firecrawl-build-search
Installation
Summary
Web search discovery and source ranking for query-driven workflows.
- Designed for applications that start with a search query rather than a known URL, enabling discovery before extraction
- Returns ranked search results with snippets and URLs suitable for answer generation, competitive research, or topic exploration
- Integrates with downstream Firecrawl skills: escalate to
/scrapefor content extraction or/interactfor pages requiring clicks and form submission - Supports both hosted Firecrawl and self-hosted deployments via configurable API endpoint
SKILL.md
Firecrawl Build Search
Use this when the application starts with a query, not a URL.
Use This When
- the user asks a question and the product must discover sources first
- the feature needs current web results
- you want to turn a search query into a shortlist of pages for later scraping
Default Recommendations
- Use
/searchfirst when URL discovery is part of the product behavior. - Keep search and extraction conceptually separate unless scraping search results is clearly required.
- Prefer selective follow-up extraction over broad hydration when cost or latency matters.