Where are the screenshots and PDFs saved?

By default, all generated visual assets and output files are saved to the ./tmp/playwright/ directory in your current project folder.

What are the prerequisites for using this skill?

You must have Node.js installed, along with Playwright and the Chromium browser, which can be installed globally via npm.

Can it handle complex interactions like drag-and-drop?

Yes, the skill includes specialized templates designed to handle multi-step logic, including drag-and-drop, hovers, and keyboard interactions.

Does this skill require a separate MCP server?

No, this skill uses a lightweight hybrid approach using CLI commands and local templates to provide automation directly through your environment without MCP overhead.

When should I use the CLI versus templates?

Use CLI commands for simple, single-action tasks like screenshots or PDFs. Use the included templates for tasks requiring state management, event listening, or multi-step logic.

Playwright Browser Automation

Name: Playwright Browser Automation
Author: ether-moon

byether-moon

浏览器自动化

Automates browser interactions and web testing using Playwright CLI and specialized interaction templates.

关于

This skill provides a powerful hybrid approach to browser automation within Claude Code, leveraging the Playwright CLI for quick tasks and JavaScript templates for complex interactions. It enables developers to capture high-quality screenshots and PDFs, automate form submissions, and monitor console or network activity without the need for a dedicated MCP server. Ideal for developers needing to perform end-to-end testing, visual regression checks, or automated web data collection directly from their terminal-based AI environment, this tool streamlines web workflows with minimal configuration.

主要功能

Perform complex user interactions including clicks, hovers, and drag-and-drop
Capture full-page screenshots and generate PDFs via simple CLI commands
Automate multi-field form filling with built-in validation
Monitor real-time console messages and network requests
Conduct accessibility audits and snapshot captures for UI/UX testing
0 GitHub stars

使用场景

Scraping dynamic content and monitoring network logs during page interactions
Automating end-to-end user journey testing on web applications
Generating visual documentation and performance snapshots for web pages

关于

主要功能

Perform complex user interactions including clicks, hovers, and drag-and-drop
Capture full-page screenshots and generate PDFs via simple CLI commands
Automate multi-field form filling with built-in validation
Monitor real-time console messages and network requests
Conduct accessibility audits and snapshot captures for UI/UX testing
0 GitHub stars

使用场景

Scraping dynamic content and monitoring network logs during page interactions
Automating end-to-end user journey testing on web applications
Generating visual documentation and performance snapshots for web pages