Browser Agents and Computer Use skills for Claude Code and Codex
Skills that let an agent drive a browser or desktop: Browserbase and Browser Use cloud browsers, Vercel's agent-browser CLI, Playwright and Puppeteer automation, Notte sessions, Firecrawl's navigating agent, WebMCP tools that make a site callable by agents, and Amazon WorkSpaces access to Windows desktop apps. They turn click-through tasks into steps an agent can run and verify.
Highest-scoring browser agent skills in the October 22, 2026 snapshot: playwright-skill from lackeyjb/playwright-skill (85/100), browser-use-to-stagehand from browserbase/skills (84/100) and unbrowse from unbrowse-ai/unbrowse (83/100). Scores come from the Suede Skill Check.
- 29 listed skills
- 15 repositories
- 11 with full pages
19 from official publishers. 5 bundle scripts. 8 connect to an outside service. Listed in Developer Tools and Frameworks (11), AI Agents and LLM Engineering (8), Testing and QA (6), Productivity and Knowledge Work (3), Data, Analytics and Databases (1).
All 29 browser agent skills
No matching skills. Try fewer words or clear your search.
| Skill | Repository | What it does |
|---|---|---|
| add-webmcp 83/100 · B | browserbase/skills | Analyzes an existing web application for safe user-visible capabilities, implements first-party WebMCP tools, and validates discovery and invocation with Stagehand. |
| autobrowse 83/100 · B | browserbase/skills | Improves browser automation through an iterative loop that runs a browsing task, reads the trace, and refines the navigation strategy until it reliably passes. |
| browser-to-api 80/100 · B | browserbase/skills | Turns a website's observable HTTP traffic into a best-effort OpenAPI 3.1 spec by analyzing a browser-trace capture, to discover endpoints from a browser session. |
| browser-trace 80/100 · B | browserbase/skills | Captures a DevTools-protocol trace of browser automation, including CDP events, screenshots, and DOM dumps, and splits it into per-page searchable buckets for debugging. |
| browser-use-to-stagehand 84/100 · B | browserbase/skills | Migrates browser-use Python automation scripts to Stagehand v3 TypeScript on Browserbase, mapping browser-use features and APIs to Stagehand primitives. |
| dev-browser 77/100 · C | SawyerHood/dev-browser | Automates browser tasks through the dev-browser CLI with persistent named pages, such as navigating sites, filling forms, taking screenshots, and extracting web data. |
| document-hunter 82/100 · B | bitwize-music-studio/claude-ai-music-skills | Searches and retrieves primary source documents, such as court filings, government reports, and public records, from free public sources using automated browser navigation. |
| playwright-cli 80/100 · B | testdino-hq/playwright-skill | Automates browser interactions with playwright-cli to test web applications you own, including navigation, form filling, screenshots, tracing, debugging, and generating Playwright test code. |
| playwright-skill 85/100 · B | lackeyjb/playwright-skill | Automates browsers with Playwright, auto-detecting dev servers and writing reusable test scripts for screenshots, responsive checks, UX validation, login flows, and link checks. |
| safe-browser 75/100 · C | browserbase/skills | Builds constrained-browser agents whose safe_browser tool enforces a domain allowlist, so an agent can browse without raw browser, shell, or CDP access. |
| unbrowse 83/100 · B | unbrowse-ai/unbrowse | Searches and calls websites through Unbrowse's API or remote MCP, reusing indexed site tools, reading pages, and learning missing routes in its cloud browser. |
| agent-browser 75/100 · C | vercel-labs/agent-browser | Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking… |
| amazon-workspaces-agent-access 83/100 · B | aws/agent-toolkit-for-aws | Connects AI agents to remote Windows desktop applications on Amazon WorkSpaces Applications (AppStream 2.0) through the managed Agent Access MCP… |
| browser 78/100 · C | browserbase/skills | Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract… |
| browser-automation-notte 69/100 · D | gooseworks-ai/goose-skills | Browser automation - control browser sessions, scrape pages, and run AI agents |
| browser-use 69/100 · D | browser-use/browser-use | Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers… |
| chrome-devtools 77/100 · C | github/awesome-copilot | Expert-level browser automation, debugging, and performance analysis using Chrome DevTools MCP. Use for interacting with web pages, capturing… |
| chrome-mcp-troubleshooting 87/100 · B | trailofbits/skills | Diagnose and fix Claude in Chrome MCP extension connectivity issues. Use when mcp__claude-in-chrome__* tools fail, return "Browser extension is not… |
| cloud 81/100 · B | browser-use/browser-use | Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation. Use this skill whenever the user needs help… |
| firecrawl-agent 79/100 · C | firecrawl/skills | Autonomously navigate websites and extract structured data across pages. Use when the task requires navigation or no suitable ready-made workflow or… |
| geb-skill 81/100 · B | LambdaTest/agent-skills | Generates Geb browser automation tests in Groovy with Spock integration. jQuery-like content DSL and page object pattern. Use when user mentions… |
| open-gstack-browser 70/100 · C | garrytan/gstack | Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. |
| puppeteer-skill 81/100 · B | LambdaTest/agent-skills | Generates Puppeteer scripts for browser automation, scraping, and PDF generation. Triggers on: "Puppeteer", "headless Chrome", "page.goto"… |
| remote-browser 66/100 · D | browser-use/browser-use | Controls an isolated Browser Use Cloud browser from a sandboxed machine with the current Browser Use CLI. |
| restaurant-booking 81/100 · B | gooseworks-ai/goose-skills | Book restaurant reservations via browser automation. Use when asked to make dinner reservations, book a table, or find availability at restaurants… |
| setup-browser-cookies 70/100 · C | garrytan/gstack | Import cookies from your real Chromium browser into the headless browse session. (gstack) |
| webmcp-gen 77/100 · C | browserbase/skills | Create, compile, and validate site-specific WebMCP init scripts from a target URL and desired tool capability. Use when the user wants to author… |
| webmcpify 83/100 · B | github/awesome-copilot | Make a web app agent-ready — propose a WebMCP tool manifest, integrate, verify in a real browser, heal; unrelated code stays untouched. Use for… |
| website-screenshot-notte 76/100 · C | gooseworks-ai/goose-skills | Take screenshots of any website using Notte browser automation. Use when asked to screenshot, capture, or snap a webpage. |
How to choose browser agent skills
Decide between a local browser and a hosted one. Local CLIs (agent-browser, dev-browser, Playwright) run on your machine; Browserbase, Browser Use Cloud and Notte run remote sessions and read an API key shown under Before you install.
For sites you own, consider WebMCP skills (add-webmcp, webmcp-gen, webmcpify). Exposing real tools is more reliable than having an agent click through the interface.
Browsing agents act with whatever session they hold. Use safe-browser's domain allowlist or a separate browser profile, and avoid importing personal cookies into automation you do not supervise.
Ranked browser agent shortlists
Related topics
Web Scraping and Browser Automation 30MCP Servers 82End-to-End and Browser Testing 56Test Automation 134Agent Safety and Guardrails 27
Find your next useful skill
Explore Rising Skills with quality scores and source reports, or search from inside your agent.
Get Rising Skills by email · Read Rising Skills · Install the finder · State of Agent Skills