YouTube Channel Auditor

Yt audit

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

Audit a YouTube channel end to end - packaging, consistency, the first fifteen seconds, and what to fix first. Use for "audit my channel", "why isn't my channel growing", "review my videos", or a pasted channel URL.

---
name: yt-audit
description: >-
  Audit a YouTube channel end to end - packaging, consistency, the first
  fifteen seconds, and what to fix first. Use for "audit my channel", "why
  isn't my channel growing", "review my videos", or a pasted channel URL.
---

# yt-audit

An audit that lists twenty problems is a way of avoiding the one that matters. This ends in ONE fix.

## Before you write

1. Read `~/.claude/youtube/voice.md` if it exists. That is the user's voice profile: how they talk
   on camera, the words they never use, who they are talking to, what they will not claim. If it
   does not exist, ask for **three of their own videos**, read or transcribe them, infer the voice,
   and write the file. A script in the wrong voice is worse than no script, because they have to

Overview

An audit that lists twenty problems is a way of avoiding the one that matters. This ends in ONE fix.

Manual install (npx, ZIP)

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

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

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.md2.3 KB

Read SKILL.md here

Jakeschincariol/main1 file shown

SKILL.md2.3 KB

Browse every file on GitHub↗

SKILL.md

Show the full text49 lines

yt-audit/SKILL.md49 lines · 2.3 KB

PreviewCode

Outline

RawView on GitHub

yt-audit

An audit that lists twenty problems is a way of avoiding the one that matters. This ends in ONE fix.

Before you write

Read ~/.claude/youtube/voice.md if it exists. That is the user's voice profile: how they talk on camera, the words they never use, who they are talking to, what they will not claim. If it does not exist, ask for three of their own videos, read or transcribe them, infer the voice, and write the file. A script in the wrong voice is worse than no script, because they have to read it out loud.
Never invent a number, a result or a source. If a figure would strengthen it and you do not have one, ask for it or write the line without it.

What to look at, in this order

The last ten titles, as a set. Read them as a list, the way the channel page shows them. Do they promise different things? Run them through ../yt-package/title.py. A channel where every title is the same shape has a format problem, not a title problem.
The thumbnails, at feed size. Shrink them. What survives? If three of them are unreadable at that size, that is the fix and nothing else matters yet.
The first fifteen seconds of the three most recent. Transcribe them and score with ../yt-script/hookscore.py. This is where most channels lose.
Upload rhythm. Not frequency - CONSISTENCY. Six videos in one week and then nothing for a month is worse than one a fortnight forever.
The retention shape, if they can export it. /yt-retention.

What to hand back

The single biggest fix, named, with what to do this week.
Three things that are already working, so they do not break them. Be specific; "your energy is good" is not an observation.
What NOT to do yet, and why.

Never open an audit with praise you do not mean, and never end one with a list of twenty things.

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-audit
3	description: >-
4	Audit a YouTube channel end to end - packaging, consistency, the first
5	fifteen seconds, and what to fix first. Use for "audit my channel", "why
6	isn't my channel growing", "review my videos", or a pasted channel URL.
7	---
8
9	# yt-audit
10
11	An audit that lists twenty problems is a way of avoiding the one that matters. This ends in ONE fix.
12
13	## Before you write
14
15	1. Read `~/.claude/youtube/voice.md` if it exists. That is the user's voice profile: how they talk
16	on camera, the words they never use, who they are talking to, what they will not claim. If it
17	does not exist, ask for three of their own videos, read or transcribe them, infer the voice,
18	and write the file. A script in the wrong voice is worse than no script, because they have to
19	read it out loud.
20	2. Never invent a number, a result or a source. If a figure would strengthen it and you do not have
21	one, ask for it or write the line without it.
22
23	## What to look at, in this order
24
25	1. The last ten titles, as a set. Read them as a list, the way the channel page shows them. Do
26	they promise different things? Run them through `../yt-package/title.py`. A channel where every
27	title is the same shape has a format problem, not a title problem.
28	2. The thumbnails, at feed size. Shrink them. What survives? If three of them are unreadable at
29	that size, that is the fix and nothing else matters yet.
30	3. The first fifteen seconds of the three most recent. Transcribe them and score with
31	`../yt-script/hookscore.py`. This is where most channels lose.
32	4. Upload rhythm. Not frequency - CONSISTENCY. Six videos in one week and then nothing for a
33	month is worse than one a fortnight forever.
34	5. The retention shape, if they can export it. `/yt-retention`.
35
36	## What to hand back
37
38	- The single biggest fix, named, with what to do this week.
39	- Three things that are already working, so they do not break them. Be specific; "your energy is
40	good" is not an observation.
41	- What NOT to do yet, and why.
42
43	Never open an audit with praise you do not mean, and never end one with a list of twenty things.
44
45	## The gate
46
47	Nothing here publishes. This skill writes and you publish. Every output ends in a block the user
48	copies, and the last line of every run is the question: ship it, or change it?
49