dev-browser

Automate browser tasks with persistent state using Playwright and Node.js.

3|2|Updated Apr 24, 2026
One-click install
npx skills add https://github.com/openeuler-mirror/witty-diagnosis-agent --skill dev-browser-openeuler-mirror
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dev-browser
Source: https://github.com/openeuler-mirror/witty-diagnosis-agent/tree/main/src/opencode/features/builtin-skills/dev-browser
Command: npx skills add https://github.com/openeuler-mirror/witty-diagnosis-agent --skill dev-browser-openeuler-mirror

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires tsx, playwright, and includes references (resource) components.

What problem does it solve?

This Skill solves the challenge of automating complex web interactions, such as navigating sites, filling out forms, scraping data, and testing web applications, by maintaining persistent browser state across tasks.

Core Features & Use Cases

  • Persistent Browser Automation: Maintains page state across multiple script executions, allowing for complex, multi-step workflows.
  • Flexible Interaction Modes: Supports both standalone Chromium instances for fresh sessions and Extension Mode to control your existing, authenticated browser sessions.
  • Advanced Scraping: Provides tools for intercepting network requests and replaying API calls, which is significantly more reliable and faster than traditional DOM-based scraping.

Quick Start

Use the dev-browser skill to navigate to the target website and extract the main page content using the provided client API.

Frequently Asked Questions about dev-browser

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

FAQPage Schema
How do I automate browser workflows and maintain page state across multiple script executions?

To automate browser workflows with persistent page state, this Skill maintains the browser context across multiple script executions, allowing complex, multi-step web interactions like navigation and form submission to run sequentially without losing session data.

What is the best way to scrape dynamic websites without relying on DOM parsing?

The best way to scrape dynamic websites is by intercepting network requests and replaying API calls. This approach extracts structured data directly from network traffic, which is significantly faster and more reliable than traditional DOM-based scraping.

Can I use Playwright to automate tasks on my existing authenticated browser sessions?

Yes, you can automate tasks on authenticated browser sessions using Extension Mode. This feature allows Playwright to control your existing, logged-in browser instances instead of launching standalone Chromium instances with fresh sessions.

Do I need Node.js and Playwright installed to run web automation and testing scripts?

Yes, you need both Node.js and Playwright installed. The Skill requires Playwright to execute browser interactions and Node.js to run the tsx environment needed to handle network request interception and web navigation.

How does network request interception improve web scraping and application testing?

Network request interception improves web scraping and testing by capturing and replaying API calls directly. This mechanism bypasses dynamic DOM rendering issues, providing structured data extraction and reliable testing of web application network flows.