agent-browser

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

Updated Mar 2, 2026
One-click install
npx skills add https://github.com/nous-labs/oh-my-opencode --skill agent-browser-nous-labs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/nous-labs/oh-my-opencode/tree/main/src/features/builtin-skills/agent-browser
Command: npx skills add https://github.com/nous-labs/oh-my-opencode --skill agent-browser-nous-labs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Automates browser interactions for web testing, form filling, screenshots, and data extraction, enabling teams to automate repetitive web tasks with consistent results.

Core Features & Use Cases

  • Browser automation: Navigate pages, interact with elements, and verify behavior across web apps.
  • Form filling & data extraction: Auto-fill forms, capture inputs, and export data for reporting.
  • Visual verification: Take screenshots and compare UI states to ensure visual correctness.
  • Use Case: Imagine a QA engineer needing to test a checkout flow across multiple browsers and capture test evidence with minimal manual clicks.

Quick Start

Open a URL and start automating common browser tasks with agent-browser.

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 data extraction?

You automate browser interactions by using CLI-based orchestration to navigate pages, interact with elements, and export data as JSON. This approach handles web testing, form filling, and data extraction across websites and web apps with consistent results.

What is the best way to automate form filling and capture screenshots across web apps?

Automating form filling and screenshot capture involves using browser control to navigate web pages, auto-fill inputs, and take screenshots for visual verification. This allows teams to capture test evidence and export data for reporting across multiple web apps.

Can I use browser automation to extract data and export it as JSON?

Yes, browser automation can extract data from web pages and export it as JSON output. This satisfies CLI-based orchestration for data extraction tasks, allowing you to capture inputs and export data for reporting across websites and web apps.

Does browser automation work for visual verification and UI state comparison?

Browser automation supports visual verification by taking screenshots and comparing UI states to ensure visual correctness. This enables teams to capture test evidence and verify UI behavior across web apps with minimal manual clicks.

What are the limitations of browser automation for web testing?

Browser automation for web testing is limited to CLI-based orchestration with navigation, interaction, form filling, screenshot, and data export capabilities. It relies on session handling and may require additional configuration for complex dynamic content or browser-specific edge cases.

Do I need any dependencies to start automating web tasks with browser control?

No dependencies are required to start automating web tasks with browser control. The tool operates independently with CLI-based orchestration for navigation, interaction, form filling, screenshots, and data export, enabling teams to automate repetitive web tasks without external dependencies.