Deep Voice Analysis — Premium Skill

What Makes This Different From the Free Style-Clone Skill

style-clone

The 47 Markers

Rhythm Markers (12)

1. Average sentence length (words)
2. Sentence length variance (burstiness)
3. Short sentence frequency (1-5 words)
4. Medium sentence frequency (6-15 words)
5. Long sentence frequency (16-25 words)
6. Very long sentence frequency (26+)
7. Paragraph average length (sentences)
8. Paragraph length variance
9. Scene-opening sentence length pattern
10. Chapter-opening sentence length pattern
11. Dialogue line average length
12. Action beat average length

Vocabulary Markers (10)

1. Vocabulary richness (unique/total word ratio)
2. Perplexity score (word unpredictability)
3. Top 20 signature words (words you overuse — in a good way)
4. Top 10 avoided words (words you never use)
5. Formality level (casual ↔ academic)
6. Jargon/domain-specific vocabulary
7. Curse word frequency and type
8. Sensory word distribution (sight/sound/touch/smell/taste)
9. Emotional vocabulary range
10. Abstract vs. concrete word ratio

Structural Markers (8)

1. Narrative distance (close/medium/distant POV)
2. Scene-to-sequel ratio
3. Dialogue-to-narrative ratio
4. Description density per scene
5. Flashback/memory frequency
6. Transition style (hard cuts vs. smooth)
7. Chapter hook style (question, action, dialogue, mystery)
8. White space usage (single-line paragraphs as emphasis)

Dialogue Markers (7)

1. Tag preference (said/asked vs. creative tags)
2. Action beat vs. tag ratio
3. Average dialogue line length
4. Subtext level (direct ↔ heavily implied)
5. Interruption frequency
6. Character voice differentiation score
7. Monologue vs. rapid exchange ratio

Punctuation & Mechanics (5)

1. Em dash frequency
2. Semicolon frequency
3. Ellipsis frequency
4. Exclamation mark frequency
5. Parenthetical frequency

Voice & Tone (5)

1. Humor type (dry, sarcastic, physical, dark, witty, none)
2. Humor frequency
3. Emotional register style (body-first, thought-first, action-first)
4. Metaphor/simile density
5. Overall humanness score (AI-detection bypass potential)

Analysis Process

1. Intake: Author provides 5,000+ words (ideal: 20,000+). Multiple samples across scenes/chapters is best.
2. Tokenize: Break text into sentences, paragraphs, scenes, dialogue blocks.
3. Measure: Calculate all 47 markers with statistical confidence.
4. Compare: Benchmark against genre averages to identify what's distinctive.
5. Generate: Create the Voice Profile markdown file.
6. Validate: Show the author their profile and ask "does this sound like you?"

Output: Enhanced Voice Profile

workspace/soul/VOICE-PROFILE.md

# Voice Profile — Deep Analysis (47 Markers)
## Generated: [date] | Sample size: [N] words

## Humanness Score: [0-100]

## Rhythm
- Avg sentence: [N] words | Variance: [N] (burstiness)
- Distribution: [%] short / [%] medium / [%] long / [%] very long
- Paragraphs: [N] sentences avg
- Openers: [pattern description]

## Vocabulary
- Richness: [score] | Perplexity: [score] | Formality: [level]
- SIGNATURE WORDS (use naturally): [list]
- NEVER USE: [anti-AI words list]
- Sensory bias: [primary sense]

## Structure
- Narrative distance: [level]
- Dialogue ratio: [%] of text
- Description density: [level]
- Chapter hooks: [dominant style]

## Dialogue
- Tags: [preference] | Beats: [frequency]
- Avg line: [N] words | Subtext: [level]
- Voice differentiation: [score]

## Mechanics
- Em dashes: [freq] | Semicolons: [freq]
- Ellipsis: [freq] | Exclamation: [freq]

## Voice
- Humor: [type] at [frequency]
- Emotional style: [body/thought/action]-first
- Metaphor density: [level]

## RULES FOR AI
When writing as this author:
1. Follow the sentence distribution above (this is critical for humanness)
2. Use signature words naturally — don't force them but let them appear
3. NEVER use the avoided words list
4. Match the punctuation profile
5. Keep the narrative distance at [level]
6. Apply the [type] humor at appropriate moments
7. Lead with [body/thought/action] for emotional moments
8. Maintain [level] metaphor density — no more, no less

Commands

• deep voice analysis

  or

  analyze my voice deeply

  — Start the full 47-marker analysis

• show voice profile

  — Display the current enhanced profile

• voice check [text]

  — Score new text against all 47 markers

• voice report

  — Generate a detailed report comparing recent writing to the profile

• update voice profile from [text]

  — Refine the profile with new sample data