yt-package — Claude Code skill for YouTube packaging
The yt-package Claude Code skill pairs YouTube titles with thumbnail text and checks for truncation, repetition, and vague wording. It runs on requests for title ideas or a new package for an existing video.
MIT 1,300 installs ★ 6,796 updated 2026-09-16
npx skills add Jakeschincariol/youtube-agent-skill --skill yt-package -a claude-codeWhat yt-package does
The skill drafts YouTube titles and thumbnail copy as a single package, then checks each pair for repetition, truncation, and vague phrasing. The title.py script checks an individual title and thumbnail or ranks entries from titles.txt.
It generates ten title options, presents the top three with scores and specific issues, then outlines the thumbnail for the chosen title: expression, framing, text, and background. It does not publish videos. Running the checks requires python3. If ~/.claude/youtube/voice.md is missing, the skill asks for three of the creator’s videos to infer their voice and write the profile file.
What it helps with
- pair a video title with distinct thumbnail copy
- catch title or thumbnail text that may be cut off
- rank candidate titles from
titles.txt - draft a visual brief for the selected title
Example prompts for the agent
- Suggest ten titles for my video and check each against its thumbnail text.
- Repackage this published video with a new title and thumbnail wording.
- Rank the options in
titles.txtand explain the issues with the best ones.
How to install yt-package
1Skills CLI (Vercel)
npx skills add Jakeschincariol/youtube-agent-skill --skill yt-package -a claude-code2Manually: put the files in place
~/.claude/skills/yt-package/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/yt-package/
1Skills CLI (Vercel)
npx skills add Jakeschincariol/youtube-agent-skill --skill yt-package -a codex2Manually: put the files in place
.agents/skills/yt-package/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Jakeschincariol/youtube-agent-skill --skill yt-package -a cursor2Manually: put the files in place
.cursor/skills/yt-package/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Jakeschincariol/youtube-agent-skill skills/yt-package2Manually: put the files in place
.github/skills/yt-package/SKILL.md1Skills CLI (Vercel)
npx skills add Jakeschincariol/youtube-agent-skill --skill yt-package -a gemini-cli2Platform CLI
gemini skills install https://github.com/Jakeschincariol/youtube-agent-skill --path skills/yt-packageManually: put the files in place
.devin/skills/yt-package/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add Jakeschincariol/youtube-agent-skill --skill yt-package -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about yt-package
How do I install yt-package in Claude Code?
Run npx skills add Jakeschincariol/youtube-agent-skill --skill yt-package -a claude-code. The skill file is installed at ~/.claude/skills/yt-package/SKILL.md.
What does yt-package do?
It creates and checks YouTube titles alongside thumbnail text, flagging repetition, truncation, and vague wording. For the chosen title, it drafts a visual brief; it does not publish the video.
What does yt-package need to run?
The checks require python3. If ~/.claude/youtube/voice.md does not exist, provide three of the creator’s videos so the skill can infer their voice and create the profile.
Source text
SKILL.md · MIT
--- 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 ``` ## 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 read it out loud. 2. 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?**
© Jakeschincariol · MIT · Jakeschincariol/youtube-agent-skill