MCPInstall

youtube-title-creator

Generate high-CTR YouTube titles and thumbnails using framework fitting method. Match content to 119 proven formulas from Creator Hooks, apply psychological principles, test variations.

Installs
55
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/cdeistopened/skill-stack --skill youtube-title-creator
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads youtube-title-creator automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

YouTube Title & Thumbnail Creator

Purpose

Generate YouTube titles and thumbnails with a high degree of complementarity that achieve 6%+ click-through rates using the framework fitting method: extract your concept, match to 119 proven formulas ranked by performance, generate variations, select best.

Core Philosophy: Good titles follow proven frameworks. The skill is in matching your concept to the delivery mechanism that amplifies it best.

When to Use This Skill

Use this skill when you need to:

  • Create YouTube titles for podcast episodes or educational videos
  • Generate thumbnail text that complements titles
  • A/B test title variations for same content

Do NOT use for:

  • Blog post headlines (use hook-and-headline-writing instead)
  • Social media captions (use social-caption-writer instead)
  • Newsletter subject lines (use hook-and-headline-writing instead)

Key Principles

The Framework Fitting Method

Extract your content concept → Review ALL applicable frameworks → Test the fit → Generate volume → Select best.

Critical Rule: Avoid First-Match Bias Do NOT default to first framework that seems to fit. The best framework might not be the obvious one.

The Complementarity Principle

Title + thumbnail work TOGETHER, not repeat each other.

Example:

  • ❌ Title: "Five Productivity Myths" + Thumbnail: "Five Productivity Myths"
  • ✅ Title: "Five Productivity Myths" + Thumbnail: "You're doing it wrong"

Universalization Strategy (Andrew Muto - July 8)

"Every word after your sexy hook is a filter to lessen the audience."

Examples:

  • ❌ "Five Productivity Myths Every Entrepreneur Believes" (filters to entrepreneurs only)
  • ✅ "Five Productivity Myths" (anyone interested in productivity)
  • ❌ "What to Do When Your Team Doesn't Respect You" (filters to managers)
  • ✅ "How to Handle Disrespect at Work" (universalized)

When to narrow: When targeting specific audience is strategic goal. Otherwise, broaden.

What Makes Hooks Work: 10 Proven Principles

Across all 119 frameworks, these psychological principles drive clicks:

  1. Curiosity - Open loops that make viewers need answers ("What happens to...?", "Do X really...?")
  2. Desire - Tap into what viewers want (success, beauty, money, health, status, confidence)
  3. Negativity - Warnings, fears, and problems grab attention faster than benefits
  4. Controversy - Counterintuitive claims and polarizing takes create conflict and engagement
  5. Authority - Names, titles, and credentials build trust ("Expert reveals...", "CIA officer explains...")
  6. Specificity - Numbers, timeframes, and concrete examples feel more real ("5 habits," "in 3 seconds")
  7. Lists - Numbered frameworks feel scannable and tangible (5, 7, 10, 50...)
  8. Constraint - Limiting the scope makes ideas feel more valuable ("The ONE choice," "This ONE trick")
  9. Contrast - Juxtaposing opposites creates interest ("Not X, but Y," "I'm 52 but feel 32")
  10. Speed/Ease - Promises of quick results or easy methods (5-minute, "feel unnatural," "GENIUS mode")

Application: Review your generated title options and check which principles they use. Titles using 2-3 of these principles typically outperform single-principle titles.


The 3-Phase Workflow

Phase 1: Extract Content Elements

Goal: Identify the core components of your content

Step 1: Summarize Content in 1-2 Sentences

What is this video actually about? What value does it deliver?

Example: "Sarah Chen explains that micromanagement kills productivity when teams lack autonomy. She suggests letting teams experience low-stakes failures early to build ownership."

Step 2: Identify Content Elements

Watch for these 6 elements:

  1. Problem - What pain/struggle exists?

    • Example: "Teams are burned out and disengaged"
  2. Goal - What result does viewer want?

    • Example: "Build a self-directed, high-performing team"
  3. Benefit - What will their life look like after?

    • Example: "Teams with ownership, less burnout, more innovation"
  4. Concept - What idea/principle applies?

    • Example: "Micromanagement backfires"
  5. Example/Data - What story/stat illustrates this?

    • Example: "Let junior devs ship small features, fail on staging before production"
  6. Process - What steps lead to result?

