Terminal
Terminal/Skill
Guides adding Firecrawl /search to app code so a product can find web pages from a query before extracting them.
By Firecrawl
Works with
npx skills add firecrawl/skills --skill firecrawl-build-searchUse this when the application starts with a query, not a URL.
/search first when URL discovery is part of the product behavior./scrape or /interactNote that "research workflow" here means discovering web pages. If the product is searching published papers, that is a different surface — see the escalation rules below.
/search is the wrong surface. Use the research paper index instead: firecrawl-research-index. Passing categories: ["research"] to /search does not query that index; it filters an ordinary web search to research-affiliated websites (the list includes PubMed, bioRxiv, medRxiv, arXiv, and publisher sites) and returns page results from them — no abstract search, related-paper expansion, or full-text passages.categories: ["developer"]./search as discovery, ranking, and source selection.Read the source-of-truth page for your project language before writing integration code: