Voice Extractor

Voice Extractor

AI-generated content all sounds the same. The fix isn't better prompts — it's teaching the AI how you actually communicate.

This skill extracts your communication DNA from writing samples and produces a Voice Guide: documented, tested, and ready to use.

---

Mode

Detect from context or ask: "Quick voice snapshot, full Voice Guide, or full guide with examples?"

Default: `standard` — use quick if they just need a fast reference. Use deep if they're onboarding a ghostwriter or building a content team.

---

Context Loading Gates

Before extracting, collect:

• [ ] Writing samples — minimum 3 samples OR 500 total words (see priority list below)
• [ ] Purpose of voice guide — AI training? Ghostwriter onboarding? Team alignment?
• [ ] Confidence zones — Any topics where they want to sound more/less authoritative?
• [ ] Known anti-patterns — Any words or phrases they already know they want to avoid?

Sample priority (most → least authentic): 1. Casual Slack or email (raw, unedited voice) 2. Podcast or call transcript 3. LinkedIn posts or articles 4. Website copy (often edited, less authentic)

Minimum sample gate: If samples total under 500 words, stop:

"These samples are too short to extract reliable patterns. Please add 2-3 more — emails, Slack messages, or transcripts work best. The messier and more casual, the better."

Do not attempt full extraction from under 500 words. Offer quick mode instead.

---

Phase 1: Sample Quality Assessment

Before extracting, reason through:

1. Sample authenticity: Are these samples from edited/polished contexts (website, press) or raw contexts (Slack, email)? More polish = less authentic voice. 2. Sample variety: Do the samples cover different contexts (professional, casual, educational)? Single-context samples produce single-dimension voice guides. 3. Exclusion check: Identify and flag patterns that are NOT the authentic voice:

• Platform formatting tics (LinkedIn line breaks, Twitter brevity forcing)
• Typos and autocorrect errors
• Phrases borrowed from others (quotes, retweets)
• Unusually formal writing (legal docs, press releases)

4. Sample size adequacy: Is there enough material for full mode, or should I use quick mode?

Output a sample assessment:

"I have [X samples / Y words] to work with. Quality: [high/medium — why]. I'll use [full/quick] mode. Excluding: [any patterns and why]."

---

Phase 2: Core Energy Extraction

Identify the fundamental communication mode:

Role:

• Teacher (breaks things down systematically)
• Challenger (pushes back on assumptions)
• Cheerleader (builds confidence and momentum)
• Straight-shooter (cuts through BS efficiently)

Default energy:

• Calm authority ("Here's what works.")
• High enthusiasm ("This is exciting — let me show you.")
• Understated confidence ("I've seen this a hundred times.")

Recurring themes: What topics appear unprompted across samples? These are the things they actually care about.

---

Phase 3: Phrase Extraction (Systematic)

Scan all samples and extract:

Transition phrases (how they shift topics):

• Quote exact examples from samples
• Pattern: "Here's the thing...", "What I've learned...", "Let me put it differently..."

Emphasis phrases (how they land a point):

• Quote exact examples
• Pattern: "The reality is...", "This is the part people miss...", "Here's the actual problem..."

Closers (how they wrap up):

• Quote exact examples
• Pattern: "That's the move.", "Start there.", "You've got this."

---

Phase 4: Confidence Zone Mapping

Map their stated expertise areas to each zone. This calibration is what makes the voice feel real vs. one-dimensional.

---

Phase 5: Anti-Pattern Documentation

Extract what they'd NEVER say:

• Words that would feel wrong in their voice
• Phrases that make them cringe
• Tones they naturally avoid
• Industry jargon they hate

Source these from sample evidence where possible: "You never used [word] across [X samples] — it doesn't fit your voice."

---

Phase 6: Validation Test (REQUIRED)

After extracting the full profile, generate 2 test sentences on the same topic:

Version A (using the extracted voice profile):

"[Sample sentence in their voice]"

Version B (wrong voice — contrasting example):

"[Same content, different voice — shows what to avoid]"

Ask the user: "Does Version A actually sound like you when you're not overthinking it? What feels off?"

