为任何兼容Agent Skills的代理（通过Skills CLI获得77+）提供去AI写作技能，并支持Claude Code、Codex、Grok Build和Antigravity的原生插件。
概览
去AI写作，处理真正暴露AI的层面。虚构作品在任何人触及用词之前就修复了叙事架构;专业文件（发布说明、公关回复、事后分析、门票、技术文章）都被匹配到与其场合的规则。 一个可移植的代理技能：任何会说该标准的代理都可以加载，支持 77+ 代理的 Skills CLI 只需一个命令即可安装。Claude Code、Codex、Grok Build 和 Antigravity 还获得了原生插件打包，且在这四个平台都经过安装验证。一个规范 SKILL.md，不允许各平台分支。四个操作：，（仅诊断）、（最小化编辑）、（完全重写）。 每个流行的人文化工具都会编辑用词和句法。StoryScope（Russell 等，2026：61,608篇故事，人类+5个前沿大型语言模型）显示，使用分类器检测AI虚构时的比例为93.2%，且编辑表面风格几乎不移动（95.5%→93.9%）。
概述（AI 翻译）
英语 |繁體中文 |简体中文
在真正暴露AI的层面去去AI写作。虚构在任何人动用词之前就修复了叙事结构;专业文件（发布说明、公关回复、事后分析、门票、技术文章）都会根据其场地匹配规则。
一个可移植的代理技能：任何会说该标准的代理都可以加载，支持 77+ 代理的 Skills CLI 只需一个命令即可安装。Claude Code、Codex、Grok Build、Antigravity 和 QwenPaw 还获得了原生插件打包。一个规范的 SKILL.md，没有各平台分支。四个操作：write、review（仅诊断）、refactor（最小编辑）、recreate（完全重写）。
目录
- 为什么又要人性化
- 操作条目
- 实验性：具备声乐技能的作曲
- 句子节奏与中文校准
- 安装
- 卸载
- 布局
- 星级历史
- 资料来源
- 支持
- 许可证
为什么又是另一个人性化者
每个流行的人文化工具都会编辑用词和句法。StoryScope（Russell 等人）
本页由 AI 翻译，技术细节请以原文为准。
README
以下为原文 README 节选，完整内容请查看原文。
sepia
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:
| Pass | Layer | Examples |
|---|---|---|
| 1 | Narrative architecture (fiction) | stop explaining the theme, loosen the causal chain, back-load revelations, mix emotion modes, sparse character networks, name real things |
推荐工具
换一个关键词，或者移除筛选条件。
安装
npx skillfish add nanako0129/sepia