firecrawl-agent

Search, navigate, and extract structured web data via Firecrawl's agent.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/ethanolivertroy/ets-agent-skills --skill firecrawl-agent
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: firecrawl-agent
Source: https://github.com/ethanolivertroy/ets-agent-skills/tree/main/firecrawl-agent
Command: npx skills add https://github.com/ethanolivertroy/ets-agent-skills --skill firecrawl-agent

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires firecrawl-py, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Perform autonomous web research using Firecrawl's /agent endpoint to search, navigate, and extract structured data from websites without needing initial URLs.

Core Features & Use Cases

  • Use cases include company research, competitive intelligence, pricing extraction, and extracting structured data for questions that require live web data.
  • The agent can be invoked via the CLI script to return results in a structured JSON format based on an optional schema.
  • It supports starting URLs and schema-based outputs for integration into workflows.

Quick Start

Run a quick test by executing the script with a research prompt such as finding the founders of Anthropic.

Frequently Asked Questions about firecrawl-agent

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract structured data from websites without a starting URL?

You can extract structured data without a starting URL by using an autonomous web research agent to search and navigate websites automatically. The Firecrawl agent endpoint handles search and extraction tasks, returning results formatted as structured JSON based on an optional schema.

Can I get structured JSON output for competitive intelligence research?

Yes, you can get structured JSON output for competitive intelligence by applying an optional JSON schema to the research prompt. The agent formats the extracted live web data into structured outputs based on your schema, enabling seamless integration into downstream workflows.

Do I need a Firecrawl API key and Python 3.9 to run web research automation?

Yes, you need a Firecrawl API key and Python 3.9+ to run this web research automation. The environment requires the FIRECRAWL_API_KEY environment variable to be set and the firecrawl-py package installed to execute the autonomous research scripts.

What's the best way to automate pricing analysis from live web data?

The best way to automate pricing analysis from live web data is using an autonomous web research agent to search and extract current pricing information. The Firecrawl agent navigates target websites and structures the extracted pricing data into JSON format for competitive analysis.

Does the Firecrawl Python package support providing optional starting URLs for extraction?

Yes, the firecrawl-py package supports providing optional starting URLs for extraction. While the agent can autonomously search the web without initial URLs, supplying starting URLs directs the web research agent to specific websites for structured data extraction.