themes": ["leadership", "technical"],
          "metrics": ["17x improvement", "$3M revenue"],
          "keywords": ["cross-functional", "program"],
          "source_resumes": ["resume1.md"]
        }
      ]
    }
  ],
  "skills": {
    "technical": ["Python", "Kusto", "AI/ML"],
    "product": ["Roadmap", "Strategy"],
    "leadership": ["Stakeholder mgmt"]
  },
  "education": [...],
  "user_preferences": {
    "typical_length": "1-page|2-page",
    "section_order": ["summary", "experience", "education"],
    "bullet_style": "pattern"
  }
}

Tag content automatically:
- Themes: Scan for keywords (leadership, technical, analytics, etc.)
- Metrics: Extract numbers, percentages, dollar amounts
- Keywords: Frequent technical terms, action verbs

Output: In-memory database ready for matching

Code pattern:

python

undefined

始终首先执行——构建全新的简历数据库

流程：

定位简历目录：

用户提供路径或默认使用./resumes/
验证目录是否存在

扫描Markdown文件：

使用Glob工具：pattern="*.md" path={resume_directory}
统计找到的文件数量
提示："正在构建简历库... 找到{N}份简历"

解析每份简历： 针对每份简历文件：
- 使用Read工具加载内容
- 提取板块：职位、项目 bullet、技能、教育背景
- 识别格式模式：bullet结构、长度、排版

构建经历数据库结构：

json

{
  "roles": [
    {
      "role_id": "company_title_year",
      "company": "公司名称",
      "title": "职位名称",
      "dates": "YYYY-YYYY",
      "description": "职位概述",
      "bullets": [
        {
          "text": "完整bullet文本",
          "themes": ["leadership", "technical"],
          "metrics": ["17x improvement", "$3M revenue"],
          "keywords": ["cross-functional", "program"],
          "source_resumes": ["resume1.md"]
        }
      ]
    }
  ],
  "skills": {
    "technical": ["Python", "Kusto", "AI/ML"],
    "product": ["Roadmap", "Strategy"],
    "leadership": ["Stakeholder mgmt"]
  },
  "education": [...],
  "user_preferences": {
    "typical_length": "1-page|2-page",
    "section_order": ["summary", "experience", "education"],
    "bullet_style": "pattern"
  }
}

自动为内容打标签：
- 主题：扫描关键词（领导力、技术、分析等）
- 量化指标：提取数字、百分比、金额
- 关键词：高频技术术语、动作动词

输出： 可用于匹配的内存数据库

代码模式参考：

python

undefined

Pseudo-code for reference

参考伪代码

library = { "roles": [], "skills": {}, "education": [] }

for resume_file in glob("resumes/*.md"): content = read(resume_file) roles = extract_roles(content) for role in roles: role["bullets"] = tag_bullets(role["bullets"]) library["roles"].append(role)

return library

undefined

library = { "roles": [], "skills": {}, "education": [] }

for resume_file in glob("resumes/*.md"): content = read(resume_file) roles = extract_roles(content) for role in roles: role["bullets"] = tag_bullets(role["bullets"]) library["roles"].append(role)

return library

undefined

Phase 1: Research Phase

阶段1：研究阶段

Goal: Build comprehensive "success profile" beyond just the job description

Inputs:

Job description (text or URL from user)
Optional: Company name if not in JD

Process:

1.1 Job Description Parsing:

Use research-prompts.md JD parsing template
Extract: requirements, keywords, implicit preferences, red flags, role archetype

1.2 Company Research:

WebSearch queries:
- "{company} mission values culture"
- "{company} engineering blog"
- "{company} recent news"

Synthesize: mission, values, business model, stage

1.3 Role Benchmarking:

WebSearch: "site:linkedin.com {job_title} {company}"
WebFetch: Top 3-5 profiles
Analyze: common backgrounds, skills, terminology

If sparse results, try similar companies

1.4 Success Profile Synthesis:

Combine all research into structured profile (see research-prompts.md template)

Include:
- Core requirements (must-have)
- Valued capabilities (nice-to-have)
- Cultural fit signals
- Narrative themes
- Terminology map (user's background → their language)
- Risk factors + mitigations

Checkpoint:

Present success profile to user:

"Based on my research, here's what makes candidates successful for this role:

{SUCCESS_PROFILE_SUMMARY}

Key findings:
- {Finding 1}
- {Finding 2}
- {Finding 3}

Does this match your understanding? Any adjustments?"

Wait for user confirmation before proceeding.

Output: Validated success profile document

目标： 构建超越职位描述的全面“成功画像”

输入：

职位描述（用户提供的文本或URL）
可选：若JD中未包含公司名称，需用户提供

流程：

1.1 职位描述解析：

使用research-prompts.md中的JD解析模板
提取：要求、关键词、隐含偏好、风险点、职位类型

1.2 公司研究：

WebSearch查询：
- "{company} mission values culture"
- "{company} engineering blog"
- "{company} recent news"

综合信息：使命、价值观、商业模式、发展阶段

1.3 职位基准分析：

WebSearch: "site:linkedin.com {job_title} {company}"
WebFetch: 前3-5份相关档案
分析：共同背景、技能、术语

若结果较少，可参考同类公司

1.4 成功画像整合：

将所有研究整合成结构化画像（详见research-prompts.md模板）

包含：
- 核心要求（必备项）
- 增值能力（加分项）
- 文化适配信号
- 叙事主题
- 术语映射（用户背景 → 目标公司术语）
- 风险因素及应对方案

检查点：

向用户展示成功画像：

"基于我的研究，以下是该职位的成功候选人画像：

{SUCCESS_PROFILE_SUMMARY}

关键发现：
- {发现1}
- {发现2}
- {发现3}

是否符合你的认知？是否需要调整？"

等待用户确认后再继续。

输出： 经验证的成功画像文档

Phase 2: Template Generation

阶段2：模板生成

Goal: Create resume structure optimized for this specific role

Inputs:

Success profile (from Phase 1)
User's resume library (from Phase 0)

Process:

2.1 Analyze User's Resume Library:

Extract from library:
- All roles, titles, companies, date ranges
- Role archetypes (technical contributor, manager, researcher, specialist)
- Experience clusters (what domains/skills appear frequently)
- Career progression and narrative

2.2 Role Consolidation Decision:

When to consolidate:

Same company, similar responsibilities
Target role values continuity over granular progression
Combined narrative stronger than separate
Page space constrained

When to keep separate:

Different companies (ALWAYS separate)
Dramatically different responsibilities that both matter
Target role values specific progression story
One position has significantly more relevant experience

Decision template:

For {Company} with {N} positions:

OPTION A (Consolidated):
Title: "{Combined_Title}"
Dates: "{First_Start} - {Last_End}"
Rationale: {Why consolidation makes sense}

OPTION B (Separate):
Position 1: "{Title}" ({Dates})
Position 2: "{Title}" ({Dates})
Rationale: {Why separate makes sense}

