{
  "$schema": "https://top-agent-skills.com/schemas/catalog.v1.json",
  "type": "primary-category",
  "slug": "browser-automation",
  "title": "Browser & Web Automation",
  "shortTitle": "Browser Automation",
  "description": "Headless browser control, scraping, navigation, and structured extraction at scale.",
  "canonical": "https://top-agent-skills.com/top-skills-for-browser-automation",
  "alternates": {
    "html": "https://top-agent-skills.com/top-skills-for-browser-automation",
    "markdown": "https://top-agent-skills.com/top-skills-for-browser-automation.md",
    "json": "https://top-agent-skills.com/top-skills-for-browser-automation.json"
  },
  "rubricVersion": "1.0",
  "methodology": "https://top-agent-skills.com/about/methodology",
  "contentLastUpdated": "2026-08-25",
  "count": 12,
  "topPick": {
    "slug": "playwright-cli",
    "name": "playwright-cli",
    "score": 60,
    "tagline": "Microsoft's first-party Playwright skill, invoked through the CLI — the reference implementation for driving a real browser, with no credentials required.",
    "url": "https://top-agent-skills.com/skill/playwright-cli"
  },
  "ranking": [
    {
      "rank": 1,
      "slug": "playwright-cli",
      "name": "playwright-cli",
      "score": 60,
      "tagline": "Microsoft's first-party Playwright skill, invoked through the CLI — the reference implementation for driving a real browser, with no credentials required.",
      "bestFor": "Driving a real browser from the agent and working with an existing Playwright suite — navigation, assertions, tracing, video, request mocking, and test generation.",
      "notIdealFor": "Hosted scraping at scale. It drives a local browser, so rate limiting and anti-bot handling are your problem — reach for a hosted extraction skill when the target fights back.",
      "provenance": "verified-org",
      "publisher": "Microsoft",
      "license": "Apache-2.0",
      "compatibility": [
        "claude-code"
      ],
      "install": "playwright-cli install --skills",
      "url": "https://top-agent-skills.com/skill/playwright-cli",
      "json": "https://top-agent-skills.com/skill/playwright-cli.json"
    },
    {
      "rank": 2,
      "slug": "browserbase-browser",
      "name": "browser",
      "score": 58,
      "tagline": "Local browser with no credentials, or a hosted Browserbase session with CAPTCHA solving and residential proxies when the target is protected.",
      "bestFor": "Sites that resist automation. The local mode works with zero setup; the remote mode adds verified browsers, CAPTCHA handling, and proxies for pages that block plain headless traffic.",
      "notIdealFor": "Licence-strict procurement. The repository has no LICENSE file — MIT is declared only in the skill frontmatter, so confirm that is sufficient for your compliance rules before adopting it.",
      "provenance": "verified-org",
      "publisher": "Browserbase",
      "license": "MIT (declared in SKILL.md frontmatter; no repo LICENSE file)",
      "compatibility": [
        "claude-code"
      ],
      "install": "npx skills add browserbase/skills",
      "url": "https://top-agent-skills.com/skill/browserbase-browser",
      "json": "https://top-agent-skills.com/skill/browserbase-browser.json"
    },
    {
      "rank": 3,
      "slug": "browserbase-ui-test",
      "name": "ui-test",
      "score": 58,
      "tagline": "Diff-aware adversarial QA: it reads the git diff and tests only what changed, across correctness, accessibility, layout and UX.",
      "bestFor": "QA on a pull request, where testing the whole app is too slow and testing nothing is what actually happens.",
      "notIdealFor": "Deterministic regression suites. It explores and spawns sub-agents with step budgets, so results vary between runs — use it alongside a fixed suite, not instead of one.",
      "provenance": "verified-org",
      "publisher": "Browserbase",
      "license": "MIT (declared in SKILL.md frontmatter; no repo LICENSE file)",
      "compatibility": [
        "claude-code"
      ],
      "install": "npx skills add browserbase/skills",
