{"skill":{"slug":"voice-matched-content-system","displayName":"Voice-Matched Content System","summary":"Extract someone's authentic writing voice from samples, build a complete Voice DNA profile, then generate content that sounds like them — not AI. Covers conf...","description":"---\nname: voice-matched-content\ndescription: \"Extract someone's authentic writing voice from samples, build a complete Voice DNA profile, then generate content that sounds like them — not AI. Covers confidence calibration, energy mapping, transition patterns, audience adaptation, and platform-specific voice tuning. Triggers on: capture my voice, write like me, voice guide, brand voice, sound like me, voice profile, my writing style, content in my voice, doesn't sound like me, too AI.\"\n---\n\n# Voice-Matched Content System\n\nThe #1 complaint about AI content: \"It doesn't sound like me.\"\n\nThis skill fixes that permanently. Not with a one-line tone instruction. With a complete voice operating system that understands HOW someone communicates — their patterns, energy, confidence zones, transitions, and editing instincts.\n\nBuilt from a real voice extraction methodology refined over 15+ years of brand strategy work.\n\n---\n\n## Routing\n\n### ✅ Use This Skill When:\n- Someone wants to capture their authentic writing voice\n- Content \"sounds too AI\" and needs to match the creator's real style\n- Building a voice guide for consistent content across platforms\n- Ghostwriting or creating content on behalf of someone\n- User says: \"write like me,\" \"capture my voice,\" \"this doesn't sound like me,\" \"make it sound like me,\" \"voice guide,\" \"brand voice\"\n\n### ❌ Do NOT Use When:\n- Writing generic content with no voice reference → Use standard content skills\n- Editing existing copy for grammar/clarity only → Use copy-editing tools\n- Creating content strategy (what to write, not how) → Use content strategy skills\n- Need a brand messaging framework → Use positioning skills\n\n### Inputs Required:\n- **Minimum:** 3 writing samples (blog posts, emails, social posts, transcripts — anything they've written)\n- **Better:** 5-10 samples across different contexts (professional, casual, teaching, selling)\n- **Best:** Samples + a 5-minute conversation about how they think about communication\n\n### Outputs Produced:\n- Complete Voice DNA Profile (reusable across all future content)\n- Content generated in their authenticated voice\n- Platform-specific voice adaptations (LinkedIn vs X vs email vs proposals)\n- Voice consistency checklist for self-editing\n\n---\n\n## Phase 1: Voice Extraction\n\n### Step 1: Collect Samples\n\nAsk for 3-10 writing samples. The more variety, the better the profile.\n\n**Good samples:**\n- Social posts they're proud of\n- Emails they wrote quickly (less filtered = more authentic)\n- Blog posts or articles\n- Podcast/video transcripts (spoken voice often reveals real patterns)\n- Texts or casual messages (if they're comfortable sharing)\n\n**What to tell the user:**\n> \"Send me 3-5 pieces of writing you've done. Mix of professional and casual is ideal. The ones you wrote fast without overthinking are often the most useful — that's where your real voice lives.\"\n\n### Step 2: Analyze Voice DNA\n\nRead all samples and extract these 8 dimensions:\n\n#### 1. Sentence Architecture\n- Average sentence length (short and punchy? Long and flowing?)\n- Do they use fragments? (\"Not a chance.\" / \"Game over.\")\n- Sentence variety pattern (short-short-long? Building momentum?)\n- Paragraph length preference\n\n#### 2. Opening Patterns (How They Start)\n- Do they hook with a question? A bold statement? A story? A contrarian take?\n- First-line energy level (explosive vs. measured)\n- Do they set context first or dive straight in?\n\n#### 3. Transition Signatures\nMap their recurring bridge phrases. Everyone has them. Examples:\n- \"Here's the thing...\"\n- \"What that means is...\"\n- \"The reality is...\"\n- \"But here's what's interesting...\"\n- \"Let me break this down...\"\n- \"So here's what happened...\"\n\n**Extract at least 8-10 transition phrases from their samples.** These are fingerprints.\n\n#### 4. Energy Mapping\n- Baseline energy level (calm authority? Electric enthusiasm? Quiet confidence?)\n- What triggers their high-energy mode?\n- How do they express excitement? (Exclamation marks? ALL CAPS? Power words?)\n- Do they use humor? What kind? (Self-deprecating? Observational? Sarcastic?)\n\n#### 5. Authority Zones vs. Learning Zones\nThis is critical and most voice tools miss it entirely.