—skills · counting…
30,375MCP servers
Give your AI agents eyes on the web. These scraping and crawling skills turn raw websites into clean Markdown and structured JSON, handling dynamic JavaScript rendering and modern bot protection.
Turns any known URL into clean Markdown or structured data through the Firecrawl CLI — main content only, links included, with an option to wait for JavaScript to render first.
npx skills add firecrawl/cli --skill firecrawl-scrapeBulk-extracts many pages from one site or section — for example everything under /docs — with depth limits and status checks for long-running crawls.
npx skills add firecrawl/cli --skill firecrawl-crawlMicrosoft's official Playwright skill: open pages, interact through accessibility snapshots, take screenshots and work with Playwright tests straight from the terminal.
npx skills add microsoft/playwright-cli --skill playwright-cliA browser automation CLI built for AI agents: navigate, fill forms, click, take screenshots and extract data from websites — for scraping, QA and exploratory testing.
npx skills add vercel-labs/agent-browser --skill agent-browserEvery card above has its own npx skills add command and a copy button. Installing only requires Node.js; a few skills need an extra tool or API key, noted in their description.
The CLI asks which agents to install for — Claude Code, Cursor and other supported agents — and adds the skill to your project. Add -g to install it for your user account across every project.
Start a new agent session and ask in plain words. The agent loads the skill when your request matches its description. Read the SKILL.md on GitHub before installing anything on a system that matters.
Collect only public data, respect robots.txt and each site's terms of service, avoid personal data unless you have a lawful basis to process it, and rate-limit requests so you never burden a server. A skill doesn't change those rules — you remain responsible for how the data is collected and used. This is general guidance, not legal advice.
Yes. playwright-cli and agent-browser drive a real browser, so pages run their JavaScript before anything is extracted, and the agent can click, scroll and fill forms when content only appears after an interaction. firecrawl-scrape can also wait for rendering before returning clean Markdown.
Use firecrawl-scrape when you know the exact pages, firecrawl-crawl to bulk-extract everything under a section such as /docs, and a browser skill when you must log in or interact before the data appears. The Firecrawl skills run through the Firecrawl CLI, which uses a Firecrawl API key.
Code review, conventional commits, test-driven development and safe refactoring.
Explore Coding skillsTechnical SEO audits, crawls, structured data and Core Web Vitals fixes.
Explore SEO skillsDockerfiles, Kubernetes manifests, CI/CD workflows and Terraform.
Explore DevOps skillsSecurity code review, Semgrep scans, secret scanning and dependency audits.
Explore Security skillsBuild, generate and call Model Context Protocol servers and MCP Apps.
Explore MCP skillsThe open skills directory for Claude Code & AI agents
© 2026 findaskill