skills.rest
Roentek
RoentekOFFICIAL
Explore all skills by this author →
Website𝕏@roentekdesignsGitHub

firecrawl

Scrape web pages, crawl domains, and extract structured data via Firecrawl CLI.

4|4|Updated Apr 6, 2026
Search Tags:#structured data#web scraping#web crawling#content extraction#url discovery#api key setup#mcp fallback
One-click install
npx skills add https://github.com/Roentek/Claude_Code_Boilerplate_Framework --skill firecrawl-roentek
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: firecrawl
Source: https://github.com/Roentek/Claude_Code_Boilerplate_Framework/tree/main/.claude/skills/firecrawl
Command: npx skills add https://github.com/Roentek/Claude_Code_Boilerplate_Framework --skill firecrawl-roentek

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the friction of manually copying web pages by helping you reliably scrape, crawl, search, and extract both unstructured and structured information from websites.

Core Features & Use Cases

  • Single-page scraping: Retrieve page content (optionally as HTML, Markdown, or JSON) from a specific URL.
  • Site crawling & URL mapping: Crawl multiple pages with depth/limits or map all URLs across a domain.
  • Web search & AI extraction: Search the web and extract information, including schema-driven structured data via agent/extract flows.
  • Fallback strategy: Use the Firecrawl CLI first for speed and token efficiency, escalating to the Firecrawl MCP only when needed (batch scrape, schema extraction, or async status polling).
  • Guardrails: Handles common setup and runtime issues like missing CLI/API keys, rate limiting, and crawl timeouts.

Quick Start

Ask the firecrawl skill to scrape a URL and return the extracted 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 web page and get the content as Markdown?▼

To scrape web pages and get Markdown, you provide a specific URL to the firecrawl skill. It retrieves the page content and returns the extracted output as usable Markdown text.

Can I crawl an entire domain and discover all its URLs?▼

Yes, you can crawl an entire domain to discover all URLs. The skill supports multi-page crawling with configurable depth and limits, as well as full domain URL mapping.

How do I extract structured data from web search results?▼

You can extract structured data from web search results by using the schema-driven extraction flow. This allows you to define a schema and retrieve information as structured JSON outputs.

Do I need an API key to extract structured data from websites?▼

Yes, you need an API key set up to perform schema-driven structured data extraction. The skill checks for necessary CLI and API keys during setup to prevent runtime issues.

What is the best way to handle batch scraping and async job status checks?▼

The best way to handle batch scraping and async job status checks is using the MCP fallback. The firecrawl skill uses the CLI by default for speed but escalates to MCP for these specific tasks.

Why does web crawling fail or time out during extraction?▼

Web crawling can fail or time out due to rate limiting or missing configuration keys. The skill includes guardrails to handle these common runtime issues and crawl timeouts automatically.

Related Skills

Explore More Data & Analytics Skills→
antgroupantgroup
16

firecrawl

Access Firecrawl API for web search, scraping, and site crawling.

Official
Intermediate
HwFeeHwFee

requirement-intake

Parse user report requests into a structured JSON requirements schema.

Community
Intermediate
cxnaivecxnaive

nemo-curator

Curate large-scale LLM training datasets with GPU-accelerated deduplication, filtering, and PII redaction.

Community
Advanced
nathanvalenathanvale
2

firecrawl

Fetch web content and extract structured data via the Firecrawl API.

Community
Advanced