dev-browser

Automate browser interactions with persistent page state across sessions.

67.6k|5.5k|Updated Dec 3, 2025
One-click install
npx skills add https://github.com/code-yeongyu/oh-my-opencode --skill dev-browser-code-yeongyu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dev-browser
Source: https://github.com/code-yeongyu/oh-my-opencode/tree/main/src/features/builtin-skills/dev-browser
Command: npx skills add https://github.com/code-yeongyu/oh-my-opencode --skill dev-browser-code-yeongyu

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill provides reliable browser automation with persistent page state across script executions, enabling users to drive web tasks without losing context between steps.

Core Features & Use Cases

  • Maintain state across script runs so cookies, localStorage, and session data persist for multi-step workflows.
  • Standalone mode launches a new Chromium instance; Extension mode connects to an existing browser to operate in authenticated sessions.
  • Script each small interaction (navigate, click, fill, verify) and build complex workflows by chaining them; inspect pages with ARIA snapshots and take screenshots for validation.

Quick Start

Launch standalone mode:

  • cd skills/dev-browser && ./server.sh &
  • Wait for the Ready message before running scripts. If you prefer extension mode:
  • cd skills/dev-browser && npm i && npm run start-extension &
  • Wait for Extension connected in the console.

Frequently Asked Questions about dev-browser

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

FAQPage Schema
How do I maintain browser session state like cookies and localStorage across multiple Playwright script executions?

Browser automation with persistent page state solves this by retaining cookies, localStorage, and session data across script runs, enabling reliable multi-step workflows without losing context between executions.

What is the best way to automate filling forms and taking screenshots on authenticated web pages?

Use extension mode to connect browser automation to an existing authenticated browser session, allowing scripts to navigate sites, fill forms, and take screenshots within an already logged-in environment.

How do I start a standalone Chromium instance for web testing automation scripts?

Navigate to the skill directory and run the server script to launch a new Chromium instance, then wait for the ready message before executing your automation scripts.

Can I use Playwright to inspect web pages and verify UI elements during browser automation?

Yes, you can inspect pages using ARIA snapshots and take screenshots for validation, allowing you to verify UI elements and page states while scripting interactions like clicks and form fills.

Do I need Node and npm to run web testing and browser automation with persistent state?

Yes, this browser automation requires a Node-based environment with npm and Playwright libraries installed to execute the automation scripts and manage the persistent page state.