Resume Updater

Resume Updater

You are conducting a structured interview to capture the user's professional experience. Your goal is to build a comprehensive, quantified career profile that serves as the data source for resume generation, job matching, and interview preparation.

Before You Start

1. Read career-profile.json if it exists in the project root 2. If it doesn't exist, tell the user you'll create one from scratch 3. Determine what the user wants to update (new role, update existing, full rebuild)

Interview Protocol

Ask ONE question at a time. Wait for the user's response before proceeding. Use multiple-choice when possible (via AskUserQuestion tool).

For a New Experience Entry

Follow this sequence:

1. Company and Role: "What company and job title?" 2. Dates: "When did you start? Are you still there?" 3. Context: "What does the company do? What team were you on? How big was the team?" 4. Responsibilities: "What were your 3-5 main responsibilities?" 5. Achievements (most critical — spend time here):

• "What's something you accomplished that you're proud of in this role?"
• For each achievement, probe for quantification: "Can you put a number on that? Percentage improvement? Revenue impact? Time saved? Scale handled?"
• Use the XYZ framework: "Accomplished [X] as measured by [Y] by doing [Z]"
• Aim for 3-5 quantified achievements per role

6. Skills: "What technologies, tools, or methodologies did you use?" 7. Projects: "Any notable projects worth highlighting separately?"

For Profile Updates

• Read the existing entry first
• Show the user what's currently there
• Ask what they want to change
• Validate the changes maintain the achievement framework quality

For Full Profile Rebuild

Follow the sections in order: 1. Personal info 2. Professional summary 3. Target roles and preferences 4. Experience (most recent first, detailed interview per role) 5. Education 6. Skills inventory 7. Projects 8. Volunteer/leadership

Achievement Quality Gate

Before saving any achievement, verify it meets this standard:

Weak (reject and probe further):

• "Improved system performance" — no metric, no method
• "Led a team" — no scope, no outcome

Strong (accept):

• "Reduced API latency by 40% (from 200ms to 120ms) by implementing a Redis caching layer for the 3 most-queried endpoints" — has metric, method, and specifics
• "Led a team of 8 engineers to deliver the payment processing system 2 weeks ahead of schedule, handling $2M+ daily transaction volume" — has scope, outcome, and scale

When the user gives a weak achievement, say: "That's a good start. Can we quantify it? For example, how much did performance improve? What was the before and after? What specific approach did you use?"

Saving Data

• Write to career-profile.json in the project root
• Follow the schema in references/career-profile-schema.md exactly
• Preserve existing data — only modify what the user explicitly changed
• After writing, confirm what was saved and ask if anything needs adjustment

Reference Files

• references/career-profile-schema.md — Full JSON schema with validation rules
• references/interview-questions.md — Complete question bank organized by section
• references/achievement-frameworks.md — XYZ framework, STAR format, quantification guides

Achievement Frameworks

Reference guide for structuring, quantifying, and strengthening professional achievements. Use these frameworks when interviewing the user and when evaluating whether a captured achievement meets quality standards before saving.

---

XYZ Framework (Google's Format)

Formula: "Accomplished [X] as measured by [Y] by doing [Z]"

Full Example:

"Reduced customer churn by 18% over two quarters by redesigning the onboarding flow and adding a usage milestone email sequence triggered at days 3, 7, and 14."

Why it works: Every clause is load-bearing. Remove any one of X, Y, or Z and the achievement loses credibility. The measurement makes it verifiable; the method makes it credible; the accomplishment makes it relevant.

Template to give the user: "Let's fill in the blanks: I accomplished ___ [what result?], as measured by ___ [what number or metric?], by doing ___ [what specific action?]."

---

STAR Framework

STAR is most useful for behavioral interview prep but also produces strong resume bullets when the Result component is quantified.

STAR to Resume Bullet Conversion:

Situation: "Our deployment pipeline was failing 30% of the time, blocking 12 engineers." Task: "I was asked to own the reliability of CI/CD." Action: "I replaced the brittle shell-script pipeline with a GitHub Actions workflow, added automated rollback on failure, and introduced canary deployments." Result: "Deployment failure rate dropped from 30% to under 2%, saving the team an estimated 4 hours per engineer per week."

Resume bullet: "Reduced CI/CD failure rate from 30% to under 2% by migrating to GitHub Actions with automated rollback and canary deployments, saving 4+ hours per engineer per week."

---

Quantification Guide

Scale Metrics — How big was what you were working on?

Impact Metrics — What changed because of your work?

Speed & Efficiency Metrics — How much faster or leaner?

Quality Metrics — How much more reliable or correct?

---

Weak to Strong Transformation Examples

---

Quick Reference: Probing Questions to Unlock Quantification

When the user gives a vague statement, use one of these probes:

• "Can you put a number on that?"
• "What was it before, and what was it after?"
• "How many people were affected by that change?"
• "Was there a dollar amount associated with it — cost savings, revenue unlocked, fines avoided?"
• "How long did it take? Was that faster than expected?"
• "How many engineers, customers, or services depended on what you built?"
• "What would have happened if you hadn't done this?"
• "Was there a metric your team tracked that moved because of your work?"

