star-story-extraction
Auto-invoke after task completion to extract interview-ready STAR stories from completed work.
Best use case
star-story-extraction is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. Auto-invoke after task completion to extract interview-ready STAR stories from completed work.
Auto-invoke after task completion to extract interview-ready STAR stories from completed work.
Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.
Practical example
Example input
Use the "star-story-extraction" skill to help with this workflow task. Context: Auto-invoke after task completion to extract interview-ready STAR stories from completed work.
Example output
A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.
When to use this skill
- Use this skill when you want a reusable workflow rather than writing the same prompt again and again.
When not to use this skill
- Do not use this when you only need a one-off answer and do not need a reusable workflow.
- Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/star-story-extraction/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How star-story-extraction Compares
| Feature / Agent | star-story-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 extract interview-ready STAR stories 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
# STAR Story Extraction > "Every feature you build is an interview answer waiting to be told." ## Purpose Transform completed work into compelling interview stories using the STAR method. These stories demonstrate real problem-solving ability. --- ## The STAR Method | Component | Question | Focus | |-----------|----------|-------| | **S**ituation | "What was the context?" | Set the scene, explain the problem | | **T**ask | "What were YOU responsible for?" | YOUR specific role and responsibility | | **A**ction | "What did YOU do?" | Specific technical actions YOU took | | **R**esult | "What was the outcome?" | Impact, metrics, improvements | --- ## Extraction Flow ### Step 1: Identify the Story Type What kind of problem did you solve? | Story Type | Good For Questions Like | |------------|------------------------| | Technical challenge | "Tell me about a difficult bug you solved" | | Feature implementation | "Describe a feature you're proud of" | | Performance optimization | "How did you improve system performance?" | | Security fix | "Tell me about a security issue you addressed" | | Refactoring | "Describe a time you improved code quality" | | Learning curve | "Tell me about a time you learned something quickly" | ### Step 2: Guide Through STAR #### Situation (2-3 sentences) > "What was the context? What problem or challenge existed before you started?" **Good elements:** - Business context (why it mattered) - Technical constraints - Scale/impact of the problem **Avoid:** - Too much background - Irrelevant details - Blaming others #### Task (1-2 sentences) > "What were YOU specifically responsible for? What was your role?" **Good elements:** - Clear ownership - Specific scope - Why you were the one to do it **Avoid:** - "We did this" (use "I") - Vague responsibilities #### Action (The meat - 3-5 sentences) > "Walk me through the specific steps YOU took. Be technical." **Good elements:** - Specific technologies used - Problem-solving approach - Trade-offs considered - Technical decisions made **Avoid:** - Glossing over the how - Buzzword soup - "I just implemented it" #### Result (1-2 sentences) > "What was the outcome? Can you quantify the impact?" **Good elements:** - Metrics where possible (50% faster, 0 bugs in production) - Business impact - What you learned **Avoid:** - "It worked" (too vague) - No mention of impact --- ## Story Quality Checklist - [ ] Uses "I" not "we" (shows ownership) - [ ] Includes specific technologies - [ ] Demonstrates problem-solving - [ ] Shows technical depth - [ ] Has measurable result if possible - [ ] Is 2-3 minutes when spoken - [ ] Answers the implied "why hire you?" --- ## Story Template ```markdown # STAR Story: [Feature/Problem Name] **Date:** [When completed] **Type:** [Technical Challenge / Feature / Performance / Security / Refactor] ## Situation [The context. What problem existed? Why did it matter?] ## Task [YOUR specific responsibility. What were YOU asked to do?] ## Action [The specific steps YOU took. Be technical. Show your thought process.] ## Result [The outcome. Metrics if possible. What impact did it have?] --- ## Interview Variations This story can answer: - "Tell me about a time you [X]" - "Describe a challenging [Y] you worked on" - "How did you approach [Z]?" ## Key Technical Points to Mention - [Technology/pattern 1] - [Technology/pattern 2] - [Decision/trade-off made] ``` --- ## Example: Good vs Bad STAR ### Bad Story > "I built a login form. It had validation. It worked." Problems: No context, no challenge, no depth, no impact. ### Good Story > **Situation:** Our SaaS application was experiencing a 40% drop-off during signup because the existing form had poor UX and no real-time validation, frustrating users. > > **Task:** I was responsible for rebuilding the entire authentication flow, focusing on reducing friction while maintaining security. > > **Action:** I implemented a multi-step form with real-time validation using React Hook Form for performance. I added JWT authentication with secure refresh token rotation to handle long sessions. The key challenge was balancing security (short token expiry) with UX (no jarring logouts), which I solved by implementing silent refresh 5 minutes before expiry. > > **Result:** Sign-up completion improved by 35%, and we've had zero authentication-related security incidents since launch. The pattern I built is now used across our other products. --- ## Socratic Story Questions Guide the junior with these: 1. **Finding the story:** "What was the hardest part of this feature?" 2. **Adding depth:** "Walk me through your debugging process when X happened." 3. **Showing ownership:** "What decision did YOU make that shaped this?" 4. **Quantifying results:** "How would you measure the impact of this work?" 5. **Interview connection:** "If an interviewer asked about [topic], how would this story fit?" --- ## Common Story Mistakes | Mistake | Fix | |---------|-----| | "We built..." | Use "I implemented..." | | Too long (10+ minutes) | Cut to 2-3 minutes | | No technical depth | Add specific technologies and decisions | | No result | Always end with impact | | Only happy path | Include challenges overcome | --- ## Save Location Stories are saved to: ``` mentorspec/career/stories/[date]-[feature-name].md ``` Example: `mentorspec/career/stories/2026-01-15-jwt-auth.md`
Related Skills
startup-metrics-framework
This skill should be used when the user asks about "key startup metrics", "SaaS metrics", "CAC and LTV", "unit economics", "burn multiple", "rule of 40", "marketplace metrics", or requests guidance on tracking and optimizing business performance metrics.
startup-financial-modeling
This skill should be used when the user asks to "create financial projections", "build a financial model", "forecast revenue", "calculate burn rate", "estimate runway", "model cash flow", or requests 3-5 year financial planning for a startup.
startup-business-analyst-market-opportunity
Generate comprehensive market opportunity analysis with TAM/SAM/SOM calculations
startup-business-analyst-financial-projections
Create detailed 3-5 year financial model with revenue, costs, cash flow, and scenarios
startup-business-analyst-business-case
Generate comprehensive investor-ready business case document with market, solution, financials, and strategy
startup-analyst
Expert startup business analyst specializing in market sizing, financial modeling, competitive analysis, and strategic planning for early-stage companies. Use PROACTIVELY when the user asks about market opportunity, TAM/SAM/SOM, financial projections, unit economics, competitive landscape, team planning, startup metrics, or business strategy for pre-seed through Series A startups.
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.
data-storytelling
Transform data into compelling narratives using visualization, context, and persuasive structure. Use when presenting analytics to stakeholders, creating data reports, or building executive presentations.
convex-quickstart
Initializes a new Convex project from scratch or adds Convex to an existing app. Use this skill when starting a new project with Convex, scaffolding with npm create convex@latest, adding Convex to an existing React, Next.js, Vue, Svelte, or other frontend, wiring up ConvexProvider, configuring environment variables for the deployment URL, or running npx convex dev for the first time, even if the user just says "set up Convex" or "add a backend."
rmcp-quickstart
Quick start guide for creating MCP servers with the rmcp crate - installation, concepts, and first server
cold-start-optimizer
Provides guidance on reducing Lambda cold start times through binary optimization, lazy initialization, and deployment strategies. Activates when users discuss cold starts or deployment configuration.
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.