RECOMMENDED: Option {A/B} because {reasoning}

2.3 Title Reframing Principles:

Core rule: Stay truthful to what you did, emphasize aspect most relevant to target

Strategies:

Emphasize different aspects:
- "Graduate Researcher" → "Research Software Engineer" (if coding-heavy)
- "Data Science Lead" → "Technical Program Manager" (if leadership)
Use industry-standard terminology:
- "Scientist III" → "Senior Research Scientist" (clearer seniority)
- "Program Coordinator" → "Project Manager" (standard term)
Add specialization when truthful:
- "Engineer" → "ML Engineer" (if ML work substantial)
- "Researcher" → "Computational Ecologist" (if computational methods)
Adjust seniority indicators:
- "Lead" vs "Senior" vs "Staff" based on scope

Constraints:

NEVER claim work you didn't do
NEVER inflate seniority beyond defensible
Company name and dates MUST be exact
Core responsibilities MUST be accurate

2.4 Generate Template Structure:

markdown

undefined

目标： 创建针对该职位的优化简历结构

输入：

成功画像（来自阶段1）
用户的简历库（来自阶段0）

流程：

2.1 分析用户简历库：

从简历库提取：
- 所有职位、头衔、公司、任职时间
- 职位类型（技术贡献者、管理者、研究员、专家）
- 经历集群（频繁出现的领域/技能）
- 职业发展脉络与叙事

2.2 职位合并决策：

合并场景：

同一家公司，职责相似
目标职位更看重连续性而非细分发展
合并后的叙事比单独呈现更有说服力
简历页数受限

单独呈现场景：

不同公司（始终单独呈现）
职责差异显著且均与目标职位相关
目标职位看重特定的职业发展路径
某一职位的相关经历远多于其他

决策模板：

针对{Company}的{N}个职位：

选项A（合并）：
头衔："{Combined_Title}"
时间："{First_Start} - {Last_End}"
理由：{合并的合理性}

选项B（单独）：
职位1："{Title}" ({Dates})
职位2："{Title}" ({Dates})
理由：{单独呈现的合理性}

推荐：选项{A/B}，因为{理由}

2.3 头衔重构原则：

核心规则： 忠实于实际工作内容，突出与目标职位最相关的方面

策略：

突出不同维度：
- "Graduate Researcher" → "Research Software Engineer"（若工作以编码为主）
- "Data Science Lead" → "Technical Program Manager"（若工作以管理为主）
使用行业标准术语：
- "Scientist III" → "Senior Research Scientist"（更清晰体现资深级别）
- "Program Coordinator" → "Project Manager"（标准术语）
如实添加专业方向：
- "Engineer" → "ML Engineer"（若机器学习工作占比大）
- "Researcher" → "Computational Ecologist"（若以计算方法为主）
调整资深级别表述：
- 根据工作范围选择"Lead"、"Senior"、"Staff"

约束：

绝不虚构未从事的工作
绝不夸大资深级别
公司名称与任职时间必须准确
核心职责必须真实

2.4 生成模板结构：

markdown

undefined

Professional Summary

专业概述

[GUIDANCE: {X} sentences emphasizing {themes from success profile}] [REQUIRED ELEMENTS: {keywords from JD}]

[指导：{X}句话，突出{成功画像中的主题}] [必备元素：{JD中的关键词}]

Key Skills

核心技能

[STRUCTURE: {2-4 categories based on JD structure}] [SOURCE: Extract from library matching success profile]

[结构：{基于JD结构的2-4个分类}] [来源：从简历库中提取匹配成功画像的技能]

Professional Experience

职业经历

[ROLE 1 - Most Recent/Relevant]

[职位1 - 最新/最相关]

[CONSOLIDATION: {merge X positions OR keep separate}] [TITLE OPTIONS: A: {emphasize aspect 1} B: {emphasize aspect 2} Recommended: {option with rationale}] [BULLET ALLOCATION: {N bullets based on relevance + recency}] [GUIDANCE: Emphasize {themes}, look for {experience types}]

Bullet 1: [SEEKING: {requirement type}] Bullet 2: [SEEKING: {requirement type}] ...

[合并决策：{合并X个职位或单独呈现}] [头衔选项： A: {突出维度1} B: {突出维度2} 推荐：{选项及理由}] [Bullet分配：{基于相关性与时效性的N个bullet}] [指导：突出{主题}，寻找{经历类型}]

Bullet 1: [需求类型：{需求类型}] Bullet 2: [需求类型：{需求类型}] ...

[ROLE 2]

[职位2]

...

Education

教育背景

[PLACEMENT: {top if required/recent, bottom if experience-heavy}]

[位置：{若为必备/近期则放在顶部，若经历丰富则放在底部}]

[Optional Sections]

[可选板块]

[INCLUDE IF: {criteria from success profile}]


**Checkpoint:**

Present template to user:

"Here's the optimized resume structure for this role:

STRUCTURE: {Section order and rationale}

ROLE CONSOLIDATION: {Decisions with options}

TITLE REFRAMING: {Proposed titles with alternatives}

BULLET ALLOCATION: Role 1: {N} bullets (most relevant) Role 2: {N} bullets ...

Does this structure work? Any adjustments to:

Role consolidation?
Title reframing?
Bullet allocation?"

Wait for user approval before proceeding.


**Output:** Approved template skeleton with guidance for each section

[包含条件：{成功画像中的标准}]


**检查点：**

向用户展示模板：

"以下是针对该职位的优化简历结构：

结构： {板块顺序及理由}

职位合并决策： {决策及选项}

头衔重构： {提议的头衔及替代选项}

Bullet分配：职位1：{N}个bullet（相关性最高）职位2：{N}个bullet ...

该结构是否可行？是否需要调整：

职位合并方式？
头衔重构？
Bullet分配数量？"

等待用户批准后再继续。


**输出：** 经批准的模板框架，包含各板块的指导说明

Phase 2.5: Experience Discovery (OPTIONAL)

阶段2.5：经历挖掘（可选）

Goal: Surface undocumented experiences through conversational discovery

When to trigger:

After template approval, if gaps identified:

"I've identified {N} gaps or areas where we have weak matches:
- {Gap 1}: {Current confidence}
- {Gap 2}: {Current confidence}
...

Would you like to do a structured brainstorming session to surface
any experiences you haven't documented yet?

This typically takes 10-15 minutes and often uncovers valuable content."

User can accept or skip.

Branching Interview Process:

Approach: Conversational with follow-up questions based on answers

For each gap, conduct branching dialogue (see branching-questions.md):

Start with open probe:
- Technical gap: "Have you worked with {skill}?"
- Soft skill gap: "Tell me about times you've {demonstrated_skill}"
- Recent work: "What have you worked on recently?"
Branch based on answer:
- YES/Strong → Deep dive (scale, challenges, metrics)
- INDIRECT → Explore role and transferability
- ADJACENT → Explore related experience
- PERSONAL → Assess recency and substance
- NO → Try broader category or move on
Follow-up systematically:
- Ask "what," "how," "why" to get details
- Quantify: "Any metrics?"
- Contextualize: "Was this production?"
- Validate: "Does this address the gap?"
Capture immediately:
- Document experience as shared
- Ask clarifying questions (dates, scope, impact)
- Help articulate as resume bullet
- Tag which gap(s) it addresses

Capture Structure:

markdown

undefined

目标： 通过对话式挖掘发掘未记录的经历

触发时机：

模板获批后，若识别到差距：

"我识别到{N}个差距或匹配度较弱的领域：
- {差距1}：当前匹配度{Current confidence}
- {差距2}：当前匹配度{Current confidence}
...

