playwright

Controls web pages to automate browsing, scraping, and end-to-end testing via DOM extraction and scripting tools.

10|Updated Mar 22, 2026
One-click install
npx skills add https://github.com/Lee-SiHyeon/oh-my-copilot --skill playwright-lee-sihyeon
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: playwright
Source: https://github.com/Lee-SiHyeon/oh-my-copilot/tree/main/.github/skills/playwright
Command: npx skills add https://github.com/Lee-SiHyeon/oh-my-copilot --skill playwright-lee-sihyeon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Browser-based tasks often require precise, repeatable interaction with complex web UIs, which is hard to do reliably and manually.

Core Features & Use Cases

  • Deterministic browser automation: navigate, snapshot, and interact with UI elements using stable references for reliable testing and verification.
  • Information gathering & scraping: extract text, HTML, attributes, titles, URLs, and element counts from targeted parts of a page.
  • Media outputs for evidence: take screenshots (including full-page) and export PDFs for documentation and debugging.
  • Stealth-style authentication guidance: includes an approach for handling browser automation signals that can block logins (e.g., common Google OAuth detection vectors) when used legitimately.

Quick Start

Ask your agent to open a URL, take an interactive snapshot of the page, then fill the login form fields and submit using the snapshot element references.

Frequently Asked Questions about playwright

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

FAQPage Schema
How do I automate web form submission and scrape the resulting page data?

You can automate web form submission and scrape resulting data by using deterministic browser automation to navigate pages, take interactive snapshots, fill form fields using element references, and extract DOM-derived text or attributes.

Can I capture full-page screenshots and export PDFs for web testing evidence?

Yes, browser automation supports capturing full-page screenshots and exporting PDFs. These media outputs provide visual evidence and documentation for web testing, verification, and debugging workflows.

How does browser automation handle stealth login for Google OAuth detection vectors?

Stealth login for Google OAuth detection vectors is handled through an approach that mitigates browser automation signals blocking authentication, allowing legitimate logins to proceed within an isolated session or profile.

What's the best way to extract specific HTML elements and attributes during web scraping?

The best way to extract specific HTML elements and attributes during web scraping is by controlling pages with deterministic commands, targeting page parts, and pulling text, HTML, titles, URLs, and element counts from the DOM.

Does browser automation support scripted waits for page navigation and specific page states?

Yes, browser automation supports scripted waits for page navigation and specific page states. This ensures deterministic command execution by pausing interactions until the targeted UI elements or page conditions fully load.

Why are my manual browser interactions with complex web UIs unreliable for repeat testing?

Manual browser interactions with complex web UIs are unreliable for repeat testing because they lack precise, repeatable control. Deterministic browser automation solves this by using stable references to navigate and interact with elements consistently.