Setup & Installation
openclaw skills install @kjaylee/playwright-testing
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install playwright-testing
What This Skill Does
Runs Playwright browser automation on a MiniPC node using headless Chromium. Handles web app and game QA, screenshot capture, DOM inspection, and console log collection. Executes via nodes.run or browser.proxy rather than the local machine.
Running tests on a dedicated MiniPC node keeps browser execution off the development machine and avoids display dependency issues.
When to use it
- Verifying a game loads and renders its canvas correctly
- Capturing screenshots of a web app at specific states
- Checking for JavaScript console errors during page interaction
- Automating click sequences to test UI flows
- Confirming score or state changes after user input
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: test that the game at localhost:9877 loads and the canvas is visible
AGENT
- 1Navigate to http://localhost:9877/game.html on MiniPC via browser.proxy or nodes.run
- 2Wait for networkidle state to ensure JS has finished executing
- 3Locate the canvas element and assert it is visible
- 4Click the canvas to trigger game interaction
- 5Take a screenshot and capture any console errors
OUTPUT
Screenshot saved to /tmp/game-test.png confirming canvas renders; console error list returned