Desktop app tester
Point it at your Electron app. Get it launched and driven by clicks and typing, with screenshots and logs.
Desktop app tester is a free AI skill for the job "Test and fix code". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · MIT licence · Made by sickn33 · Level: advanced
Made by sickn33. See the original on GitHub; we copied it as it is, with its licence.
What it does
Your Electron app, opened and used by the AI the way a person would, with screenshots and logs to show what happened. You can confirm a UI change works in the real app, not just in unit tests. A script launches the app under Playwright in the background and keeps it running between commands. The AI reads an accessibility snapshot to find buttons and fields by name, then clicks, types, waits for text, and takes screenshots it can look at. Each run uses a fresh profile. It suits first-run screens and bugs that only show in a built app. It needs Electron and Playwright installed, and it handles one window at a time.
You give it
- Your Electron project folder
- Electron and Playwright installed in it
- A description of what to click or check
- A launch config file (optional)
You get
- The app launched and driven step by step
- Screenshots of each important state
- Console and app logs
- A plain report of what worked and what broke
Use it when
- You changed a screen in your Electron app and want proof it works before you ship.
- A bug only shows up in the built app, not in development.
- You need to check the first-run or onboarding flow without clicking through it yourself.
- You want to confirm a feature works end to end, including the main process.
How to use it
- Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
- Ask for the job in your own words. Your AI opens the skill when it fits.
- It works best when your AI can run code and take screenshots.