mcpField
Y
yt-viral

yt-viral

github.com/jakeschincariolMarketing & growth3.5k494 installsUpdated 6w ago
Repository

About yt-viral

yt-viral is a skill for finding unusually successful YouTube video ideas by comparing each video's views with its channel's median. It reports title formulas and shared structure, while leaving publishing to the user.

Key features

  1. 01Ranks videos by views-to-channel-median multiple
  2. 02Skips channels with fewer than four videos
  3. 03Classifies titles with 21 formulas
  4. 04Returns top five and a shared structure
  5. 05Does not publish

Use cases

  1. 01Comparing ideas across channels of different sizes
  2. 02Finding title patterns among overperforming videos
  3. 03Choosing a video idea feasible to make this week

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/jakeschincariol/youtube-agent-skill --skill yt-viral

After installing, type/yt-viralin Claude Code to confirm it loaded.

Bundled filesswipe.py

Details

From the project README

yt-viral

Raw view counts rank channel size, not ideas. This ranks by multiple over each channel's own median, which is the only version of the question that is about the video.

python3 swipe.py collected.json --min 2.0

Collecting the input

You need at least four videos per channel or a median means nothing, and the tool will skip the channel and tell you it did. Collect them however the user prefers - yt-dlp --flat-playlist -J against a channel URL is the fastest, the public page works, a manual list works.

[{"channel":"...","title":"...","views":412000,"url":"...","duration":613}]

Read, do not scrape. Public listings only, never a logged-in session, never the user's own account credentials.

Reading the output

The multiple is the signal. The formula line is a judgement about the TITLE, matched against the 21 formulas - it is not a claim about why the video worked, and you should say so when you present it.

What to hand back: the top five with their multiples, the formula each used, and the ONE structural thing they share. Then the harder line - which of those the user could actually make this week, in their voice, with what they have.

The gate

Nothing here publishes. This skill writes and you publish. Every output ends in a block the user copies, and the last line of every run is the question: ship it, or change it?

Comments

Markdown supported