browser

Automate web navigation, element interaction, and data extraction via agent-browser.

Updated Mar 1, 2026
One-click install
npx skills add https://github.com/Dorpeer95/stocks-trading --skill browser-dorpeer95
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browser
Source: https://github.com/Dorpeer95/stocks-trading/tree/main/.claude/skills/browser
Command: npx skills add https://github.com/Dorpeer95/stocks-trading --skill browser-dorpeer95

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Web automation and testing often require brittle, manual browser interactions. This skill provides AI-optimized browser control to automate tasks, navigate pages, and extract information with stable element references.

Core Features & Use Cases

  • Open, navigate, and interact with pages using a robust set of commands (open, snapshot, click, fill, screenshot, close).
  • AI-optimized snapshots with element references to reduce DOM context and improve reliability across dynamic pages.
  • Support for multi-session workflows, data extraction, and UI testing through deterministic interactions and refs.
  • Seamless integration with Claude Flow MCP tools for scripted automation and rapid task orchestration.

Quick Start

Open a URL with agent-browser open <url>, snapshot interactive elements, and interact using refs to automate the task.

Frequently Asked Questions about browser

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

FAQPage Schema
How do I automate web interaction and browser navigation without brittle selectors?

AI-optimized browser automation uses agent-browser snapshots with stable element references to execute web interaction, reducing DOM context and improving navigation reliability across dynamic pages.

What is the best way to extract web data across multiple sites using deterministic task execution?

Web data extraction across multiple sites is handled through multi-session workflows that apply deterministic interactions and element refs, ensuring stable data extraction from varied page structures.

Can I use Claude Flow MCP tools for scripted browser automation and UI testing?

Claude Flow MCP tools integrate seamlessly with browser automation for scripted UI testing, enabling rapid task orchestration and deterministic execution through exposed browser commands.

How do I start automating browser tasks using agent-browser commands?

Start browser automation by running the agent-browser open command with a URL, take a snapshot of interactive elements, and interact using element refs to complete the task.

Does AI-driven browser control support multi-session workflows for UI testing?

AI-driven browser control supports multi-session workflows, allowing simultaneous UI testing and web interaction across multiple sites using deterministic element refs and session management.

Why use AI-optimized snapshots instead of raw DOM parsing for web automation?

AI-optimized snapshots reduce DOM context size and provide stable element references, preventing web automation failures on dynamic pages where raw DOM parsing and brittle selectors break.