This validation catches extraction errors before the guide is put into production.

---

Quick Mode (--quick)

When samples are thin (300–500 words) or time is short:

1. Read 3 samples fast 2. Pull 10 signature phrases 3. Note 3 things they'd never say 4. Write 1 sentence describing their energy

Output: Minimum viable voice guide.

Difference from full mode:

• Quick: ~10 phrases, 3 anti-patterns, 1-sentence energy descriptor
• Full: Complete profile with confidence calibration, validated test sentences, and source-cited examples

---

Phase 7: Self-Critique Pass (REQUIRED)

After generating the Voice Guide:

• [ ] Are the extracted phrases actually from the samples, or am I inferring them?
• [ ] Does the anti-pattern list include specific words/phrases, or just vague categories?
• [ ] Do the validation test sentences demonstrate a real difference between in-voice and out-of-voice?
• [ ] Is the confidence zone mapping specific to named topics, or just generic?
• [ ] Would a ghostwriter be able to use this guide without asking follow-up questions?

Flag any issues: "The anti-pattern section only has 2 entries — not enough for a usable guide. I need more samples or direct input from the user."

---

Output Structure

## Voice Guide: [Name] — [Date]

### Sample Assessment
- Samples: [count, types]
- Total words: [count]
- Quality: [high/medium — reason]
- Mode: [quick/full]
- Excluded: [patterns excluded + why]

---

### Core Energy
- Role: [teacher/challenger/cheerleader/straight-shooter]
- Default energy: [description]
- Recurring themes: [list]

### Signature Phrases
**Transitions:**
- "[Phrase]" (source: [email/post])
- "[Phrase]"

**Emphasis:**
- "[Phrase]" (source: [email/post])

**Closers:**
- "[Phrase]"

### Confidence Calibration
**Full authority (no hedging):**
Topics: [list]
Sounds like: "[example sentence]"

**Earned perspective:**
Topics: [list]
Sounds like: "[example sentence]"

**Active exploration:**
Topics: [list]
Sounds like: "[example sentence]"

### Anti-Patterns (Never Use)
- [Word/phrase] — why: [evidence from samples]
- [Word/phrase] — why: [evidence]

### Validation Test
**This sounds like you:**
"[Version A]"

**This doesn't:**
"[Version B — contrast]"

### Self-Critique Notes
[Any gaps, things to validate with user]

### Usage Instructions
- For AI: Paste this guide into your system prompt
- For ghostwriter: Share on day 1 — cuts revision cycles in half
- For team: This is the benchmark for "on brand"

---

Skill by Brian Wagner | AI Marketing Architect | brianrwagner.com

Platform: OpenClaw (token-optimized)

Required Inputs

• Writing samples — minimum 3 samples OR 500 total words
• Purpose — AI training / ghostwriter onboarding / team alignment
• Confidence zones (optional) — topics where they want more/less authority
• Known anti-patterns (optional) — words/phrases they already want to avoid

Sample priority (most → least authentic): 1. Casual Slack or email (raw, unedited) 2. Podcast or call transcript 3. LinkedIn posts or articles 4. Website copy (often edited, least authentic)

Minimum gate: Under 500 words → stop: "Too short. Add 2–3 more samples — emails, Slack messages, or transcripts work best."

Mode

Phase 1: Sample Assessment

Assess: authenticity (polished vs. raw), variety (contexts covered), exclusions (platform tics, typos, borrowed phrases).

Output: "I have [X samples / Y words]. Quality: [high/medium]. Using [full/quick] mode. Excluding: [what and why]."

Phase 2: Extract Core Energy

Role: Teacher / Challenger / Cheerleader / Straight-shooter Default energy: Calm authority / High enthusiasm / Understated confidence Recurring themes: Topics appearing unprompted across samples

Phase 3: Phrase Extraction

Extract from samples (quote exact examples):

• Transition phrases — how they shift topics
• Emphasis phrases — how they land a point
• Closers — how they wrap up

Phase 4: Confidence Zone Map

Phase 5: Anti-Pattern List

What they'd NEVER say — sourced from sample evidence: "You never used [word] across [X samples] — it doesn't fit your voice."

