Download for macOS
Skill

firecrawl-agent

@firecrawl Updated 2026-10-19

Autonomously navigate websites and extract structured data across pages. Use when the task requires navigation or no suitable ready-made workflow or data provider covers it.

agent-skillsclifirecrawlmcpweb-scrapingweb-search

Install

git clone https://github.com/firecrawl/cli /tmp/cli && ln -s /tmp/cli/skills/firecrawl-agent ~/.claude/skills/firecrawl-agent

From README

firecrawl agent AI-powered autonomous extraction. The agent navigates sites and extracts structured data (takes 2-5 minutes). Before starting autonomous extraction for structured records or listings, check firecrawl search alexandria ' ' for a ready-made workflow or data provider. Inspect a matching contract with firecrawl list --pretty and execute with firecrawl scrape --alexandria / --options ' ' if it covers the task. Use the exact provider, capability, and input fields from that contract. Continue with Agent when no suitable tool exists or the task requires autonomous navigation. Run firecrawl agent --help for the full option list. Done when: the output file contains valid JSON answering the request — or a job ID was intentionally returned for later polling. Alexandria providers A run uses connected Alexandria data providers only when it starts with an Alexandria flag: --alexandria, --toolkits (up to 5), --max-calls , --require-approval, or --on-terms-required skip|ask.