      "url": "https://top-agent-skills.com/skill/browserbase-ui-test",
      "json": "https://top-agent-skills.com/skill/browserbase-ui-test.json"
    },
    {
      "rank": 4,
      "slug": "chrome-devtools",
      "name": "chrome-devtools",
      "score": 57,
      "tagline": "Chrome's own team, giving agents the DevTools protocol: drive it, inspect it, debug it.",
      "bestFor": "Debugging a live page — performance, accessibility, memory, or why a flow breaks in a real browser.",
      "notIdealFor": "Large-scale scraping of blocked sites; that is what the proxy-based scraping skills exist for.",
      "provenance": "verified-org",
      "publisher": "Chrome DevTools (Google)",
      "license": "Apache-2.0",
      "compatibility": [
        "claude-code"
      ],
      "install": "/plugin marketplace add ChromeDevTools/chrome-devtools-mcp",
      "url": "https://top-agent-skills.com/skill/chrome-devtools",
      "json": "https://top-agent-skills.com/skill/chrome-devtools.json"
    },
    {
      "rank": 5,
      "slug": "verify",
      "name": "verify",
      "score": 50,
      "tagline": "Real feature verification — run the app, drive it, prove it works.",
      "bestFor": "Pre-merge verification for UI changes when type checks and unit tests verify code, not feature correctness.",
      "notIdealFor": null,
      "provenance": "anthropic",
      "publisher": "Anthropic",
      "license": "MIT",
      "compatibility": [
        "claude-code",
        "cursor"
      ],
      "install": "Built into Claude Code. Invoke with /verify.",
      "url": "https://top-agent-skills.com/skill/verify",
      "json": "https://top-agent-skills.com/skill/verify.json"
    },
    {
      "rank": 6,
      "slug": "firecrawl",
      "name": "firecrawl",
      "score": 49,
      "tagline": "Web scraping, search, and browser automation built to be agent-friendly.",
      "bestFor": "Research workflows, structured extraction at scale, search-grounded answers.",
      "notIdealFor": null,
      "provenance": "verified-org",
      "publisher": "Firecrawl",
      "license": "Proprietary",
      "compatibility": [
        "claude-code",
        "claude-api",
        "cursor",
        "codex"
      ],
      "install": "npx -y firecrawl-cli@latest init --all --browser",
      "url": "https://top-agent-skills.com/skill/firecrawl",
      "json": "https://top-agent-skills.com/skill/firecrawl.json"
    },
    {
      "rank": 7,
      "slug": "brightdata-skills",
      "name": "brightdata",
      "score": 48,
      "tagline": "The anti-bot problem, handled: proxies, SERP, and structured extraction at scale.",
      "bestFor": "Price comparison, competitive intelligence, and RAG pipelines over sites that fight scrapers.",
      "notIdealFor": "Simple public-page fetching, where a crawl-to-markdown skill is lighter and free.",
      "provenance": "verified-org",
      "publisher": "Bright Data",
      "license": "MIT",
      "compatibility": [
        "claude-code"
      ],
      "install": "/plugin marketplace add brightdata/skills",
      "url": "https://top-agent-skills.com/skill/brightdata-skills",
      "json": "https://top-agent-skills.com/skill/brightdata-skills.json"
    },
    {
      "rank": 8,
      "slug": "agent-browser",
      "name": "agent-browser",
      "score": 47,
      "tagline": "Deterministic web control. ref-based clicks/fills, no flaky selectors, parallel sessions.",
      "bestFor": "When you need browser automation that does not rely on clean APIs and survives selector churn.",
      "notIdealFor": null,
      "provenance": "verified-org",
      "publisher": "Vercel Labs",
      "license": "Apache-2.0",
      "compatibility": [
        "claude-code",
        "cursor"
      ],
      "install": "npm install -g agent-browser",
      "url": "https://top-agent-skills.com/skill/agent-browser",
      "json": "https://top-agent-skills.com/skill/agent-browser.json"
    },
    {
      "rank": 9,
      "slug": "valyu",
      "name": "valyu",
      "score": 46,
