Novel Knowledge logo

Novel Knowledge

Community
Wooooooooood
novel-knowledge

小说知识库管理工具。管理时间线、物价锚点、流行文化、品牌对照、对标书、参考资料,支持Markdown+HTML双备份。当用户需要查询时代背景、验证物价合理性、管理设定知识、查证细节、管理对标书时使用。触发词:知识库、时间线、物价、时代背景、查证、品牌对照、对标书、参考资料。

Overview

PublisherWooooooooood
Repositoryai-fiction-writer
Skill namenovel-knowledge
Stars
67
Forks
11
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Novel Knowledge 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-knowledge
  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 Knowledge 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 Knowledge 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 Knowledge 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 Knowledge — 知识库管理

管理 .novel/knowledge/ 下的真实/考据型时代背景知识,支持时间线对照、物价锚点、品牌对照、对标书管理与 Markdown+HTML 双备份。

核心原则:知识库是作品世界一致性的最后防线,写作前必须查询,写作后必须校验。

与 novel-worldbuilding 的分工:

  • knowledge:真实历史、物价、品牌、考据资料、参考文献
  • worldbuilding:虚构世界设定、地图、历法、势力、种族/职业、规则体系、文化禁忌

穿越题材中,「现实世界」由 knowledge 管理,「作品世界规则」由 worldbuilding 管理。

工作区规范

.novel/
├── knowledge/
│   ├── timeline/                # 时间线对照
│   │   ├── {年份}.md
│   │   └── ...
│   ├── economy/                 # 物价/经济
│   │   ├── 物价表.md
│   │   └── 收入对照.md
│   ├── culture/                 # 流行文化
│   │   ├── 品牌对照表.md
│   │   └── {文化条目}.md
│   ├── refs/                    # 用户上传参考文献
│   │   └── {资料}.md
│   └── benchmark/               # 对标书
│       └── {对标书}.md
└── tracking/
    └── knowledge-usage.json     # 知识使用记录

知识库 Markdown 规范

时间线条目

markdown
---
category: timeline
year: {年份}
story_month: 1              # 对应故事第几个月
real_date: "{真实日期}"
event: {事件名称}
impact_level: high          # 高/中/低
butterfly_risk: false       # 是否容易被主角改变
novel_used: false
chapter_ref: ""
source: {来源}
---

## 事件详情

{事件描述}

## 小说应用建议

{如何应用到故事中}

物价条目

markdown
---
category: economy
year: {年份}
region: {地区}
item: {物品名称}
price: "{价格}"
unit: {单位}
context: {场景}
source: {来源}
---

## 背景说明

{背景描述}

## 小说使用注意

{使用注意}

品牌对照条目

markdown
---
category: brand
real_name: "{现实品牌名}"
fiction_name: "{作品世界品牌名}"
type: "{类型}"
first_seen: "ch01"
---

## 现实原型

{现实原型描述}

## 作品世界映射

{作品世界中的对应设定}

## 使用规则

- 正文中使用"{作品世界品牌名}"指代
- 不能出现"{现实品牌名}"字样
- 穿越者/知情角色内心可用现实名称思考,但对话中必须使用作品世界名称

对标书条目

markdown
---
category: benchmark
title: "{书名}"
author: "{作者}"
platform: "{平台}"
type: "{类型}"
word_count: "{字数}"
rating: "{评分}"
---

## 对标维度

### 开篇力
- 前500字:{分析}
- 前3000字:{分析}
- 值得借鉴:{点}

### 爽点设计
- 爽点密度:{密度}
- 爽点类型:{类型}
- 值得借鉴:{点}

### 人设塑造
- 主角:{分析}
- 女主:{分析}
- 值得借鉴:{点}

## 本书差距分析

| 维度 | 对标书 | 本书 | 差距 |
|------|--------|------|------|
| 开篇力 | 强 | 中 | {改进点} |
| 爽点密度 | 高 | 中 | {改进点} |
| 女主戏份 | 多 | 少 | {改进点} |

## 改进建议

1. {建议}
2. {建议}

核心操作

0. 写作前时代背景查询

AI 写作或修改正文前,必须根据当前场景查询以下知识:

  1. 时代用语:当前时代是否已有该词汇/说法?禁用后世词
  2. 社会常识:场景是否符合时代背景(城市面貌、建筑状态、行业生态)
  3. 籍贯方言:角色籍贯决定其方言、粗口、习惯用语
  4. 品牌对照:正文中出现现实品牌必须替换为作品世界名称

时代场景合理性规则:

