agent-browser

Automate browser interactions for web testing, form filling, and data extraction.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/b0nsu/oh-my-shit-memory --skill agent-browser-b0nsu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/b0nsu/oh-my-shit-memory/tree/main/src/features/builtin-skills/agent-browser
Command: npx skills add https://github.com/b0nsu/oh-my-shit-memory --skill agent-browser-b0nsu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Streamline manual browser tasks by automating web interactions, reducing repetitive testing and data-entry effort.

Core Features & Use Cases

  • Automate navigation, element interaction, and form filling across websites.
  • Capture screenshots, generate reports, and extract data from web pages for testing or data collection.
  • Use cases include automated UI testing, form submission workflows, and quick website explorations.

Quick Start

Open a URL and perform a simple interaction to verify the page loads.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate browser interactions for web testing and form filling?

Automated browser interactions for web testing and form filling are executed through a CLI-based control surface that manages element references, applies actions to found refs, and maintains state. This approach provides reliable, repeatable browser workflows across modern websites.

Can I capture screenshots and extract data from web pages during automated testing?

Yes, you can capture screenshots and extract data from web pages during automated testing workflows. The automation tool handles navigation and element interaction, allowing you to generate visual validation reports and collect data simultaneously across modern websites.

What is a CLI-based control surface for browser automation?

A CLI-based control surface for browser automation is an interface that locates page elements via element references, applies actions to those refs, and manages state. It provides robust error handling for reliable web testing, form filling, and data extraction workflows.

Does browser automation work for automated UI testing and form submission workflows?

Browser automation works effectively for automated UI testing and form submission workflows by streamlining manual tasks. It reduces repetitive testing and data-entry effort through reliable navigation, element interaction, and form filling across modern websites.

How do I handle error handling and state management in web testing automation?

Error handling and state management in web testing automation are managed by the underlying CLI-based control surface. It tracks element references and maintains state across actions, ensuring robust error handling during navigation, form filling, and data extraction workflows.