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/endpoint-selection.md

Endpoint Selection

Ask this before picking an endpoint:

  • What should Firecrawl do in the product?

Use the narrowest endpoint that matches the feature:

| Endpoint | Use when | Do not start here when | |---|---|---| | /scrape | You already have the URL and need one page | The feature starts with a query | | /search | The feature starts with a query and must discover sources | The target URL is already known | | /interact | The page must be clicked, typed into, or navigated after scrape | Plain /scrape already returns the data |

Default priority for most product integrations:

  1. /scrape
  2. /search
  3. /interact

Escalation rules:

  • Start with /scrape before /interact.
  • Start with /search when URL discovery is part of the product behavior.

Beyond The Three Endpoints

Two Firecrawl indexes sit beside /scrape, /search, and /interact. Neither is queried by /search:

| Index | Use when | Reached by | |---|---|---| | Research paper index | The query is for published research papers — biomedical, clinical, and life-science literature (PubMed, bioRxiv, medRxiv) or arXiv preprints — rather than web pages | MCP firecrawl_research_*, CLI firecrawl research <subcommand>. See firecrawl-research-index | | Developer index | The answer belongs in an issue, merged pull request, README, or documentation page: code behavior, an API contract, an error string, a known bug | GET or POST /v2/search/developer, MCP firecrawl_developer_search, CLI firecrawl developer. See firecrawl-developer-index |

The categories: ["research"] and categories: ["developer"] options on /search are website filters. They restrict an ordinary web search to a short list of domains and return page results from them — the research list includes PubMed, bioRxiv, medRxiv, arXiv, and publisher sites. They reach those sites' web pages but do not query either index, so there is no abstract search, related-paper expansion, or full-text passage retrieval behind them. Choose them when a web search is what the feature wants and those sources should be weighed in the same call.