The ai-job-search repository is an AI-powered job application framework built on Claude Code that automates and streamlines the entire job search process. Created by Mads Lorentzen, a geophysicist who used this exact workflow to secure an AI engineer position in June 2026, the framework is designed to run entirely on a user's machine, giving them full ownership and control over their job search automation. The repository is written in TypeScript and covers the complete application lifecycle: evaluating job postings for fit, tailoring CVs, writing cover letters, and preparing for interviews.
The core workflow is language and country-agnostic, built around self-profiling, structured fit evaluation, and a drafter-reviewer application pipeline. The job portal search capabilities are currently configured for the Danish market, supporting platforms like Jobindex, Jobnet, and Akademikernes Jobbank, but the architecture is designed to be adapted for other regional job boards. The framework encodes career guidance best practices including structured evaluation criteria, forward-looking cover letter framing, and optional salary benchmarking. According to the README, Lorentzen's personal results with this system were sixty-nine tailored applications, twenty first interviews, and ultimately one signed contract, demonstrating the framework's practical effectiveness.
The `/apply` command represents the heart of the system, implementing a drafter-reviewer workflow with mandatory PDF compilation. This process parses job postings, evaluates fit against the user's profile across dimensions like skills, experience, culture, location, and career alignment, then drafts tailored CV and cover letter documents in LaTeX. A reviewer agent researches the company and critiques the drafts, leading to revisions based on feedback. The system compiles both PDFs using lualatex for the CV and xelatex for the cover letter, with Claude iterating on the LaTeX until the CV is exactly two pages with proper formatting and the cover letter is exactly one page. An ATS-check verifies the CV's text layer for keyword coverage and readability the way automated applicant tracking systems would parse it, ensuring genuine skills are highlighted without fabrication.
Beyond the core `/apply` workflow, the repository includes seven additional commands extending functionality. The `/interview` command prepares users for scheduled interviews by building stage-specific prep packs from archived applications, researching companies and interviewers with verification protocols, mapping likely questions to STAR examples, and offering mock interviews. The `/outcome` command records application results and updates the tracking system. The `/rank` command batch-scores newly scraped postings against the fit framework using parallel agents, returning a ranked shortlist with honest per-job strengths and gaps. The `/expand` command enriches user profiles by scanning public sources like GitHub repos and portfolios. The `/upskill` command analyzes skill gaps between the user's profile and tracked job postings, producing prioritized heatmaps and learning plans with time estimates. The `/add-template` and `/add-portal` commands allow users to register custom LaTeX templates and add job portal search skills for their local markets.
The repository requires Claude Code CLI, Python 3.10 or higher, Bun for job search CLI tools, and a LaTeX distribution with lualatex and xelatex. The optional pdftotext utility from poppler enhances ATS parseability checks. Setup begins with forking and cloning, installing job search tools, populating a user profile through the `/setup` command which can read from a documents folder or conduct an interview, then searching for jobs with `/scrape` and applying with `/apply`. The project explicitly states it has no affiliated cryptocurrency, token, or paid sponsorship program and is not affiliated with or endorsed by Anthropic. As of the most recent GitGenius tracking data from July 14, 2026, the repository had grown to 22,381 stargazers, reflecting sustained community interest in this practical approach to AI-assisted job searching.
