santifer/career-ops

⭐ 43,849  ·  JavaScript  ·  GitHub Repo

AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.

ai-agent anthropic automation career claude claude-code cli golang

1-Sentence Summary

Treat your job search like an engineering problem with an AI-powered command center for systematic evaluation and application.

🔥 Key Capabilities & USP

• 6-Block Evaluation System: Scores job offers across role summary, CV match, level strategy, compensation, personalization, and interview prep using a structured A-F scoring system with 10 weighted dimensions. Solves the pain point of subjective, inconsistent job evaluation by providing a data-driven framework that forces you to systematically assess every opportunity.

• ATS-Optimized PDF Generation: Creates keyword-injected, tailored CVs per job description using Space Grotesk + DM Sans design, generated via Playwright. Eliminates the tedious manual tailoring of resumes for each application while ensuring ATS compatibility.

• Portal Scanner: Automatically scans 45+ pre-configured companies (Anthropic, OpenAI, ElevenLabs, etc.) and major job boards (Greenhouse, Ashby, Lever, Wellfound) for new offers. Solves the problem of missing opportunities by continuously monitoring your target companies without manual checking.

• Batch Processing: Evaluates 10+ offers in parallel using sub-agents, with automated merge, dedup, and pipeline integrity checks. Addresses the time sink of evaluating multiple roles individually by parallelizing analysis while maintaining quality control.

• Interview Story Bank: Accumulates STAR+Reflection stories across evaluations, building 5-10 master stories that answer any behavioral question. Turns every evaluation into interview preparation material, compounding value over time.

USP: Career-Ops transforms any AI coding CLI into a job search command center, treating job search as an engineering problem with structured scoring, batch processing, and human-in-the-loop control — while being fully customizable by the AI agent itself.

Technical Architecture

Component	Technology	Purpose
AI CLI Integration	Claude Code, OpenCode, Gemini CLI, Codex	Execution environment for the agent pipeline
Backend Pipeline	Node.js (JavaScript)	Core agent logic, evaluation scoring, batch processing
Dashboard TUI	Go	Terminal-based user interface for tracking applications
Browser Automation	Playwright (Chromium)	Portal scanning and PDF generation
Configuration	YAML	Profile settings (config/profile.yml) and portal definitions (portals.yml)
Data Storage	Markdown, TSV, PDF	Reports, CVs, application tracker
Multi-language	8 languages	README localization (EN, ES, PT-BR, KO, JA, RU, ZH-CN, ZH-TW)

Architectural Highlights:

• Human-in-the-loop design ensures no auto-submission of applications
• Sub-agent architecture for parallel evaluation of multiple offers
• Modular mode system (14 skill modes) that Claude can modify dynamically
• Pipeline integrity checks for deduplication and merge validation

Quick Start Guide

# 1. Clone and install
git clone https://github.com/santifer/career-ops.git
cd career-ops && npm install
npx playwright install chromium   # Required for PDF generation

# 2. Check setup
npm run doctor                     # Validates all prerequisites

# 3. Configure
cp config/profile.example.yml config/profile.yml  # Edit with your details
cp templates/portals.example.yml portals.yml       # Customize companies

# 4. Add your CV
# Create cv.md in the project root with your CV in markdown

# 5. Personalize with Claude
claude   # Open Claude Code in this directory

# 6. Start using
# Paste a job URL or run /career-ops

Pros, Cons & Use Cases

Pros

• Proven results: 740+ evaluations, 100+ CVs generated, creator landed Head of Applied AI role
• Deeply customizable: Claude can modify modes, archetypes, scoring weights, and negotiation scripts on the fly
• Quality over quantity: Strongly recommends against applying to anything scoring below 4.0/5, preventing wasted applications
• Free tier available: Gemini CLI integration provides a no-cost entry point
• Compounding value: Interview Story Bank grows richer with every evaluation

Cons

• Cold start problem: First evaluations won't be great — requires feeding context (CV, career story, preferences) to improve
• Technical barrier: Requires comfort with CLI, Git, and AI coding assistants
• Setup complexity: Multiple steps involved (Playwright, configuration files, CV creation)
• Not a "spray-and-pray" tool: Deliberately designed against mass applications, which may frustrate some users

Who should NOT use this?

• Non-technical job seekers who are uncomfortable with command-line interfaces and Git workflows
• Quantity-focused applicants who believe in applying to hundreds of roles indiscriminately
• Users seeking a GUI-based tool with no terminal interaction
• Job seekers outside tech/AI/engineering roles — the evaluation system is heavily optimized for these domains
• Anyone unwilling to invest upfront time in configuration and context-building

Ideal Use Cases

• Senior engineers and AI/ML professionals targeting top-tier companies (Anthropic, OpenAI, FAANG, etc.)
• Technical product managers who want data-driven decision making for their job search
• Career switchers who need systematic evaluation of how their background maps to new roles
• Job seekers managing 5+ active applications who need structured tracking and comparison
• Interview preparation — using the STAR+R story bank to build a library of behavioral responses

Community & Activity

With 43,849 stars, Career-Ops has clearly struck a nerve in the developer community. This is not just a niche tool — it's a movement in how technical professionals approach job hunting. The project is actively maintained (last updated May 2026) and has generated significant buzz as one of the most practical applications of AI coding assistants for personal career management.

The multi-language README (8 languages) signals a global community, and the creator's documented success (landing a Head of Applied AI role) provides compelling social proof. The project's momentum suggests it's evolving rapidly, with the ecosystem of 14 skill modes and portal scanner expanding as users contribute their own configurations and company targets.