browse

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

1|Updated Feb 22, 2026
One-click install
npx skills add https://github.com/TarunTeja44/portfolio --skill browse-tarunteja44
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/TarunTeja44/portfolio/tree/main/.agents/skills/gstack-browse
Command: npx skills add https://github.com/TarunTeja44/portfolio --skill browse-tarunteja44

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Manually verifying that a web page loads correctly, that a user flow works end to end, or that a deployment matches staging requires repetitive clicking and visual checking. This Skill automates that work by driving a persistent headless Chromium browser through simple commands, producing snapshots, diffs, and annotated screenshots as evidence. ## Core Features & Use Cases - Page and flow verification: Navigate any URL, fill forms, click elements, and assert element states (visible, enabled, checked, focused) to validate user flows like login or checkout. - Visual evidence and diffs: Capture annotated screenshots with labeled element refs, take responsive screenshots at mobile/tablet/desktop viewports, and diff page state before and after actions or between two environments. - Diagnostics and handoff: Inspect console errors, network requests, cookies, and storage, and hand off to a visible Chrome window when hitting CAPTCHAs or multi-factor auth. - Use Case: After deploying a new feature, ask the agent to open the staging URL, walk through the signup flow, verify the dashboard appears, and produce an annotated screenshot plus console log as a bug report. ## Quick Start Ask the agent to open your site in the browser, test the login flow, and take an annotated 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 snapshot -i to list interactive elements, fill and click to walk through flows, and check text, console, and network output to verify the page loads and behaves correctly.

How do I take annotated screenshots of a web page for a bug report?

Run snapshot -i -a -o with an output path to capture a screenshot with red overlay boxes labeling each interactive element. Combine it with the console command to attach the error log as supporting evidence.

Can a headless browser handle CAPTCHAs or multi-factor login?

Headless automation cannot solve CAPTCHAs or MFA prompts. Use the handoff command to open a visible Chrome window at the current page so the user completes the challenge, then run resume to continue with preserved cookies and session state.

How do I compare staging and production versions of a site?

Use the diff command with two URLs to get a text diff between the pages. For visual comparison, take screenshots of each environment at the same viewport and compare them side by side.

Why does the browse tool need a setup step before first use?

The browse binary must be compiled once, which takes about ten seconds via the setup script in the skill directory. It requires bun, which can be installed with the official curl installer if missing.