DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to pull Shorts candidates out of a long video with ChatGPT YouTube Agent Skill

Find the Shorts already hiding in a long video and cut dead air from the edit list.

  • Content
  • Intermediate
  • 30 minutes
  • From the README
  • Codex

Who it is forA creator with a long finished video who wants short clips for the Shorts feed.

The problemStrong short moments sit inside long videos and are slow to find by scrubbing through the timeline.

The outcomeA list of Shorts candidates from the long video, plus an edit decision list with dead air flagged.

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

  1. Install the skills from the README link or the git clone and copy commands.
  2. Restart the app.
  3. Paste the transcript of the long video into the chat.
  4. Ask the yt-shorts skill to find the Shorts candidates in the transcript.
  5. Ask the yt-edit skill for an edit decision list, then (inferred) run python deadair.py on the transcript to flag dead air. (inferred, check the README)

Prompt for your agent

Using the chatgpt-youtube-agent-skill repo, run the yt-shorts skill on the transcript of <long-video-title> and then the yt-edit skill on the same transcript. Expected output: a list of Shorts candidates with start and end points and an edit decision list with dead air flagged. Verify that each candidate's timestamps fall within the transcript.

Caveat. The README says the skills write and you upload, so each Shorts candidate and cut still needs your own review and export before publishing.

Share: 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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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