agent-browser

Automate web browsing tasks with CLI-style commands for research and data extraction.

Updated Mar 5, 2026
One-click install
npx skills add https://github.com/jeffreykthomas/nanoclaw-golf --skill agent-browser-jeffreykthomas
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/jeffreykthomas/nanoclaw-golf/tree/main/container/skills/agent-browser
Command: npx skills add https://github.com/jeffreykthomas/nanoclaw-golf --skill agent-browser-jeffreykthomas

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates web research, form interactions, and data extraction by controlling a browser from the command line, reducing repetitive tasks and manual browsing.

Core Features & Use Cases

  • Open URLs, navigate back/forward, reload pages, and manage browser state.
  • Snapshot the DOM to identify interactive elements and drive actions like click and fill.
  • Extract text, attributes, and data, test web app flows, and capture screenshots for validation.

Quick Start

Open a target URL with agent-browser to begin automated browsing.

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 browsing to extract data from public websites?

Automate web browsing tasks by using CLI-style commands to open URLs, interact with pages, and extract data. It controls the browser hands-free to gather answers and reduce manual research.

Can I use saved state authentication for UI testing on internal apps?

Yes, UI testing supports optional saved state authentication. This allows reliable, repeatable automated checks and form filling across internal apps that require login credentials to access.

How do I identify interactive elements when automating web page interactions?

To identify interactive elements, take a DOM snapshot. This captures the page structure, allowing you to target elements for actions like click and fill during your web automation workflow.

What's the best way to automate form filling and navigate web pages programmatically?

Automate form filling by opening a target URL and using command actions to fill fields and click buttons. You can navigate back, forward, and reload pages while managing browser state.

Does this web testing approach handle wait strategies for dynamically loaded content?

Yes, web testing implements wait strategies to handle dynamically loaded content. This ensures elements are present before actions are executed, making automated browsing reliable.

How do I capture screenshots for validation during web data extraction?

Capture screenshots for validation by using the snapshot command during your automation flow. This allows you to capture page states, extract text, and validate web app flows.