Does this skill require a global Playwright installation?

No, it uses the uv package manager to run self-contained scripts, though browser binaries must be downloaded once using the recommended installation commands.

Can I run browsers in headed mode to see the automation?

Yes, you can disable headless mode by setting the HEADLESS=0 environment variable to visually debug and watch the browser interactions.

Is it suitable for web scraping dynamic content?

Absolutely; unlike simple HTTP clients, this skill renders the full page including JavaScript, making it ideal for scraping modern SPAs.

Can I use this for automated form filling?

Yes, it includes a dedicated script for navigating to URLs, populating fields, and submitting forms automatically.

How does this skill handle modern web elements like shadow DOM?

It utilizes Playwright's modern locator API which is designed to handle shadow DOM and asynchronous loading automatically.

Playwright Automation

Name: Playwright Automation
Author: dashed

bydashed

•

ブラウザ自動化

Automates browser interactions, web testing, and data scraping using Playwright for Python.

概要

This skill empowers Claude to perform advanced browser automation tasks using Playwright and the Python uv package manager. It enables reliable end-to-end web testing, automated form submission, high-quality screenshots, and dynamic web scraping through optimized scripts. By leveraging semantic locators and headless browser technology, it provides a robust framework for interacting with modern web applications without requiring complex global installations, making it an essential tool for developers building or testing web interfaces.

主な機能

Content extraction for page titles, URLs, links, and text content
Automated form filling and submission using stable semantic locators
Automated screenshot capture with full-page and headless support
Dynamic JavaScript execution and DOM evaluation
Advanced debugging tools including browser tracing and headed mode
2 GitHub stars

ユースケース

Scraping data from JavaScript-heavy websites that require full browser rendering
Generating visual previews and audit logs of web pages via automated screenshots
Automating end-to-end testing for web applications to ensure UI stability

概要

主な機能

Content extraction for page titles, URLs, links, and text content
Automated form filling and submission using stable semantic locators
Automated screenshot capture with full-page and headless support
Dynamic JavaScript execution and DOM evaluation
Advanced debugging tools including browser tracing and headed mode
2 GitHub stars

ユースケース

Scraping data from JavaScript-heavy websites that require full browser rendering
Generating visual previews and audit logs of web pages via automated screenshots
Automating end-to-end testing for web applications to ensure UI stability