browse

Navigate URLs and interact with page elements in a persistent headless browser.

1|Updated Mar 1, 2026
One-click install
npx skills add https://github.com/anishs1207/agentic-cli --skill browse-anishs1207
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/anishs1207/agentic-cli/tree/main/.agents/skills/gstack-browse
Command: npx skills add https://github.com/anishs1207/agentic-cli --skill browse-anishs1207

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. Use when asked to "open in browser", "test the site", "take a screenshot", or "dogfood this".

Core Features & Use Cases

  • Navigate URLs and interact with page elements in a fast, persistent headless browser.
  • Verify page state, diff before/after actions, capture annotated screenshots, test responsive layouts, handle dialogs, and assert element states.
  • Use cases include feature verification, regression checks, bug reproduction, and end-to-end QA across deployments.

Quick Start

Run the gstack browse skill to start a persistent headless browser and begin QA tests.

Frequently Asked Questions about browse

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

FAQPage Schema
What is headless browser QA testing for feature verification?

Headless browser QA testing executes deterministic commands to navigate URLs, interact with elements, and verify page state for feature verification, regression checks, and bug reproduction without a graphical interface.

How do I test responsive layouts and capture screenshots in a headless browser?

You test responsive layouts by navigating to a URL in a persistent headless browser, interacting with elements, and capturing annotated screenshots to verify the page state across different viewport sizes.

Can I automate web testing for forms, uploads, and dialog handling?

Yes, web automation supports testing forms, uploads, and dialog handling by executing deterministic commands in a persistent headless browser to interact with these page elements and assert their states reliably.

What is the best way to reproduce bugs and diff page states during regression checks?

The best way to reproduce bugs is by navigating the headless browser to the affected URL, interacting with elements, and diffing the page state before and after actions to capture evidence with annotated screenshots.

Does this headless browser require external dependencies to run QA tests?

No external dependencies are required to run QA tests. The headless browser operates persistently and executes deterministic commands at approximately 100ms per command for fast, reliable web automation.

When should I not use a fast headless browser for dogfooding?

You should not use a fast headless browser for dogfooding when you need visual rendering confirmation or manual exploratory testing, as it operates without a graphical interface and focuses on deterministic command execution.