agent-browser

Automate browser interactions including navigation, form filling, clicks, screenshots, and data extraction.

7|2|Updated Feb 25, 2026
One-click install
npx skills add https://github.com/wenerme/ai --skill agent-browser-wenerme
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/wenerme/ai/tree/main/skills/agent-browser
Command: npx skills add https://github.com/wenerme/ai --skill agent-browser-wenerme

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

agent-browser removes the friction of manually browsing, clicking, and copying data by executing consistent browser actions on behalf of an AI agent.

Core Features & Use Cases

  • Browser automation for real web tasks: Navigate pages, fill forms, click buttons, and complete multi-step website workflows.
  • Reliable element targeting: Use accessibility-tree snapshots and compact @eN element references to interact with dynamic UIs.
  • Testing and automation beyond plain websites: Perform QA, exploratory testing, bug hunts, and automate Electron desktop apps, Slack workflows, and cloud/browser environments.

Quick Start

Use the agent-browser skill when you need to automate a website task like opening a login page, entering credentials, and extracting specific data from the resulting page.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate web form filling and data extraction for AI workflows?

Browser automation for AI agents uses accessibility-tree snapshots and compact @eN element references to interact with dynamic UIs. This mechanism ensures reliable element targeting for clicks and form filling during multi-step web workflows.

Can I use browser automation for QA testing and Electron app automation?

Yes, QA testing and Electron app automation are supported through deterministic, stateful sessions. The Skill handles exploratory testing and bug hunts by applying browser control techniques to desktop applications and cloud environments.

Do I need a CDP-based Chrome setup for website automation?

A CDP-based Chrome or Chromium setup is required for website automation. This prerequisite enables the accessibility-tree snapshots and element references necessary to maintain deterministic, stateful browser sessions for AI agents.

What is the best way to handle dynamic UIs during web scraping and browser control?

Handling dynamic UIs during web scraping is best achieved using accessibility-tree snapshots with compact @eN element references. This approach provides reliable element targeting for consistent interactions in changing website layouts.

Why use accessibility tree snapshots instead of standard selectors for browser automation?

Accessibility tree snapshots are used instead of standard selectors to provide deterministic element targeting in dynamic UIs. This method generates compact @eN references, ensuring reliable browser interactions for AI agents.