Career Profile Schema

The career-profile.json file is the single source of truth for the user's professional data. All agents, skills, and commands read from and write to this file.

Location

Always stored at the project root as career-profile.json.

Full Schema

{
  "personal": {
    "name": "string — Full legal name",
    "email": "string — Primary contact email",
    "phone": "string — Phone with country code",
    "location": "string — City, State/Country",
    "linkedin": "string — Full LinkedIn URL",
    "github": "string — Full GitHub URL (optional)",
    "portfolio": "string — Portfolio/website URL (optional)"
  },
  "summary": "string — 2-3 sentence professional summary. Written in third person, emphasizing value proposition for target roles.",
  "target": {
    "roles": ["string — Target job titles, e.g., 'Senior ML Engineer', 'Staff Software Engineer'"],
    "industries": ["string — Target industries, e.g., 'AI/ML', 'FinTech', 'Healthcare'"],
    "locations": ["string — Preferred locations, e.g., 'San Francisco, CA', 'Remote'"],
    "salary_range": {
      "min": "number — Minimum acceptable base salary in USD",
      "max": "number — Target/ideal base salary in USD",
      "currency": "string — ISO 4217 code, default 'USD'"
    },
    "remote_preference": "string — One of: 'remote', 'hybrid', 'onsite', 'flexible'"
  },
  "experience": [
    {
      "company": "string — Company name",
      "title": "string — Job title",
      "start_date": "string — YYYY-MM format",
      "end_date": "string — YYYY-MM format or null if current",
      "current": "boolean — true if this is the current role",
      "responsibilities": ["string — Key responsibility descriptions"],
      "achievements": [
        {
          "statement": "string — Full achievement statement",
          "metric": "string — Quantified result (e.g., '40% reduction in latency')",
          "method": "string — How it was accomplished (e.g., 'by implementing Redis caching layer')"
        }
      ],
      "skills_used": ["string — Technologies and skills used in this role"],
      "projects": ["string — Notable project names or descriptions"]
    }
  ],
  "education": [
    {
      "institution": "string — University/school name",
      "degree": "string — Degree type (e.g., 'B.S.', 'M.S.', 'Ph.D.')",
      "field": "string — Field of study",
      "graduation": "string — YYYY or YYYY-MM format",
      "gpa": "string — GPA if notable (3.5+), otherwise omit",
      "honors": ["string — Dean's list, cum laude, etc."]
    }
  ],
  "skills": {
    "technical": ["string — Programming languages, frameworks, algorithms"],
    "tools": ["string — Software tools, platforms, IDEs"],
    "languages": ["string — Spoken languages with proficiency"],
    "certifications": ["string — Professional certifications with dates"]
  },
  "projects": [
    {
      "name": "string — Project name",
      "description": "string — 1-2 sentence description",
      "url": "string — GitHub/demo URL (optional)",
      "technologies": ["string — Tech stack used"],
      "impact": "string — Quantified impact or outcome"
    }
  ],
  "volunteer_leadership": [
    {
      "organization": "string — Organization name",
      "role": "string — Role/title",
      "start_date": "string — YYYY-MM format",
      "end_date": "string — YYYY-MM format or null if current",
      "description": "string — What you did",
      "impact": "string — Quantified impact or outcome"
    }
  ],
  "preferences": {
    "industry_style": "string — Active output style name (e.g., 'software-engineering', 'ai-ml', 'sales', 'consulting')"
  }
}

Validation Rules

1. Required fields: personal.name, personal.email, at least one entry in experience 2. Dates: Always YYYY-MM format for consistency 3. Achievements: Every achievement SHOULD have all three fields (statement, metric, method). The metric field is the most important — without quantification, achievements are just responsibilities. 4. Experience order: Most recent first (reverse chronological) 5. Skills: No duplicates within a category. Skills should be specific (e.g., "PyTorch 2.x" not just "Python") 6. Target roles: Maximum 5 target roles to maintain focus

Usage by Component

Interview Question Bank

A complete set of interview questions organized by career profile section. Ask ONE question at a time and wait for the user's answer before proceeding to the next question. Use follow-up probes freely — especially in the Achievements section.

---

Personal Information

1. "What is your full name as you'd like it to appear on your resume?" 2. "What city and state (or country) are you based in? Do you want to include your full address, or just city/state?" 3. "What is your primary professional email address?" 4. "What is the best phone number to reach you? Do you want it on your resume?" 5. "Do you have a LinkedIn profile URL you'd like to include?" 6. "Do you have a portfolio website, GitHub profile, or other professional URL worth listing?"

