skills.rest
joonlab
joonlabCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

browser-automation

Route browser tasks between cmux CLI and Playwright agents.

8|Updated Jul 26, 2026
Search Tags:#automation#workflow#playwright#scraping#browser#web-agent
One-click install
npx skills add https://github.com/joonlab/joonlab-claudecode-setting-for-share --skill browser-automation-joonlab
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser-automation
Source: https://github.com/joonlab/joonlab-claudecode-setting-for-share/tree/main/claude/skills/browser-automation
Command: npx skills add https://github.com/joonlab/joonlab-claudecode-setting-for-share --skill browser-automation-joonlab

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill solves the fragmentation of web interaction by providing a single, intelligent interface to drive real browsers for tasks ranging from simple scraping to complex, multi-step authenticated workflows.

Core Features & Use Cases

  • Dual-Backend Execution: Automatically routes tasks between a fast, deterministic CLI (cmux) for parallel scraping and a full AI-driven Playwright agent (aside) for complex, autonomous browser tasks.
  • Authenticated Session Management: Operates within your existing logged-in browser sessions, allowing for secure interaction with internal portals, SaaS dashboards, and personal accounts.
  • Use Case: Use this to automate daily tasks like logging into a dashboard to download reports, filling out multi-page web forms, or performing parallel research across multiple websites without manual intervention.

Quick Start

Use the browser-automation skill to open the target website and extract all text content from the main body.

Frequently Asked Questions about browser-automation

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

FAQPage Schema
How do I automate web scraping and form submission with Playwright?▼

This skill automates web scraping and form submission by routing tasks between a deterministic CLI for fast parallel scraping and an autonomous AI-driven Playwright agent for complex, multi-step workflows.

Can I use browser automation to interact with authenticated web sessions?▼

Yes, you can interact with authenticated web sessions. This skill operates within your existing logged-in browser environments to securely manage internal portals, SaaS dashboards, and personal accounts.

What is the best way to handle multi-step web workflows across different sites?▼

The best way to handle multi-step web workflows is using a dual-backend execution approach that automatically routes tasks between fast deterministic CLI scraping and full AI-driven browser agents for autonomous interaction.

Do I need cmux and Aside.app to run autonomous browser agents?▼

Yes, you need cmux and Aside.app to run autonomous browser agents. These integrations are required to manage persistent browser sessions and provide the Playwright-based execution environments.

Does browser automation support parallel scraping without manual intervention?▼

Yes, browser automation supports parallel scraping without manual intervention. It routes tasks to a deterministic CLI for fast parallel web interaction across multiple websites, while an AI agent handles autonomous research.

Related Skills

Explore More Software Engineering Skills→
drgon1drgon1
1

browser-agent-debug

Debug browser automation failures using CDP-connected Playwright sessions on port 9222.

Community
Advanced
abhishekmmgnabhishekmmgn

scrape

Extract text, tables, and metadata from web pages via Bash.

Community
Advanced
erencodingerencoding

Browser Use

Automates web browsing tasks including scraping, form filling, and testing via Python, Playwright, and npm tools with headless option and session management.

Community
Advanced
andreahakuandreahaku
1

browser-agent

Automate Chrome browser interactions via the DevTools Protocol using a Bun runtime.

Community
Intermediate