是否要进行结构化头脑风暴，发掘你尚未记录的经历？

该过程通常需要10-15分钟，往往能发现有价值的内容。"

用户可选择接受或跳过。

分支式访谈流程：

方法： 对话式，根据用户回答提出跟进问题

针对每个差距，进行分支式对话（详见branching-questions.md）：

开放式提问开场：
- 技术差距："你是否有过{skill}相关的工作经历？"
- 软技能差距："请分享你展现{demonstrated_skill}的经历"
- 近期工作："你最近在做什么项目？"
根据回答分支：
- 是/明确相关 → 深入挖掘（规模、挑战、量化成果）
- 间接相关 → 探索职位关联性与可迁移性
- 相邻领域 → 探索相关经历
- 个人项目 → 评估时效性与重要性
- 否 → 尝试更宽泛的类别或跳过
系统性跟进：
- 问"什么"、"如何"、"为什么"以获取细节
- 量化："是否有可量化的成果？"
- 场景化："这是生产环境中的项目吗？"
- 验证："这能填补当前差距吗？"
即时记录：
- 记录用户分享的经历
- 询问澄清问题（时间、范围、影响）
- 帮助用户将其整理为简历bullet
- 标记该经历填补的差距

记录结构：

markdown

undefined

Newly Discovered Experiences

新发掘的经历

Experience 1: {Brief description}

经历1：{简要描述}

Context: {Where/when}
Scope: {Scale, duration, impact}
Addresses: {Which gaps}
Bullet draft: "{Achievement-focused bullet}"
Confidence: {How well fills gap - percentage}

背景：{时间/地点}
范围：{规模、时长、影响}
填补差距：{对应的差距}
Bullet草稿："{以成果为导向的bullet}"
匹配度：{填补差距的程度 - 百分比}

Experience 2: ...

经历2：...


**Integration Options:**

After discovery session:

"Great! I captured {N} new experiences. For each one:

ADD TO CURRENT RESUME - Integrate now
ADD TO LIBRARY ONLY - Save for future, not needed here
REFINE FURTHER - Think more about articulation
DISCARD - Not relevant enough

Let me know for each experience."


**Important Notes:**
- Keep truthfulness bar high - help articulate, NEVER fabricate
- Focus on gaps and weak matches, not strong areas
- Time-box if needed (10-15 minutes typical)
- User can skip entirely if confident in library
- Recognize when to move on - don't exhaust user

**Output:** New experiences integrated into library, ready for matching


**整合选项：**

挖掘会话结束后：

"很好！我记录了{N}个新经历。针对每个经历，你可以选择：

添加到当前简历 - 立即整合
仅添加到简历库 - 保存供未来使用，本次不整合
进一步优化 - 完善表述
丢弃 - 相关性不足

请告知你的选择。"


**重要注意事项：**
- 严格保持真实性 - 仅帮助优化表述，绝不编造经历
- 聚焦差距与匹配度弱的领域，而非已有优势
- 可设置时间限制（通常10-15分钟）
- 用户可随时跳过该环节
- 适时停止，避免让用户疲惫

**输出：** 新经历整合到简历库，可用于后续匹配

Phase 3: Assembly Phase

阶段3：内容填充阶段

Goal: Fill approved template with best-matching content, with transparent scoring

Inputs:

Approved template (from Phase 2)
Resume library + discovered experiences (from Phase 0 + 2.5)
Success profile (from Phase 1)

Process:

3.1 For Each Template Slot:

Extract all candidate bullets from library
- All bullets from library database
- All newly discovered experiences
- Include source resume for each
Score each candidate (see matching-strategies.md)
- Direct match (40%): Keywords, domain, technology, outcome
- Transferable (30%): Same capability, different context
- Adjacent (20%): Related tools, methods, problem space
- Impact (10%): Achievement type alignment
Overall = (Direct × 0.4) + (Transfer × 0.3) + (Adjacent × 0.2) + (Impact × 0.1)
Rank candidates by score
- Sort high to low
- Group by confidence band:
  - 90-100%: DIRECT
  - 75-89%: TRANSFERABLE
  - 60-74%: ADJACENT
  - <60%: WEAK/GAP

Present top 3 matches with analysis:

TEMPLATE SLOT: {Role} - Bullet {N}
SEEKING: {Requirement description}

MATCHES:
[DIRECT - 95%] "{bullet_text}"
  ✓ Direct: {what matches directly}
  ✓ Transferable: {what transfers}
  ✓ Metrics: {quantified impact}
  Source: {resume_name}

[TRANSFERABLE - 78%] "{bullet_text}"
  ✓ Transferable: {what transfers}
  ✓ Adjacent: {what's adjacent}
  ⚠ Gap: {what's missing}
  Source: {resume_name}

[ADJACENT - 62%] "{bullet_text}"
  ✓ Adjacent: {what's related}
  ⚠ Gap: {what's missing}
  Source: {resume_name}

RECOMMENDATION: Use DIRECT match (95%)
ALTERNATIVE: If avoiding repetition, use TRANSFERABLE (78%) with reframing

Handle gaps (confidence <60%):

GAP IDENTIFIED: {Requirement}

BEST AVAILABLE: {score}% - "{bullet_text}"

REFRAME OPPORTUNITY: {If applicable}
Original: "{text}"
Reframed: "{adjusted_text}" (truthful because {reason})
New confidence: {score}%

OPTIONS:
1. Use reframed version ({new_score}%)
2. Acknowledge gap in cover letter
3. Omit bullet slot (reduce allocation)
4. Use best available with disclosure

RECOMMENDATION: {Most appropriate option}

3.2 Content Reframing:

When good match (>60%) but terminology misaligned:

Apply strategies from matching-strategies.md:

Keyword alignment (preserve meaning, adjust terms)
Emphasis shift (same facts, different focus)
Abstraction level (adjust technical specificity)
Scale emphasis (highlight relevant aspects)

Show before/after for transparency:

REFRAMING APPLIED:
Bullet: {template_slot}

Original: "{original_bullet}"
Source: {resume_name}

Reframed: "{reframed_bullet}"
Changes: {what changed and why}
Truthfulness: {why this is accurate}

Checkpoint:

"I've matched content to your template. Here's the complete mapping:

COVERAGE SUMMARY:
- Direct matches: {N} bullets ({percentage}%)
- Transferable: {N} bullets ({percentage}%)
- Adjacent: {N} bullets ({percentage}%)
- Gaps: {N} ({percentage}%)

REFRAMINGS APPLIED: {N}
- {Example 1}
- {Example 2}

GAPS IDENTIFIED:
- {Gap 1}: {Recommendation}
- {Gap 2}: {Recommendation}

OVERALL JD COVERAGE: {percentage}%

Review the detailed mapping below. Any adjustments to:
- Match selections?
- Reframings?
- Gap handling?"

