browser-automation

Automate browser interactions with Playwright MCP for E2E testing and web data extraction.

150|48|Updated Jan 24, 2026
One-click install
npx skills add https://github.com/irahardianto/awesome-agv --skill browser-automation-irahardianto
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browser-automation
Source: https://github.com/irahardianto/awesome-agv/tree/main/.agents/skills/browser-automation
Command: npx skills add https://github.com/irahardianto/awesome-agv --skill browser-automation-irahardianto

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Browser automation helps you reliably interact with complex web UIs without brittle selectors or flaky timing, so you can validate behavior, capture evidence, and extract data consistently.

Core Features & Use Cases

  • Snapshot-first page state control for deterministic click/type/navigate and reliable verification.
  • Playwright MCP interaction toolkit covering navigation, element actions, waiting, evaluation, console/network inspection, dialogs, tabs, and viewport resizing.
  • E2E testing and debugging playbooks including assertion patterns, network mocking for isolation, and an error diagnosis protocol.
  • Visual regression, accessibility, and scraping workflows using screenshot and aria snapshot strategies, plus evaluate-based extraction.

Quick Start

Use the browser-automation skill to test a login flow by snapshotting the page, navigating to the login URL, filling the email and password fields, clicking Submit, and then snapshotting again to verify the post-login state.

Frequently Asked Questions about browser-automation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate browser interactions without brittle selectors or flaky timing?

Browser automation uses a snapshot-first approach to capture page state before and after mutations, applying explicit ref targeting from snapshots to ensure deterministic click, type, and navigate actions for reliable verification.

What is the best way to run E2E testing and extract web data from live pages?

E2E testing and web scraping are handled through a Playwright MCP interaction toolkit covering navigation, element actions, waiting, and evaluation, enabling deterministic snapshot-verify loops for UI state review and data extraction.

Can I use Playwright MCP for visual regression and accessibility checks?

Yes, Playwright MCP supports visual regression and accessibility workflows by utilizing screenshot and aria snapshot strategies, along with evaluate-based extraction to capture and verify UI state from live pages.

How do I debug network issues and isolate tests during web scraping?

Playwright MCP provides E2E testing and debugging playbooks that include network mocking for test isolation, console and network inspection, and an error diagnosis protocol to resolve issues during browser automation.

Why should I avoid mixing MCP with CLI actions during browser automation?

Browser automation enforces a single-session rule that avoids mixing MCP with CLI actions to maintain deterministic snapshot-verify loops and prevent flaky timing when interacting with complex web UIs.

Does browser automation support viewport resizing and tab management?

Yes, the Playwright MCP interaction toolkit covers viewport resizing, tab management, and dialog handling, allowing you to test user flows and review UI state across different viewport configurations.