dev-browser

Automate browser interactions with persistent page state via a Playwright-based client API.

Updated Dec 24, 2025
One-click install
npx skills add https://github.com/baramnim/skill.md --skill dev-browser-baramnim
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dev-browser
Source: https://github.com/baramnim/skill.md/tree/main/dev-browser
Command: npx skills add https://github.com/baramnim/skill.md --skill dev-browser-baramnim

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Browser automation that preserves page state across script executions, letting you build workflows incrementally without re-navigating or re-authenticating.

Core Features & Use Cases

  • Persistent pages: maintain sessions and local storage between runs for reliable automation.
  • Script-based actions: write small, focused scripts that perform one action at a time (navigate, click, fill, screenshot) and compose them into complex workflows.
  • AI-assisted inspection: access tools like getAISnapshot, getOutline, and getVisibleText to understand pages and extract data.
  • Use cases include testing web apps, data extraction, form filling, and repetitive browser tasks across domains.

Quick Start

Launch the dev-browser server and connect a client to create and interact with a named page.

Frequently Asked Questions about dev-browser

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

FAQPage Schema
How do I keep browser automation sessions persistent across multiple script executions?

Persistent browser automation preserves page state, sessions, and local storage between script executions, letting you build workflows incrementally without re-navigating or re-authenticating each time.

Can I use Playwright with CDP to maintain local storage and login state?

Yes, this approach supports a Playwright-based client API with both launched and extension CDP modes, maintaining persistent profiles so local storage and login states survive across runs.

How do I extract data and inspect pages during stateful browser automation?

You can extract data and inspect pages using AI-assisted tools like getAISnapshot, getOutline, and getVisibleText to understand page structure and retrieve information during automation scripts.

What's the best way to automate multi-step web testing without re-authenticating?

Write small, focused scripts that perform one action at a time—navigate, click, fill, screenshot—and compose them into complex workflows using persistent pages that maintain sessions between runs.

Does browser automation support filling forms and taking screenshots across repeated runs?

Yes, script-based actions support navigating pages, filling forms, taking screenshots, and extracting data across repeated runs while preserving page state for reliable multi-step task automation.

When should I not use persistent browser profiles for web automation?

Persistent profiles are unnecessary for one-off stateless tasks or single-page scrapes where session continuity and local storage preservation between script executions provide no workflow benefit.