Skip to main content
ClaudeWave
Skill95 repo starsupdated 1mo ago

youtube-viral-optimizer

Generate high-CTR YouTube thumbnails, titles, and video scripts optimized for virality. Use when the user asks to create YouTube video titles, thumbnail text/concepts, video scripts, optimize existing titles for CTR, analyze why a video isn't performing, or needs help making content more clickable. Covers thumbnail wording, title copywriting, video script structuring (Pattern Interrupt → Hook → Framing → Curiosity Loop → Escalation → Payoff → Relevance Bridge → Loop Reopen), and YouTube algorithm optimization.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/infranodus/skills /tmp/youtube-viral-optimizer && cp -r /tmp/youtube-viral-optimizer/skill-viral-videos ~/.claude/skills/youtube-viral-optimizer
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# YouTube Viral Optimizer

Generate titles, thumbnails, and hooks that maximize click-through rate using proven psychological triggers, SEO principles, and YouTube algorithm dynamics.

## Channel Context

Before generating titles or scripts, establish the channel's context. Ask for or infer:

- **Core topics**: What 2-4 subjects does the channel cover?
- **Audience**: Who watches? (e.g., beginners, professionals, prosumers, hobbyists)
- **YouTube's perception of the channel**: What topics does the algorithm associate with this channel?
- **Unique angle / differentiator**: What perspective or expertise sets this channel apart from competitors?

### The Differentiator Principle

Every channel needs a unique lens — the thing that makes its take on any topic different from everyone else's. This differentiator should thread through titles, hooks, and scripts.

**Examples of differentiators by niche**:
- **Cooking channel**: "Restaurant-quality meals with only pantry staples"
- **Finance channel**: "Behavioral psychology behind money decisions"
- **Tech review channel**: "Real-world durability tests, not specs"
- **Fitness channel**: "Science-backed routines for people who hate gyms"
- **AI/Knowledge channel**: "Knowledge graphs as the lens for making AI actually work"

**Framing principle**: Don't just show "how to do [thing]" — show "how [your differentiator] makes [thing] actually work"

**Title angle examples**:
- Generic: "How to Start Investing"
- With differentiator: "Why Your Brain Sabotages Every Investment (And How to Fix It)"
- Generic: "Best Camera Settings for Video"
- With differentiator: "The Camera Settings YouTubers Actually Use (Not What They Tell You)"

## Core Process

1. **SEO Research** (use InfraNodus MCP tools if available):
   - Analyze search intent for video topic keywords
   - Map search results to find content gaps
   - Identify low-competition, high-volume opportunities
2. Analyze the video topic/transcript for key tensions and outcomes
3. Check topic alignment with channel's algorithm positioning
4. Generate multiple title + thumbnail combinations targeting identified gaps
5. Self-rate each option against CTR rules AND algorithm factors
6. Recommend top choices with reasoning

## SEO-Driven Title Strategy (InfraNodus MCP)

Use InfraNodus tools to research before finalizing titles:

### Step 1: Analyze Search Intent
```
Tool: InfraNodus:analyze_related_search_queries
- Input your main topic keywords
- Get the graph of what people actually search for
- Identify topical clusters in search demand
```

### Step 2: Map Search Results
```
Tool: InfraNodus:analyze_google_search_results
- See what content currently ranks
- Identify which topics are saturated vs underserved
- Find the gaps between what people search and what exists
```

### Step 3: Find Content Gaps
```
Tool: InfraNodus:search_queries_vs_search_results
- Compare search demand graph vs search supply graph
- Keywords in demand but NOT in results = your opportunity
- These gaps = low competition + high intent
```

### Step 4: Generate Gap-Targeting Titles
```
Tool: InfraNodus:generate_research_questions
- Input combined search data
- Get questions that bridge content gaps
- Transform into title angles
```

### SEO Sweet Spot Formula

**Target**: Topics where:
- Search volume exists (people are looking)
- Competition is low (big channels haven't covered it)
- Your differentiator adds unique value (not just another take)
- Gap exists between what's searched and what ranks

**Title should**:
- Include high-volume keyword (for discoverability)
- Address the content gap (for topical authority)
- Add your unique differentiator (for uniqueness)

