Novel Character logo

Novel Character

Community
Wooooooooood
novel-character

小说角色档案管理工具。管理角色卡、言行一致性检测、关系图谱、角色弧线、出场统计。当用户需要创建/编辑角色、查看角色档案、检测角色言行一致性、管理角色关系、追踪角色成长时使用。触发词:角色、人物、角色卡、档案、言行一致、OOC检测、关系网、角色弧线。

Overview

PublisherWooooooooood
Repositoryai-fiction-writer
Skill namenovel-character
Stars
67
Forks
11
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Wooooooooood on GitHub. Read the source before you install it.

Installation

Install the Novel Character AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Wooooooooood/ai-fiction-writer/tree/main/纯净版skill/novel-character
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Use it in TypingMind

Enable Novel Character in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Novel Character on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Novel Character is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Novel Character — 角色档案管理

管理 .novel/characters/ 下的角色档案,支持言行一致性检测、关系图谱与角色弧线追踪。

核心原则:角色档案是 Source of Truth,AI 写作前必须读取,写作中必须约束角色言行。

工作区规范

.novel/
├── characters/
│   ├── {角色名}.md              # 人编辑(Source of Truth)
│   ├── {角色名}.html            # AI 消费(自动同步)
│   └── new/                     # 新增配角档案
│       └── {新角色名}.md
└── tracking/
│   ├── relationships.json       # 关系网数据
│   ├── character-arcs.json      # 角色弧线追踪
│   └── appearances.json         # 出场统计

角色档案 Markdown 规范

markdown
---
name: {角色名}
type: {主角/女主/反派/配角/穿越者/原住民}
origin_era: "{原属时代,如适用}"
current_era: "{当前时代,如适用}"
cover_identity: {当前身份}
age: {年龄}

# 与世界 building 关联
faction: {所属势力}
race: {种族}
profession: {职业/身份}
status: {社会阶层}

# 知情边界
known_info:
  - {信息A}: {来源章节}
  - {信息B}: {来源章节}
unknown_info:
  - {信息C}: {预计获知章节}
  - {信息D}: {预计获知章节}

# 外貌
appearance:
  height: "{身高}"
  weight: "{体重}"
  build: "{体型}"
  face: "{面部特征}"
  features: "{显著特征}"

# 语言风格
speech_pattern: {角色通用语言风格}
speech_era: {时代用语风格,如适用}

# 性格标签(用于一致性检测)
personality_tags:
  - {标签1}
  - {标签2}
  - {标签3}

# 情绪状态(随剧情更新)
emotion_state:
  current: "{当前情绪}"
  baseline: "{基础情绪}"
  stress_level: 3  # 0-10,压力值

# 能力值(用于爽点设计,可选)
abilities:
  {能力1}: 9
  {能力2}: 8

# 风险规则(什么不能说/做)
risk_rules:
  - {规则1}
  - {规则2}

# 关系网
relationships:
  - target: {关系对象}
    type: {关系类型}
    stage: "{关系阶段}"
    desc: "{关系描述}"

# 成长弧线
growth_arc:
  - stage: "{阶段名称}"
    chapter_range: "{章节范围}"
    trait: "{阶段特征}"
    goal: "{阶段目标}"

# 标志性言行
signature_behaviors:
  - "{行为1}"
  - "{行为2}"

# 禁忌清单
forbidden_list:
  | 场景 | 禁止行为 | 后果 |
  |------|---------|------|
  | {场景1} | {禁止行为} | {后果} |
---

## 现代身份(如适用)

{角色在原属时代的身份、经历、能力}

## 当前身份

{角色在当前作品世界中的身份、处境}

## 性格核心

{性格分析}

## 角色弧线

### 阶段1:{阶段名}(ch{X}-ch{Y})
- **起点**:{起点状态}
- **冲突**:{冲突}
- **成长**:{成长}
- **转折点**:ch{Z} {转折点}

核心操作

0. 写作前角色档案读取

AI 续写或修改正文前,必须完成以下步骤:

  1. 扫描当前章节出场角色
  2. 读取 .novel/characters/{角色名}.md 和 .novel/characters/new/{角色名}.md
  3. 重点确认:
    • 身份/职业:教授、军人、高管、学生等行为边界
    • 性格标签:冷静、倔强、温和等
    • dialect/籍贯:方言、粗口是否符合籍贯
    • 关系阶段:对其他角色的关系亲密度
    • 禁忌清单:什么不能说/做
  4. 未读取角色档案不得写该角色戏份
  5. 若角色有 faction / race / profession 字段,必须同步读取 .novel/worldbuilding/ 中对应档案
  6. 必须读取角色的 known_info 和 unknown_info,约束其言行符合知情边界
  7. 角色行为必须同时符合:职业身份、所属势力立场、种族/职业/阶层设定、知情边界

职业决定行为规则:

  • 教授/教师:可看书、写论文、指导学生,不宜做与职业身份冲突的事
  • 军人/干部:雷厉风行,不拖泥带水
  • 学生:可谨慎、可冲动,但应符合具体人设
  • 经纪人/高管:职业化、利益导向
  • 任何与职业身份冲突的行为必须向作者确认

1. 创建/编辑角色卡

  1. 用户在对话中提供角色信息
  2. 按规范生成 Markdown 文件,保存到 .novel/characters/{角色名}.md
  3. 触发双备份同步 → 生成同名 .html
  4. 更新关系网数据 .novel/tracking/relationships.json

