Title Thumbnail Packager

Yt package

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

Write and lint the title and thumbnail for a YouTube video as one pairing, checking truncation, duplication and vagueness before publish. Use for title ideas", "what should I call this", "thumbnail text", "my CTR is bad", packaging, or…

---
name: yt-package
description: >-
  Write and lint the title and thumbnail for a YouTube video as one pairing,
  checking truncation, duplication and vagueness before publish. Use for
  "title ideas", "what should I call this", "thumbnail text", "my CTR is
  bad", packaging, or any request to rename or repackage an existing video.
---

# yt-package

The title and the thumbnail are ONE unit. Writing them separately is why most packaging fails: the
thumbnail repeats the title, and half the click surface says the same thing twice.

```bash
python3 title.py --title "..." --thumb "AI RAN IT"
python3 title.py titles.txt            # one per line, ranked
```

Overview

The title and the thumbnail are ONE unit. Writing them separately is why most packaging fails: the thumbnail repeats the title, and half the click surface says the same thing twice.

Manual install (npx, ZIP)

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

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

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.md2.2 KB

Read SKILL.md here

Jakeschincariol/main1 file shown

SKILL.md2.2 KB

Browse every file on GitHub↗

SKILL.md

Show the full text50 lines

yt-package/SKILL.md50 lines · 2.2 KB

PreviewCode

Outline

RawView on GitHub

yt-package

The title and the thumbnail are ONE unit. Writing them separately is why most packaging fails: the thumbnail repeats the title, and half the click surface says the same thing twice.

python3 title.py --title "..." --thumb "AI RAN IT"
python3 title.py titles.txt            # one per line, ranked

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.

Rules the tool enforces, and why

60 characters is where desktop search truncates, 40 is a mobile home feed. Both are reported because they fail differently: a desktop cut loses the tail, a mobile cut can lose the subject.
The thumbnail must not repeat the title. Different words, same promise.
Three words maximum on the thumbnail. At feed size a fourth word is a grey smear.
A number, a name or a date beats every adjective available to you.
Two all-caps words is the ceiling before a title reads as spam.

Write ten, keep two

Generate ten titles, run them all through title.py, show the user the top three with their scores and the specific issue on each. For the winner, write the thumbnail brief: the expression, the framing, the three words, and what the background has to do to hold contrast at feed size.

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-package
3	description: >-
4	Write and lint the title and thumbnail for a YouTube video as one pairing,
5	checking truncation, duplication and vagueness before publish. Use for
6	"title ideas", "what should I call this", "thumbnail text", "my CTR is
7	bad", packaging, or any request to rename or repackage an existing video.
8	---
9
10	# yt-package
11
12	The title and the thumbnail are ONE unit. Writing them separately is why most packaging fails: the
13	thumbnail repeats the title, and half the click surface says the same thing twice.
14
15	```bash
16	python3 title.py --title "..." --thumb "AI RAN IT"
17	python3 title.py titles.txt # one per line, ranked
18	```
19
20	## Before you write
21
22	1. Read `~/.claude/youtube/voice.md` if it exists. That is the user's voice profile: how they talk
23	on camera, the words they never use, who they are talking to, what they will not claim. If it
24	does not exist, ask for three of their own videos, read or transcribe them, infer the voice,
25	and write the file. A script in the wrong voice is worse than no script, because they have to
26	read it out loud.
27	2. Never invent a number, a result or a source. If a figure would strengthen it and you do not have
28	one, ask for it or write the line without it.
29
30	## Rules the tool enforces, and why
31
32	- 60 characters is where desktop search truncates, 40 is a mobile home feed. Both are
33	reported because they fail differently: a desktop cut loses the tail, a mobile cut can lose the
34	subject.
35	- The thumbnail must not repeat the title. Different words, same promise.
36	- Three words maximum on the thumbnail. At feed size a fourth word is a grey smear.
37	- A number, a name or a date beats every adjective available to you.
38	- Two all-caps words is the ceiling before a title reads as spam.
39
40	## Write ten, keep two
41
42	Generate ten titles, run them all through `title.py`, show the user the top three with their scores
43	and the specific issue on each. For the winner, write the thumbnail brief: the expression, the
44	framing, the three words, and what the background has to do to hold contrast at feed size.
45
46	## The gate
47
48	Nothing here publishes. This skill writes and you publish. Every output ends in a block the user
49	copies, and the last line of every run is the question: ship it, or change it?
50