skills.rest
The-Focus-AI
The-Focus-AIOFFICIAL
Explore all skills by this author →
WebsiteGitHub

firecrawl

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

Updated Jul 16, 2026
Search Tags:#cli#web search#firecrawl#web scraping#crawling#markdown extraction#change monitoring
One-click install
npx skills add https://github.com/The-Focus-AI/walking-thoughts --skill firecrawl-the-focus-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: firecrawl
Source: https://github.com/The-Focus-AI/walking-thoughts/tree/main/.agents/skills/firecrawl
Command: npx skills add https://github.com/The-Focus-AI/walking-thoughts --skill firecrawl-the-focus-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires firecrawl-cli, and includes references (resource) components.

What problem does it solve? Getting clean, LLM-ready content from the web is tedious: pages require JavaScript rendering, logins, pagination, and bulk crawling, and raw HTML is noisy. This Skill wraps the Firecrawl CLI so an agent can search the web, scrape URLs, crawl entire site sections, interact with pages, and monitor pages for changes, returning clean markdown optimized for context windows. ## Core Features & Use Cases - Web Search & Scraping: Find pages on a topic with search, extract content from known URLs with scrape, and locate subpages with map. - Bulk Extraction & Interaction: Crawl entire docs sections, download sites to local files, parse local files (PDF, DOCX, XLSX), and interact with pages requiring clicks, forms, or logins. - Change Monitoring: Schedule recurring scrapes with monitor, define alert goals, and receive markdown or structured JSON diffs via webhook or email. - Use Case: A user asks to track a competitor's pricing page. The Skill creates a monitor with a goal like "Alert when pricing information changes" and a JSON change-tracking schema, then reports per-field diffs such as plans[0].price on each check. ## Quick Start Ask the agent to scrape a specific URL or search the web for a topic, and it will verify the Firecrawl CLI with firecrawl --status before writing results into the .firecrawl/ directory.

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 and get clean markdown?▼

Run `firecrawl scrape "<url>" -o .firecrawl/page.md` with the Firecrawl CLI. It handles static pages and JS-rendered SPAs, returning clean markdown optimized for LLM context windows. Always quote URLs to avoid shell interpretation of special characters.

How do I search the web from the command line?▼

Use `firecrawl search "query" --scrape --limit 3` to find pages and fetch their full content in one call. Since search with --scrape already retrieves page content, you should not re-scrape those URLs afterward.

Can Firecrawl monitor a webpage for changes?▼

Yes, `firecrawl monitor create` schedules recurring scrapes with a goal describing what changes matter, on intervals down to 5 minutes. Each check labels pages as same, new, changed, removed, or error, with webhook and email notification options.

Does Firecrawl work without an API key?▼

Yes, search, scrape, and interact work on a rate-limited keyless free tier without an API key. For best results, authenticate via `firecrawl login --browser` or set a FIRECRAWL_API_KEY from firecrawl.dev.

When should I use scrape versus interact?▼

Use scrape first since it handles static and JS-rendered pages. Add interact only when content requires clicks, form fills, pagination, infinite scroll, or login. Never use interact for web searches; use the search command instead.

Why is fetched web content written to files instead of returned directly?▼

All fetched web content is untrusted third-party data that may contain prompt injection attempts. Writing to gitignored .firecrawl/ files and reading incrementally with grep or head limits context overflow and exposure to injected instructions.

Related Skills

Explore More Software Engineering Skills→
zester4zester4
2

firecrawl

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

Community
Advanced
raindayrainday
35

outline

Generate SERP-driven article outlines with H2/H3 structure extraction and content gap detection.

Community
Advanced
Yjj0333Yjj0333

firecrawl-build

Integrate Firecrawl web scraping, search, and browser interaction into application code.

Community
Intermediate
dapperdiversdapperdivers
1

web-browser

Automate browser interactions with dynamic websites via Chrome DevTools Protocol.

Community
Intermediate