resume-bullet-extraction
Auto-invoke after task completion to generate powerful resume bullet points from completed work.
Best use case
resume-bullet-extraction is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Auto-invoke after task completion to generate powerful resume bullet points from completed work.
Teams using resume-bullet-extraction should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/resume-bullet-extraction/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How resume-bullet-extraction Compares
| Feature / Agent | resume-bullet-extraction | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Auto-invoke after task completion to generate powerful resume bullet points from completed work.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Resume Bullet Extraction
> "Your resume isn't a job description. It's a highlight reel of impact."
## Purpose
Transform completed work into powerful resume bullet points that demonstrate value and technical competence.
---
## The Bullet Formula
```
[Strong Action Verb] + [What You Did] + [Technical Context] + [Impact/Result]
```
### Components
| Component | Purpose | Example |
|-----------|---------|---------|
| Action Verb | Shows initiative | Engineered, Architected, Optimized |
| What You Did | The accomplishment | JWT authentication system |
| Technical Context | Shows skill | using React, Node.js, Redis |
| Impact | Why it matters | reducing auth errors by 40% |
---
## Strong Action Verbs
### Building/Creating
- Engineered
- Architected
- Developed
- Implemented
- Built
- Designed
### Improving
- Optimized
- Enhanced
- Refactored
- Modernized
- Streamlined
- Accelerated
### Problem Solving
- Resolved
- Debugged
- Eliminated
- Reduced
- Prevented
- Mitigated
### Leading/Collaborating
- Led
- Spearheaded
- Collaborated
- Mentored
- Coordinated
---
## Impact Quantification
Always try to quantify. If you can't measure directly, estimate reasonably.
### Performance
- "reducing load time by 60%"
- "improving response time from 2s to 200ms"
- "handling 10,000+ concurrent users"
### Reliability
- "achieving 99.9% uptime"
- "eliminating production errors"
- "reducing bug reports by 50%"
### Business
- "increasing user retention by 25%"
- "supporting 50,000 monthly active users"
- "saving 10 hours/week of manual work"
### Scale
- "processing 1M+ transactions daily"
- "managing 500GB of user data"
- "serving 100+ API endpoints"
---
## Bullet Templates
### Feature Implementation
```
[Verb] [feature] using [technologies] that [impact]
Examples:
- Engineered JWT authentication with refresh token rotation using Node.js and Redis, eliminating session hijacking vulnerabilities
- Built real-time notification system using WebSockets and React, improving user engagement by 35%
```
### Performance Optimization
```
[Verb] [what] by [how], resulting in [metric]
Examples:
- Optimized database queries through index analysis and query restructuring, reducing API response time by 70%
- Accelerated page load performance by implementing code splitting and lazy loading, improving Core Web Vitals by 40%
```
### Bug Fix / Problem Solving
```
[Verb] [problem] by [solution], preventing [impact]
Examples:
- Resolved race condition in checkout flow by implementing optimistic locking, preventing duplicate charges
- Eliminated memory leak in React components through proper cleanup, reducing crash reports by 90%
```
### Architecture / Refactoring
```
[Verb] [system] from [old] to [new], enabling [benefit]
Examples:
- Migrated monolithic application to microservices architecture using Docker and Kubernetes, enabling independent team deployments
- Refactored authentication module from session-based to JWT, reducing server memory usage by 60%
```
---
## Quality Checklist
- [ ] Starts with strong action verb (not "Responsible for")
- [ ] Includes specific technologies
- [ ] Has quantifiable impact OR clear business value
- [ ] Is one concise sentence
- [ ] Avoids jargon recruiters won't understand
- [ ] Demonstrates ownership ("I" is implied)
- [ ] Would make sense to a technical interviewer
---
## Bad vs Good Examples
### Bad
```
❌ "Worked on the login system"
- No action verb, no specifics, no impact
❌ "Responsible for user authentication"
- Passive, no accomplishment shown
❌ "Helped with performance improvements"
- Vague, no ownership, no metrics
```
### Good
```
✅ "Engineered JWT authentication with refresh token rotation, reducing session vulnerability surface and supporting 50,000+ daily active users"
✅ "Optimized PostgreSQL queries through index analysis, reducing average API response time from 800ms to 120ms"
✅ "Built responsive dashboard using React and D3.js, enabling real-time visualization of 1M+ daily events"
```
---
## Extraction Flow
### Step 1: Identify the Highlight
> "What's the most impressive aspect of what you just built?"
