playwright

Automates browser navigation and DOM interaction to extract data from dynamic websites.

1|Updated Mar 11, 2026
One-click install
npx skills add https://github.com/antonyfmunoz/OS --skill playwright-antonyfmunoz
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: playwright
Source: https://github.com/antonyfmunoz/OS/tree/main/skills/tools/playwright
Command: npx skills add https://github.com/antonyfmunoz/OS --skill playwright-antonyfmunoz

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It removes the need for manual browser work by automating navigation, login, DOM interaction, and extraction in complex, JavaScript-heavy web apps.

Core Features & Use Cases

  • Headless/Headed browser automation: Run Chromium in Docker to drive real UI flows and reliably test or scrape pages.
  • Session persistence for real sites: Save and restore authenticated sessions via storage_state (cookies + localStorage), which is critical for sites like Instagram.
  • Robust DOM interaction and waiting: Use selectors, locators, and wait conditions to handle dynamic content and reduce flaky automation.
  • Troubleshooting support: Produce diagnostic screenshots on failures to speed up recovery.

Quick Start

Ask the AI to use the playwright tool to open the Instagram DM inbox and extract unread thread messages using a saved instagram_session.json session.

Frequently Asked Questions about playwright

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

FAQPage Schema
How do I automate browser navigation and DOM interaction for JavaScript-heavy web scraping?

Browser automation for web scraping uses headless Chromium to drive real UI flows, navigate dynamic pages, and extract data via DOM interaction without manual clicking. It handles JavaScript-heavy web apps by using reliable selectors and wait conditions.

Can I persist authenticated login sessions for automated social monitoring on sites like Instagram?

Yes, session persistence saves and restores authenticated login sessions using storage_state, which retains cookies and localStorage. This allows automated social monitoring to access protected areas like an Instagram DM inbox without repeated manual logins.

What is the best way to run headless Chromium in Docker for UI-driven data collection?

Running headless Chromium in Docker for UI-driven data collection requires specific browser configurations like the --no-sandbox flag and sufficient /dev/shm allocation. This Docker-safe setup ensures reliable browser automation and scraping within containerized environments.

Why does my browser automation script fail to extract information from dynamic websites?

Browser automation fails on dynamic websites when selectors and wait conditions are not properly configured for asynchronous content. Using robust locators and capturing diagnostic screenshots on failures helps troubleshoot and reduce flaky automation behavior.

Do I need Playwright to automate login flows and UI-driven data collection?

Yes, automating complex login flows and UI-driven data collection requires Playwright, specifically its Python sync API. It provides the necessary browser contexts, DOM interaction capabilities, and session persistence to reliably extract information from dynamic websites.