    • Example: "Give low-stakes ownership early, gradually increase responsibility"

Step 3: Determine Video Type

Educational Content:

  • How-to, explainer, tutorial, myth-busting, comparison

Storytelling Content:

  • Personal journey, transformation, experiment, investigation

Controversial Content:

  • Counter-intuitive take, challenge conventional wisdom, polarizing opinion

Phase 2: Framework Matching (THE CRITICAL PHASE)

Goal: Match content to best-fit formulas from 119 proven frameworks

Step 1: Review Applicable Framework Categories

Don't jump to first match. Browse these categories:

High-Performance Frameworks (Hook Score 8000+):

  • Experiment/Test format (#1: "I tested X vs Y")
  • Contradiction format (#2: "Getting ADDICTED to X is Easy")
  • How-to without objection (#3: "How to X Without Y")
  • Warning format (#4: "NEVER Say This...")

Question-Based Frameworks:

  • "What Happens to X That Never Y?" (#5)
  • "Is there a difference between X and Y?" (#1 variation)

Reality/Timeliness Frameworks:

  • "The REALITY of X in 2025" (#6)
  • Current year emphasis

List Frameworks:

  • "5 X Habits That Y" (#7)
  • "I Went to All X (Here Are My Rankings)" (#8)

See full list: references/creator-hooks-frameworks.md (119 frameworks)

Step 2: Brainstorm Framework Fits (Generate Volume)

For EACH promising framework, test the fit:

## Framework #3: How To (Achieve goal)! Without (Unwanted action)

**Fit Assessment:** ✅ STRONG / ⚠️ MODERATE / ❌ WEAK

**Why it fits:** Directly addresses "build high-performing teams without micromanagement"

**Hook Score:** 11,492 (proven high performer)

**Psychological Principles:**
- Desire (audience wants high-performing teams)
- Refute Objection (don't have to control everything)

**Title Option:** "How to Build High-Performing Teams Without Micromanagement"

**Thumbnail Concept:** Team collaborating independently + "Let them own it"

Minimum: Test 5-10 frameworks before selecting

Step 3: Apply Andrew Muto Strategies

Universalization:

  • Remove filters that narrow audience
  • Test both specific and broad versions

Example:

  • Specific: "Five Productivity Myths Every Founder Believes"
  • Universal: "Five Productivity Myths"
  • Test: "The Myth That's Destroying Your Focus"

Dial to 11 (July 11): "What is the most extreme version of that title?"

  • Start: "Teams Are Burned Out"
  • Dial up: "Why Your Team Is Burned Out"
  • Dial up: "The #1 Reason Your Team Is Burned Out"
  • Dial up: "This Management Mistake Is Destroying Your Team"

Keep dialing until absurd, then pull back one notch.

From X to Y Formula (July 1):

  • "From Screw-Up to Legend: George Washington's Biggest Failure"
  • "From Micromanager to Trusted Leader"

Step 4: Generate 10+ Title Variations

Use different combinations:

  • 3-4 different frameworks
  • Universalized vs. specific versions
  • "Dial to 11" variations
  • Different psychological triggers

Quality Check:

  • Reviewed 5-10 frameworks minimum
  • Tested fit strength for each
  • Generated 10+ title variations
  • Applied universalization where appropriate
  • Created "Dial to 11" options
  • Avoided first-match bias

Phase 3: Select Best & Create Thumbnail Strategy

Goal: Choose top 3 titles and pair with complementary thumbnails

Step 1: Apply Psychological Principles Filter

For each title variation, check which principles it triggers:

Curiosity:

  • Opens loop without answering
  • Asks question
  • Creates information gap
  • Uses "secret," "truth," "reality"

Desire:

  • Promises specific outcome audience wants
  • "How to," "Get," "Achieve"

Negativity/Fear:

  • Warning, avoid mistakes
  • "Never," "Don't," "Stop"
  • FOMO, loss aversion

Credibility:

  • Data, experiments, expertise
  • "I tested," "After 10 years," "300 startups"

Contrast/Controversy:

  • Contradicts expectations
  • "Easy, Actually" vs hard task
  • "Without" formula (have cake, eat it too)

Timeliness:

  • Current events, trending topics
  • Year/date references

Specificity:

  • Numbers, stats, precise details
  • "99%," "5 Morning Habits," "All 30"

Goal: Each title should trigger 3-4 principles minimum

Step 2: Thumbnail Complementarity Design

Rule: Thumbnail should NOT repeat title.

