Firecrawl

This is a comprehensive web scraping and search toolkit that wraps the Firecrawl CLI. You get five main operations: search the web for topics, scrape individual URLs, map entire sites to find specific pages, crawl documentation sections in bulk, and interact with dynamic content that needs clicks or form fills. The skill includes detailed workflow guidance that escalates from simple scraping to browser interaction, plus smart patterns for parallel operations, credit tracking, and output management. All results save to a local .firecrawl directory as markdown or JSON. It's well suited for research tasks, documentation extraction, and any scenario where you need clean LLM-ready content from the web without manual copy-pasting.

skills.sh installs: 289
GitHub stars: 18
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add connorads/dotfiles --skill firecrawl --agent claude-code

Installs into .claude/skills of the current project.

Files

Firecrawl CLI

Search, scrape, and interact with the web. Returns clean markdown optimized for LLM context windows.

Run firecrawl --help or firecrawl <command> --help for full option details. For app integration or outcome workflows (research briefs, SEO audits, etc.), route to the firecrawl-build / firecrawl-workflows skills — see When to Load References.

Prerequisites

Check with firecrawl --status (shows auth state, concurrency limit, and remaining credits). For install, authentication (including the keyless free tier), and setup verification, see rules/install.md. For output handling guidelines, see rules/security.md.