One-click install
npx skills add https://github.com/bhianerd/aimemory --skill browse-bhianerd
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/bhianerd/aimemory/tree/main/.claude/skills/gstack/browse
Command: npx skills add https://github.com/bhianerd/aimemory --skill browse-bhianerd

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill removes the uncertainty of whether a web feature actually works by letting you automatically navigate, interact, and verify UI state while producing clear visual evidence.

Core Features & Use Cases

  • Headless QA browsing: Navigate to any URL, interact with elements, handle dialogs, and inspect page state to confirm expected behavior.
  • Evidence generation: Capture annotated and plain screenshots, plus diff views (before/after) to show exactly what changed.
  • Verification workflows: Assert visibility/enabled/disabled/checked/focused states, validate forms (including uploads), and test responsive layouts across viewports.
  • Use Case: You suspect a login regression after a deployment. Use this Skill to load the login page, fill credentials, submit, verify the post-login state, and attach screenshots and diffs for a bug report.

Quick Start

Tell the agent to test a specific user flow and produce screenshots and a before/after diff as evidence.

Frequently Asked Questions about browse

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

FAQPage Schema
How do I automate headless browsing to capture evidence screenshots for QA testing?

Headless browsing for QA testing automates navigation, element interaction, and state assertions on arbitrary URLs, capturing annotated screenshots and before/after diffs as visual evidence. You simply direct the agent to test a specific user flow and generate the required visual proof.

Can I validate forms and file uploads using a headless browser?

Yes, form validation including file uploads is supported by the headless browser. It interacts with form elements, submits data, and verifies the resulting page state, capturing screenshots to confirm whether the form submission behavior matches expectations.

What is the best way to verify responsive layouts across different viewport sizes?

The best way to verify responsive layouts is using headless browsing to render pages across different viewport sizes, capturing screenshots to check UI behavior. This automated approach confirms visibility and state assertions while producing visual evidence of layout consistency.

Does this headless browser tool work with dialog-handling and state assertions?

Yes, headless browsing supports dialog-handling scenarios and state assertions. It verifies visibility, enabled, disabled, checked, and focused states during navigation, maintaining persistent browser state across commands to accurately test complex UI interactions.

What happens when headless execution cannot proceed during web UI verification?

When headless execution cannot proceed during web UI verification, the tool performs a safe handoff and resume operation. This ensures persistent browser state is maintained, allowing command execution to continue accurately without losing interaction context or element targeting.

How do I generate before and after diff screenshots to show UI changes?

To generate diff screenshots, run automated headless browsing tasks before and after a change. The tool captures plain and annotated screenshots of each state, then produces a diff view highlighting exactly what changed in the web UI for bug reports.