agent-browser

Automate browser interactions for web testing and form filling.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/Dunc4nJ/agent-skills --skill agent-browser-dunc4nj
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/Dunc4nJ/agent-skills/tree/main/skills/agent-browser
Command: npx skills add https://github.com/Dunc4nJ/agent-skills --skill agent-browser-dunc4nj

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates browser interactions for web testing, form filling, screenshots, and data extraction, reducing manual repetitive tasks across websites. It enables users to navigate pages, interact with UI elements, capture evidence, and extract information for reporting.

Core Features & Use Cases

  • Open URLs and snapshot the page to discover interactive elements.
  • Interact with elements using refs or semantic locators to fill forms, click buttons, and navigate.
  • Capture screenshots, inspect state, and extract text or data for verification and reporting.
  • Use cases include automated web testing, form automation, UI exploration, and data extraction from websites.

Quick Start

Open a URL, snapshot elements, and interact with elements using refs to complete a form and verify results.

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 testing and form filling without manual repetition?

Automate web testing by opening URLs, snapshotting the accessibility tree or DOM, and interacting with UI elements using refs or semantic locators to fill forms and click buttons. This reduces manual repetitive tasks across websites by navigating pages and capturing screenshots automatically.

Can I extract data from websites by capturing page state and UI elements?

Yes, data extraction from websites is done by opening a URL, snapshotting elements, and gathering information from the page. You extract text or data for verification and reporting by inspecting the state and interacting with UI elements via refs or semantic locators.

What is the best way to locate and interact with UI elements during browser automation?

The best way to locate UI elements during browser automation is by snapshotting the page to discover interactive elements, then using element refs or semantic locators. This allows you to precisely fill forms, click buttons, and navigate pages.

Does browser automation work for managing cookies, storage, and network behavior?

Browser automation supports managing state, cookies, storage, and network behavior. You can optionally manage these aspects while navigating pages, interacting with UI elements, and taking screenshots to verify results.

How do I take screenshots during automated web testing for verification?

Take screenshots during automated web testing by navigating to the desired URL and interacting with UI elements. The automation commands capture screenshots, inspect state, and extract text or data for verification and reporting.

What are the limitations of using browser automation for UI exploration and data capture?

Browser automation for UI exploration and data capture requires snapshotting the accessibility tree or DOM to discover elements. It relies on element refs or semantic locators for interaction, which may need adjustment if the website's structure changes dynamically.