영어 | 繁體中文 | 简体中文

AI를 드러내는 층에서 AI를 제거하세요. 소설은 단어 선택에 손대기 전에 내러티브 구조를 먼저 고쳐야 합니다; 전문 문서들(출시 노트, 홍보 답변, 사후 분석, 티켓, 기술 기사)은 각각 장소에 맞는 규칙을 받습니다.

휴대용 에이전트 스킬: 표준을 구사하는 모든 에이전트가 로드할 수 있으며, 77+ 에이전트를 지원하는 Skills CLI가 한 번의 명령어로 설치합니다. Claude Code, Codex, Grok Build, Antigravity, QwenPaw도 네이티브 플러그인 패키징을 제공합니다. 하나의 정식 SKILL.md, 플랫폼별 포크 없음. 네 가지 연산: write, review(진단만), refactor(최소한의 편집), recreate(완전 재작성).

목차

• 왜 또 다른 인간화자야
• 연산 항목
• 실험: 보컬 기술을 활용한 작곡
• 문장 리듬과 중국어 보정
• 설치
• 삭제
• 레이아웃
• 스타 역사
• 출처
• 지원
• 면허

---

왜 또 다른 인간화자가 되는가

모든 인기 있는 휴머머니저들은 단어 선택과 구문을 편집합니다. 스토리스코프 (러셀 외,

sepia

English | 繁體中文 | 简体中文

De-AI writing at the layer that actually gives AI away. Fiction gets its narrative architecture repaired before anyone touches word choice; professional documents (release notes, PR replies, postmortems, tickets, technical articles) each get rules matched to their venue.

A portable Agent Skill: any agent that speaks the standard can load it, and the Skills CLI, which supports 77+ agents, installs it with one command. Claude Code, Codex, Grok Build, Antigravity, and QwenPaw additionally get native plugin packaging. One canonical SKILL.md, no per-platform forks. Four operations: write, review (diagnose only), refactor (minimal edits), recreate (full rewrite).

Table of Contents

• Why another humanizer
• Operation entries
• Experimental: composing with voice skills
• Sentence rhythm and Chinese calibration
• Install
• Uninstall
• Layout
• Star History
• Sources
• Support
• License

---

Why another humanizer

Every popular humanizer edits word choice and syntax. StoryScope (Russell et al., 2026: 61,608 stories, human + 5 frontier LLMs) showed that a classifier using narrative-structure features alone detects AI fiction at 93.2% macro-F1. In the same study’s LAMP-edited condition, where human editors had rewritten the surface style, detection dropped only from 95.5% to 93.9%. The tells that survive are architectural: themes explained by the narrator, single-track causally-tidy plots, emotions rendered only as bodily sensation, no real-world references, no reader, linear time, endings resolved by protagonist growth and acceptance.

sepia turns those measured gaps, together with the related studies digested in research/, into a three-pass writing and revision protocol for fiction: