# Just Intonation Calibration

> Calibrate generation parameters as just-intonation ratios by task type (factual, creative, code) instead of one global temperature. Use when the same model is too loose on facts or too stiff on drafts. Scope boundary — prompt wording itself → `prompt-optimizer`; compute budget class → `emergency-triage-compute`.

- Skill: `catcorner22/just-intonation-calibration` (Agent Skill)
- Install (CLI): `npx skillmds@latest add catcorner22/just-intonation-calibration`
- Raw SKILL.md: https://api.skillmd.com/api/skills/catcorner22/just-intonation-calibration/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: CatCorner22 (https://skillmd.com/u/catcorner22)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/catcorner22/just-intonation-calibration

---

# Just intonation parameter calibration

**#31** · **Domain:** Music theory (tuning) · **Category:** extension · **Difficulty:** 🟡 Medium

## Core principle

Simple-integer frequency ratios stay consonant; arbitrary detune beats.

## AI problem addressed

One temperature/top-p for every task type produces mush or rigidity.

## Implementation

| Task | Temp | top_p | Cap |
| Factual | 0.3 | 0.85 | short |
| Code | 0.2 | 0.9 | medium |
| Creative | 0.8 | 0.95 | long |
Set the ratio table before generate; do not retune mid-sentence.

## Boundaries

- Prototype as prompt scaffold (🟢) before full pipeline middleware (🟡/🔴)
- Category router: **`ai-transfer-extension`**
- Catalog: **`ai-transfer-ecosystem-primer`**
- Runtime plugin id: `just_intonation`