YouTube retention reader
Give it your retention export. Get where viewers leave, what you said then, and the one change to make.
YouTube retention reader is a free AI skill for the job "Grow on social". 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 Jake Schincariol
Made by Jake Schincariol. See the original on GitHub; we copied it as it is, with its licence.
What it does
Export your audience retention data and learn where viewers leave, what you were saying at that moment, and the one change to make. You download the retention file from Studio under Analytics, then run a small Python tool on it. It separates three problems. A hook leak is the share lost in the first 30 seconds, where under 25 percent is healthy. A cliff is one steep drop, and with a transcript the tool prints the words spoken right then. A slide is a steady loss across the middle, which means pacing and calls for cutting. You get the biggest leak and one fix. If numbers look fine, it points you to packaging.
You give it
- The retention CSV from YouTube Studio
- The video length in seconds
- Your transcript as an SRT file (optional)
- Transcript (optional)
You get
- A hook leak reading
- Cliff points with what you said there
- A note on any steady slide
- The one change to make first
Use it when
- A video lost half its viewers early and you want to know why.
- You see a sharp drop in the graph and want the words behind it.
- You are deciding what to change in your next video's opening.
- Your retention looks fine but views are low.
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 Python code.