Complementarity Strategies:

Strategy A: Title asks, Thumbnail hints

  • Title: "Five Dyslexia Myths"
  • Thumbnail: "Schools are getting this wrong"

Strategy B: Title promises, Thumbnail adds urgency

  • Title: "How to Raise Confident Kids"
  • Thumbnail: "Before it's too late"

Strategy C: Title states problem, Thumbnail shows emotion

  • Title: "Why Kids Are So Anxious"
  • Thumbnail: Distressed child + "It's not your fault"

Strategy D: Title broad, Thumbnail specific

  • Title: "His Kids Missed 100 Days of School"
  • Thumbnail: Guest face + "CRAZY"

Visual Rules (Andrew Muto - July 11):

  • Shock value > recognition (unless George Clooney-famous)
  • Stock photos > illustrations
  • Show outcome/situation, not just person's face
  • Dial to 11: "Most extreme version of that title?"
  • Simplify text: Fewer words, higher contrast, more charged

Thumbnail Text Formulas:

  • "Here's how"
  • "Number 3 will shock you"
  • "This changed everything"
  • "Schools are wrong"
  • "CRAZY"
  • Question: "Is that even allowed?"

Step 3: Quality Test All Title Variations

Before finalizing your 5 titles, test each against these criteria:

The McDonald's Test (Andrew Muto - July 8): "Someone who works at McDonald's should understand your headline instantly."

  • No jargon
  • Accessible language
  • Instant comprehension

The Ultimate Hook Test:

  • Would this make ME stop scrolling?
  • Creates curiosity or emotion in first 2 seconds?
  • Can my grandmother understand instantly?
  • Hints at payoff without giving it away?

Discard any titles that fail these tests. Keep the strongest 5.

Step 4: Generate 5 Titles with 3 Thumbnail Options Each

Generate 5 distinct title variations across different frameworks and strategic approaches. For each title, create 3 complementary thumbnail options that vary the visual approach while staying simple (3 elements max).

For each title, structure as:

  • Title (single, clear concept)
  • Framework reference
  • 3 thumbnail options (each with visual description + on-screen text)

Why 3 thumbnails per title? Testing allows you to optimize visual delivery without changing the messaging. Different thumbnail styles appeal to different viewer segments.

Thumbnail variation strategies:

  • Option A: Direct visual (show the problem/outcome)
  • Option B: Emotional/reaction (show what it feels like)
  • Option C: Curiosity/question (hint at the answer without giving it)

This approach gives the video production team multiple ready-to-test options without requiring additional iteration.


Output Format

Simplified Output for Practical Use

Create file: [Video_Topic]_YouTube_Titles_Thumbnails.md

# YouTube Titles & Thumbnails - [Topic]

---

## TITLE 1: "[Title]"

**Framework:** #3 - How To (Achieve goal)! Without (Unwanted action)

**Thumbnail Option A:**
- Visual: [Description of image/scene]
- Text: [On-screen text]

**Thumbnail Option B:**
- Visual: [Description of image/scene]
- Text: [On-screen text]

**Thumbnail Option C:**
- Visual: [Description of image/scene]
- Text: [On-screen text]

---

## TITLE 2: "[Title]"

**Framework:** #6 - The REALITY of (Polarizing entity) in (Current year)

**Thumbnail Option A:**
- Visual: [Description of image/scene]
- Text: [On-screen text]

**Thumbnail Option B:**
- Visual: [Description of image/scene]
- Text: [On-screen text]

**Thumbnail Option C:**
- Visual: [Description of image/scene]
- Text: [On-screen text]

---

[Repeat for Titles 3, 4, and 5]

Key Rules:

  • 5 titles total
  • 3 thumbnail options per title
  • Each thumbnail: 3 elements max (visual + text, keep it simple)
  • No detailed explanation of principles or Hook Scores
  • Focus on actionable output ready for video production

Bundled Resources

Framework Libraries

  • references/creator-hooks-ranked.md - All 119 frameworks sorted by Hook Score
  • references/psychological-principles-guide.md - Deep dive on each trigger
  • references/ctr-benchmarks.md - Performance expectations and troubleshooting

Strategy Guides

  • references/universalization-examples.md - Before/after comparisons
  • references/thumbnail-complementarity.md - Visual pairing strategies
  • references/andrew-muto-formulas.md - Additional formulas from sessions

Examples

  • examples/katie-kimball-walkthrough.md - Complete framework fitting process
  • examples/dyslexia-universalization.md - Narrowing vs. broadening analysis
  • examples/george-washington-from-x-to-y.md - Transformation formula

Common Pitfalls to Avoid

Phase 1 Issues

❌ Vague content summary - Can't match frameworks without clarity ❌ Missing elements - Incomplete extraction leads to weak options ❌ Wrong video type - Misclassifying content limits framework options

