dev-browser

Automate browser interactions with persistent page state across Playwright script executions.

1|Updated Oct 21, 2025
One-click install
npx skills add https://github.com/wredzio/core2 --skill dev-browser-wredzio
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dev-browser
Source: https://github.com/wredzio/core2/tree/main/.claude/skills/dev-browser
Command: npx skills add https://github.com/wredzio/core2 --skill dev-browser-wredzio

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Browser automation with persistent page state to streamline repeated website tasks across sessions. This Skill enables maintaining session data, cookies, and navigation context so that scripts can build on prior work without restarting from scratch.

Core Features & Use Cases

  • Stateful control: Create named pages and reuse them across script executions for deterministic automation.
  • Two operating modes: Standalone mode with a fresh Chromium and Extension mode via a CDP relay for wired or authed contexts.
  • What you can do: Navigate, fill forms, take screenshots, and scrape data while preserving page state between runs, enabling repeatable workflows.

Quick Start

Start the dev-browser server and connect a Playwright client. Use the named page API to create or reuse pages and script subsequent steps (navigate, click, fill, screenshot) in separate tasks.

Frequently Asked Questions about dev-browser

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

FAQPage Schema
How do I preserve browser page state across multiple Playwright script executions?

Persistent browser automation maintains session data, cookies, and navigation context across script executions. Named pages can be created and reused, allowing subsequent scripts to build on prior work without restarting the browser session from scratch.

What is stateful browser automation and when do I need it for web scraping?

Stateful browser automation preserves page state between script runs, enabling repeatable web scraping workflows. It is needed when tasks like navigating websites, filling forms, or scraping data require session continuity and cookies to access authenticated or contextual content.

Can I use a browser extension with Playwright for authenticated automation contexts?

Yes, an extension mode is available via a CDP relay for wired or authenticated contexts. This operates alongside a standalone mode with fresh Chromium, allowing Playwright to interact with existing browser sessions rather than isolated instances.

How do I take screenshots and fill forms while maintaining cookies between automation runs?

By using a named page API, scripts can navigate, fill forms, and take screenshots while preserving page state between runs. This ensures cookies and session data persist, enabling deterministic automation without losing context across separate executions.

Do I need a local server to run persistent browser automation with Playwright?

Yes, a local dev-browser server is required to operate alongside a Playwright client. The server manages the persistent page states and facilitates the connection, whether running in standalone mode or using the optional extension relay.

What are the limitations of using standalone mode versus extension mode for browser automation?

Standalone mode uses a fresh Chromium instance without pre-existing session data, while extension mode connects via a CDP relay to access wired or authenticated contexts. Standalone is simpler but lacks built-in session continuity without explicit state management.