[Present full detailed mapping]

Wait for user approval before generation.

Output: Complete bullet-by-bullet mapping with confidence scores and reframings

目标： 为获批的模板填充匹配度最高的内容，并提供透明的评分

输入：

获批的模板（来自阶段2）
简历库 + 新发掘的经历（来自阶段0 + 2.5）
成功画像（来自阶段1）

流程：

3.1 针对每个模板空位：

从简历库提取所有候选bullet
- 简历库数据库中的所有bullet
- 所有新发掘的经历
- 标注每个bullet的来源简历
为每个候选bullet评分（详见matching-strategies.md）
- 直接匹配（40%）：关键词、领域、技术、成果
- 可迁移匹配（30%）：能力相同，场景不同
- 相邻匹配（20%）：工具、方法、问题领域相关
- 成果匹配（10%）：成果类型匹配
总分 = (直接匹配×0.4) + (可迁移×0.3) + (相邻×0.2) + (成果×0.1)
按分数排序候选bullet
- 从高到低排序
- 按匹配度分组：
  - 90-100%：直接匹配
  - 75-89%：可迁移匹配
  - 60-74%：相邻匹配
  - <60%：弱匹配/差距

展示前3个匹配结果及分析：

模板空位：{职位} - Bullet {N}
需求：{需求描述}

匹配结果：
[直接匹配 - 95%] "{bullet_text}"
  ✓ 直接匹配：{直接匹配点}
  ✓ 可迁移：{可迁移点}
  ✓ 量化成果：{量化影响}
  来源：{简历名称}

[可迁移匹配 - 78%] "{bullet_text}"
  ✓ 可迁移：{可迁移点}
  ✓ 相邻：{相邻点}
  ⚠ 差距：{缺失点}
  来源：{简历名称}

[相邻匹配 - 62%] "{bullet_text}"
  ✓ 相邻：{相关点}
  ⚠ 差距：{缺失点}
  来源：{简历名称}

推荐：使用直接匹配（95%）
替代方案：若避免重复，可使用可迁移匹配（78%）并重构表述

处理差距（匹配度<60%）：

识别到差距：{需求}

最佳可用匹配：{score}% - "{bullet_text}"

重构机会：{若适用}
原表述："{text}"
重构后："{adjusted_text}"（真实合理，理由：{reason}）
新匹配度：{score}%

选项：
1. 使用重构后的表述（{new_score}%）
2. 在求职信中说明差距
3. 省略该bullet空位（减少分配数量）
4. 使用最佳可用匹配并标注

推荐：{最合适的选项}

3.2 内容重构：

当匹配度较好（>60%）但术语不匹配时：

应用matching-strategies.md中的策略：

关键词对齐（保留原意，调整术语）
重点转移（事实不变，突出不同重点）
抽象级别调整（调整技术细节程度）
规模突出（强调相关维度）

透明展示前后对比：

已应用重构：
空位：{template_slot}

原表述："{original_bullet}"
来源：{resume_name}

重构后："{reframed_bullet}"
调整点：{调整内容及原因}
真实性：{为何该表述准确}

检查点：

"我已为模板匹配好内容。以下是完整的匹配情况：

覆盖情况汇总：
- 直接匹配：{N}个bullet（{percentage}%）
- 可迁移匹配：{N}个bullet（{percentage}%）
- 相邻匹配：{N}个bullet（{percentage}%）
- 差距：{N}个（{percentage}%）

已应用的重构：{N}处
- {示例1}
- {示例2}

识别到的差距：
- {差距1}：{推荐方案}
- {差距2}：{推荐方案}

整体JD覆盖度：{percentage}%

请查看下方详细匹配情况。是否需要调整：
- 匹配内容选择？
- 重构表述？
- 差距处理方式？"

[展示完整详细匹配情况]

等待用户批准后再生成文件。

输出： 完整的逐bullet匹配结果，包含匹配度评分与重构说明

Phase 4: Generation Phase

阶段4：生成阶段

Goal: Create professional multi-format outputs

Inputs:

Approved content mapping (from Phase 3)
User's formatting preferences (from library analysis)
Target role information (from Phase 1)

Process:

4.1 Markdown Generation:

Compile mapped content into clean markdown:

markdown

undefined

目标： 创建专业的多格式输出文件

输入：

获批的内容匹配结果（来自阶段3）
用户的排版偏好（来自简历库分析）
目标职位信息（来自阶段1）

流程：

4.1 Markdown生成：

将匹配内容整理为清晰的Markdown格式：

markdown

undefined

{User_Name}

{用户姓名}

{Contact_Info}

{联系方式}

Professional Summary

专业概述

{Summary_from_template}

{来自模板的概述}

Key Skills

核心技能

{Category_1}:

{Skills_from_library_matching_profile}

{Category_2}:

{Skills_from_library_matching_profile}

{Repeat for all categories}

{分类1}：

{来自简历库且匹配画像的技能}

{分类2}：

{来自简历库且匹配画像的技能}

{重复所有分类}

Professional Experience

职业经历

{Job_Title}

{职位头衔}

{Company} | {Location} | {Dates}

{Role_summary_if_applicable}

• {Bullet_1_from_mapping} • {Bullet_2_from_mapping} ...

{公司} | {地点} | {任职时间}

{若适用，添加职位概述}

• {来自匹配结果的Bullet 1} • {来自匹配结果的Bullet 2} ...

{Next_Role}

{下一个职位}

...

Education

教育背景

{Degree} | {Institution} ({Year}) {Degree} | {Institution} ({Year})


**Use user's preferences:**
- Formatting style from library analysis
- Bullet structure pattern
- Section ordering
- Typical length (1-page vs 2-page)

**Output:** `{Name}_{Company}_{Role}_Resume.md`

**4.2 DOCX Generation:**

**Use document-skills:docx:**

REQUIRED SUB-SKILL: Use document-skills:docx

Create Word document with:

Professional fonts (Calibri 11pt body, 12pt headers)
Proper spacing (single within sections, space between)
Clean bullet formatting (proper numbering config, NOT unicode)
Header with contact information
Appropriate margins (0.5-1 inch)
Bold/italic emphasis (company names, titles, dates)
Page breaks if 2-page resume

See docx skill documentation for:

Paragraph and TextRun structure
Numbering configuration for bullets
Heading levels and styles
Spacing and margins


**Output:** `{Name}_{Company}_{Role}_Resume.docx`

**4.3 PDF Generation (Optional):**

**If user requests PDF:**

OPTIONAL SUB-SKILL: Use document-skills:pdf

Convert DOCX to PDF OR generate directly Ensure formatting preservation Professional appearance for direct submission


