voice-calibration

Voice Calibration

Build a voice profile from live writing samples typed in the terminal. The profile captures sentence rhythm, rhetorical habits, vocabulary tendencies, and tonal signatures — then saves it as a reusable reference for future content generation.

Why Live Samples

AI-assisted writing blends the author's voice with the model's defaults. To capture authentic voice, every sample must be typed fresh by the user in the terminal with no AI drafting or editing. Quantity matters less than authenticity — 6-8 raw responses are enough.

Workflow

Round 1 (General)     → 4 prompts — capture base voice
Round 2 (Domain)      → 4 prompts — capture subject-matter tone
Analysis              → extract patterns
Voice profile         → save to file

---

Round 1: General Voice (4 prompts)

Ask these one at a time using AskUserQuestion. Wait for each response before asking the next. Do NOT paraphrase or suggest answers.

Prompt 1 — Opinion

You have 3-4 sentences. What's something most people in your field get wrong?

Prompt 2 — Explanation

Explain something you understand deeply to someone who knows nothing about it. 3-5 sentences.

Prompt 3 — Reaction

Think of something you read recently that made you stop and think. What was it, and what was your reaction? Write it as if you're telling a friend.

Prompt 4 — Contrast

Describe two things that most people think are similar but you think are fundamentally different. 2-4 sentences.

---

Round 2: Domain Voice (4 prompts)

If --domain was passed, use that topic. Otherwise ask:

What domain will this voice profile be used for? (e.g., I-Ching commentary, product marketing, technical writing)

Then ask these one at a time, tailored to the stated domain:

Prompt 5 — Hook

Write the opening 2-3 sentences of a post about [domain topic]. Assume the reader doesn't care yet — make them care.

Prompt 6 — Corrective

What's a common misconception in [domain]? Correct it in 3-4 sentences the way you'd actually say it.