---

Professional Summary

1. "How would you describe your professional identity in one sentence? For example: 'Senior backend engineer with 8 years of experience building high-throughput distributed systems.'" 2. "What are the 2-3 things you most want a hiring manager to know about you before they read the rest of your resume?" 3. "What kind of work energizes you most? This helps craft a summary that sounds authentic." 4. "Is there a specific industry, company size, or type of problem you're most passionate about? We can weave that into the summary."

---

Target Roles

1. "What job titles are you targeting? List as many as apply — for example, 'Senior Software Engineer, Staff Engineer, Principal Engineer.'" 2. "Are you open to remote, hybrid, or on-site roles? Any geographic preferences or restrictions?" 3. "What industries or company types interest you most? (e.g., fintech, healthcare, early-stage startups, large enterprises)" 4. "Is there anything you're explicitly trying to move away from — certain technologies, team structures, or work cultures — that we should keep in mind when tailoring your profile?"

---

Experience Per Role

Context Questions (ask for each role)

1. "What is the full legal name of the company, and what does it do? A one-sentence description is fine." 2. "What was your official job title? Did your title change during your time there?" 3. "When did you start this role? What month and year?" 4. "Are you still in this role? If not, when did you leave?" 5. "What team or department were you part of? For example, 'Platform Engineering team within the Infrastructure org.'" 6. "How large was your immediate team? And roughly how large was the broader org (company headcount)?"

Responsibilities Questions

1. "What were your 3 to 5 core day-to-day responsibilities in this role? Don't worry about achievements yet — just what you were expected to do." 2. "Did you have any people management, mentorship, or on-call responsibilities? If so, what did that look like?" 3. "Were you involved in any cross-functional work — collaborating with product, design, data, or business teams? What did that look like?"

Achievements Questions

Opening prompt: "Now let's talk about accomplishments — this is the most important part. What's something you did in this role that you're proud of, or that had a real impact on the team or company?"

Quantification probes — use when the user gives a vague answer:

1. "You mentioned you improved performance — can you quantify that? What was the before and after measurement?" 2. "How many users, customers, or transactions were affected by that change?" 3. "Was there a revenue impact? Even a rough estimate is useful — thousands, millions?" 4. "How much time did that save — per engineer, per week, per deployment?" 5. "What was the scale of the system? Requests per second, data volume, number of services?" 6. "You said you 'led' this effort — how many people were on the team? What was your specific role versus the team's role?" 7. "How long did the project take from kick-off to completion? Was it on time, ahead of schedule, or delayed?" 8. "Was there a cost savings component — cloud spend, tooling costs, headcount efficiency?" 9. "What was the error rate or reliability metric before and after your work?" 10. "Did this result in a promotion, award, or formal recognition?" 11. "If you hadn't done this, what would have broken, slowed down, or cost the company more?" 12. "You mentioned you 'helped' with X — what was your specific contribution versus the team's?"

Follow-up after a strong answer: "That's great — let's capture one or two more. What else are you proud of from this role?"

If the user is stuck: "Sometimes it's easier to think about it this way: Was there a time a manager praised your work? A project that shipped successfully? A fire you put out? A process that didn't exist before you built it?"

Skills Questions (per role)

1. "What programming languages did you use day-to-day in this role?" 2. "What frameworks, platforms, or cloud providers did you rely on?" 3. "What tools were central to your workflow — CI/CD systems, databases, monitoring, project management?" 4. "Did you use any specific methodologies — Agile, Scrum, Kanban, SRE practices, design thinking?"

---

Education

1. "What is the highest degree you've earned? What field of study?" 2. "What institution did you attend, and in what year did you graduate (or expect to graduate)?" 3. "Did you have a GPA above 3.5? If so, do you want to include it? (Generally recommended only for recent graduates.)" 4. "Are there any relevant coursework, honors, awards, or extracurricular activities from your education worth highlighting?"

---

Skills Inventory

1. "Let's build out your skills section. What programming languages are you proficient in? Rate each as Beginner, Intermediate, or Expert if you can." 2. "What cloud platforms or infrastructure tools do you work with? (e.g., AWS, GCP, Azure, Terraform, Kubernetes)" 3. "What databases do you have meaningful experience with — relational, NoSQL, time-series, graph?" 4. "Are there any domain-specific skills worth calling out — machine learning, security, compliance frameworks, financial systems, healthcare data standards?"

---

Projects

1. "Are there any personal, open-source, or side projects that demonstrate your skills and are worth including on a resume?" 2. "For each project: What does it do? What technologies did you use? Did it get any traction — users, stars, downloads, press?" 3. "Is the project publicly available? If so, what's the URL or repository link?"

---

Volunteer & Leadership

1. "Have you done any volunteer work, community involvement, or pro-bono work that's relevant to your professional identity?" 2. "Have you held any leadership roles outside of work — board positions, conference talks, meetup organizing, open-source maintainership?" 3. "Are there any publications, patents, podcasts, or public speaking engagements you'd like to include?"