\n\n**Authority zones** = Topics where they write with full confidence\n- Definitive language: \"Here's what works,\" \"The data shows,\" \"What I've learned\"\n- No hedging, no \"I think maybe\"\n\n**Learning zones** = Topics where they're exploring\n- Exploratory language: \"What I'm seeing,\" \"In my experience so far,\" \"What I'm learning\"\n- Still confident, but framed as ongoing discovery\n\n**Map which topics fall into which zone.** This prevents the AI from writing with false authority on topics the person is still learning about.\n\n#### 6. Vocabulary Fingerprint\n- Words they use often (favorites)\n- Words they NEVER use (allergies)\n- Industry jargon: do they embrace it or avoid it?\n- Formality level (contractions? Slang? Academic?)\n- Profanity comfort level\n\n#### 7. Structural Preferences\n- Do they use lists? Numbered or bulleted?\n- Headers or flowing prose?\n- Short paragraphs (1-2 sentences) or longer blocks?\n- Do they use bold/italic for emphasis?\n- Do they end with a CTA, a question, or a statement?\n\n#### 8. Editing Instincts\n- Do they tend to cut shorter or add more?\n- What do they delete first? (Usually: hedging words, jargon, or filler)\n- What's their \"red flag\" — the thing that makes them cringe in writing?\n\n---\n\n## Phase 2: Build the Voice DNA Profile\n\nAfter extraction, generate a structured Voice DNA document. This becomes the permanent reference for all future content.\n\n### Voice DNA Profile Template\n\n```markdown\n# [Name]'s Voice DNA Profile\n*Generated from [X] writing samples on [date]*\n\n---\n\n## Voice Foundation\n**Core Identity:** [One sentence — who they are as a communicator]\n**Natural Role:** [How they relate to their audience — teacher? Coach? Peer? Provocateur?]\n**Authority Zones:** [Topics where they write with full confidence]\n**Learning Zones:** [Topics where they're exploring/experimenting]\n**Writing Philosophy:** [Their implicit belief about communication — extracted, not asked]\n\n---\n\n## Sentence Architecture\n- Average sentence length: [short/medium/long]\n- Uses fragments: [yes/no — with examples]\n- Typical paragraph length: [1-2 / 3-4 / 5+ sentences]\n- Rhythm pattern: [describe their cadence]\n\n## Opening Patterns\n- Primary hook style: [question / bold statement / story / contrarian]\n- First-line energy: [1-10 scale]\n- Context-setting: [dives in / sets scene first]\n\n**Their best opening lines (from samples):**\n1. \"[example]\"\n2. \"[example]\"\n3. \"[example]\"\n\n## Transition Signatures\n[List 8-12 of their actual transition phrases, organized by type]\n\n### Authority Transitions:\n- \"[phrase]\"\n- \"[phrase]\"\n\n### Energy Transitions:\n- \"[phrase]\"\n- \"[phrase]\"\n\n### Story Bridges:\n- \"[phrase]\"\n- \"[phrase]\"\n\n## Energy Profile\n- Baseline energy: [calm / warm / enthusiastic / electric]\n- High-energy triggers: [what topics fire them up]\n- Excitement markers: [how they show it — exclamation marks, caps, power words]\n- Humor style: [type and frequency]\n\n## Confidence Calibration\n\n### Write with FULL AUTHORITY when discussing:\n- [topic 1]\n- [topic 2]\n- [topic 3]\n**Voice:** Confident, definitive\n**Phrases:** \"[their authority phrases]\"\n\n### Write with INFORMED PERSPECTIVE when discussing:\n- [topic 1]\n- [topic 2]\n**Voice:** Curious, exploratory but still confident\n**Phrases:** \"[their learning phrases]\"\n\n## Vocabulary\n**Favorites:** [words they use often]\n**Allergies:** [words they never use or hate]\n**Jargon stance:** [embraces / avoids / selective]\n**Formality:** [scale 1-10]\n**Profanity:** [none / occasional / frequent]\n\n## Structural Preferences\n- Lists: [yes/no, numbered/bulleted]\n- Headers: [yes/no]\n- Paragraph style: [short punchy / mixed / long form]\n- Emphasis: [bold / italic / caps / none]\n- Endings: [CTA / question / statement / callback to opening]\n\n## Editing Instincts\n- Default edit direction: [cuts shorter / adds more]\n- First things they'd delete: [hedging / jargon / filler / examples]\n- Red flags: [what makes them cringe]\n\n---\n\n## Voice Check Questions\nBefore publishing as [Name], ask:\n1. Energy Test: Does this feel like [their baseline] or flat?\n2. Authority Test: Am I writing from confidence where they'd be confident?\n3. Simplicity Test: Would [their target audience] get this immediately?\n4. Landing Test: Did I land the plane or keep circling?\n5. Authenticity Test: Does this sound like [Name] or like \"AI writing\"?\n\n## Example Transformations\n\n**Generic AI version:**\n\"[example of how AI would write it]\"\n\n**In [Name]'s voice:**\n\"[example rewritten in their actual voice]\"\n```\n\n---\n\n## Phase 3: Generate Voice-Matched Content\n\nWith the Voice DNA Profile built, use it to generate any content type.\n\n### Content Generation Process\n\n1. **Load the Voice DNA Profile** (read the profile before writing anything)\n2. **Identify the content type** (social post, article, email, proposal, etc.)