skills.rest
tumf
tumfCOMMUNITY
Explore all skills by this author →
Website𝕏@tumfGitHub

firecrawl

Automate web scraping and data extraction via the Firecrawl API.

3|1|Updated Jan 24, 2026
Search Tags:#automation#cli#firecrawl#data-extraction#web-scraping#web-crawling
One-click install
npx skills add https://github.com/tumf/skills --skill firecrawl-tumf
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: firecrawl
Source: https://github.com/tumf/skills/tree/main/firecrawl
Command: npx skills add https://github.com/tumf/skills --skill firecrawl-tumf

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Web data is scattered, hard to structure, and manually collecting it is slow and error-prone. This toolkit provides a programmable solution to scrape, search, map, crawl, and extract data from the web via the Firecrawl API, enabling fast, repeatable data gathering.

Core Features & Use Cases

  • Single-page scraping with scrape.py to extract content from a URL.
  • Web search with search.py to discover relevant pages and content.
  • URL discovery via map.py to surface all links on a site.
  • Multi-page crawling with crawl.py to aggregate content from related pages.
  • Structured data extraction via extract.py with optional JSON schemas.
  • Autonomous data gathering with agent.py to plan and execute data collection tasks.

Quick Start

Set your FIRECRAWL_API_KEY and run a basic scrape on https://example.com to see the output.

Frequently Asked Questions about firecrawl

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

FAQPage Schema
How do I extract structured data from web pages using a JSON schema?▼

You can extract structured data by running the extract.py script with an optional JSON schema. The Firecrawl API parses the web page content and returns the extracted results formatted as JSON for easy integration.

What is the best way to automate multi-page web crawling across an entire site?▼

The best way to automate multi-page web crawling is using the crawl.py script. It aggregates content from related pages across a website via the Firecrawl API, returning comprehensive JSON results for your data extraction needs.

Do I need an API key to use Firecrawl for web scraping?▼

Yes, you need a FIRECRAWL_API_KEY to authenticate requests. The Python CLI scripts under scripts/ require this environment variable to execute web scraping, crawling, and data extraction tasks via the Firecrawl API.

Can I discover all available URLs on a website before crawling?▼

Yes, you can discover all available URLs on a website using the map.py script. This URL discovery feature surfaces all links on a target site via the Firecrawl API, allowing you to plan your web crawling strategy.

How does autonomous data gathering work for web scraping tasks?▼

Autonomous data gathering works by running the agent.py script, which plans and executes data collection tasks automatically. It leverages the Firecrawl API to gather web data across websites without requiring manual step-by-step intervention.

Related Skills

Explore More Software Engineering Skills→
nathanvalenathanvale
2

firecrawl

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

Community
Advanced
iOfficeAIiOfficeAI
31.8k

xlsx

Create, edit, and analyze Excel spreadsheets with pandas and openpyxl.

Official
Advanced
b-open-iob-open-io
14

dev-browser

Automate browser navigation, interaction, and content extraction for UI testing.

Official
Advanced
zeronx798zeronx798

scrapling

Scrape static, dynamic, and protected websites using the scrapling library.

Community
Advanced