Who it is forA solo YouTube creator who wastes takes on intros that do not hold attention.
The problemA weak opening loses viewers in the first seconds, and a bad hook is often only noticed after the video is filmed.
The outcomeA script built from a chosen hook formula, with a hook score to check before you record.
What you need first
- ChatGPT or the Codex app that loads skills from ~/.codex/skills/
- git installed, if you use the clone option
- Python 3 to run the bundled scripts (the README says they need no packages)
- Your own channel data, such as an audience-retention export, for the analysis skills
Steps
- Install the skills by pasting https://github.com/Jakeschincariol/chatgpt-youtube-agent-skill into ChatGPT and saying install skill, or run
git clone https://github.com/Jakeschincariol/chatgpt-youtube-agent-skillthencp -r chatgpt-youtube-agent-skill/skills/yt-* ~/.codex/skills/. - Restart the app so the skills load.
- Copy
templates/voice.mdto~/.codex/youtube/voice.mdand fill it in, or send ChatGPT three of your own videos and say write my voice profile from these. - Ask the yt-script skill for a script on your topic using the hook formulas.
- Run
python hookscore.pyon the opening lines to get a hook score before you film. (inferred, check the README)
Prompt for your agent
Using the chatgpt-youtube-agent-skill repo, run the yt-script skill on the topic <topic> and use the voice file at ~/.codex/youtube/voice.md. Return a script with an opening written from one of the 21 hook formulas and a hook score for that opening. Verify that the output includes both the script and the score before recording.
Caveat. The README says nothing gets published until you upload it yourself, so the script and hook score are drafts you still need to review and film.
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page