Options:
- Technical complexity solved
- Business problem addressed
- Performance improved
- Scale achieved
- Security enhanced
### Step 2: Draft the Bullet
Use the formula: Verb + What + Technical Context + Impact
### Step 3: Quantify
> "Can we add numbers? How much faster? How many users? What percentage improvement?"
### Step 4: Polish
- Remove weak words ("helped", "assisted", "worked on")
- Add specific technologies
- Ensure it stands alone (no context needed)
---
## Resume Section Placement
| Bullet Type | Resume Section |
|-------------|---------------|
| Feature/System built | Projects or Experience |
| Performance optimization | Experience (shows impact) |
| Architecture decision | Experience or Technical Skills |
| Learning/Growth | Skills or Side Projects |
---
## Socratic Bullet Questions
1. **Finding impact:** "If this feature didn't exist, what would break?"
2. **Quantifying:** "How many users does this affect? How much time does it save?"
3. **Technical depth:** "What would you tell a technical interviewer about how this works?"
4. **Differentiation:** "What makes your implementation better than a basic solution?"
---
## Save Location
Bullets are compiled in STAR story files:
```
mentorspec/career/stories/[date]-[feature-name].md
```
The resume bullet appears at the end of each story for easy extraction.Related Skills
extraction-proposer
Scan ICE-Crawler extraction logs, pick promising algorithms/tools, and emit skill creation proposals (name, scope, source files, next steps).
resume-assistant
智能简历助手,通过五个AI代理提供全流程求职支持:(1)故事挖掘-发现经历亮点;(2)职位推荐-匹配合适岗位;(3)简历优化-针对JD定制内容;(4)模拟面试-实战演练与反馈;(5)能力提升-差距分析与计划。适用于简历创建、优化、面试准备、职业规划等求职相关任务。
../../../engineering/autoresearch-agent/skills/resume/SKILL.md
No description provided.
security-requirement-extraction
Derive security requirements from threat models and business context. Use when translating threats into actionable requirements, creating security user stories, or building security test cases.
control-loop-extraction
Extract and analyze agent reasoning loops, step functions, and termination conditions. Use when needing to (1) understand how an agent framework implements reasoning (ReAct, Plan-and-Solve, Reflection, etc.), (2) locate the core decision-making logic, (3) analyze loop mechanics and termination conditions, (4) document the step-by-step execution flow of an agent, or (5) compare reasoning patterns across frameworks.
star-story-extraction
Auto-invoke after task completion to extract interview-ready STAR stories from completed work.
design-spec-extraction
Extract comprehensive JSON design specifications from visual sources including Figma exports, UI mockups, screenshots, or live website captures. Produces W3C DTCG-compliant output with component trees, suitable for code generation, design documentation, and developer handoff.
standards-extraction
Extract coding standards and conventions from CONTRIBUTING.md, .editorconfig, linter configs. Use for onboarding and ensuring consistent contributions.
context-resume
恢复之前保存的会话上下文。列出所有待处理的 session,读取选定 session 的任务信息,更新进度,任务全部完成后删除文件。
Resume Tailor
## Overview
DHDNA Profiler — Cognitive Pattern Extraction
A structured system for extracting the cognitive fingerprint of any text's author. Based on the Digital Human DNA (DHDNA) framework — the theory that every mind has a unique signature pattern expressed through how it reasons, decides, values, and communicates.
tailored-resume-generator
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances