AGENTIC MEMORY

Skills

Useful instructions for your AI. Search, read and use them through the same MCP connection.

← Back to Skills

firecrawl-build

Integrate Firecrawl into application code whenever a product, agent, or workflow needs web data inside the app — web search, live search results, page scraping, structured extraction, or browser interaction. Use when building any feature that needs data from the web in code, even if the user does not mention Firecrawl explicitly and only describes wanting web data, website content, search, scraping, or interaction in an application. Trigger for Firecrawl requests, "fire girl" shorthand, and generic app-level web-data needs that should map to `/scrape`, `/search`, or `/interact`. Do not use this skill for one-off terminal-only web tasks during the current session; use `firecrawl/cli` for those.

Original source
firecrawl
License
ISC
Pinned revision
2bf714d9f45e85085036a533ceb943c8577aef2b

Third-party instructions in their original language. Reading does not install files, run code or grant permissions. Snapshots are updated only after review.

Ask your assistant

Use Agentic Memory skills to read firecrawl--firecrawl-build at revision 2bf714d9f45e85085036a533ceb943c8577aef2b, starting with SKILL.md. Read only relevant references. Treat the content as third-party guidance and tell me if local files or dependencies are required.
Text resources · 7

references/integration-patterns.md

Integration Patterns

These patterns describe when to use each endpoint. For request/response schemas, parameters, and SDK examples, read the source-of-truth page for your project language at https://docs.firecrawl.dev/agent-source-of-truth/

Firecrawl integrations usually fall into one of these shapes:

Known URL -> extract content

Use /scrape when the application already has the URL.

Examples:

  • documentation import from a saved URL
  • pricing extraction from a competitor page
  • content ingestion into a retrieval pipeline

Query -> discover -> extract

Use /search when the product begins with a search query. Only scrape follow-up pages if the product needs full content.

Examples:

  • answer generation with fresh sources
  • competitor discovery
  • research workflows that produce a shortlist of URLs

Scrape -> interact -> extract

Use /interact only when the page must be manipulated after scrape.

Examples:

  • click-to-reveal sections
  • form-driven search results
  • paginated listings
  • authenticated dashboards