**Output:** `{Name}_{Company}_{Role}_Resume.pdf`

**4.4 Generation Summary Report:**

**Create metadata file:**

```markdown

{学位} | {院校} ({毕业年份}) {学位} | {院校} ({毕业年份})


**遵循用户偏好：**
- 简历库分析得出的排版风格
- Bullet结构模式
- 板块顺序
- 常规长度（1页vs2页）

**输出：** `{姓名}_{公司}_{职位}_Resume.md`

**4.2 DOCX生成：**

**使用document-skills:docx：**

必备子技能：使用document-skills:docx

创建Word文档要求：

专业字体（正文字体Calibri 11pt，标题12pt）
合理间距（板块内单倍行距，板块间空行）
清晰的Bullet格式（正确编号配置，非unicode符号）
包含联系方式的页眉
合适的页边距（0.5-1英寸）
加粗/斜体强调（公司名称、头衔、时间）
若为2页简历，添加分页符

详见docx技能文档：

段落与TextRun结构
Bullet编号配置
标题级别与样式
间距与页边距


**输出：** `{姓名}_{公司}_{职位}_Resume.docx`

**4.3 PDF生成（可选）：**

**若用户要求PDF：**

可选子技能：使用document-skills:pdf

将DOCX转换为PDF或直接生成确保格式完全保留外观专业，可直接提交


**输出：** `{姓名}_{公司}_{职位}_Resume.pdf`

**4.4 生成汇总报告：**

**创建元数据文件：**

```markdown

Resume Generation Report

简历生成报告

{Role} at {Company}

Date Generated: {timestamp}

{职位} @ {公司}

生成日期：{时间戳}

Target Role Summary

目标职位概述

Company: {Company}
Position: {Role}
IC Level: {If known}
Focus Areas: {Key areas}

公司：{公司}
职位：{职位}
IC级别：{若已知}
核心领域：{关键方向}

Success Profile Summary

成功画像概述

Key Requirements: {top 5}
Cultural Fit Signals: {themes}
Risk Factors Addressed: {mitigations}

核心要求：{前5项}
文化适配信号：{主题}
已处理的风险因素：{应对方案}

Content Mapping Summary

内容匹配汇总

Total bullets: {N}
Direct matches: {N} ({percentage}%)
Transferable: {N} ({percentage}%)
Adjacent: {N} ({percentage}%)
Gaps identified: {list}

总Bullet数：{N}
直接匹配：{N}个（{percentage}%）
可迁移匹配：{N}个（{percentage}%）
相邻匹配：{N}个（{percentage}%）
识别到的差距：{列表}

Reframing Applied

已应用的重构

{bullet}: {original} → {reframed} [Reason: {why}] ...

{bullet}：{原表述} → {重构后} [原因：{理由}] ...

Source Resumes Used

使用的源简历

{resume1}: {N} bullets
{resume2}: {N} bullets ...

{resume1}：{N}个bullet
{resume2}：{N}个bullet ...

Gaps Addressed

差距处理情况

Before Experience Discovery:

经历挖掘前：

{Gap analysis showing initial state}

{初始差距分析}

After Experience Discovery:

经历挖掘后：

{Gap analysis showing final state}

{最终差距分析}

Remaining Gaps:

剩余差距：

{Any unresolved gaps with recommendations}

{未解决的差距及推荐方案}

Key Differentiators for This Role

该职位的核心竞争力

{What makes user uniquely qualified}

{用户的独特优势}

Recommendations for Interview Prep

面试准备建议

Stories to prepare
Questions to expect
Gaps to address


**Output:** `{Name}_{Company}_{Role}_Resume_Report.md`

**Present to user:**

"Your tailored resume has been generated!

FILES CREATED:

{Name}{Company}{Role}_Resume.md
{Name}{Company}{Role}_Resume.docx
{Name}{Company}{Role}Resume_Report.md {- {Name}{Company}_{Role}_Resume.pdf (if requested)}

QUALITY METRICS:

JD Coverage: {percentage}%
Direct Matches: {percentage}%
Newly Discovered: {N} experiences

Review the files and let me know:

Save to library (recommended)
Need revisions
Save but don't add to library"

undefined

需要准备的故事
可能遇到的问题
需要弥补的差距


**输出：** `{姓名}_{公司}_{职位}_Resume_Report.md`

**向用户交付：**

"你的定制化简历已生成！

创建的文件：

{姓名}{公司}{职位}_Resume.md
{姓名}{公司}{职位}_Resume.docx
{姓名}{公司}{职位}Resume_Report.md {- {姓名}{公司}_{职位}_Resume.pdf（若用户要求）}

质量指标：

JD覆盖度：{percentage}%
直接匹配占比：{percentage}%
新发掘的经历：{N}个

请查看文件并告知：

保存到简历库（推荐）
需要修订
保存但不添加到简历库"

undefined

Phase 5: Library Update (CONDITIONAL)

阶段5：简历库更新（可选）

Goal: Optionally add successful resume to library for future use

When: After user reviews and approves generated resume

Checkpoint Question:

"Are you satisfied with this resume?

OPTIONS:
1. YES - Save to library
   → Adds resume to permanent location
   → Rebuilds library database
   → Makes new content available for future resumes

2. NO - Need revisions
   → What would you like to adjust?
   → Make changes and re-present

3. SAVE BUT DON'T ADD TO LIBRARY
   → Keep files in current location
   → Don't enrich database
   → Useful for experimental resumes

Which option?"

If Option 1 (YES - Save to library):

Process:

Move resume to library:

Source: {current_directory}/{Name}_{Company}_{Role}_Resume.md
Destination: {resume_library}/{Name}_{Company}_{Role}_Resume.md

Also move:
- .docx file
- .pdf file (if exists)
- _Report.md file

Rebuild library database:

Re-run Phase 0 library initialization
Parse newly created resume
Add bullets to experience database
Update keyword/theme indices
Tag with metadata:
  - target_company: {Company}
  - target_role: {Role}
  - generated_date: {timestamp}
  - jd_coverage: {percentage}
  - success_profile: {reference to profile}

Preserve generation metadata:

json

{
  "resume_id": "{Name}_{Company}_{Role}",
  "generated": "{timestamp}",
  "source_resumes": ["{resume1}", "{resume2}"],
  "reframings": [
    {
      "original": "{text}",
      "reframed": "{text}",
      "reason": "{why}"
    }
  ],
  "match_scores": {
    "bullet_1": 95,
    "bullet_2": 87,
    ...
  },
  "newly_discovered": [
    {
      "experience": "{description}",
      "bullet": "{text}",
      "addresses_gap": "{gap}"
    }
  ]
}

Announce completion:

"Resume saved to library!

Library updated:
- Total resumes: {N}
- New content variations: {N}
- Newly discovered experiences added: {N}

This resume and its new content are now available for future tailoring sessions."

If Option 2 (NO - Need revisions):

"What would you like to adjust?"