Phase 2 Issues

❌ First-match bias - Using first framework that fits ❌ Insufficient volume - Testing only 2-3 frameworks ❌ Ignoring Hook Scores - Not prioritizing proven performers ❌ Over-filtering - Adding too many audience limiters

Phase 3 Issues

❌ Thumbnail repetition - Title and thumbnail say same thing ❌ Failing McDonald's Test - Using jargon or complexity ❌ Single variation - Not creating A/B test options ❌ Low principle count - Triggering only 1-2 psychological levers


Advanced Techniques

The False Binary

Present two extremes as only options: "Burnout or Boredom: Where Most Careers End"

The Credibility Bomb

Drop credentials mid-controversy: "After Managing 300 Teams: This Generation Can't..."

The Mirror Moment

Make viewer see themselves: "If Your Team Can't Do This One Thing..."

Time-Based Urgency

Add current year or timeframe: "The Reality of Remote Work in 2025"

Reverse Expectations

Flip the expected outcome: "My First Launch Failed. Perfect."



Related Skills

  • hook-and-headline-writing - Provides foundational hook strategies
  • cold-open-creator - Creates opening that delivers on title promise
  • social-caption-writer - Adapts titles for social platforms

Version History

  • v1.0 (2025-10-28): Initial skill creation
    • Framework fitting method from social-content-creation
    • 119 Creator Hooks frameworks integrated
    • Andrew Muto strategies (universalization, dial to 11, CTR benchmarks)
    • Complementarity principle
    • 3-phase workflow
    • Quality control systems

For complete framework library, psychological principles, and examples, see references folder

FAQ

What does the youtube-title-creator skill do?

Generate high-CTR YouTube titles and thumbnails using framework fitting method. Match content to 119 proven formulas from Creator Hooks, apply psychological principles, test variations.

How do I install youtube-title-creator?

Run npx skills add https://github.com/cdeistopened/skill-stack --skill youtube-title-creator in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/youtube-title-creator/ (personal) or .claude/skills/youtube-title-creator/ (project).

Which AI agents can use youtube-title-creator?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is youtube-title-creator safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains youtube-title-creator?

It is published by cdeistopened in cdeistopened/skill-stack. It has 55 recorded installs.

More from cdeistopened/skill-stack

View all →

youtube-scriptwriting

cdeistopened/skill-stack

Transform raw ideas and brain dumps into polished YouTube scripts through a structured checkpoint workflow. Use when the user wants to write a YouTube script, improve video retention, craft hooks, structure educational or entertainment content, or turn source material (transcripts, notes, research) into a compelling video script. Guides through research, hook writing, story structure, body content, and editing phases.

image-prompt-generator

cdeistopened/skill-stack

Generate AI images using Gemini image generation API. Use this skill when content needs images - thumbnails, social posts, blog headers, or creative visuals. Follows an iterative workflow - brainstorm concepts, select direction, generate in multiple styles, then produce via API.

Media & Creative291 installs

anti-ai-writing

cdeistopened/skill-stack

Open the skill to read its SKILL.md instructions.

Docs & Writing216 installs

amazon-category-research

cdeistopened/skill-stack

Research profitable Amazon KDP categories for book publishing. Use when planning a book launch, analyzing competition, or optimizing category selection for discoverability.

hook-and-headline-writing

cdeistopened/skill-stack

Open the skill to read its SKILL.md instructions.

Docs & Writing77 installs

ghostwriter

cdeistopened/skill-stack

Master the art of converting source material into authentic, human-written content. Transform transcripts, notes, and research into polished prose that avoids AI tells while maintaining distinctive voice. Combines anti-AI writing fundamentals with voice style adaptation.

Media & Creative71 installs

Popular testing & qa skills

View category →

tdd

mattpocock/skills

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

Testing & QA1.2M installs

grilling

mattpocock/skills

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Testing & QA996.2K installs

migrate-to-shoehorn

mattpocock/skills

Migrate test files from as type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace as in tests, or needs partial test data.

Testing & QA484.1K installs

run-train

lllllllama/rigorpilot-skills

Rigor Train skill for deep learning research repositories. Use when a documented or selected training command should be run conservatively for startup verification, short-run verification, full kickoff, or resume, with command, config, seed, log, checkpoint, status, and metric evidence written to standardized trainoutputs/. Do not use for environment setup, exploratory sweeps, speculative idea implementation, or end-to-end orchestration.

Testing & QA337.8K installs

test-driven-development

obra/superpowers

Use when implementing any feature or bugfix, before writing implementation code

Testing & QA261.8K installs

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

Testing & QA216.8K installs