moai-domain-humanize

name	moai-domain-humanize
description	AI text humanization and 윤문 (post-editing) specialist that detects and removes AI tells while preserving meaning, facts, and figures. Covers Korean, English, Japanese, and Chinese with a shared severity model (S1/S2/S3), quality grades (A/B/C/D), and 30%/50% over-editing guardrails. Use to make AI-generated text read as human-authored without changing what it says (de-ai, naturalness pass).
when_to_use	Use for AI-text humanization and post-editing (윤문): detecting and removing AI tells across Korean, English, Japanese, and Chinese, applying the S1/S2/S3 severity model and quality grades while preserving meaning, facts, and figures.
license	Apache-2.0
compatibility	Designed for Claude Code
allowed-tools	Read, Write, Edit, Grep, Glob
user-invocable	false
metadata	{"version":"1.0.0","category":"domain","status":"active","updated":"2026-06-15","tags":"humanize, ai-tell, 윤문, post-edit, naturalness, multilingual"}
progressive_disclosure	{"enabled":true,"level1_tokens":100,"level2_tokens":5000}

moai-domain-humanize

Post-editing specialist that removes "AI tells" from generated text and rewrites it to read as human-authored, while preserving meaning. This is the editing counterpart to text generation: it does not write new content, it refines how existing content is said. Covers Korean, English, Japanese, and Chinese.

---

Quick Reference

Operating Principles (4)

1. Meaning preservation is the top rule. Facts, numbers, statistics, named entities, quotations, citations, and the author's stance/certainty stay intact. Any meaning drift forces a rollback.
2. Evidence-based edits only. Every change must trace to a detected tell on a specific span. Stylistic "improvements" unconnected to a catalogued tell are themselves an over-editing signal and are forbidden.
3. Genre and register preservation. Humanize within the source register — academic stays academic, casual stays casual. Never push formal text into slang or vice versa.
4. Over-editing prevention. Flag at >30% change (WARN), halt at >50% change (forced stop / human review). Above 50% you are regenerating, not humanizing.

Mode Selection

• Fast mode (default, up to ~5,000 chars): a single pass — detect, rewrite, self-verify against the meaning-preservation checklist.
• Strict mode (long or high-stakes text, or when requested): separate stages — detect → surgical rewrite → content-fidelity audit (facts/figures/stance unchanged) → naturalness review. Re-run a second pass when the result lands at Grade C.

Output Contract

Return two things:

1. The humanized text.
2. A short change report: categories hit (with counts), the final quality grade (A/B/C/D), and the percent changed (character-level edit distance ÷ source length). When a guardrail fires, state it explicitly (WARN at >30%, HALT at >50%).

---

Common Severity Model (shared by all 4 languages)

Each tell carries one severity tier. Detectors gate by occurrence count and overlap, because a single tell rarely proves AI authorship — confidence comes from clustering.

Tier	Name	Rule
S1	Decisive	A single occurrence strongly confirms AI authorship → remove on first occurrence.
S2	Strong	Acceptable at 1–2 instances → remove at 3 or more.