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/verification.md

Verification

Do not stop at "the code compiles." Verify that a real Firecrawl request works.

Fresh Project Smoke Test

Use the smallest request that proves auth, networking, and SDK wiring work:

  • /scrape -> request one known URL
  • /search -> run one small query with a limit of 1
  • /interact -> start from /scrape, then run one minimal browser action

Existing Project Smoke Test

Verify the integration in the actual place where it will run:

  • start the app, worker, or script that owns the Firecrawl call
  • trigger one request through the real integration path
  • confirm the Firecrawl response is received and handled correctly
  • confirm secrets are being read from the intended env source

What Counts As Done

  • credentials are loaded from .env or the deployment secret store
  • the chosen endpoint succeeds once with real data
  • the result reaches the intended application path
  • obvious auth or base-URL mistakes are ruled out

If verification fails, debug auth, env loading, base URL, SDK install, or endpoint choice before moving on.