Automate This

You record yourself doing something tedious on your computer, hand over the video file, and this skill extracts frames and audio to figure out what you're actually doing step by step. It then proposes automation at three levels: a quick shell alias or AppleScript for the worst part, a full standalone script that handles the whole workflow, and finally a scheduled version with logging and error handling. What's smart here is that it fingerprints your environment first, checking what you already have installed (Python, Node, Playwright, etc.) so it only suggests automation using tools you can actually run. It won't propose some elaborate Selenium setup if you just need a curl command. The tiered approach means you can get a win in five minutes instead of abandoning the whole thing because full automation feels like a project.

skills.sh installs: 2.3K
GitHub stars: 41K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add github/awesome-copilot --skill automate-this --agent claude-code

Installs into .claude/skills of the current project.

Files

Automate This

Analyze a screen recording of a manual process and build working automation for it.

The user records themselves doing something repetitive or tedious, hands you the video file, and you figure out what they're doing, why, and how to script it away.

Prerequisites Check

Before analyzing any recording, verify the required tools are available. Run these checks silently and only surface problems:

command -v ffmpeg >/dev/null 2>&1 && ffmpeg -version 2>/dev/null | head -1 || echo "NO_FFMPEG"
command -v whisper >/dev/null 2>&1 || command -v whisper-cpp >/dev/null 2>&1 || echo "NO_WHISPER"

ffmpeg is required. If missing, tell the user: brew install ffmpeg (macOS) or the equivalent for their OS.
Whisper is optional. Only needed if the recording has narration. If missing AND the recording has an audio track, suggest: pip install openai-whisper or brew install whisper-cpp. If the user declines, proceed with visual analysis only.