Phase 6: Validation Test (required)

Generate 2 sentences on the same topic:

• Version A: Using extracted voice profile
• Version B: Wrong voice (contrasting example)

Ask: "Does Version A actually sound like you when you're not overthinking it?"

Output Format

# Voice Guide: [Name/Brand]

**Voice Summary:** [2-3 sentences capturing the essence]
**Core Role:** [Teacher/Challenger/Cheerleader/Straight-shooter]
**Default Energy:** [Calm authority/High enthusiasm/Understated confidence]

## Vocabulary Guide
Use: [words/phrases from samples]
Avoid: [anti-patterns]

## Rhythm Patterns
[Sentence length patterns, paragraph style, structural habits]

## Confidence Zones
[Mapped topics to zones]

## Transition Phrases
[Quoted from samples]

## Emphasis Phrases
[Quoted from samples]

## Closers
[Quoted from samples]

## Validation Examples
A (correct): "[sentence]"
B (wrong): "[sentence]"

--- Skill by Brian Wagner | AI Marketing Architect

Voice Guide

Your communication DNA, documented.

---

🎯 Core Identity

Who You Are

What You Care About

_The themes you can't help but return to:_

1. 2. 3.

---

✍️ Signature Phrases

Transitions — How You Shift Topics

Emphasis — How You Land a Point

Closers — How You Wrap Up

---

🎚️ Confidence Calibration

Full Authority Zone _(no hedging, definitive statements)_

Topics where you're THE expert:

- - -

Voice here: "Here's what works." / "This is how it's done." / "The answer is..."

Earned Perspective Zone _(confident but not absolute)_

Topics where you have real experience:

- - -

Voice here: "What I've found..." / "In my experience..." / "The pattern I see..."

Active Exploration Zone _(curious, learning out loud)_

Topics you're actively figuring out:

- - -

Voice here: "What I'm testing..." / "I'm starting to think..." / "Early take:..."

---

🚫 Anti-Patterns — What You Never Do

Words You Never Use

Tones You Avoid

- - -

Formatting Habits to Skip

- -

---

📐 Structural Patterns

How You Open

_Your typical first-line energy:_

• [ ] Jump straight to the point
• [ ] Start with a provocative statement
• [ ] Open with a story/scenario
• [ ] Lead with a question
• [ ] Other: _______________

Example opening in your voice: >

How You Build

_Your typical structure:_

• [ ] Short punchy paragraphs
• [ ] Longer flowing sections
• [ ] Heavy use of bullet points
• [ ] Numbered lists for steps
• [ ] Mix of all above

How You Close

_Your typical ending energy:_

• [ ] Clear call to action
• [ ] Thought-provoking question
• [ ] Punchy one-liner
• [ ] Callback to opening
• [ ] Other: _______________

Example closer in your voice: >

---

✅ Voice Check — Quick Reference

Before publishing, ask:

---

📝 Side-by-Side Examples

✅ This Sounds Like Me:

_[Paste an example of content that nails your voice]_

❌ This Doesn't:

_[Paste the same content written in a generic/wrong voice]_

Why the Difference:

_[Note what specifically makes the first one "you"]_

---

🤖 AI Prompt Integration

Paste this into any AI system prompt to write in your voice:

VOICE INSTRUCTIONS:

Write as [NAME] — [one-sentence description of your energy].

Core patterns:
- [Signature phrase 1]
- [Signature phrase 2]
- [Signature phrase 3]

Never use: [banned words]
Always: [key habit]

Confidence calibration:
- Expert topics (full authority): [list]
- Experienced topics (earned perspective): [list]
- Learning topics (exploratory): [list]

---

_Generated with Voice Extractor by Brian Wagner_ _https://brianwagner4.gumroad.com_