browser

Automate web browser interactions using AI-optimized accessibility snapshots and stable element references.

Updated Feb 10, 2026
One-click install
npx skills add https://github.com/monktui/git-review --skill browser-monktui
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browser
Source: https://github.com/monktui/git-review/tree/main/.claude/skills/browser
Command: npx skills add https://github.com/monktui/git-review --skill browser-monktui

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill reduces the effort required to manually operate websites during agent workflows by letting you drive the browser using compact, AI-friendly accessibility snapshots with stable element references instead of brittle DOM scraping.

Core Features & Use Cases

  • AI-Optimized Snapshots with Element Refs: Take snapshots (especially interactive-only) and interact via element refs like @e1, @e2 to minimize context size and improve determinism.
  • End-to-End Web Automation: Perform navigation and typical UI actions (click, fill, type, select, hover, scroll) followed by re-snapshot after page state changes.
  • Extraction and Waiting Utilities: Retrieve text/HTML/values/attributes and wait for selectors, text, URLs, or network idle to synchronize reliably.

Quick Start

Ask your agent to navigate to a target page, take an interactive snapshot, fill the login fields, click the submit button, and wait until the post-login dashboard URL loads.

Frequently Asked Questions about browser

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

FAQPage Schema
How do I automate web scraping without breaking selectors when the DOM changes?

You can automate web scraping without breaking selectors by using AI-optimized accessibility snapshots with stable element references like @e1 or @e2, ensuring deterministic interactions even when the underlying DOM structure changes on dynamic pages.

What is an accessibility snapshot for web automation?

An accessibility snapshot is a compact, AI-friendly representation of a web page's interactive elements that provides stable element references, minimizing context size and improving the determinism of browser interaction workflows.

How do I fill forms and click buttons using an AI agent in a web browser?

To fill forms and click buttons, take an interactive snapshot of the target page, use the generated element refs to perform actions like fill or click, and then re-snapshot after the page state changes to synchronize reliably.

Does web automation work for login flows and navigation-driven UI testing?

Yes, web automation supports login flows, form submissions, and navigation-driven UI testing by driving deterministic clicks, fills, and waits on dynamic pages, waiting for selectors, text, URLs, or network idle to synchronize reliably.

Why do I need to re-snapshot a web page after performing browser interactions?

Re-snapshotting a web page after browser interactions is required because dynamic pages update their state and DOM structure, and taking a new accessibility snapshot ensures your subsequent element refs remain accurate and deterministic.