browser-automation-orchestrator

name	browser-automation-orchestrator
description	Route a browser / UI automation task to the right driver among the cluster's specialists — debug-first headless Chromium, local-webapp Playwright testing, native macOS UI capture and control, and the interactive-TTY harness that supervises them. USE WHEN a user wants to drive, screenshot, scrape, test, or verify a web page or desktop UI but hasn't named which engine or session model to use.
cluster	browser-automation
version	1.0.0

Browser Automation Orchestrator

The single entry skill for browser and UI automation work. It places the task on the surface × session-model map — what are you driving (the web/DOM layer vs the native OS UI layer) and how long does the driver live (one-shot vs persistent) — and delegates to one of the specialist spokes. The cross-cutting model every spoke shares — the two automation surfaces, the session lifecycle, the selector/targeting strategy, and the debug-first evidence rule — lives in browser-automation-core; read it before choosing an engine or claiming a UI "works".

Cluster map (spoke → role)

• browser — debug-first headless Chromium driver. Console logs, network requests, and page errors are captured by default; primary command navigates + screenshots + reports diagnostics in one shot. The go-to for "load this URL and tell me what's broken."
• webapp-testing — Playwright toolkit for web apps. Manages dev-server lifecycle (), then runs native Python Playwright scripts using a reconnaissance-then-action pattern (wait for , inspect DOM, act on discovered selectors).