\n3. **Check confidence calibration** — Is this topic in their authority zone or learning zone?\n4. **Write the first draft using their patterns:**\n   - Open with their preferred hook style\n   - Use their transition signatures (not generic ones)\n   - Match their sentence architecture\n   - Apply their energy level\n   - End with their preferred closing style\n5. **Run the Voice Check** — Ask all 5 questions from the profile\n6. **Apply their editing instincts** — Would they cut this shorter? Remove the hedging? Add more energy?\n\n### Platform-Specific Adaptations\n\nThe same voice adapts differently per platform. Apply these modifications ON TOP of the base voice:\n\n#### LinkedIn\n- Slightly more structured (headers, line breaks)\n- Authority dialed up 10%\n- Hook must work in first 2 lines (before \"see more\")\n- Professional energy, not casual\n- End with engagement driver (question or bold statement)\n\n#### X/Twitter\n- Punchiest version of their voice\n- Fragments encouraged\n- Energy at maximum\n- No hedging at all — every character counts\n- Thread format: each tweet must stand alone AND build\n\n#### Email\n- Most conversational version\n- Can be slightly longer\n- Personal touches (references to shared context)\n- Clear CTA at the end\n- Warmth > authority\n\n#### Long-form (Blog/Article)\n- Full voice expression\n- Stories and examples get more room\n- Structural preferences fully applied\n- Mix of authority and learning zones\n- Land the plane clearly at the end\n\n#### Proposals/Professional Documents\n- Authority mode by default\n- Concise, confident, no filler\n- Proof and specifics over claims\n- Clear structure (they're scanning, not reading)\n\n---\n\n## Phase 4: Voice Consistency Maintenance\n\n### Ongoing Calibration\n- When the user edits your output, note WHAT they changed. Those edits are voice data.\n- If they say \"this doesn't sound like me,\" ask which specific parts feel off.\n- Update the Voice DNA Profile quarterly with new samples and corrections.\n\n### Common Failure Modes and Fixes\n\n| Problem | Cause | Fix |\n|---------|-------|-----|\n| \"Sounds too formal\" | Formality level too high | Add more contractions, fragments, casual transitions |\n| \"Sounds too casual\" | Energy overdone | Pull back excitement markers, add more structure |\n| \"Sounds like AI\" | Generic transitions, no voice fingerprints | Replace ALL generic phrases with their actual transitions |\n| \"Too hedgy\" | Writing in authority zone with learning-zone voice | Check confidence calibration, remove hedging language |\n| \"Not enough energy\" | Baseline energy too low | Add their power words, shorten sentences, punch up hooks |\n| \"Doesn't land the plane\" | Missing their closing pattern | Apply their specific ending style from the profile |\n\n---\n\n## Guardrails\n\n- **Never fabricate voice samples.** Only extract from content the user provides.\n- **Never assume authority zones.** Ask or infer from samples — don't guess.\n- **Always produce the Voice DNA Profile first** before generating content. Skip this step and the output will be generic.\n- **If fewer than 3 samples provided,** flag that the profile will be less accurate and ask for more.\n- **Log all voice profile updates** so changes can be reviewed and reverted.\n- **The Voice DNA Profile is the user's asset.** Output it in full so they own it and can use it anywhere.\n\n---\n\n## Quick Start\n\n**Minimum viable run:**\n1. User provides 3 writing samples\n2. Skill extracts Voice DNA → generates profile\n3. User reviews profile, corrects anything off\n4. Skill generates requested content using the profile\n\n**Time: 15-20 minutes for profile. 2-5 minutes per content piece after that.**\n\n**The profile is reusable forever.** Build once, use for every piece of content going forward. Update when their voice evolves.\n","tags":{"latest":"2.0.0"},"stats":{"comments":0,"downloads":972,"installsAllTime":36,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1771601407155,"updatedAt":1778491594064},"latestVersion":{"version":"2.0.0","createdAt":1771601407155,"changelog":"v2 — refined Voice DNA extraction with confidence calibration, energy mapping, and platform-specific voice adaptation.","license":null},"metadata":null,"owner":{"handle":"brianrwagner","userId":"s17566b11xz21pmxew2sh62nbs884e1t","displayName":"Brian Wagner","image":"https://avatars.githubusercontent.com/u/3800703?v=4"},"moderation":{"isSuspicious":false,"isMalwareBlocked":false,"verdict":"clean","reasonCodes":["review.llm_review"],"summary":"Review: review.llm_review","engineVersion":"v2.4.24","updatedAt":1779943151406}}