karpathy-jobs-bls-visualizer

Skill by ara.so — Daily 2026 Skills collection. A research tool for visually exploring Bureau of Labor Statistics Occupational Outlook Handbook data across 342 occupations. The interactive treemap colors rectangles by employment size (area) and any chosen metric (color): BLS growth outlook, median pay, education requirements, or LLM-scored AI exposure. The pipeline is fully forkable — write a new prompt, re-run scoring, get a new color layer. Live demo: karpathy.ai/jobs Create a .env file with your OpenRouter API key (required only for LLM scoring): Run these in order for a complete fresh build: The most powerful feature: write any scoring prompt, run score.py , get a new treemap color layer. Example row: The visualization is a single self-contained HTML file using D3.js. Then update build_site_data.py to include your new score field in data.json . Package all 342 occupations + aggregate stats into a single file for LLM chat: The BLS blocks automated bots, so scrape.py uses non-headless Playwright (real visible browser window): If scraping fails or is rate-limited: playwright install fails BLS scraping blocked / returns empty pages score.py OpenRouter errors site/data.json not updating after re-scoring Treemap shows blank / no data - The html/ directory already contains cached pages in the repo - You can skip scraping entirely and run from process.py onward - If re-scraping,...