home / skills / az9713 / ai-co-writing-claude-skills / voice-dna-creator

voice-dna-creator skill

/.claude/skills/voice-dna-creator

This skill analyzes writing samples to produce a voice DNA profile that enables AI to emulate your authentic writing style across contexts.

npx playbooks add skill az9713/ai-co-writing-claude-skills --skill voice-dna-creator

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
4.2 KB
---
name: voice-dna-creator
description: Analyze writing samples to create a comprehensive voice DNA profile. Use when the user wants to capture their unique writing voice, needs to create a voice profile for AI content, or is setting up a new writing system.
---

# Voice DNA Creator

Analyze writing samples to extract and codify a unique voice profile that AI can use to replicate your authentic writing style.

## When to Use This Skill

- Setting up a new writing system
- Creating voice profiles for clients (ghostwriting)
- Updating voice profiles after style evolution
- Onboarding into content creation workflow

## Requirements

The user must provide:
- **Minimum**: 3 writing samples (500+ words each)
- **Ideal**: 5-10 samples across different content types
- **Best**: Mix of casual (social posts) and formal (articles) content

## Analysis Process

### Step 1: Collect Samples

Ask: "Please share 3-10 writing samples that represent your authentic voice. These can be:
- Newsletter issues
- Blog posts
- Social media posts
- Emails you've written
- Any content where you feel 'this sounds like me'

Paste them here or point me to files in the knowledge folder."

### Step 2: Analyze Core Elements

For each sample, analyze:

**Personality Markers**
- What personality traits come through?
- What's the energy level?
- How does the writer relate to the reader?

**Emotional Range**
- What emotions are expressed?
- How intense are they?
- What's the dominant emotional tone?

**Communication Style**
- Formality level (casual to professional)
- Sentence length patterns
- Paragraph structure
- Use of questions, commands, statements

**Language Patterns**
- Signature phrases that repeat
- Power words used frequently
- Transition phrases
- Opening and closing patterns

**What They Avoid**
- Words or phrases never used
- Tones never taken
- Approaches avoided

**Formatting Habits**
- Emoji usage
- List usage
- Header styles
- Bold/italic patterns

### Step 3: Synthesize Findings

Combine analysis across all samples to identify:
- Consistent patterns (appear in most samples)
- Contextual variations (change based on content type)
- Core voice elements (never change)

### Step 4: Generate Voice DNA

Create the profile following this structure:

```json
{
  "voice_dna": {
    "version": "1.0",
    "last_updated": "YYYY-MM-DD",
    "core_essence": {
      "identity": "",
      "primary_role": "",
      "unique_angle": ""
    },
    "personality_traits": {
      "primary": [],
      "how_it_shows": {}
    },
    "emotional_palette": {
      "dominant_emotions": [],
      "emotional_range": {},
      "energy_level": ""
    },
    "communication_style": {
      "formality": "",
      "complexity": "",
      "sentence_structure": {},
      "paragraph_style": ""
    },
    "language_patterns": {
      "signature_phrases": [],
      "power_words": [],
      "words_to_avoid": [],
      "transitions": []
    },
    "never_say": {
      "phrases": [],
      "tones": [],
      "approaches": []
    },
    "formatting_preferences": {},
    "content_philosophy": {},
    "voice_examples": {
      "opening_lines": [],
      "closing_lines": [],
      "transitional_phrases": []
    }
  }
}
```

## Output Instructions

1. After analysis, present key findings in a summary

2. Generate the complete JSON voice profile

3. Save to `/context/voice-dna.json`

4. Provide 3 example sentences written in the captured voice for validation

5. Ask: "Does this capture your voice? What would you adjust?"

## Best Practices

- Focus on TONE and PERSONALITY, not just word choice
- Avoid creating a profile that just repeats phrases
- Capture the "feeling" of the writing, not just patterns
- Include what NOT to do (equally important)
- Make the profile actionable for content generation

## Validation Test

After creating the profile, write a short paragraph on any topic using ONLY the voice DNA as guidance. Ask the user: "Does this sound like you?"

If not, iterate on the profile based on feedback.

## Common Pitfalls to Avoid

- Don't just list frequently used words
- Don't create a parody of the voice (too exaggerated)
- Don't ignore context (social posts ≠ articles)
- Don't miss the underlying personality
- Don't forget emotional elements

Overview

This skill analyzes your writing samples to create a reproducible Voice DNA profile that an AI can use to write in your authentic voice. It distills personality, emotion, language patterns, and formatting habits into a structured, actionable profile. Use it to onboard AI co-writers, create client voice packs, or standardize a multi-writer content program.

How this skill works

Provide 3–10 representative writing samples across formats (social posts, newsletters, articles, emails). The skill inspects personality markers, emotional tone, sentence and paragraph patterns, signature phrases, and formatting habits, then synthesizes consistent elements and contextual variations. It outputs a JSON-style Voice DNA profile plus example lines and a short validation paragraph for immediate testing and iteration.

When to use it

  • Setting up a new AI-assisted writing system
  • Creating a voice profile for a client or brand
  • Onboarding writers into a unified content style
  • Refreshing a voice after a style evolution
  • Validating that AI output matches a human writer

Best practices

  • Provide at least three 500+ word samples; five diverse samples are ideal
  • Include mixed contexts (casual social posts and formal articles) to capture range
  • Focus analysis on tone and personality first, words second
  • Document what to avoid as clearly as what to emulate
  • Validate with short, live writing samples and iterate

Example use cases

  • Generate a client-specific voice profile for ghostwriting projects
  • Seed a content generator so every asset reads like the same author
  • Audit and align multi-author newsletters to a single voice
  • Create style guardrails for contractors and AI assistants
  • Evolve a brand voice over time while preserving core identity

FAQ

How many samples do I need?

Minimum three 500+ word samples; five to ten across different content types yields the best profile.

Will the profile copy exact phrases?

No. The profile captures patterns, tone, and constraints to avoid parroting exact phrases while enabling consistent voice replication.