browse

Automate browser QA tasks with a persistent headless browser.

Updated Apr 11, 2026
One-click install
npx skills add https://github.com/Scivor/helm --skill browse-scivor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/Scivor/helm/tree/main/skills/gstack/browse
Command: npx skills add https://github.com/Scivor/helm --skill browse-scivor

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Fast, reliable QA testing without setup friction. Navigate any URL, interact with elements, verify page state, and capture evidence across sessions, all powered by a persistent headless browser.

Core Features & Use Cases

  • Persistent headless browser that AI agents can drive to test features, dogfood flows, and verify UI behavior
  • Support for interaction, form testing, dialogs, diffing, and annotated screenshots to produce actionable evidence
  • State persistence across commands to enable end-to-end workflows and reproducible test harnesses

Quick Start

Use the browse skill to open a URL and drive automated QA checks, interact with the page, and collect evidence.

Frequently Asked Questions about browse

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

FAQPage Schema
How do I automate browser QA testing with a persistent headless browser?

Automate browser QA testing by using a persistent headless browser to navigate URLs, interact with elements, and verify page state across sessions. This enables AI agents to drive end-to-end workflows and capture actionable evidence like annotated screenshots without setup friction.

What is state persistence in headless browser testing and why does it matter?

State persistence in headless browser testing maintains browser context across sequential commands, enabling continuous end-to-end workflows. It allows AI agents to execute multi-step feature testing and create reproducible test harnesses without losing session data between interactions.

Can I capture evidence for bug reporting using an automated web browser?

Capture evidence for bug reporting by driving an automated web browser to interact with pages and take annotated screenshots. The browser supports form testing, dialog handling, and page diffing to produce actionable visual proof of UI behavior and feature failures.

Does this headless browser support form testing and dialog interaction?

The headless browser fully supports form testing and dialog interaction. AI agents can navigate to any URL, fill out forms, handle dialog boxes, interact with elements, and verify resulting page state to comprehensively test feature flows and report bugs.

What's the best way to verify UI behavior during feature testing without manual setup?

Verify UI behavior during feature testing by driving a persistent headless browser via AI agents. This approach eliminates manual setup friction, allowing you to navigate pages, interact with elements, and automatically capture evidence for reproducible test harnesses.