[Collect user feedback]
[Make requested changes]
[Re-run relevant phases]
[Re-present for approval]

[Repeat until satisfied or user cancels]

If Option 3 (SAVE BUT DON'T ADD TO LIBRARY):

"Resume files saved to current directory:
- {Name}_{Company}_{Role}_Resume.md
- {Name}_{Company}_{Role}_Resume.docx
- {Name}_{Company}_{Role}_Resume_Report.md

Not added to library - you can manually move later if desired."

Benefits of Library Update:

Grows library with each successful resume
New bullet variations become available
Reframings that work can be reused
Discovered experiences permanently captured
Future sessions start with richer library
Self-improving system over time

Output: Updated library database + metadata preservation (if Option 1)

目标： 可选将获批简历添加到简历库供未来使用

时机： 用户审核并批准生成的简历后

确认问题：

"你对这份简历满意吗？

选项：
1. 是 - 保存到简历库
   → 将简历添加到永久存储位置
   → 重建简历库数据库
   → 新内容可用于未来简历定制

2. 否 - 需要修订
   → 请告知需要调整的内容
   → 修改后重新交付

3. 保存但不添加到简历库
   → 将文件保存在当前目录
   → 不更新数据库
   → 适用于实验性简历

你的选择是？"

若选择选项1（是 - 保存到简历库）：

流程：

将简历移动到简历库：

来源：{current_directory}/{姓名}_{公司}_{职位}_Resume.md
目标：{resume_library}/{姓名}_{公司}_{职位}_Resume.md

同时移动：
- .docx文件
- .pdf文件（若存在）
- _Report.md文件

重建简历库数据库：

重新运行阶段0的简历库初始化
解析新生成的简历
将bullet添加到经历数据库
更新关键词/主题索引
添加元数据标签：
  - target_company: {Company}
  - target_role: {Role}
  - generated_date: {timestamp}
  - jd_coverage: {percentage}
  - success_profile: {画像引用}

保留生成元数据：

json

{
  "resume_id": "{姓名}_{公司}_{职位}",
  "generated": "{timestamp}",
  "source_resumes": ["{resume1}", "{resume2}"],
  "reframings": [
    {
      "original": "{text}",
      "reframed": "{text}",
      "reason": "{why}"
    }
  ],
  "match_scores": {
    "bullet_1": 95,
    "bullet_2": 87,
    ...
  },
  "newly_discovered": [
    {
      "experience": "{description}",
      "bullet": "{text}",
      "addresses_gap": "{gap}"
    }
  ]
}

完成通知：

"简历已保存到简历库！

简历库已更新：
- 总简历数：{N}
- 新增内容变体：{N}
- 新增发掘的经历：{N}

这份简历及其新内容现在可用于未来的定制会话。"

若选择选项2（否 - 需要修订）：

"请告知需要调整的内容？"

[收集用户反馈]
[进行所需修改]
[重新运行相关阶段]
[重新交付供用户批准]

[重复直到用户满意或取消]

若选择选项3（保存但不添加到简历库）：

"简历文件已保存到当前目录：
- {姓名}_{公司}_{职位}_Resume.md
- {姓名}_{公司}_{职位}_Resume.docx
- {姓名}_{公司}_{职位}_Resume_Report.md

未添加到简历库——你可在之后手动移动。"

更新简历库的优势：

每一份获批简历都能丰富简历库
新增的bullet变体可复用
有效的重构表述可重复使用
发掘的经历被永久记录
未来会话可从更丰富的简历库开始
系统随使用不断自我优化

输出： 更新后的简历库数据库 + 元数据保留（若选择选项1）

Error Handling & Edge Cases

错误处理与边缘场景

Edge Case 1: Insufficient Resume Library

SCENARIO: User has only 1-2 resumes, limited content

HANDLING:
"⚠️ Limited resume library detected ({N} resumes).

This may result in:
- Fewer matching options
- More gaps in coverage
- Less variety in bullet phrasing

RECOMMENDATIONS:
- Proceed with available content (I'll do my best!)
- Consider adding more resumes after this generation
- Experience Discovery phase will be especially valuable

Continue? (Y/N)"

Edge Case 2: No Good Matches (confidence <60% for critical requirement)

SCENARIO: Template slot requires experience user doesn't have

HANDLING:
"❌ GAP: {Requirement}

No matches found with confidence >60%

OPTIONS:
1. Run Experience Discovery - might surface undocumented work
2. Reframe best available ({score}%) - I'll show you the reframing
3. Omit bullet slot - reduce template allocation
4. Note for cover letter - emphasize learning ability

Which approach?"

[Don't force matches - be transparent about gaps]

Edge Case 3: Research Phase Failures

SCENARIO: WebSearch fails, LinkedIn unavailable, company info sparse

HANDLING:
"⚠️ Limited company research available.

What I found:
- {Available info}

What's missing:
- {Missing areas}

Falling back to job description-only analysis.
Result: Template will be optimized for JD but may miss cultural nuances.

Do you have additional context about:
- Company culture?
- Team structure?
- Technologies used?

(Optional - you can share or skip)"

[Proceed with best-effort approach]

Edge Case 4: Job Description Quality Issues

SCENARIO: Vague JD, missing requirements, poorly written

HANDLING:
"⚠️ Job description lacks detail in areas:
- {Missing area 1}
- {Missing area 2}

This may limit template optimization.

Do you have additional context about:
- {Question 1}
- {Question 2}

(Optional - I'll work with what's available)"

[Extract what's possible, proceed]

Edge Case 5: Ambiguous Role Consolidation

SCENARIO: Unclear whether to merge roles or keep separate

HANDLING:
"🤔 Ambiguous consolidation decision for {Company}

OPTION A (Consolidated): {Rationale}
OPTION B (Separate): {Rationale}

Both are defensible. Which do you prefer?

(This becomes your preference for similar situations)"

[Remember preference for future]

Edge Case 6: Resume Length Constraints

SCENARIO: Too much good content, exceeds 2 pages

HANDLING:
"⚠️ Content exceeds 2 pages (current: {N} bullets, ~{pages} pages)

PRUNING SUGGESTIONS (ranked by relevance):
Remove:
- {Bullet X}: {score}% match (lowest)
- {Bullet Y}: {score}% match
...

Keep all bullets and accept >2 pages?
OR
Remove {N} bullets to fit 2 pages?

Your preference?"

