How does it handle login credentials?

It securely reads authentication data from a .env.claude file, ensuring sensitive information is used for automation without being exposed in logs.

Where are the test screenshots saved?

All screenshots are automatically stored in the test-results/ directory for easy review and evidence collection.

Does this skill generate Playwright scripts?

No, it prioritizes using agent-browser commands directly for more reliable execution, though it can fall back to MCP Playwright tools if necessary.

What happens if a test fails?

The skill includes a strict rule to always close the browser session, regardless of success or failure, to prevent resource leaks.

Can I see the browser while the test runs?

Yes, the skill mandates the --headed option so you can monitor the browser interactions in real-time as the agent performs them.

Browser Testing & Automation

Name: Browser Testing & Automation
Author: simula-labs

bysimula-labs

ブラウザ自動化

Automates end-to-end browser testing and website interactions using agentic control for reliable UI validation.

概要

This skill provides a standardized framework for executing browser-based tasks and E2E tests directly within Claude Code. It prioritizes the agent-browser tool over manual script generation, ensuring a consistent environment with forced headed execution for visual verification. By automating server detection, handling authentication through secure environment variables, and mandating screenshot evidence stored in a dedicated results directory, it streamlines the debugging and testing workflow for modern web applications.

主な機能

Intelligent local server detection and automatic background startup.
Agent-first browser control using agent-browser for reliable execution.
Mandatory headed browser mode for real-time visual progress monitoring.
0 GitHub stars
Automatic screenshot capture in test-results/ for every execution step.
Secure credential management via .env.claude for automated logins.

ユースケース

Executing complex web workflows like multi-step authentication and organization switching.
Capturing visual evidence and screenshots for UI/UX audits and bug reporting.
Running automated E2E tests for web applications during the development cycle.

概要

主な機能

Intelligent local server detection and automatic background startup.
Agent-first browser control using agent-browser for reliable execution.
Mandatory headed browser mode for real-time visual progress monitoring.
0 GitHub stars
Automatic screenshot capture in test-results/ for every execution step.
Secure credential management via .env.claude for automated logins.

ユースケース

Executing complex web workflows like multi-step authentication and organization switching.
Capturing visual evidence and screenshots for UI/UX audits and bug reporting.
Running automated E2E tests for web applications during the development cycle.