Viral Pattern Finder

Yt viral

by Jakeschincariol · MIT license · ★ 1,136 on GitHub

Find what is actually working in the user's niche on YouTube and rank it by how far each video beat its own channel, then name the formula. Use for what's working right now", "find viral videos in my niche", "why did this blow up",…

---
name: yt-viral
description: >-
  Find what is actually working in the user's niche on YouTube and rank it
  by how far each video beat its own channel, then name the formula. Use for
  "what's working right now", "find viral videos in my niche", "why did this
  blow up", competitor research, or a swipe file.
---

# 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.

```bash
python3 swipe.py collected.json --min 2.0
```

Overview

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.

Manual install (npx, ZIP)

Claude Codenpx skills add Jakeschincariol/youtube-agent-skill --skill yt-viral -g -a claude-code

Claude Code (degit)npx degit Jakeschincariol/youtube-agent-skill/skills/yt-viral#main ~/.claude/skills/yt-viral

Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.

Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

SKILL.md1.7 KB

Read SKILL.md here

Jakeschincariol/main1 file shown

SKILL.md1.7 KB

Browse every file on GitHub↗

SKILL.md

Show the full text46 lines

yt-viral/SKILL.md46 lines · 1.7 KB

PreviewCode

Outline

RawView on GitHub

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?

1	---
2	name: yt-viral
3	description: >-
4	Find what is actually working in the user's niche on YouTube and rank it
5	by how far each video beat its own channel, then name the formula. Use for
6	"what's working right now", "find viral videos in my niche", "why did this
7	blow up", competitor research, or a swipe file.
8	---
9
10	# yt-viral
11
12	Raw view counts rank channel size, not ideas. This ranks by **multiple over each channel's own
13	median**, which is the only version of the question that is about the video.
14
15	```bash
16	python3 swipe.py collected.json --min 2.0
17	```
18
19	## Collecting the input
20
21	You need at least four videos per channel or a median means nothing, and the tool will skip the
22	channel and tell you it did. Collect them however the user prefers - `yt-dlp --flat-playlist -J`
23	against a channel URL is the fastest, the public page works, a manual list works.
24
25	```json
26	[{"channel":"...","title":"...","views":412000,"url":"...","duration":613}]
27	```
28
29	Read, do not scrape. Public listings only, never a logged-in session, never the user's own
30	account credentials.
31
32	## Reading the output
33
34	The multiple is the signal. The formula line is a judgement about the TITLE, matched against
35	[the 21 formulas](../yt-script/hooks.json) - it is not a claim about why the video worked, and you
36	should say so when you present it.
37
38	What to hand back: the top five with their multiples, the formula each used, and the ONE structural
39	thing they share. Then the harder line - which of those the user could actually make this week, in
40	their voice, with what they have.
41
42	## The gate
43
44	Nothing here publishes. This skill writes and you publish. Every output ends in a block the user
45	copies, and the last line of every run is the question: ship it, or change it?
46