browse

Drive a headless browser to automate QA testing and capture evidence.

Updated Apr 20, 2026
One-click install
npx skills add https://github.com/sennett-lau/alice --skill browse-sennett-lau
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/sennett-lau/alice/tree/main/framework/skills/browse
Command: npx skills add https://github.com/sennett-lau/alice --skill browse-sennett-lau

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a fast, extensible headless browser framework to automate QA testing, site dogfooding, and evidence collection across web deployments.

Core Features & Use Cases

  • Fast navigation, element interaction, and state verification across URLs.
  • Snapshot, diff, and annotated visuals to support bug reports and reviews.
  • Stateful context management (cookies, localStorage, storage) and support for headed or headless operation.

Quick Start

Install the skill and run the CLI to connect to a local server by issuing goto <url>.

Frequently Asked Questions about browse

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

FAQPage Schema
How do I automate headless browser QA testing for web deployments?

Automate headless browser QA testing by driving a Playwright-based browser to load pages, run interactions, and capture evidence for feature verification and regression checks. It supports stateful context management and annotated visuals.

Can I capture screenshots and visual diffs during automated browser interactions?

Yes, you can capture screenshots and visual diffs during automated browser interactions. The skill supports snapshots, diffs, and annotated visuals to support bug reports and reviews across loaded URLs and sessions.

Does Playwright support frame-aware navigation and state handling for feature verification?

Playwright supports frame-aware navigation and robust state handling for feature verification. The skill leverages this to manage cookies, localStorage, and storage while executing interactions and recovering from errors.

What is the best way to run regression checks across multiple URLs and sessions?

The best way to run regression checks across URLs and sessions is using a fast, extensible headless browser framework. It drives element interactions, verifies state, and captures evidence for performance validation.

How do I manage cookies and localStorage when driving a headless browser for site dogfooding?

Manage cookies and localStorage during site dogfooding through stateful context management. The skill handles storage state automatically, supporting both headed and headless operation while navigating across pages.

Why does headless browser automation fail to recover from navigation errors during performance validation?

Headless browser automation fails to recover when robust state handling and error recovery are missing. This skill implements frame-aware navigation and stateful context management to prevent failures during performance validation.