browse

Controls a persistent headless Chromium browser for QA testing, page verification, and screenshot capture.

Updated Mar 16, 2026
One-click install
npx skills add https://github.com/bobbo01/B2BPlatform --skill browse-bobbo01
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/bobbo01/B2BPlatform/tree/main/.agents/skills/gstack-browse
Command: npx skills add https://github.com/bobbo01/B2BPlatform --skill browse-bobbo01

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires bun.

What problem does it solve? Manually verifying that a web page loads correctly, a form submits, or a deployment works requires opening a browser and clicking through flows by hand. This Skill automates that loop with a persistent headless Chromium instance, letting you navigate, interact, assert element states, and capture visual evidence in about 100ms per command. ## Core Features & Use Cases - Page and flow verification: Navigate any URL, fill forms, click elements, and diff page state before and after actions to confirm a change worked. - Visual evidence and responsive testing: Take plain or annotated screenshots, capture mobile/tablet/desktop viewports, and export pages as PDF for bug reports. - State inspection and assertions: Read console logs, network requests, cookies, and localStorage, and assert visibility, enabled, checked, or focused states of elements. - Use Case: After deploying a login flow, navigate to the login page, fill credentials via element refs, submit, then run a snapshot diff and check that the dashboard element is visible, attaching an annotated screenshot as proof. ## Quick Start Ask the AI to open your staging site in the browser, test the login flow, and take a screenshot of the result.

Frequently Asked Questions about browse

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

FAQPage Schema
How do I test a website with a headless browser?

Navigate to the URL with the goto command, then use text, console, and network commands to verify content loads without errors. Use snapshot -i to list interactive elements and click or fill them by their @e refs to test user flows.

How to take annotated screenshots for bug reports?

Run snapshot -i -a -o with an output path to capture a screenshot with red overlay boxes labeling each interactive element. Combine it with console output to attach both visual evidence and error logs to the bug report.

Can a headless browser handle CAPTCHA or MFA login?

Headless automation cannot solve CAPTCHAs or multi-factor authentication. Use the handoff command to open a visible Chrome window at the current page, let the user complete the challenge, then call resume to continue with preserved cookies and session state.

How do I test responsive layouts across devices?

Use the responsive command to capture mobile (375x812), tablet (768x1024), and desktop (1280x720) screenshots in one step. Alternatively set a specific size with the viewport command and take individual screenshots.

Why do element refs stop working after navigation?

Snapshot @e refs are invalidated whenever the page navigates or reloads. Run snapshot again after any goto, click that triggers navigation, or reload to get fresh refs before interacting with elements.