Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/MadsLorentzen/ai-job-search/llms.txt

Use this file to discover all available pages before exploring further.

AI Job Search is an open-source framework that turns Claude Code into a full-stack job application assistant. Fork the repo, run /setup to build your profile, and let Claude handle the heavy lifting — from scraping job boards to drafting and compiling tailored PDFs.

Introduction

Understand what the framework does, how the workflow fits together, and what makes it different.

Quickstart

Fork, install, and run your first job application in under 15 minutes.

Prerequisites

Everything you need installed before getting started: Claude Code, Bun, LaTeX, and more.

File Structure

A map of every file and directory in the repo and what each one does.

The Core Workflow

Three commands cover the full job application lifecycle from search to submission.
1

Build your profile with /setup

Run /setup inside Claude Code to populate your candidate profile. Choose from three onboarding paths: read your documents/ folder, import a single CV, or walk through a structured interview. Your profile drives every downstream command.
2

Find matching jobs with /scrape

Run /scrape to search multiple job portals simultaneously. Claude deduplicates results and presents them sorted by fit. Use /rank to batch-score all results before deciding where to apply.
3

Apply with /apply

Pass a job URL or paste a posting to /apply. Claude evaluates your fit, drafts a tailored CV and cover letter in LaTeX, spawns a reviewer agent to critique the drafts, revises based on feedback, compiles both PDFs, and runs an ATS parseability check — all automatically.

What Makes This Different

Drafter-Reviewer Pipeline

Two separate Claude agents collaborate on every application: one drafts, one researches the company and critiques. The drafter then revises. Single-pass generation never reaches this quality.

PDF Verification Loop

Every application compiles and visually inspects the PDFs. Orphaned job titles, overflowing cover letters, and font mismatches are fixed automatically before you ever see the output.

ATS Text-Layer Check

/apply extracts the compiled CV’s text layer with pdftotext and verifies that contact details, reading order, and posting keywords survive the way an ATS parser sees them.

Extensible by Design

Add your own job portals with /add-portal, swap in your own LaTeX templates with /add-template, and expand your profile with /expand. The framework grows with your needs.

Extended Commands

Once your profile is in place, six more commands extend the framework:

/outcome

Log interview stages, offers, and rejections. Archives submitted materials and calibrates your fit framework over time.

/expand

Enriches your profile by scanning GitHub, LinkedIn, and other public sources you’ve linked.

/upskill

Analyzes skill gaps between your profile and target postings, with a prioritized learning plan.

/add-portal

Scaffolds a job-portal search skill for any job board in any country.

/add-template

Register your own LaTeX CV or cover letter template and wire it into /apply.

/reset

Wipe profile data, documents, or both — with a mandatory confirmation step.
AI Job Search is an independent open-source project and is not affiliated with, endorsed by, or maintained by Anthropic. Anthropic and Claude Code are referenced only to describe the toolchain this workflow uses.

Build docs developers (and LLMs) love