← ClaudeAtlas

firecrawl-scrapelisted

Use when the user gives a URL and wants its content: "scrape", "grab", "fetch", "pull", "get the page", "extract from this URL", "read this webpage". Returns clean LLM-ready markdown from any page, including JavaScript-rendered SPAs and several URLs at once. Needs the Firecrawl CLI. Prefer it over a plain web fetch for page content.
marian-kamenistak/founder-pipeline · ★ 11 · Data & Documents · score 72
Install: claude install-skill marian-kamenistak/founder-pipeline
# firecrawl scrape Scrape one or more URLs. Returns clean, LLM-optimized markdown. Multiple URLs are scraped concurrently. ## Requires Firecrawl is a commercial scraping service (firecrawl.dev). This skill wraps its CLI, so it needs two things the user configures once, outside this plugin: - the `firecrawl` CLI available on the path (or reachable via `npx`) - a Firecrawl account and API key, configured wherever that CLI expects to find it — follow Firecrawl's own setup docs; this plugin never reads a key itself Without both, the skill cannot run. Say so plainly rather than silently degrading to a plain fetch — a plain fetch loses exactly the content some pipeline steps depend on (see **Raw HTML** below). ## When to use - You have a specific URL and want its content - The page is static or JS-rendered (SPA) - Step 2 in the escalation ladder: search → **scrape** → map → crawl → interact. Only this rung ships with the plugin; the others are separate Firecrawl commands you can call directly if you have the CLI. ## Quick start ```bash # Basic markdown extraction firecrawl scrape "<url>" -o .firecrawl/page.md # Main content only, no nav/footer firecrawl scrape "<url>" --only-main-content -o .firecrawl/page.md # Wait for JS to render, then scrape firecrawl scrape "<url>" --wait-for 3000 -o .firecrawl/page.md # Multiple URLs (each saved to .firecrawl/) firecrawl scrape https://example.com https://example.com/blog https://example.com/docs # Get markdown and links to