firecrawl/cli
10 skills689k installs5.6k starsGitHub
Install
npx skills add https://github.com/firecrawl/cliSkills in this repo
1FirecrawlThe firecrawl skill from firecrawl/cli wraps the official Firecrawl CLI so agents can search the web, scrape URLs, map site sections, crawl documentation, parse local files, and interact with pages that need clicks, forms, or logins. After verifying firecrawl --status shows a valid FIRECRAWL_API_KEY, agents follow a six-step escalation from search through scrape, map plus scrape, crawl, monitor, and interact, writing outputs to .firecrawl/ as markdown or JSON. The skill covers monitor creation with natural-language goals, webhook and email alerts, JSON-mode change tracking for structured pricing fields, parallel scrapes up to the account concurrency limit, and search-feedback credits. It explicitly excludes local file, git, or deployment tasks, pointing integration work to firecrawl-build and outcome workflows such as research briefs or SEO audits to firecrawl-workflows. Developers reach for firecrawl when agents need full page bodies, multi-page doc extraction, or ongoing change detection beyond native fetch limits.96kinstalls2Firecrawl SearchPerforms web search with optional full-page content extraction. Returns search results as JSON with options to scrape complete markdown from each result page. Supports news, image, and web source filtering.77.6kinstalls3Firecrawl ScrapeExtracts clean markdown from URLs including JavaScript-rendered single-page applications. Returns LLM-optimized content with options for main content extraction and concurrent scraping of multiple pages.77.5kinstalls4Firecrawl CrawlBulk extracts content from entire websites by following links up to specified depth. Supports path filtering, concurrent extraction, depth limits, and async job handling with status monitoring.75.7kinstalls5Firecrawl AgentAI-powered autonomous extraction that navigates complex websites and returns structured data as JSON. Supports optional JSON schema specification for predictable output. Takes 2-5 minutes per extraction task.75.6kinstalls6Firecrawl MapDiscovers and lists URLs on a website with optional search filtering to find specific pages. Supports sitemap handling strategies and subdomain discovery for navigating large sites.75.3kinstalls7Firecrawl DownloadDownloads entire websites as local files combining site mapping and scraping. Supports path filtering, multiple output formats per page, and organized local directory structures for offline access.75kinstalls8Firecrawl Interactfirecrawl-interact is a firecrawl/cli skill for controlling live browser sessions on any scraped page by clicking buttons, filling forms, navigating multi-step flows, and extracting data with natural language prompts or code. Developers invoke it when static scrapes fail on JavaScript-rendered content, login walls, pagination, infinite scroll, checkout wizards, or authenticated pages via profiles. The skill extends Firecrawl from read-only scraping to interactive automation for agents and CLI workflows. It supports profiles to persist browser state across scrapes and handles authenticated scraping before data extraction.60.4kinstalls9Firecrawl Parsefirecrawl-parse converts local documents into clean markdown, removing formatting noise while preserving structure. It handles PDFs, Word documents, spreadsheets, and HTML files, with options to generate AI summaries or answer questions about content.46.5kinstalls10Firecrawl Monitor| --- name: firecrawl-monitor description: | Detect when content on a website changes and get notified by webhook or email - no cron jobs, scrapers, or diff scripts required. Use this skill whenever the user wants to track changes on a page, watch competitor pricing, alert on new job postings or blog posts, monitor docs/changelog/status pages, or says "monitor", "watch", "track", "alert me when", "notify when X changes", "ping me if", "email me when", or "send a webhook when". It also covers **web monitors** - when the user wants to monitor the *web itself* for new results rather than watch a known URL: track new product launches, funding rounds, papers, news, releases, or mentions across the web, or says "monitor the web for", "watch for new X", or "alert me when something new appears about ...". For those, give search queries plus a goal instead of a URL.28.8kinstalls