[User decides priority]

Error Recovery:

All checkpoints allow going back to previous phase
User can request adjustments at any checkpoint
Generation failures (DOCX/PDF) fall back to markdown-only
Progress saved between phases (can resume if interrupted)

Graceful Degradation:

Research limited → Fall back to JD-only analysis
Library small → Work with available + emphasize discovery
Matches weak → Transparent gap identification
Generation fails → Provide markdown + error details

边缘场景1：简历库内容不足

场景：用户仅有1-2份简历，内容有限

处理方式：
"⚠️ 检测到简历库内容有限（{N}份简历）。

这可能导致：
- 匹配选项更少
- 覆盖度差距更多
- Bullet表述多样性不足

推荐：
- 使用现有内容继续（我会尽力优化！）
- 考虑在本次生成后补充更多简历
- 经历挖掘阶段将尤为重要

是否继续？(Y/N)"

边缘场景2：无优质匹配（关键需求匹配度<60%）

场景：模板空位要求的经历用户未拥有

处理方式：
"❌ 差距：{需求}

未找到匹配度>60%的内容

选项：
1. 运行经历挖掘——可能发掘未记录的工作经历
2. 重构最佳可用内容（{score}%）——我会展示重构方案
3. 省略该bullet空位——减少模板分配数量
4. 在求职信中说明——强调学习能力

你选择哪种方式？"

[绝不强行匹配——透明告知差距]

边缘场景3：研究阶段失败

场景：WebSearch失败、LinkedIn不可用、公司信息稀少

处理方式：
"⚠️ 公司研究信息有限。

已找到的信息：
- {可用信息}

缺失的信息：
- {缺失领域}

将 fallback 到仅基于职位描述的分析。
结果：模板将针对JD优化，但可能缺失文化适配细节。

你是否有额外信息可以提供：
- 公司文化？
- 团队结构？
- 使用的技术？

（可选——你可以分享或跳过）"

[尽最大努力继续]

边缘场景4：职位描述质量问题

场景：JD模糊、缺失要求、撰写质量差

处理方式：
"⚠️ 职位描述在以下领域缺乏细节：
- {缺失领域1}
- {缺失领域2}

这可能限制模板优化效果。

你是否有额外信息可以提供：
- {问题1}
- {问题2}

（可选——我会基于现有内容继续）"

[提取可用信息，继续流程]

边缘场景5：职位合并决策模糊

场景：无法明确是否合并职位

处理方式：
"🤔 {Company}的职位合并决策模糊

选项A（合并）：{理由}
选项B（单独）：{理由}

两种选择均合理。你偏好哪种？

（该选择将作为未来类似场景的偏好）"

[记住用户偏好供未来使用]

边缘场景6：简历长度限制

场景：优质内容过多，超过2页

处理方式：
"⚠️ 内容超过2页（当前：{N}个bullet，约{pages}页）

修剪建议（按相关性排序）：
移除：
- {Bullet X}：{score}%匹配度（最低）
- {Bullet Y}：{score}%匹配度
...

保留所有bullet并接受超过2页？
或
移除{N}个bullet以适配2页？

你的选择是？"

[由用户决定优先级]

错误恢复：

所有检查点允许回到上一阶段
用户可在任何检查点要求调整
生成失败（DOCX/PDF）时 fallback 到仅生成Markdown
阶段间保存进度（中断后可恢复）

优雅降级：

研究受限 → 仅基于JD分析
简历库内容少 → 使用现有内容 + 强调挖掘环节
匹配度低 → 透明识别差距
生成失败 → 提供Markdown文件 + 错误详情

Usage Examples

使用示例

Example 1: Internal Role (Same Company)

USER: "I want to apply for Principal PM role in 1ES team at Microsoft.
      Here's the JD: {paste}"

SKILL:
1. Library Build: Finds 29 resumes
2. Research: Microsoft 1ES team, internal culture, role benchmarking
3. Template: Features PM2 Azure Eng Systems role (most relevant)
4. Discovery: Surfaces VS Code extension, Bhavana AI side project
5. Assembly: 92% JD coverage, 75% direct matches
6. Generate: MD + DOCX + Report
7. User approves → Library updated with new resume + 6 discovered experiences

RESULT: Highly competitive application leveraging internal experience

Example 2: Career Transition (Different Domain)

USER: "I'm a TPM trying to transition to ecology PM role. JD: {paste}"

SKILL:
1. Library Build: Finds existing TPM resumes
2. Research: Ecology sector, sustainability focus, cross-domain transfers
3. Template: Reframes "Technical Program Manager" → "Program Manager,
             Environmental Systems" emphasizing systems thinking
4. Discovery: Surfaces volunteer conservation work, graduate research in
             environmental modeling
5. Assembly: 65% JD coverage - flags gaps in domain-specific knowledge
6. Generate: Resume + gap analysis with cover letter recommendations

RESULT: Bridges technical skills with environmental domain

Example 3: Career Gap Handling

USER: "I have a 2-year gap while starting a company. JD: {paste}"

SKILL:
1. Library Build: Finds pre-gap resumes
2. Research: Standard analysis
3. Template: Includes startup as legitimate role
4. Discovery: Surfaces skills developed during startup (fundraising,
             product development, team building)
5. Assembly: Frames gap as entrepreneurial experience
6. Generate: Resume presenting gap as valuable experience

RESULT: Gap becomes strength showing initiative and diverse skills

Example 4: Multi-Job Batch (3 Similar Roles)

USER: "I want to apply for these 3 TPM roles:
      1. Microsoft 1ES Principal PM
      2. Google Cloud Senior TPM
      3. AWS Container Services Senior PM
      Here are the JDs: {paste 3 JDs}"

SKILL:
1. Multi-job detection: Triggered (3 JDs detected)
2. Intake: Collects all 3 JDs, initializes batch
3. Library Build: Finds 29 resumes (once)
4. Gap Analysis: Identifies 14 gaps, 8 unique after deduplication
5. Shared Discovery: 30-minute session surfaces 5 new experiences
   - Kubernetes CI/CD for nonprofits
   - Azure migration for university lab
   - Cross-functional team leadership examples
   - Recent hackathon project
   - Open source contributions
6. Per-Job Processing (×3):
   - Job 1 (Microsoft): 85% coverage, emphasizes Azure/1ES alignment
   - Job 2 (Google): 88% coverage, emphasizes technical depth
   - Job 3 (AWS): 78% coverage, addresses AWS gap in cover letter recs
7. Batch Finalization: All 3 resumes reviewed, approved, added to library

RESULT: 3 high-quality resumes in 40 minutes vs 45 minutes sequential
        5 new experiences captured, available for future applications
        Average coverage: 84%, all critical gaps resolved

Example 5: Incremental Batch Addition

WEEK 1:
USER: "I want to apply for 3 jobs: {Microsoft, Google, AWS}"
SKILL: [Processes batch as above, completes in 40 min]

WEEK 2:
USER: "I found 2 more jobs: Stripe and Meta. Add them to my batch?"
SKILL:
1. Load existing batch (includes 5 previously discovered experiences)
2. Intake: Adds Job 4 (Stripe), Job 5 (Meta)
3. Incremental Gap Analysis: Only 3 new gaps (vs 14 original)
   - Payment systems (Stripe-specific)
   - Social networking (Meta-specific)
   - React/frontend (both)
4. Incremental Discovery: 10-minute session for new gaps only
   - Surfaces payment processing side project
   - React work from bootcamp
   - Large-scale system design course
5. Per-Job Processing (×2): Jobs 4, 5 processed independently
6. Updated Batch Summary: Now 5 jobs total, 8 experiences discovered

RESULT: 2 additional resumes in 20 minutes (vs 30 min if starting from scratch)
        Time saved by not re-asking 8 previous gaps: ~20 minutes

