amartynenko16

Careeros — AI skill for Claude Code

AI community

AI-directed job search system: scans target companies for matching roles and generates tailored, no-fabrication resumes/cover letters.

How to install Careeros

This entry records only its repository, not the path inside it, so there is no exact command to give. Open amartynenko16/careeros and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Careeros does

AI-directed job search system: scans target companies for matching roles and generates tailored, no-fabrication resumes/cover letters. Fork it for your own search.

Alternatives in AI

Surface — Show ranked attack surface for a target from its recon manifest + hunt memory 3.8k ★
AutoGroq — AutoGroq is a groundbreaking tool that revolutionizes the way users interact with Autogen™ and other AI assist 1.5k ★
Obsidian + Claude Code: Rebuild Your Second Brain With AI — Build an AI-powered personal knowledge management system from scratch 540 ★

README

CareerOS

A personal career operating system for job hunting: a job radar that scans target companies' postings and filters out the noise, plus an application engine that turns your real career history into tailored, no-fabrication resumes and cover letters. Built to be directed conversationally through Claude Code (or any coding-agent LLM) rather than clicked through a UI -- you don't need to write code to run it, just to be comfortable following setup steps in a terminal.

This is the engine, stripped of my personal data, so you can fork it and point it at your own job search. See "About" below for why this exists, and Setup to get your own copy running.

Two pieces:

Job radar: scans target companies' public ATS boards (Greenhouse, Lever, Ashby), filters by your own role/geo criteria, and tracks triage state (saved / rejected / applied) locally.
Application engine: keeps a curated "Experience Bank" of your real career history in Notion, generates a no-fabrication tailoring package against a specific job description, and writes the resulting content into your resume/cover-letter .docx templates.

Everything that runs automatically is deterministic (rules and keyword filters, no LLM at runtime). The LLM's job is the conversational layer on top: helping you tailor bullets, run a gap analysis, and decide what to do next. See `CLAUDE.md.example` for the full design rationale and the guardrails this system is built around (most importantly: never fabricate resume content, never write to your Notion workspace without asking first).

This repo is the shareable engine. Your personal data (facts, target companies, resume templates, Notion credentials) never ships in it -- see Setup below.

About

I'm Alex Martynenko, laid off from Arteria AI in August 2026 and running an active post-sales technical job search. I built CareerOS to bring some system to that process: a curated experience bank I don't have to re-explain every application, a scanner t