Yt Title Optimizer

Community

sergebulaev

yt-title-optimizer

Write high-CTR YouTube and YouTube Shorts titles under 100 characters using 2026 packaging formulas (curiosity-gap, number, how-I outcome, mistake/loss, transformation, versus). Balances curiosity with a real keyword, front-loads the click-deciding words for the 60-char mobile cutoff, and returns 3 to 5 A/B variants tagged by goal for Test and Compare. Use to title or rework a video. Not for the description (use yt-description-writer) or the thumbnail overlay (use yt-thumbnail-brief).

Overview

Publisher	sergebulaev
Repository	`youtube-skills`
Skill name	`yt-title-optimizer`
Stars	85
Forks	21
Bundled files	1
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by sergebulaev on GitHub. Read the source before you install it.

Installation

Install the Yt Title Optimizer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/sergebulaev/youtube-skills/tree/main/skills/yt-title-optimizer
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/sergebulaev/youtube-skills.git /tmp/youtube-skills
mkdir -p .claude/skills
cp -r /tmp/youtube-skills/skills/yt-title-optimizer .claude/skills/yt-title-optimizer

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Yt Title Optimizer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Yt Title Optimizer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Yt Title Optimizer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

YouTube Title Optimizer

Titles are half the click. This skill turns a topic, a draft title, or a video URL into a shortlist of titles that earn the click honestly, then leaves the final pick (and the A/B test) to you.

When to use

User says "give me title ideas for this video"
User has a flat or clickbait title and wants sharper, honest options
User wants titles tied to a specific goal (CTR for browse, or search-intent)
User wants A/B variants to drop into YouTube's Test & Compare

Formulas this skill uses (packaging shapes, Y1-Y6)

Code	Formula	Best for
Y1	Curiosity-Gap	a surprising result whose mechanism is hidden
Y2	Number / Listicle	a finite, scannable payoff
Y3	How-I Outcome	a first-person result with a number and timeframe
Y4	Mistake / Negativity	a costly thing the viewer is getting wrong
Y5	Transformation	a before/after arc over a timeframe
Y6	Versus / Comparison	two named options in tension (search-friendly)
Y11	Third-Party Success Story	a named person/archetype who built a big number from zero

Full skeletons in ../../references/hook-formulas.md. Y11 was added from a 214-video corpus pull (July 2026) where the third-party rags-to-riches title was the most-frequent uncaptured shape; Y1/Y3/Y5 were the confirmed over-performers, and Y2/Y4/Y6 read weaker in the business/creator niche (noted in the reference).

Steps

Gather inputs. The topic or rough title, the real payoff of the video, the target viewer, the main search phrase if any, and whether it is long-form or a Short. If a URL is given, parse it with lib/url_parser.py and ask the user to paste the current title and what the video actually delivers.
Decide the job. Browse-first (lead with curiosity and emotion) or search-first (lead with the exact query phrase). Most videos want browse; how- to and comparison videos lean search.
Shortlist 2 to 3 formulas that fit the payoff, then draft.
Write 3 to 5 titles. Each one:
- Under 100 chars, ideally 40 to 60, click-deciding words first.
- One specific number where the claim allows it.
- Curiosity AND a concrete noun. Never pure mystery, never a dry label.
- Complements a thumbnail (note what the thumbnail should carry instead).
- At most one em dash, and a title rarely wants one (a colon reads cleaner); no ALL CAPS, 0 to 1 emoji.
Humanizer pass. Scrub 2026 AI vocabulary (a title is one line: any marker such as "leverage" or "game-changer" gets replaced), break stacked or hollow rule-of-three, strip reveal bridges ("Here's what nobody tells you") and sincerity framing ("honestly?", "real talk"). Replace an excess em dash with a colon, never a period.
Tag each variant with its formula, char count, and primary goal, and flag the one to lead the Test & Compare with.
Approval card. Show the variants with char counts. The user picks or asks for another round.
On approval. Titles ride along when the video is published. If the user is also uploading via this bundle, pass the chosen title as the title kwarg to lib.publish(kind="video"|"short", ...); otherwise hand it over for Studio.

Hard rules

Global voice rules: see root SKILL.md Voice rules. Additional skill-specific rules:

100-char hard cap. Aim 40 to 60 so mobile does not truncate the payoff.
Front-load: the words that decide the click go before any colon.
Title and thumbnail never repeat the same words. Note the split every time.
Curiosity must be honest. The title cannot promise more than the first 30 seconds delivers (a fast click-away is a ranking penalty).
Always return at least 3 variants. One title is not a recommendation.

Anti-patterns (skill will refuse)

Clickbait the video does not honor ("you won't believe what happened").
ALL CAPS titles or 3+ emoji for fake intensity.
Keyword-stuffing the title to chase search.
More than one em dash in a title, or a dash where a colon does the job.
Vague mystery with no concrete noun ("This changes everything").
Repeating the thumbnail's words in the title.

Resources

../../references/hook-formulas.md - Y1-Y6 title skeletons and the pairing table
../../references/algorithm-heuristics.md - CTR x retention, packaging, the 60-char cutoff
references/title-checklist.md - the per-title scrub and CTR fit list

Related skills

yt-thumbnail-brief - design the other half of the click
yt-hook-scripter - script the first 30 seconds so the title's promise lands
yt-description-writer - the SEO description and chapters
yt-content-planner - pair titles and thumbnails across a week

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

references/title-checklist.md2 KB

Frequently asked questions

What does the Yt Title Optimizer AI skill do?

Why use Yt Title Optimizer on TypingMind?

Because you install it once and use it with any model. Yt Title Optimizer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Yt Title Optimizer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/sergebulaev/youtube-skills/tree/main/skills/yt-title-optimizer. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Yt Title Optimizer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Yt Title Optimizer?

As many as you like. As long as a model supports skills, you can use Yt Title Optimizer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Yt Title Optimizer AI skill free?

Yes. It is published on GitHub by sergebulaev under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Content Engine

affaan-m

CommunityPopular

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content…

Fal Ai Media

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio…

Video Editing

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in…

Ai Presenter Video

Make a verified AI presenter video from script + image.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

YouTube Title Optimizer

When to use

Formulas this skill uses (packaging shapes, Y1-Y6)

Steps

Hard rules

Anti-patterns (skill will refuse)

Resources

Related skills

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now