firecrawl-build-scrape
Installation
Summary
Single-page content extraction from known URLs in markdown, HTML, links, or screenshots.
- Extracts page content in multiple formats (markdown, HTML, links, screenshots, metadata) optimized for retrieval, summarization, enrichment, and monitoring workflows
- Supports rendering options like
onlyMainContentto filter navigation and page chrome from article-like pages - Integrates with hosted Firecrawl or self-hosted deployments via configurable API endpoint
- Escalates to interaction-based skills when pages require clicks, typing, or multi-step navigation
SKILL.md
Firecrawl Build Scrape
Use this when the application already has the URL and needs content from one page.
Use This When
- the feature starts from a known URL
- you need page content for retrieval, summarization, enrichment, or monitoring
- you want the default extraction primitive before considering
/interact
Default Recommendations
- Return
markdownunless the feature truly needs another format. - Use
onlyMainContentfor article-like pages where nav and chrome add noise. - Add waits or other rendering options only when the page needs them.