Search, scrape, crawl, and monitor websites via the Firecrawl CLI.
npx skills add https://github.com/zester4/zilmate --skill firecrawl-zester4
Please help me install this Agent Skill. Skill: firecrawl Source: https://github.com/zester4/zilmate/tree/main/.agents/skills/firecrawl Command: npx skills add https://github.com/zester4/zilmate --skill firecrawl-zester4
search, then extract full page content as markdown with scrape, including JS-rendered SPAs. - Site Crawling & Mapping: Use map to locate subpages and crawl to bulk-extract entire sections like /docs/, or download a whole site to local files. - Page Interaction & Monitoring: Handle clicks, forms, pagination, and logins with interact, and set up recurring monitor jobs with goals, webhooks, and email alerts for change detection on pricing pages, job boards, or changelogs. - Use Case: A developer researching a library runs a search with scraping enabled, saves results to .firecrawl/, then sets a monitor on the library's changelog to get alerted when new versions ship. ## Quick Start Ask the assistant to search the web for a topic or scrape a specific URL using Firecrawl, for example: "Use firecrawl to scrape https://example.com/pricing and summarize the plans."High-intent search queries and answers about installing and using this skill.
Run firecrawl scrape with the quoted URL and an output file, for example firecrawl scrape "https://example.com" -o .firecrawl/page.md. The CLI handles static pages and JS-rendered SPAs and returns clean markdown optimized for LLM context.
Use firecrawl search "query" to find pages on a topic, and add --scrape --limit 3 to fetch full page content for the top results. Search results already include scraped content, so you should not re-scrape those URLs.
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.
Create a monitor with firecrawl monitor create, providing --page with the URL, --schedule such as "every 5 minutes", and a --goal describing what changes matter. Checks label pages as same, new, changed, removed, or error, with webhook and email notification options.
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, or when scrape fails to capture everything you need.
The npm global bin directory may not be in your PATH. Verify with npx [email protected] --version, and reinstall globally with npm install -g [email protected] if needed.
firecrawlSearch, scrape, crawl, and interact with websites via the Firecrawl CLI.
polymerdaoExtract structured website data and convert pages to Markdown via Polymer Pay endpoints.
CliffValeIntegrate Firecrawl /search API into applications for query-driven web discovery.
spideynoloveFetches web page HTML via a lightweight headless browser CLI.