2. 角色列表管理

侧边栏/列表显示:

  • 按类型分组(主角 / 女主 / 反派 / 配角 / 穿越者 / 原住民)
  • 显示角色名、当前身份、出场次数、当前状态
  • 支持搜索和筛选
  • 角色标签云(性格标签、能力标签)

3. 言行一致性检测(OOC检测)

检测流程:

  1. 扫描当前章节文本,提取角色对话和行为
  2. 对比角色档案中的 personality_tags、speech_era、risk_rules
  3. 检测时代错位(如角色使用了不属于当前时代的词汇)
  4. 检测性格OOC(如冷静角色突然冲动无铺垫)
  5. 生成警告列表

OOC检测规则示例:

json
{
  "personality_rules": {
    "{角色名}": {
      "must": ["{必须行为}"],
      "must_not": ["{禁止行为}"],
      "only_when": {
        "{特定行为}": "{允许场景}"
      }
    }
  },
  "era_speech_rules": {
    "{时代}": {
      "forbidden_words": ["{禁用词}"],
      "forbidden_phrases": ["{禁用短语}"],
      "required_style": "{用语风格}"
    }
  }
}

4. 关系图谱

关系数据 .novel/tracking/relationships.json:

json
{
  "nodes": [
    {"id": "{角色A}", "type": "{类型}", "group": "{分组}"},
    {"id": "{角色B}", "type": "{类型}", "group": "{分组}"}
  ],
  "links": [
    {"source": "{角色A}", "target": "{角色B}", "type": "{关系}", "stage": "{阶段}"}
  ]
}

关系演变追踪:

  • 记录每对关系的关键转折点(章节、事件、变化)
  • 预警:关系变化必须有铺垫,不能突兀
  • 关系网可视化(文本描述形式)

5. 角色弧线追踪

.novel/tracking/character-arcs.json:

json
{
  "arcs": [
    {
      "character": "{角色名}",
      "stages": [
        {
          "name": "{阶段名}",
          "chapter_range": "{章节范围}",
          "trait": "{特征}",
          "status": "completed"
        },
        {
          "name": "{阶段名}",
          "chapter_range": "{章节范围}",
          "trait": "{特征}",
          "status": "in_progress"
        }
      ],
      "current_stage": "{当前阶段}"
    }
  ]
}

弧线检测:

  • 角色当前行为是否符合当前阶段特征
  • 阶段转换是否有明确转折点
  • 成长轨迹是否清晰、合理

6. 出场统计

.novel/tracking/appearances.json:

json
{
  "statistics": {
    "{角色A}": {
      "total_chapters": 50,
      "last_chapter": 50,
      "chapters_since_last": 0
    },
    "{角色B}": {
      "total_chapters": 30,
      "last_chapter": 48,
      "chapters_since_last": 2
    }
  }
}

预警规则:

  • 主角连续出场<3章:正常
  • 女主连续3章未出场:预警(边缘化风险)
  • 重要配角连续10章未出场:提醒

7. 上下文注入

AI 续写时,检索当前章节出场角色,读取对应档案,注入 Prompt:

[角色上下文]
出场角色:{角色A}({类型})
- 当前身份:{身份}
- 所属势力:{势力}(与主角关系:{关系})
- 种族/职业/阶层:{race} / {profession} / {status}
- 当前状态:{状态}
- 语言风格:{风格}
- 性格标签:{标签}
- 当前弧线阶段:{阶段}
- 禁忌:{禁忌}
- 与{角色B}关系:{阶段}
- 与{角色C}关系:{阶段}

出场角色:{角色B}({类型})
- 当前身份:{身份}
- 所属势力:{势力}(与主角关系:{关系})
- 种族/职业/阶层:{race} / {profession} / {status}
- 当前状态:{状态}
- 性格标签:{标签}
- 当前弧线阶段:{阶段}
- 标志性言行:{行为}

双备份同步

  • Markdown 保存后,自动渲染为 HTML
  • HTML 保留 YAML frontmatter 为 <meta> 标签
  • 单向同步:Markdown → HTML

参考文档

设计新角色或搭建关系网时,先读 references/人物设计方法论.md:

  • 人物公式(主角辨识度 / 配角记忆点 / 反派立场 / 关系网张力)
  • 主角起点类型、金手指类型、声音标签清单;配角五型;反派类型矩阵
  • 关系网结构、九种核心关系类型、关系拆解四步法
  • 成长六阶段与角色功能对照、弧光设计技巧
  • 通用设定模板(主角卡/配角卡/反派卡/角色切入卡/成长—关系时间线/张力检查表)
  • 题材速配决策表、避坑与检查清单

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Novel Character AI skill do?

小说角色档案管理工具。管理角色卡、言行一致性检测、关系图谱、角色弧线、出场统计。当用户需要创建/编辑角色、查看角色档案、检测角色言行一致性、管理角色关系、追踪角色成长时使用。触发词:角色、人物、角色卡、档案、言行一致、OOC检测、关系网、角色弧线。

Why use Novel Character on TypingMind?

Because you install it once and use it with any model. Novel Character is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Novel Character in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Wooooooooood/ai-fiction-writer/tree/main/纯净版skill/novel-character. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Novel Character?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Novel Character?

As many as you like. As long as a model supports skills, you can use Novel Character with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Novel Character AI skill free?

Yes. It is published on GitHub by Wooooooooood under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