  • 体制内/古风场景:庄重、专业,禁用轻佻中英夹杂
  • 现代职场场景:可使用行业术语,但不宜过度网络化
  • 家庭场景:符合当时生活水平
  • 任何与时代明显冲突的细节必须向作者确认

1. 知识录入与编辑

用户通过对话提供知识 → 按规范生成 Markdown → 保存到对应分类目录。

2. 双备份同步

监听 .novel/knowledge/**/*.md 保存事件:

  1. 读取 Markdown 文件
  2. YAML frontmatter → HTML <meta> 标签
  3. Markdown 正文 → HTML <section> 结构化内容
  4. 生成同名 .html 文件

3. 品牌对照检测

扫描章节文本,检测现实品牌名称是否泄露:

  • 对比 .novel/knowledge/culture/品牌对照表.md
  • 标记违规:正文中出现"{现实品牌}"(应为"{作品世界品牌}")
  • 区分:内心独白可用现实名称,对话必须使用作品世界名称

品牌对照表格式:

markdown
| 现实名称 | 作品世界名称 | 类型 | 首次出现 |
|---------|------------|------|---------|
| {现实} | {作品世界} | {类型} | ch01 |

4. 时间线对照

根据 config.yaml 的 anchor_date 计算:

  • 故事第 N 天 = 锚点日期 + N 天
  • 自动提示该日期附近的真实/设定事件

示例:

故事第 30 天 = {日期}
真实事件:{事件}
作品世界事件:{事件}

5. 物价锚点检测

扫描章节文本中的价格描述:

  • 对比知识库中的历史/设定物价
  • 标记合理性:{年份}{地区}{物品}{价格}(✓合理)
  • 标记异常:{年份}{地区}{物品}{价格}(✗异常,当时约{价格})

6. 与 novel-worldbuilding 的协作

明确分工:

内容归属 Skill说明
真实历史事件knowledge如 1998 年金融危机、某个真实节日
虚构历史纪元worldbuilding如苍澜历、星际联盟纪元
真实物价/品牌knowledge如 1998 年猪肉价格、诺基亚手机
虚构货币/势力worldbuilding如灵石、东海商会
真实地理/城市knowledge如北京胡同、上海外滩
虚构地图/城市worldbuilding如东海城、星际空间站
考据资料knowledge参考文献、历史文献
虚构规则/魔法worldbuilding修炼体系、科技树

协作流程:

  1. 写作前,同时查询 knowledge(真实背景)和 worldbuilding(虚构设定)
  2. 穿越题材中,穿越者/知情角色内心可用现实知识,但对话中必须符合作品世界设定
  3. 若真实知识与虚构设定冲突,以 worldbuilding 为准(worldbuilding 是作品世界内的 Source of Truth)

7. 对标书管理

对标书作用:

  • 学习爆款作品的开篇力、爽点设计、人设塑造
  • 定期对比本书与对标书的差距
  • 识别改进空间

对标维度:

维度说明权重
开篇力前500字吸引力20%
爽点密度每章爽点数量20%
人设鲜明角色记忆度15%
节奏感情节推进速度15%
期待感追更动力15%
文笔描写质量15%

对标流程:

  1. 选择对标书(同类型爆款)
  2. 逐章对比分析
  3. 识别差距和改进点
  4. 将改进建议融入大纲

8. 知识库检索

用户输入关键词 → 检索所有 .md 文件:

  • 优先匹配 event、item、name 字段
  • 返回相关知识条目 + 来源

9. 知识使用记录

.novel/tracking/knowledge-usage.json:

json
{
  "usage": [
    {
      "knowledge_id": "{ID}",
      "knowledge_type": "{类型}",
      "chapter": 1,
      "usage_type": "引用",
      "context": "{使用场景}"
    }
  ]
}

内置知识模板(初始化时可选)

  • 重大历史/设定事件(按时间)
  • 品牌对照表
  • 行业规则
  • 地区物价表(日常消费、电子产品、房产等)
  • 时代特征词汇对照表
  • 流行歌曲/电影/文化清单
  • 参考资料模板

Frequently asked questions

What does the Novel Knowledge AI skill do?

小说知识库管理工具。管理时间线、物价锚点、流行文化、品牌对照、对标书、参考资料,支持Markdown+HTML双备份。当用户需要查询时代背景、验证物价合理性、管理设定知识、查证细节、管理对标书时使用。触发词:知识库、时间线、物价、时代背景、查证、品牌对照、对标书、参考资料。

Why use Novel Knowledge on TypingMind?

Because you install it once and use it with any model. Novel Knowledge 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 Knowledge 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-knowledge. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Novel Knowledge?

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 Knowledge?

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

Is the Novel Knowledge 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 👇