browser▌

Every browser automation follows this pattern:

Automate web browser interactions for scraping, testing, and workflow automation.

Skill by ara.so — Daily 2026 Skills collection.

sentry-browser-sdk

Minimal Chrome DevTools Protocol (CDP) helpers for browser automation without MCP server setup.

Build browser extensions for Chrome, Firefox, and cross-browser platforms using Manifest V3 architecture. \n \n Covers extension structure, Manifest V3 configuration, content scripts, background service workers, popup UIs, and storage patterns \n Includes communication patterns between popup, background worker, and content scripts; DOM injection and event handling on web pages \n Provides Chrome Storage API usage with async/await patterns, storage limits, and data persistence across devices \n H

Browser automation with persistent page state across sequential scripts. \n \n Two modes: standalone Chromium (default) or extension mode connecting to user's existing Chrome browser with authentication already in place \n Discover page elements via ARIA snapshot accessibility tree, then interact using element references; alternatively read source code to write direct selectors \n Small, focused scripts that run incrementally—each script does one action (navigate, click, fill, check), then you e

Fast Rust-based headless browser automation with real Chrome profile and session support. \n \n Supports headless Chromium, real Chrome with profile/OAuth reuse via Chrome DevTools Protocol, and persistent session cookies for logged-in workflows \n 30+ commands covering navigation, interaction (click, type, fill, drag, upload), extraction (text, HTML, attributes, screenshots), and state checks \n Deterministic element selection via snapshot refs (@e1, @e2, etc.) and semantic finders (role, text,

Vision-driven browser automation from screenshots, no DOM access required. \n \n Operates in a headless Puppeteer browser that persists across CLI calls, allowing sequential commands without session loss \n Interacts with all visible page elements using natural language prompts; no CSS selectors or accessibility labels needed \n Requires configuration of a vision-capable model (Gemini, Qwen, Doubao, or similar) via environment variables for visual grounding \n Supports connect, take_screenshot,

If next-browser is not already on PATH, install @vercel/next-browser globally with the user's package manager, then playwright install chromium.