/setup

/setup - Profile Onboarding

You are running the onboarding setup for the AI Job Search framework. Your goal is to collect the user's professional information and populate all profile files so the `/apply` workflow works out of the box.

There are three paths into setup. Step 0 picks the right one; all three converge on Step 3 (file generation) and Step 4 (confirmation).

---

Step 0: Welcome & Choose Path

If `$ARGUMENTS` contains `--section <name>`, skip directly to that section in Path C for an update-only flow. Do not run the path-selection prompt below.

Otherwise, first check where this working copy would publish to — **before anything is written, not after** (the Step 4 privacy note fires only once every file is already on disk, which is too late to inform the decision). Run `git remote get-url origin`; if the command fails (no remote, or not a git checkout), skip this check silently. If there is a GitHub `origin`, check it with `gh repo view <owner/repo> --json visibility,isFork` when `gh` is available. If the origin is a **public fork** of the template — or its visibility cannot be determined — warn now and wait:

> **Heads-up before we start:** your `origin` points at `<owner/repo>`, which is a > public GitHub fork. This setup writes your personal data (name, contact details, > employment history, salary expectations) into **tracked** files, and anything you > commit *and push* to that fork is visible to anyone. Two safe options: keep your > profile commits local and never push them, or push to a **private** repository > instead — SETUP.md section 8 has the two-minute private-remote recipe. Want to > continue with the setup?

Wait for the user's confirmation before showing the path prompt. A private origin, no origin, or a non-fork remote needs no warning — continue silently.

Then, before greeting the user, scan the `documents/` folder. Use Glob with `documents/**/*` and count files per subfolder (`cv/`, `linkedin/`, `diplomas/`, `references/`, `applications/`).

Then welcome the user with a single message that lists three paths. The wording changes based on what was found.

**If `documents/` has files** in one or more subfolders, lead with Path A:

> **Welcome to the AI Job Search setup!** > > I'll help you build your professional profile so Claude can evaluate job postings, tailor CVs, write cover letters, and prepare you for interviews. > > I see files in your `documents/` folder: [list per subfolder, e.g. "2 in cv/, 1 in linkedin/, 3 in references/"]. Three ways to start: > > **Path A: Read my documents folder** (recommended for what you have) - I'll read everything in `documents/`, cross-reference for consistency, and build your profile from real source materials. Idempotent and safe to re-run as you add more documents. > > **Path B: Single CV import** - Paste or @-mention a single CV/resume here. I'll extract it and ask follow-up questions for what's missing. > > **Path C: Interview mode** - I'll walk you through structured questions section by section. > > Which would you like?

**If `documents/` is empty or missing**, surface Path A as a "do this if you have materials" option:

> **Welcome to the AI Job Search setup!** > > I'll help you build your professional profile so Claude can evaluate job postings, tailor CVs, write cover letters, and prepare you for interviews. > > Three ways to start: > > **Path A: Documents folder** (best signal if you have several materials) - Drop your CV / LinkedIn export / diplomas / reference letters in the `documents/` folder, then say "go". I'll read everything and build your profile from it. See `documents/README.md` for the folder layout. > > **Path B: Single CV import** - Paste or @-mention a single CV/resume here. I'll extract it and ask follow-up questions for what's missing. > > **Path C: Interview mode** - I'll walk you through structured questions section by section. Good if you're starting from scratch. > > Which would you like?

Wait for the user's choice. If they pick A but the folder is still empty, tell them what to add (point at `documents/README.md`) and stop.

---

Path A: Documents Folder

Reads structured documents in `documents/`, cross-references them for consistency, and merges extracted data into the seven profile skill files. Read-before-write and idempotent: changes already present will not be proposed again.

Follow these steps **exactly in order**.

Step A1: Inventory

Use Glob with `documents/**/*` to scan the full tree. Print:

## Documents Found

**cv/**: [list files, or "(empty)"]
**linkedin/**: [list files, or "(empty)"]
**diplomas/**: [list files, or "(empty)"]
**references/**: [list files, or "(empty)"]
**applications/**: [list subfolders with their files, or "(empty)"]

I will read these and cross-reference before proposing any changes.

If every subfolder is empty, stop and tell the user to populate the folder. Point at `documents/README.md` for the layout.

Step A2: Read Existing Skill Files

Read these in parallel before extracting anything. You must know what is already there to make the merge intelligent.

• `.claude/skills/job-application-assistant/01-candidate-profile.md`
• `.claude/skills/job-application-assistant/02-behavioral-profile.md`
• `.claude/skills/job-application-assistant/03-writing-style.md`
• `.claude/skills/job-application-assistant/04-job-evaluation.md`
• `.claude/skills/job-application-assistant/05-cv-templates.md`
• `.claude/skills/job-application-assistant/06-cover-letter-templates.md`
• `.claude/skills/job-application-assistant/07-interview-prep.md`

Hold this content in context throughout Path A. Do not re-read.

Step A3: Parse Documents

Read each document found in Step A1. Process subfolders in this order: `cv/`, `linkedin/`, `diplomas/`, `references/`, `applications/`.

**`cv/` documents:** name, contact (email, phone, LinkedIn, GitHub), education (degree, institution, dates, thesis), work experience (title, company, dates, location, bullets), s