Novel Analyze logo

Novel Analyze

Community
Wooooooooood
novel-analyze

小说扫榜与拆文工具。支持分析热门榜单趋势、拆解对标书的大纲节奏/剧情素材/角色设定/文风特征,建立个人模块库。当用户需要扫榜选材、拆文学习、分析对标书、提取写作套路时使用。触发词:扫榜、拆文、对标、分析、文风、节奏、爽点、套路、模块库。

Overview

PublisherWooooooooood
Repositoryai-fiction-writer
Skill namenovel-analyze
Stars
67
Forks
11
Bundled files
2
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.

  • 2 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 Analyze 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-analyze
  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 Analyze 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 Analyze 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 Analyze 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 Analyze — 扫榜与拆文

核心思路:套路 = 确定性的情绪满足

专业作者的方法论三步走:

  1. 扫榜:分析热门榜单,洞察题材、人设、切入点
  2. 拆文:拆解大纲节奏与剧情素材,建立个人模块库
  3. 商业化写作:学习并运用钩子、爽感、期待感等核心技巧

工作区规范

.novel/
├── benchmarks/            # 对标书库(从拆文输出同步)
│   └── {对标书名}/
│       ├── 原文/          # 对标书原文章节
│       ├── 角色/          # 结构化角色卡
│       ├── 剧情/          # 结构化剧情线
│       ├── 设定/          # 结构化设定
│       ├── 文风.md        # 日更前读取,贴近对标书文风
│       └── 拆文报告.md    # 拆文skill输出的完整报告
├── references/            # 写作方法论知识库
│   ├── 大纲排布.md
│   ├── 钩子技法.md
│   ├── 情绪设计.md
│   ├── 对话技法.md
│   └── ...
└── tracking/
    └── 拆文记录.md        # 拆文历史记录

核心操作

1. 扫榜(Scan)

分析当前市场热门榜单,洞察趋势:

扫榜维度:

维度内容
题材趋势当前最火题材TOP10、新兴题材、衰退题材
人设套路高频人设组合、反套路人设、人设差异化空间
切入点热门开局模式、黄金三章共性、开篇钩子类型
爽点密度每章爽点数量、爽点类型分布、爽点间隔
更新策略日更字数、爆更时机、断章技巧

扫榜输出:

markdown
## 扫榜报告:{平台} {日期}

### 题材趋势
- TOP1 题材:{题材}(占比 {X}%)
- 新兴题材:{题材}
- 衰退题材:{题材}

### 人设套路
- 高频:{人设组合}
- 反套路:{人设}
- 差异化空间:{方向}

### 切入点分析
- 热门开局:{开局模式}
- 黄金三章共性:{共性}
- 开篇钩子类型:{钩子类型}

### 爽点密度
- 平均每章 {N} 个爽点
- 爽点类型:{类型分布}
- 爽点间隔:{间隔}

2. 拆文(Analyze)

深度拆解对标书,提取可复用模块:

拆文维度(六维评分):

维度权重检测要点
开篇力18%黄金三章、悬念钩子、代入感
节奏感22%爽点密度、情绪曲线、章节节拍
人物塑造18%主角动机、配角功能、关系网
世界观12%设定完整度、金手指合理性
文学性18%对话自然度、描写生动度、句式变化
表达效率12%是否有解释性旁白、重复描写、冗余环境/内心描写、散文式收尾

拆文输出结构:

benchmarks/{对标书名}/
├── 拆文报告.md          # 六维评分 + 爽点密度 + 可借鉴套路
├── 文风.md              # 句长/标点/对话潜台词/情绪节奏
├── 角色/
│   ├── 主角.md           # 完整角色档案
│   ├── 核心配角.md       # 功能+动机+弧线
│   └── 角色关系.md       # 关系网络
├── 剧情/
│   └── 故事线.md         # 框架识别 + 主线 + 支线
├── 设定/
│   ├── 世界观.md         # 核心规则 + 特殊设定
│   ├── 金手指.md         # 金手指机制 + 限制
│   └── 势力.md           # 势力档案
└── 章节/
    └── 章节摘要.md       # 每章摘要 + 情节点 + 爽点标记

