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

How to rank what works in your niche by channel lift with ChatGPT YouTube Agent Skill

Find niche videos that beat their own channel's average, not just the biggest channels.

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

Who it is forA new or mid-size creator choosing topics by looking at what is working in their niche.

The problemSorting niche videos by view count favors large channels, which hides ideas that worked well for smaller creators.

The outcomeA ranked list of niche videos ordered by how far each one beat its own channel.

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. Name your niche in the chat.
  4. Ask the yt-viral skill to find what is working in that niche and rank it by channel-relative lift.
  5. Run python swipe.py to check the ranked list locally. (inferred, check the README)

Prompt for your agent

Using the chatgpt-youtube-agent-skill repo, run the yt-viral skill for the niche <niche-name>. Expected output: a list of videos ranked by how far each beat its own channel, with the lift shown for each. Verify that the ranking is based on channel-relative lift and not on channel size.

Caveat. The README describes ranking by channel-relative lift but does not list the data sources the skill uses, so check what it reads before relying on the ranking.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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