browser▌

Minimal CDP tools for collaborative site exploration and scraping.

Use agent-browser as the default CLI for deterministic UI checks.

This skill documents best practices for using agent-browser's built-in Kernel provider (-p kernel) for cloud browser automation.

A systematic approach to web performance optimization grounded in how browsers, protocols, and networks actually work. Apply these principles when building frontend applications, reviewing performance budgets, configuring servers, or diagnosing slow page loads.

Headless Chrome automation on Cloudflare Workers with Puppeteer and Playwright. \n \n Supports both Puppeteer (v1.0.4) and Playwright (v1.1.0) for screenshots, PDFs, web scraping, and browser automation on Cloudflare's global network \n Session reuse and browser context isolation for performance optimization; multiple tabs within a single browser to reduce concurrency usage \n Includes 8 documented issue preventions covering XPath workarounds, binding configuration, timeouts, concurrency limits,

Secure browser automation for sensitive operations like login, payments, and form filling with isolated credential handling. \n \n Executes credential entry, payment processing, and personal data form filling in a dedicated subprocess isolated from the main agent context \n Supports structured sensitive data via JSON file with predefined schema for credentials, payment info, and personal details; custom fields allowed \n Integrates with agent-browser through session state handoff, enabling authe

The CLI uses Chrome/Chromium via CDP directly. Install via npm i -g agent-browser, brew install agent-browser, or cargo install agent-browser. Run agent-browser install to download Chrome. Run agent-browser upgrade to update to the latest version.

Every browser automation follows this pattern:

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

Skill by ara.so — Daily 2026 Skills collection.