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/project-intake.md

Project Intake

Before implementing Firecrawl in product code, classify the task:

Fresh Project

Use this path when the user is starting a new app, workflow, or prototype.

Default flow:

  1. Confirm the target language or stack.
  2. Install the matching SDK, or use REST if that is a better fit.
  3. Add FIRECRAWL_API_KEY to .env or the runtime secret store.
  4. Create the smallest useful Firecrawl call for the product.
  5. Run the smoke test in verification.md.

Existing Project

Use this path when the user wants Firecrawl added to an existing codebase.

Inspect the repo first and identify:

  • language and framework
  • package manager
  • project structure and file conventions
  • entry points, routes, workers, or jobs where Firecrawl should live
  • existing networking or third-party API wrappers
  • how environment variables and secrets are managed
  • any existing scraping, crawling, or browser-automation code

After inspection, ask:

  • What should Firecrawl do in this product?

Route from that answer:

  • known URL -> /scrape
  • query first -> /search
  • clicks, forms, login, or navigation after scrape -> /interact

Then install the SDK or use REST in the place that matches existing project conventions, not wherever is easiest in the moment.