03-firecrawl-research

# Firecrawl Research Given a company domain, scrape its website and return clean markdown organized by page type. Downstream skills (signal-builder, email-writer) consume this output. This skill fetches only - scoring and interpretation belong to signal-builder. ## Quick start The user provides domain(s) and optionally a mode. Default to standard. | Mode | Credits | Pages | |------|---------|-------| | standard | 5-8 | Homepage, About, Careers, Blog, Pricing, Customers, Integrations, Product | | deep | 5-11 | Standard + Changelog, Leadership | | minimal | 3 | Homepage, About only | | extract | ~20+ | Structured JSON via LLM extraction | If the user doesn't specify a mode, use standard. Confirm mode before running only when the choice is ambiguous or the batch is large (>50 domains). ## Running the scraper ```bash # Single domain python3 scripts/firecrawl_scrape.py --domain "acme.com" --mode standard # Batch (one domain per line in file) python3 scripts/firecrawl_scrape.py --batch domains.txt --mode standard # Resume interrupted batch python3 scripts/firecrawl_scrape.py --resume runs/<run-folder-name> ``` All paths are relative to the skill folder (`firecrawl-research/`). The script creates a timestamped run folder under `runs/` with a `tracker.json` for progress and per-domain JSON scan files under `runs/<name>/scans/`. After a scrape completes, read the tracker and show the user a summary (completed/failed count, total credits). ## Writing to Google Sheet Use `...