      "tagline": "Web search + 36 authoritative data sources. SEC, PubMed, ChEMBL, FRED — agent-grade research.",
      "bestFor": "Research workflows needing current, authoritative data with 79% FreshQA score.",
      "notIdealFor": null,
      "provenance": "verified-org",
      "publisher": "Valyu",
      "license": "Proprietary",
      "compatibility": [
        "claude-code",
        "claude-api",
        "cursor",
        "codex"
      ],
      "install": "npx skills add valyuai/skills",
      "url": "https://top-agent-skills.com/skill/valyu",
      "json": "https://top-agent-skills.com/skill/valyu.json"
    },
    {
      "rank": 10,
      "slug": "apify-skills",
      "name": "apify",
      "score": 45,
      "tagline": "Run the marketplace's scrapers, or turn your own scraper into a deployable Actor.",
      "bestFor": "Reaching for an existing scraper instead of writing one, or packaging your own scraper for reuse.",
      "notIdealFor": "Anything needing a local-only pipeline — Actors run on the Apify platform.",
      "provenance": "verified-org",
      "publisher": "Apify",
      "license": "Apache-2.0",
      "compatibility": [
        "claude-code"
      ],
      "install": "/plugin marketplace add apify/apify-claude-code-plugin",
      "url": "https://top-agent-skills.com/skill/apify-skills",
      "json": "https://top-agent-skills.com/skill/apify-skills.json"
    },
    {
      "rank": 11,
      "slug": "browser-use",
      "name": "browser-use",
      "score": 43,
      "tagline": "Headless browser as an agent tool. Navigate JS-heavy pages, fill forms, extract content.",
      "bestFor": "JS-rendered pages where simple HTTP scraping fails.",
      "notIdealFor": null,
      "provenance": "community",
      "publisher": "browser-use",
      "license": "MIT",
      "compatibility": [
        "claude-code",
        "cursor"
      ],
      "install": "pip install browser-use",
      "url": "https://top-agent-skills.com/skill/browser-use",
      "json": "https://top-agent-skills.com/skill/browser-use.json"
    },
    {
      "rank": 12,
      "slug": "playwright-skill",
      "name": "playwright-skill",
      "score": 40,
      "tagline": "Playwright patterns: clicks, fills, waits, retries. The do-it-right defaults.",
      "bestFor": "Adding Playwright tests where the agent would otherwise hand-roll fragile patterns.",
      "notIdealFor": null,
      "provenance": "community",
      "publisher": "lackeyjb",
      "license": "MIT",
      "compatibility": [
        "claude-code",
        "cursor"
      ],
      "install": "npx skills add lackeyjb/playwright-skill",
      "url": "https://top-agent-skills.com/skill/playwright-skill",
      "json": "https://top-agent-skills.com/skill/playwright-skill.json"
    }
  ],
  "faqs": [
    {
      "question": "Playwright or Puppeteer?",
      "answer": "Most modern browser-automation Skills default to Playwright — multi-browser support, stronger selector engine, better async API. Puppeteer remains common for Chrome-only flows."
    },
    {
      "question": "Can these Skills bypass CAPTCHAs?",
      "answer": "No. They drive real browser sessions; CAPTCHA solvers are not part of any Skill we list. Skills focused on evading detection or bypassing rate limits are not ranked here."
    },
    {
      "question": "Are scraping Skills legal?",
      "answer": "It depends on the source. The Skills do not enforce policy — that is your responsibility. Public pages, robots.txt compliance, and rate-limiting are table stakes."
    },
    {
      "question": "Do these Skills work for visual regression?",
      "answer": "Yes — several pair with Percy, Chromatic, or Playwright's built-in screenshot diff to catch unintended UI changes."
    },
    {
      "question": "Which agent works best for browser automation?",
      "answer": "Claude Code (with Preview MCP) and Cursor are the most common. Claude.ai web has narrower filesystem control and is rarely the right fit for automation work."
    }
  ],
  "license": "https://creativecommons.org/licenses/by/4.0/",
  "attribution": "Top Agent Skills (https://top-agent-skills.com)"
}