agent-browser

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

8|1|Updated Dec 29, 2025
One-click install
npx skills add https://github.com/thomasmol/opencode-config --skill agent-browser-thomasmol
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/thomasmol/opencode-config/tree/main/skill/agent-browser
Command: npx skills add https://github.com/thomasmol/opencode-config --skill agent-browser-thomasmol

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates browser interactions, streamlining tasks like web testing, form filling, taking screenshots, and extracting data from web pages.

Core Features & Use Cases

  • Web Navigation: Open, reload, and navigate back/forward through web pages.
  • Element Interaction: Click, fill forms, hover, check/uncheck, and select dropdowns using element references or semantic locators.
  • Data Extraction: Get text, HTML, attributes, titles, URLs, and count elements.
  • Screenshots & PDF: Capture screenshots of the entire page or specific elements, and save pages as PDFs.
  • Video Recording: Record browser sessions for demonstrations or debugging.
  • Use Case: Automate the process of logging into a web application, filling out a complex form, and then taking a screenshot of the confirmation page.

Quick Start

Use agent-browser to open the URL https://example.com and then fill the input field with the ID 'username' with the text 'testuser'.

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 scraping and form filling for testing?

Automate web scraping and form filling by using a browser environment to navigate URLs, interact with elements via semantic locators, and extract text or HTML. It streamlines testing by capturing screenshots and automating complex form submissions.

Can I capture screenshots of specific elements during browser automation?

Yes, you can capture screenshots during browser automation. The Skill supports capturing the entire page or targeting specific elements, and also allows saving page states as PDFs for comprehensive documentation.

Do I need a headless browser to extract data from web pages?

You need a headless or headed browser environment to extract data from web pages. This environment executes commands for retrieving content, getting element attributes, counting elements, and performing web navigation tasks.

What is the best way to record web testing sessions for debugging?

The best way to record web testing sessions is using browser automation that supports video recording. This captures browser interactions like clicks and form filling, providing visual outputs for demonstrations or debugging.

How does semantic locator interaction work for web testing?

Semantic locator interaction works by referencing elements directly to perform actions like click, hover, check, and select dropdowns. It enables precise element interaction in web testing without relying solely on specific ID selectors.