webclaw-skill

Discover and qualify B2B leads using webclaw. Start from a CSV of domains, a directory or "best tools" listing URL, or a plain-language ICP description — get back an enriched sheet of firmographics (company name, pitch, published contact email, socials, pricing model, target customer, tech signals, or any custom field) read from each company's own site via /v1/extract. Use when the user wants to find/discover leads, build a prospect list, qualify companies from their websites, or asks for a "Clay alternative" without per-seat pricing. This is the discovery + firmographics half; for founders/leadership with their LinkedIn and X, use webclaw's `lead` / `lead_batch` tools instead. Billed per extract call, not per seat.

Web extraction for AI agents. Scrape, crawl, map, batch, extract, summarize, diff, brand, search, and 28 site-specific extractors turn any URL into clean Markdown, text, or JSON. Runs locally with no key via the webclaw MCP server; set an optional WEBCLAW_API_KEY to handle bot-protected and JavaScript-rendered pages. Use when web_fetch returns blocked or empty content, or you need structured, LLM-ready extraction.