tailor-resume

What this skill does

# Resume Tailoring Skill

> **Priority hierarchy**: See `shared/references/priority-hierarchy.md` for conflict resolution.

Create compelling, tailored resumes that make it obvious you're the right candidate for a specific job.

## Quick Start

- `/proficiently:tailor-resume` - Start the flow (will ask for a job URL)
- `/proficiently:tailor-resume https://...` - Tailor resume for a specific job posting

## File Structure

```
scripts/
  tailor-resume.md        # Resume tailoring subagent prompt
```

The profile template is at `shared/templates/profile.md`.

## Data Directory

Resolve the data directory using `shared/references/data-directory.md`.

---

## Workflow

### Step 0: Check Prerequisites

Resolve the data directory, then check prerequisites per `shared/references/prerequisites.md`. Resume is required; profile is strongly recommended. If the user proceeds without a profile, set a flag to present all assumptions for verification (see Step 3a below).

If `$ARGUMENTS` is a URL, continue to Step 1.
Otherwise, ask for a job URL.

### Step 1: Get Job Details

Accept a job URL from the user (from `$ARGUMENTS` or by asking).

Use Claude in Chrome MCP tools to fetch the job posting per `shared/references/browser-setup.md`.

Parse and extract:
- **Job title** and level (IC vs. manager, seniority)
- **Company** name and what they do
- **Responsibilities** - what the job actually involves day-to-day
- **Requirements** - must-have qualifications
- **Nice-to-haves** - preferred qualifications
- **Keywords** - industry terms, tools, methodologies mentioned
- **Team context** - who they report to, team size, cross-functional partners
- **Company stage/size** indicators

**Create a job folder** at `DATA_DIR/jobs/[company-slug]-[date]/` and save the parsed job posting to `posting.md`.

If the page can't be loaded or parsed, ask the user to paste the job description directly.

### Step 2: Analyze Match

Before writing, map the candidate's experience to the job:

1. **Level match**: Confirm the candidate's experience level matches the role. A VP-level candidate applying for a Director role should lean on strategic impact. A Director applying for VP should emphasize scope and leadership growth.

2. **Requirement mapping**: For each job requirement, identify the strongest evidence from the work history profile:
   - Direct experience ("Led SEO strategy" → job asks for SEO experience)
   - Analogous experience ("Scaled marketplace from 1M to 10M users" → job asks for growth experience)
   - Transferable skills ("Managed 30-person team" → job asks for leadership)

3. **Gap identification**: Note any requirements where the candidate has no clear match. These should NOT be fabricated - instead, find adjacent experience that demonstrates capability.

4. **Keyword alignment**: Identify the job posting's language and terminology to mirror in the resume.

5. **Compelling narrative**: Determine the 2-3 sentence story of why this person is the obvious choice. What's the throughline?

### Step 3: Generate Tailored Resume

Create the tailored resume following these principles:

**Structure:**
- **Header**: Name, contact info, LinkedIn (same as original)
- **Summary/Profile**: 2-3 sentences positioning the candidate specifically for THIS role. Not generic - reference the company and role context directly.
- **Experience**: All roles from the resume, but with bullet points rewritten, reordered, and selectively emphasized
- **Skills**: Reorganized to lead with what the job asks for
- **Education**: Same as original

**Bullet point principles:**
- Lead each role with the bullets most relevant to the target job
- Rewrite bullets to mirror the job posting's language where authentic
- Include metrics and quantified impact (from work history profile)
- Remove or de-emphasize bullets that aren't relevant to this specific role
- Add bullets from the work history profile that weren't on the original resume but ARE relevant to this job
- Each bullet should start with a strong action verb
- Each bullet should show: what you did → how you did it → what the impact was

**Level-matching:**
- For executive roles: emphasize strategy, P&L ownership, board interaction, team building, cross-functional leadership
- For director roles: emphasize program ownership, team management, operational excellence, stakeholder management
- For IC roles: emphasize hands-on execution, technical depth, individual contributions, collaboration

**Writing rules (CRITICAL — target Flesch score above 90):**
- Write like a sharp executive, not a language model. Short sentences. Plain words.
- Every sentence gets one idea. If a sentence has "and" connecting two unrelated clauses, split it.
- Never use emdashes. Use commas, periods, colons, semicolons, or parentheses instead.
- Vary sentence structure. Not every bullet should follow the exact same pattern.
- No preamble clauses. Bad: "Leveraging deep expertise in marketplace dynamics, led..." Good: "Led..."
- No stacking adjectives. Bad: "cross-functional, data-driven, customer-centric approach". Pick one.
- No filler phrases: "demonstrating ability to", "showcasing expertise in", "with a track record of", "needed to drive", "spanning", "leveraging", "utilizing"
- No compound noun piles: "AI-driven product opportunity identification and execution" — just say what you did
- Summaries must be 2-3 SHORT sentences. Each sentence under 20 words. No run-on sentences connecting multiple capabilities with commas and "and".

**Strict accuracy rules (CRITICAL):**
- ONLY use information explicitly stated on the resume or in the work history profile
- NEVER assume business model (B2B vs B2C), revenue type, or company stage unless stated
- NEVER infer scope beyond what's written (e.g., don't add "P&L ownership" if resume says "revenue targets")
- NEVER add responsibilities, skills, or functional areas the candidate didn't mention
- NEVER assume cross-functional partnerships that aren't listed
- When the resume is ambiguous, use conservative language or omit the detail entirely
- If you need to frame experience differently for the target role, only reframe what IS there, never invent what ISN'T

**What NOT to do:**
- Don't fabricate experience or skills the candidate doesn't have
- Don't use generic buzzwords that aren't backed by specific experience
- Don't make the resume longer than 2 pages
- Don't change job titles or dates
- Don't remove roles (gaps look suspicious)
- Don't assume anything about the candidate's business, scope, or responsibilities that isn't explicitly documented

### Step 3b: Critique and Rewrite (MANDATORY — do this before presenting)

Before showing the resume to the user, review every line and fix AI-sounding writing. Go sentence by sentence and ask:

1. **Is this sentence doing too much?** If it has more than one comma-separated clause, split it into separate sentences or bullet points.
2. **Would a real person say this?** Read it out loud. If it sounds like a LinkedIn post or a ChatGPT response, rewrite it.
3. **Is there filler?** Cut any phrase that doesn't add information. "Demonstrating ability to identify and execute on AI-driven product opportunities from ideation through production" → "Built an AI product from idea to production."
4. **Are there stacked buzzwords?** "Cross-functional, data-driven, customer-centric leadership" → pick the one that matters for this job and give a concrete example.
5. **Is the summary under control?** Max 3 sentences. Each under 20 words. No sentence should list more than 2 things.

**Common AI patterns to kill:**
- "I combine X with Y, Z, and the W needed to..." → Split into separate statements
- "...demonstrating [abstract quality]" → Delete or replace with the actual result
- "...spanning [long list]" → Pick the most relevant 1-2 items
- "Led [action], [action], and [action] across [scope]" → One action per bullet
- Any bullet over 2 lines is probably trying to do too much — split it
- Gerund clauses tacked onto th