browse

Drive a headless browser from natural-language instructions to automate QA workflows.

2|Updated Feb 9, 2026
One-click install
npx skills add https://github.com/madebynoam/bryllen --skill browse-madebynoam
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/madebynoam/bryllen/tree/main/.claude/skills/gstack/browse
Command: npx skills add https://github.com/madebynoam/bryllen --skill browse-madebynoam

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automate end-to-end QA workflows by driving a headless browser from natural-language instructions, enabling reproducible tests and evidence without manual scripting.

Core Features & Use Cases

  • Navigate to URLs, interact with page elements, and verify states across responsive layouts.
  • Diff page changes before/after actions and generate annotated screenshots for bug reports.
  • Iterate on UI flows, validate forms and file uploads, and handle dialogs with built-in safety and state capture.

Quick Start

Describe the URL and actions you want performed; Bryllen will drive the browser to complete the workflow and return the results.

Frequently Asked Questions about browse

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

FAQPage Schema
How do I automate end-to-end QA workflows without writing manual test scripts?

Automating end-to-end QA workflows is done by driving a headless browser from natural-language instructions, enabling reproducible tests and evidence without manual scripting. You describe the URL and actions, and the browser executes the workflow automatically.

Can I generate annotated screenshots for bug reports using headless browser automation?

Yes, headless browser automation can generate annotated screenshots for bug reports. It captures page states before and after actions, allowing you to diff visual changes and attach evidence directly to your issue tracker.

Does headless browser QA automation support testing responsive layouts and form interactions?

Headless browser QA automation supports testing responsive layouts and form interactions. It can navigate to URLs, fill forms, handle file uploads, interact with dialogs, and verify page states across varying viewport sizes.

Do I need a Playwright runtime to execute natural-language browser commands?

Yes, a Playwright-based runtime is required to execute natural-language browser commands. The automation relies on Playwright to provide core commands such as goto, click, fill, screenshot, and snapshot for accessibility data.

What is the best way to validate page state and capture accessibility data during web testing?

The best way to validate page state and capture accessibility data during web testing is using a headless browser driven by natural language. It provides snapshot commands to extract accessibility data and verify UI state dynamically.