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 onlyMainContent to 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