Webnovel Deconstruct

Q: What does the Webnovel Deconstruct AI skill do?

参考书拆解。对 长篇/参考书/ 下的 txt 做深度拆书：建文件夹、搬文件、生成拆书报告+数据+章节规划+情绪曲线+节奏统计。存放于 长篇/参考书/{书名}/。

Community

ricky-theseus

webnovel-deconstruct

参考书拆解。对长篇/参考书/ 下的 txt 做深度拆书：建文件夹、搬文件、生成拆书报告+数据+章节规划+情绪曲线+节奏统计。存放于长篇/参考书/{书名}/。

Overview

Publisher	ricky-theseus
Repository	`DaisyWriter`
Skill name	`webnovel-deconstruct`
Stars	77
Forks	5
Bundled files	Instructions only
License	GPL-3.0
Links	Skill source Repository

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 ricky-theseus on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/ricky-theseus/DaisyWriter/tree/master/skills/webnovel/deconstruct
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.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/ricky-theseus/DaisyWriter.git /tmp/DaisyWriter
mkdir -p .claude/skills
cp -r /tmp/DaisyWriter/skills/webnovel/deconstruct .claude/skills/webnovel-deconstruct

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Webnovel Deconstruct 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 Webnovel Deconstruct 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 Webnovel Deconstruct 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.

拆书流程

流程

Step 0：准备

确认 长篇/参考书/ 目录存在，否则创建
检查是否有散落在 长篇/参考书/ 根目录的 txt 文件（不在子文件夹内的）
若用户提供了书名但 txt 在根目录，自动定位

Step 1：建文件夹 + 搬文件

在 长篇/参考书/ 下以书名创建文件夹（如 长篇/参考书/六爻/）
把原 txt 文件移入该文件夹
路径清洗：文件名中的特殊字符保留原样

Step 2：调 deconstruction-agent 深度拆书

使用 Agent 工具调用 webnovel-writer:deconstruction-agent
参数：reference_text_path = txt 路径, analysis_mode = deep
要求返回包含逐章数据的 JSON，每个章节至少包含：章号、字数、开篇钩子类型、章末钩子类型、核心事件/节拍、节奏类型（开场钩子/展开/小高潮/过渡/蓄势/爆发/收束）
保留原有的 init_reference_research 顶层结构，增加 chapters 数组

Step 3：生成输出文件

3.1 拆书报告 `{书名}-拆书报告.md`

根据 deconstruction-agent 返回的 JSON 编写中文可读报告，格式固定：

基本信息（作者/题材/字数/章数）
卷结构表
剧情主线（200-300字）
核心特色（金手指、感情线、叙事结构）
可借鉴模式（至少3条）
不可复制项
差异化要求

3.2 拆书数据 `{书名}-拆书数据.json`

原样保存 deconstruction-agent 返回的 JSON

3.3 章节规划 `{书名}-章节规划.md`

根据 deconstruction-agent 返回的逐章数据生成，格式固定：


# {书名} 章节规划

## 第1卷：{卷名}（第1章-第N章）

### 第1章 {章名}
- **字数**：2800
- **开篇钩子**：主角被宗门当众除名 + 全场羞辱
- **章末钩子**：神秘人从人群中注视主角离开
- **节奏类型**：开场钩子
- **核心节拍**：被逐出师门 → 当众撕毁身份文牒 → 同门嘲讽 → 离开山门 → 神秘人尾随
- **信息释放**：世界观基石（宗门等级/诡异降临背景）、主角初始状态（启灵境/弃子身份）
- **情绪起点→终点**：压抑 → 隐怒

### 第2章 {章名}
...

每章字段说明：

字段	内容
字数	该章实际字数
开篇钩子	前300字内用什么拉住读者（冲突/悬念/信息差/金句/场景）
章末钩子	最后一节如何制造"继续读"的动力
节奏类型	开场钩子 / 展开 / 小高潮 / 过渡 / 蓄势 / 爆发 / 收束
核心节拍	该章的情节拍序列（3-6个，用→连接）
信息释放	该章释放了哪些新信息给读者
情绪起点→终点	章节开头到结尾的情绪走向

卷首加一段节奏分析，格式：


## 第1卷节奏分析
- 总字数：XXX
- 章节数：XX
- 平均每章字数：XXXX
- 节奏分布：开场钩子 X 章 / 展开 X 章 / 小高潮 X 章 / 过渡 X 章 / 蓄势 X 章 / 爆发 X 章 / 收束 X 章
- 前10章节奏公式：钩→展→展→钩→蓄→爆→收→过→蓄→爆
- 快慢比：快节奏 X 章 / 慢节奏 X 章

3.4 情绪曲线 `{书名}-情绪曲线.md`

根据逐章摘要绘制全书情绪概览：

按卷分段，每卷标注整体情绪走向（上行/下行/转折/平稳）
标注关键情绪锚点：开篇钩子、催泪点、爽点爆发、虐点、收尾情绪
可选：用 ASCII 简单图表示意

3.5 节奏统计 `{书名}-节奏统计.md`

从卷结构和逐章数据估算节奏数据：

总字数、平均每章字数
卷间字数分布
卷末高潮章节密度
节奏类型分布（每种节奏类型占多少章）
前10章节奏公式
类型标签（快节奏/慢热/均衡）

Step 4：验证

文件夹存在且包含：原始 txt + 5 个生成文件
拆书报告含全部必需字段
章节规划含全部必需字段

输出清单

长篇/参考书/{书名}/ ├── {原书}.txt ├── {书名}-拆书报告.md ├── {书名}-拆书数据.json ├── {书名}-章节规划.md ├── {书名}-情绪曲线.md └── {书名}-节奏统计.md

调用方式


/webnovel-deconstruct 六爻

若 长篇/参考书/ 根目录有多个 txt 且未指定书名，列出可选并让用户选择。

Frequently asked questions

What does the Webnovel Deconstruct AI skill do?

Why use Webnovel Deconstruct on TypingMind?

Because you install it once and use it with any model. Webnovel Deconstruct 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 Webnovel Deconstruct in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ricky-theseus/DaisyWriter/tree/master/skills/webnovel/deconstruct. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Webnovel Deconstruct?

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 Webnovel Deconstruct?

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

Is the Webnovel Deconstruct AI skill free?

Yes. It is published on GitHub by ricky-theseus under the GPL-3.0 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

Karpathy Guidelines

multica-ai

OrganizationPopular

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define…

Create Agent

Create a custom agent (.agent.md) for a specific job.

Create Hook

Create a hook (.json) to enforce policy or automate agent lifecycle events.

Generate Run Commands

microsoft

OrganizationPopular

Generate or modify run commands for the current session. Use when the user wants to set up or update run commands that appear in the session's Run button.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

拆书流程

流程

Step 0：准备

Step 1：建文件夹 + 搬文件

Step 2：调 deconstruction-agent 深度拆书

Step 3：生成输出文件

3.1 拆书报告 {书名}-拆书报告.md

3.2 拆书数据 {书名}-拆书数据.json

3.3 章节规划 {书名}-章节规划.md

3.4 情绪曲线 {书名}-情绪曲线.md

3.5 节奏统计 {书名}-节奏统计.md

Step 4：验证

输出清单

调用方式

Frequently asked questions

Related AI Skills

Set up your own AI workspace now

3.1 拆书报告 `{书名}-拆书报告.md`

3.2 拆书数据 `{书名}-拆书数据.json`

3.3 章节规划 `{书名}-章节规划.md`

3.4 情绪曲线 `{书名}-情绪曲线.md`

3.5 节奏统计 `{书名}-节奏统计.md`