拆文报告模板:

markdown
## 拆文报告:《{书名}》

### 概要
- 作者:{作者}
- 平台:{平台}
- 字数:{字数}
- 评分:{总分}/100

### 六维评分
| 维度 | 得分 | 亮点 | 不足 |
|------|------|------|------|
| 开篇力 | 85 | 第一章悬念极强 | 第三章略显拖沓 |
| 节奏感 | 90 | 爽点密集且自然 | 中期有小低谷 |
| 人物塑造 | 88 | 主角动机清晰 | 某配角功能重复 |
| 世界观 | 82 | 金手指限制合理 | 设定解释过多 |
| 文学性 | 78 | 对话口语化 | 描写偶有模板化 |
| 表达效率 | 80 | 信息密度高 | 偶有解释性旁白 |

### 爽点密度分析
- 总爽点数:{N}个
- 平均每章:{N}个
- 爽点类型分布:{分布}
- 高潮章节:第{X}章、第{Y}章、第{Z}章

### 可借鉴套路
1. **开局模式**:{描述}
2. **钩子设计**:{描述}
3. **打脸节奏**:{描述}
4. **感情线设计**:{描述}
5. **反派塑造**:{描述}

### 避坑提醒
1. {描述}
2. {描述}

3. 文风提取

从对标书中提取文风特征,供日更时参考:

文风分析维度:

  • 句长分布:短句占比、长句占比、平均句长
  • 标点运用:逗号密度、句号密度、感叹号/问号使用频率
  • 对话特征:对话占比、对话标签方式、潜台词运用
  • 情绪节奏:紧张-松弛交替频率、情绪峰值位置
  • 描写风格:五感描写占比、白描vs渲染比例

文风文件模板:

markdown
## 文风特征:《{书名}》

### 句长分布
- 短句(<15字):占比 40%,用于紧张场景、动作描写
- 中句(15-30字):占比 45%,常规叙述
- 长句(>30字):占比 15%,用于心理描写、环境渲染

### 标点运用
- 逗号密度高:一句话内多停顿,营造口语感
- 句号干脆:不拖泥带水,节奏明快
- 感叹号克制:仅在真正高潮时使用

### 对话特征
- 对话占比:约 50%
- 对话标签:多用"他说""她道",少用复杂副词
- 潜台词:频繁使用,言外之意丰富

### 情绪节奏
- 紧张-松弛周期:约 3 章一循环
- 情绪峰值:每 5 章一个小高峰,每 15 章一个大高峰
- 低谷处理:用日常互动填充,不空洞

### 日更参考
写作时参考本文风,注意:
1. 保持短句节奏,不要连续使用长句
2. 对话要口语化,避免书面语
3. 情绪不要直给,用动作和细节暗示

深入参考:

使用方法

扫榜

用户:帮我扫一下{平台}最近的热门榜单
→ 分析题材趋势、人设套路、切入点、爽点密度
→ 输出扫榜报告

拆文

用户:帮我拆一下《{书名}》前20章
→ 深度分析六维评分、爽点密度、角色、剧情、设定
→ 输出结构化拆文库

文风提取

用户:提取《{书名}》的文风特征,我要对标
→ 分析句长、标点、对话、情绪节奏
→ 输出文风.md

与写作skill的配合

  1. 扫榜 → 大纲:根据扫榜结果确定题材方向和人设
  2. 拆文 → 大纲:借鉴对标书的节奏和爽点设计
  3. 文风 → 日更:日更前读取文风.md,保持风格一致
  4. 拆文库 → 角色/设定:将对标书的角色和设定模块复用或改编

参考文档

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 Analyze AI skill do?

小说扫榜与拆文工具。支持分析热门榜单趋势、拆解对标书的大纲节奏/剧情素材/角色设定/文风特征,建立个人模块库。当用户需要扫榜选材、拆文学习、分析对标书、提取写作套路时使用。触发词:扫榜、拆文、对标、分析、文风、节奏、爽点、套路、模块库。

Why use Novel Analyze on TypingMind?

Because you install it once and use it with any model. Novel Analyze 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 Analyze 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-analyze. 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 Analyze?

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 Analyze?

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

Is the Novel Analyze 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 👇