### Example SEO Workflows

**Cooking channel** — Topic idea: "Meal prepping for beginners"

1. **Search intent analysis** → reveals clusters: "easy meal prep", "meal prep on a budget", "meal prep that doesn't taste boring"
2. **Search results analysis** → shows: tons of "5-day meal prep" content, few videos on flavor variety
3. **Gap detection** → finds: "meal prep + variety" has demand but thin supply
4. **Title angle** → "Why Your Meal Prep Tastes Like Sadness (Fix It in 10 Minutes)"

**Tech channel** — Topic idea: "Best budget laptops 2025"

1. **Search intent analysis** → reveals clusters: "budget laptop for students", "cheap laptop for video editing", "laptop under $500"
2. **Search results analysis** → shows: lots of spec comparison lists, few real-world usage tests
3. **Gap detection** → finds: "budget laptop real-world performance" has demand but thin supply
4. **Title angle** → "I Used the Cheapest Laptop for a Month — Here's the Truth"

## YouTube Algorithm Factors

### The Algorithm Sweet Spot
YouTube pushes videos that hit ALL of these:
- **CTR ≥ 4%** — Below this = "wasting YouTube's real estate"
- **Subs-to-views ~1.5-2%** — Signal of NEW audience acquisition
- **Likes ~2%**, **Shares ~2%** — Engagement signals
- **Watch time ≥ channel average** — Quality signal

**Critical**: High CTR alone isn't enough. Must engage NEW viewers (subs signal).

### Topic Selection Rules

**Stay in your lane**:
- YouTube assigns channels to topics they're "good at"
- Videos on your core topics get pushed even with lower raw metrics
- Going too general = competing with everyone = suppressed

**Examples**:
- A cooking channel making a tech review → suppressed even with great metrics
- A finance channel doing general productivity advice → competing with everyone
- A tech channel doing lifestyle vlogs → outside YouTube's perception of them

**Risky moves**:
- Pure commentary on trending topics outside your niche (too competitive, not your lane)
- General advice in saturated categories
- Topics YouTube doesn't associate with your channel

### Timing Opportunities

**Trendy specialized topics win**:
- New releases, launches, or events in your niche = high interest + low competition
- Window is short — produce fast while competition is low
- Combine trending topic WITH your core angle
infranodusSkill

>

actionizeSkill

|

cognitive-variabilitySkill

Guide conversations through dynamic shifts between zoom levels (scale) and connecting/exploring (intent) to unlock creative breakthroughs and prevent rigid thinking. Helps enhance and develop biased, focused, diversified, dispersed states. Receives signals from writing assistant's pattern detection to diagnose cognitive states. Identifies structural gaps between idea clusters as spaces for innovation. Tracks temporal dwelling patterns and manages energy across personality modes. Uses playfulness for difficult transitions from chaos to clarity. Reads emotional feedback—inspiration signals continuation, exhaustion/frustration trigger transitions. Prevents obsessive loops through sustainable cycling through topical clusters and latent nodes. Maximum creative potential lives in gaps and dissipative states. Apply for complex analysis, when a user is stuck, breakthroughs, decision paralysis, group facilitation, breaking repetitive patterns, or when grammatical patterns reveal cognitive issues.

critical-perspectiveSkill

Engage in critical thinking by questioning assumptions, exploring alternative perspectives, and uncovering latent topics in conversations. Use when discussions could benefit from deeper exploration, when identifying blind spots, or when broadening understanding through respectful challenge and curiosity-driven inquiry.

embodied-navigationSkill

Transfer embodied movement principles (Vipassana equanimous scanning, Systema adaptive fluidity, contemporary dance tensegrity, EightOS confluence) to navigate work, relationships, projects, strategy, and everyday situations. Uses InfraNodus MCP tools to map situations as networks and apply body-informed intelligence to their structure. Trigger when someone is stuck, in conflict, negotiating, blocked, fixated, overwhelmed, or facing rigidity — or asks for "embodied advice", "fluid approach", "organic strategy", "adaptive strategy", "how would the body handle this". Also trigger on phrases like "I'm stuck", "standoff", "tense situation", "can't move forward". Apply proactively when situations exhibit excessive force, single-point fixation, or neglect of peripheral dynamics.

llm-wikiSkill

>

ontology-generatorSkill

Generate comprehensive ontological knowledge graphs in [[wikilinks]] syntax for InfraNodus visualization. Use when the user requests to create an ontology, extract entities and relationships from text, or generate knowledge graph structures. Handles both topic-based ontology generation and entity extraction from existing text. Output is formatted for direct paste into InfraNodus.com for network visualization and AI-powered gap analysis.

perspective-reversalSkill

>