skills.rest
raphaelmans
raphaelmansCOMMUNITY
Explore all skills by this author →
GitHub

firecrawl

Automate web scraping and browser interactions to generate Markdown from web content.

Updated Feb 28, 2026
Search Tags:#cli#firecrawl#data-extraction#web-scraping#browser-automation#crawl
One-click install
npx skills add https://github.com/raphaelmans/agent-skills --skill firecrawl-raphaelmans
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: firecrawl
Source: https://github.com/raphaelmans/agent-skills/tree/main/firecrawl
Command: npx skills add https://github.com/raphaelmans/agent-skills --skill firecrawl-raphaelmans

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates repetitive web research tasks by turning web pages, results, and browser interactions into clean Markdown that is ready for downstream analysis and reporting.

Core Features & Use Cases

  • Web search and crawl orchestration using the Firecrawl CLI to discover relevant sources.
  • Content extraction and summarization from static and JS-rendered pages, with outputs saved in .firecrawl for safe processing.
  • Site mapping, bulk crawling, and browser automation to interact with pages requiring clicks or authentication.

Quick Start

Use Firecrawl to search a topic and scrape a target page to generate a concise Markdown summary.

Frequently Asked Questions about firecrawl

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

FAQPage Schema
How do I extract web content into clean Markdown using browser automation?▼

Web scraping and browser automation extract web content from static and JS-rendered pages, generating clean, publish-ready Markdown. Outputs are saved in .firecrawl directories for safe downstream processing and analysis.

Can I crawl large sites and map content across multiple domains?▼

Yes, site mapping and bulk crawling discover relevant sources to map content across domains. The Firecrawl CLI orchestrates web search and crawl operations to handle large sites, returning structured results to .firecrawl outputs.

Does this web scraping tool work with interactive pages requiring clicks or authentication?▼

Yes, browser automation interacts with pages requiring clicks or authentication. It operates within a pre-installed, authenticated Firecrawl CLI environment to scrape JS-rendered pages and generate Markdown summaries.

What is the best way to automate repetitive web research tasks for documentation extraction?▼

Automating web research with the Firecrawl CLI turns web pages and search results into clean Markdown. It orchestrates content extraction and summarization from static and interactive pages, saving outputs for reporting.

Do I need a pre-authenticated environment to scrape web pages and generate Markdown?▼

Yes, the tool operates within a pre-installed, authenticated Firecrawl CLI environment. This setup enables browser automation for scraping interactive pages and ensures content extraction returns safely to .firecrawl outputs.

Related Skills

Explore More Software Engineering Skills→
khalidouhdanekhalidouhdane

firecrawl

Automates web data collection and browser actions via the Firecrawl CLI.

Community
Advanced
IndianBoy42IndianBoy42

paper-extraction

Extract structured equations, sections, references, and figures from academic PDFs into Markdown or data.

Community
Intermediate
Ankur2606Ankur2606
2

firecrawl

Extract markdown content from live websites via REST API or CLI.

Community
Basic
ethan-rioethan-rio

ingest-article

Scrape web articles into formatted markdown notes for Obsidian.

Community
Intermediate