示例1：内部职位（同一家公司）

用户："我想申请微软1ES团队的Principal PM职位。这是JD：{粘贴内容}"

技能处理：
1. 简历库构建：找到29份简历
2. 研究：微软1ES团队、内部文化、职位基准
3. 模板：突出PM2 Azure Eng Systems职位（相关性最高）
4. 挖掘：发掘VS Code扩展、Bhavana AI副业项目
5. 匹配：92% JD覆盖度，75%直接匹配
6. 生成：MD + DOCX + 报告
7. 用户批准 → 简历库更新，添加新简历 + 6个新发掘的经历

结果：利用内部经历打造极具竞争力的申请材料

示例2：职业转型（不同领域）

用户："我是TPM，想转型为生态领域PM。JD：{粘贴内容}"

技能处理：
1. 简历库构建：找到现有TPM简历
2. 研究：生态行业、可持续发展重点、跨领域迁移
3. 模板：将"Technical Program Manager"重构为"Program Manager,
             Environmental Systems"，突出系统思维
4. 挖掘：发掘志愿者环保工作、研究生阶段的环境建模研究
5. 匹配：65% JD覆盖度——标记领域知识差距
6. 生成：简历 + 差距分析 + 求职信建议

结果：将技术技能与环境领域需求建立关联

示例3：职业空白期处理

用户："我有2年创业空白期。JD：{粘贴内容}"

技能处理：
1. 简历库构建：找到空白期前的简历
2. 研究：标准分析
3. 模板：将创业经历作为合法职位包含
4. 挖掘：发掘创业期间培养的技能（融资、产品开发、团队建设）
5. 匹配：将空白期重构为创业经历
6. 生成：将空白期呈现为宝贵经历的简历

结果：空白期转化为展现主动性与多元技能的优势

示例4：多职位批量处理（3个相似职位）

用户："我想申请这3个TPM职位：
      1. 微软1ES Principal PM
      2. Google Cloud Senior TPM
      3. AWS Container Services Senior TPM
      这是JD：{粘贴3份JD}"

技能处理：
1. 多职位检测：触发（检测到3份JD）
2. 信息收集：收集所有3份JD，初始化批次
3. 简历库构建：找到29份简历（仅执行一次）
4. 差距分析：识别14个差距，去重后8个独特差距
5. 共享挖掘：30分钟会话发掘5个新经历
   - 为非营利组织搭建的Kubernetes CI/CD
   - 为大学实验室完成的Azure迁移
   - 跨职能团队领导力案例
   - 近期黑客松项目
   - 开源贡献
6. 按职位处理（×3）：
   - 职位1（微软）：85%覆盖度，突出Azure/1ES适配性
   - 职位2（谷歌）：88%覆盖度，突出技术深度
   - 职位3（AWS）：78%覆盖度，在求职信建议中说明AWS差距
7. 批次收尾：所有3份简历审核通过，添加到简历库

结果：40分钟内生成3份高质量简历（vs 依次处理45分钟）
        5个新经历被记录，可用于未来申请
        平均覆盖度：84%，所有关键差距已解决

示例5：增量添加职位到批次

第1周：
用户："我想申请3个职位：{微软、谷歌、AWS}"
技能：[按上述流程处理批次，40分钟完成]

第2周：
用户："我又找到2个职位：Stripe和Meta。可以添加到我的批次吗？"
技能：
1. 加载现有批次（包含5个已发掘的经历）
2. 信息收集：添加职位4（Stripe）、职位5（Meta）
3. 增量差距分析：仅3个新差距（vs 原14个）
   - 支付系统（Stripe特定）
   - 社交网络（Meta特定）
   - React/前端（两者均要求）
4. 增量挖掘：仅针对新差距的10分钟会话
   - 发掘支付处理副业项目
   - 训练营中的React学习经历
   - 大规模系统设计课程
5. 按职位处理（×2）：独立处理职位4、5
6. 更新批次汇总：共5个职位，发掘8个经历

结果：20分钟内生成2份额外简历（vs 从零开始的30分钟）
        因无需重复询问8个已有差距，节省约20分钟

Testing Guidelines

测试指南

Manual Testing Checklist:

Test 1: Happy Path

- Provide JD with clear requirements
- Library with 10+ resumes
- Run all phases without skipping
- Verify generated files
- Check library update
PASS CRITERIA:
- All files generated correctly
- JD coverage >70%
- No errors in any phase

Test 2: Minimal Library

- Provide only 2 resumes
- Run through workflow
- Verify gap handling
PASS CRITERIA:
- Graceful warning about limited library
- Still produces reasonable output
- Gaps clearly identified

Test 3: Research Failures

- Use obscure company with minimal online presence
- Verify fallback to JD-only
PASS CRITERIA:
- Warning about limited research
- Proceeds with JD analysis
- Template still reasonable

Test 4: Experience Discovery Value

- Run with deliberate gaps in library
- Conduct experience discovery
- Verify new experiences integrated
PASS CRITERIA:
- Discovers genuine undocumented experiences
- Integrates into final resume
- Improves JD coverage

Test 5: Title Reframing

- Test various role transitions
- Verify title reframing suggestions
PASS CRITERIA:
- Multiple options provided
- Truthfulness maintained
- Rationales clear

Test 6: Multi-format Generation

- Generate MD, DOCX, PDF, Report
- Verify formatting consistency
PASS CRITERIA:
- All formats readable
- Formatting professional
- Content identical across formats

Regression Testing:

After any SKILL.md changes:
1. Re-run Test 1 (happy path)
2. Verify no functionality broken
3. Commit only if passes

手动测试 checklist：

测试1：正常流程

- 提供要求明确的JD
- 简历库包含10+份简历
- 完整运行所有阶段，不跳过
- 验证生成的文件
- 检查简历库更新
通过标准：
- 所有文件生成正确
- JD覆盖度>70%
- 所有阶段无错误

测试2：简历库内容极少

- 仅提供2份简历
- 运行完整流程
- 验证差距处理
通过标准：
- 清晰提示简历库内容有限
- 仍能生成合理输出
- 差距被明确识别

测试3：研究失败

- 使用在线信息极少的小众公司
- 验证 fallback 到仅JD分析
通过标准：
- 提示研究信息有限
- 继续基于JD分析
- 模板仍合理

测试4：经历挖掘价值

- 提供存在刻意差距的简历库
- 运行经历挖掘
- 验证新经历被整合
通过标准：
- 发掘真实的未记录经历
- 整合到最终简历
- 提升JD覆盖度

测试5：头衔重构

- 测试多种职业转型场景
- 验证头衔重构建议
通过标准：
- 提供多个选项
- 保持真实性
- 理由清晰

测试6：多格式生成

- 生成MD、DOCX、PDF、报告
- 验证格式一致性
通过标准：
- 所有格式可读
- 排版专业
- 各格式内容一致

回归测试：

修改SKILL.md后：
1. 重新运行测试1（正常流程）
2. 验证功能未被破坏
3. 仅在通过后提交