firecrawl

Search, scrape, crawl, and monitor websites via the Firecrawl CLI.

Updated Apr 18, 2026
One-click install
npx skills add https://github.com/webdevarif/claude-skills --skill firecrawl-webdevarif
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: firecrawl
Source: https://github.com/webdevarif/claude-skills/tree/main/firecrawl
Command: npx skills add https://github.com/webdevarif/claude-skills --skill firecrawl-webdevarif

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires firecrawl-cli.

What problem does it solve? Getting usable web content into an AI workflow is hard: pages are JavaScript-rendered, sites require clicks or logins, and raw HTML is noisy. This Skill gives you a single CLI to search the web, scrape pages into clean markdown, crawl entire site sections, and monitor pages for changes over time. ## Core Features & Use Cases - Web Search & Scraping: Find pages on any topic and extract their content as clean markdown optimized for LLM context windows, with parallel scraping up to your concurrency limit. - Crawling, Mapping & Interaction: Map URLs within a site, bulk-crawl documentation sections, download sites to local files, and interact with pages requiring clicks, forms, pagination, or logins. - Change Monitoring: Schedule recurring scrapes with natural-language or cron schedules, diff results against snapshots, and receive webhook or email alerts when tracked content changes. - Use Case: A researcher asks you to track a competitor's pricing page. You create a monitor with a goal like "Alert when pricing information changes" and get notified with a structured per-field diff whenever prices or plan features change. ## Quick Start Ask the assistant to search the web for a topic or scrape a specific URL, for example: "Use firecrawl to scrape https://example.com/pricing and summarize the plans."

Frequently Asked Questions about firecrawl

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

FAQPage Schema
How do I scrape a webpage into markdown from the command line?

Run firecrawl scrape with the quoted URL and an output flag, such as firecrawl scrape "https://example.com" -o .firecrawl/page.md. The CLI handles static and JavaScript-rendered pages and returns clean markdown.

How do I monitor a webpage for changes and get alerts?

Use firecrawl monitor create with a --page URL, a --goal describing what changes matter, and a schedule like "every 5 minutes" or a cron expression. Each check labels pages as same, new, changed, or removed, with webhook and email notification options.

Can I use Firecrawl without an API key?

Yes, search, scrape, and interact work on a keyless free tier that is rate-limited. For best results, authenticate with firecrawl login --browser or set a FIRECRAWL_API_KEY from firecrawl.dev.

When should I use scrape versus interact for web pages?

Use scrape first since it handles static pages and JS-rendered SPAs. Add interact only when content requires clicks, form fills, pagination, infinite scroll, or login, or when scrape fails to capture everything.

Why is the firecrawl command not found after installation?

The npm global bin directory may not be in your PATH. Verify with npx [email protected] --version, then reinstall globally with npm install -g [email protected] if needed.