Windows Automation Pre-Flight Check

Stop Shipping Flaky Desktop Scripts

Automating Windows applications is notoriously fragile. Most agents default to brittle pixel-clicking, fixed sleep timers, and "blind" keystrokes that break if a window moves or a network lags. This skill installs a mandatory pre-flight safety gate for your AI agent, ensuring it designs robust, production-grade automation before it ever writes a line of code.

What it does

When you ask your agent to automate a desktop app, this skill intercepts the request to generate a structured strategy. It forces the agent to identify controls using accessibility trees (UI Automation) rather than screen coordinates, define condition-based wait states instead of time.sleep(), and implement window-focus guards to prevent typing into the wrong application.

Why use this skill?

• Fail-Safe Design: Automatically includes abort hotkeys and "no-clobber" checks for destructive actions like file overwrites.
• Environment Awareness: Differentiates between local apps and Remote Desktop/Citrix environments, adjusting the strategy from UIA to Image Match/OCR where necessary.
• Observability: Ensures every script includes error logging and automated screenshots for easy debugging of GUI failures.
• Better than Prompting: Prevents the common "AI hallucinations" regarding window titles and control IDs by mandating path discovery via print_control_identifiers() or Inspect.exe.