firecrawl

Name: firecrawl
Availability: InStock
Author: HybridAI

Scrape public web pages, crawl sites, map URLs, and extract JSON via schemas.

126|11|Updated Feb 24, 2026

Search Tags:#firecrawl #web scraping #api integration #site crawling #url mapping #json extraction #schema-driven data

Ready to run

npx skills add https://github.com/HybridAIOne/hybridclaw --skill firecrawl-hybridaione

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: firecrawl
Source: https://github.com/HybridAIOne/hybridclaw/tree/main/skills/firecrawl
Command: npx skills add https://github.com/HybridAIOne/hybridclaw --skill firecrawl-hybridaione

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It removes the manual effort of turning public web pages into usable text, URL inventories, and structured JSON data.

Core Features & Use Cases

Public page scraping: Convert one URL into markdown (or other Firecrawl formats) for quick downstream processing.
Site crawling & progress control: Crawl a public site with conservative limits, then check status and cancel jobs if needed.
URL mapping & structured extraction: Build a URL map and run JSON-schema extraction (with polling for results) for reliable, repeatable data capture.

Quick Start

Use the firecrawl skill to scrape https://example.com/docs and return the page content as markdown.

Frequently Asked Questions about firecrawl

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

FAQPage Schema

How do I scrape a public web page and convert it to markdown?▼

To scrape a public web page and convert it to markdown, provide a single URL to generate a Firecrawl v2-compatible HTTP request payload that fetches and parses server-side content into markdown for downstream processing.

Can I crawl a site section and control the crawl limits?▼

Yes, you can crawl public site sections by providing a URL and setting conservative crawl limits, then check the job status and cancel ongoing crawls if needed to control the ingestion pipeline.

How does schema-driven JSON extraction work for web data?▼

Schema-driven JSON extraction works by submitting a URL alongside a JSON schema to fetch public web pages, running the extraction, and polling for structured results that match your defined data schema.

What is URL mapping and when do I need it for web crawling?▼

URL mapping is the process of discovering and building an inventory of URLs on a public site, needed when you want to identify accessible endpoints before running targeted scraping or structured data extraction.

Do I need a bearer token to use Firecrawl for web scraping?▼

Yes, you need a bearer token because the skill generates payloads with bearer-secret injection rules required to authenticate Firecrawl v2-compatible managed or self-hosted gateway HTTP requests.

What types of sites are suitable for server-side web scraping and data extraction?▼

Server-side web scraping and data extraction are suitable for ingestion pipelines targeting documentation sites, marketing pages, changelogs, and any public endpoints where HTTP fetching and server-side parsing are sufficient.