Shortstory Deconstruct logo

Shortstory Deconstruct

Community
ricky-theseus
shortstory-deconstruct

拆解盐选短篇参考文,提取钩子设计、悬念铺设、节奏控制、收束手法等写作模式。触发词:拆这篇、拆解、分析这个短篇、做拆解、帮我把这篇拆了、提取模式

Overview

Publisherricky-theseus
RepositoryDaisyWriter
Skill nameshortstory-deconstruct
Stars
77
Forks
5
Bundled files
Instructions only
LicenseGPL-3.0
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 ricky-theseus on GitHub. Read the source before you install it.

Installation

Install the Shortstory Deconstruct 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/ricky-theseus/DaisyWriter/tree/master/skills/shortstory/deconstruct
  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.
2

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/shortstory/deconstruct .claude/skills/shortstory-deconstruct
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Shortstory 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 Shortstory 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 Shortstory 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.

触发方式

用户说了以下任何一句,直接启动拆解流程:

用户说对应动作
"拆这篇" / "帮我拆一下" (且用户提供了文本)Step 0 → 1 → 2 → 3 → 4
"分析这个短篇" / "看看这篇好在哪里"同上,全流程拆解
"提取这篇的模式" / "这篇有什么可学的"同上,重点输出句式模板+可借鉴模式
"/shortstory-deconstruct 文章名"直接匹配文章名执行拆解

拆解短篇故事

输出严格 5 个文件,缺一不可。写完后必须 Step 4 验证。

流程

Step 0:准备

  • 用户提供 md/txt 文件路径,或直接粘贴原文

  • 确认归类到哪个类型(言情/悬疑/脑洞/古风/其他)

  • 编码转换(关键防错步骤):中文 txt 常为 GB18030(CodePage 54936)或 GBK(936),极少数为 UTF-8。必须统一转为 UTF-8 无 BOM:

    powershell
    $bytes = [System.IO.File]::ReadAllBytes("源文件路径.txt")
    $text = [System.Text.Encoding]::GetEncoding(54936).GetString($bytes)
    $utf8NoBom = New-Object System.Text.UTF8Encoding $false
    [System.IO.File]::WriteAllText("目标路径\原文.md", $text, $utf8NoBom)

Step 1:建目录 + 搬文件

  • 在 短篇/参考书/{类型}/ 下以文章名创建文件夹
  • 原文存为 原文.md

Step 2:拆解分析

输出 5 个文件的全部内容到内存,确认完整后再逐个写入。

2a. 拆解数据.json

必须使用以下模板,逐字段填充,不得删改字段名:

json
{
  "title": "「文章名」",
  "author": "「作者,可选填空字符串」",
  "category": "「言情/悬疑/脑洞/古风/其他」",
  "word_count": 「整数」,
  "hook": {
    "position": "「前多少字出现钩子」",
    "technique": "「钩子手法:身份反转/意外撞见/危机开场/金句/反常情境/震撼对话/倒计时/其他」",
    "one_liner": "「一句话钩子」"
  },
  "structure": {
    "acts": [
      {"name": "「开场」", "start_chapter": 1, "end_chapter": 「整数」, "function": "「功能」"},
      {"name": "「展开」", "start_chapter": 「整数」, "end_chapter": 「整数」, "function": "「功能」"},
      {"name": "「转折」", "start_chapter": 「整数」, "end_chapter": 「整数」, "function": "「功能」"},
      {"name": "「高潮」", "start_chapter": 「整数」, "end_chapter": 「整数」, "function": "「功能」"},
      {"name": "「收束」", "start_chapter": 「整数」, "end_chapter": 「整数」, "function": "「功能」"}
    ],
    "ending_type": "「反转型/情绪收束型/开放式/循环型」"
  },
  "rhythm": {
    "formula": "「如:钩(450字)→铺(800字)→展(1200字)→转(600字)→爆(1500字)→收(500字)」",
    "segments": [
      {"label": "「钩子段/铺垫段/展开段/转折段/爆发段/收束段」", "word_count": 「整数」, "emotion": "「情绪」", "function": "「功能」"}
    ]
  },
  "characters": [
    {"name": "「角色名」", "role": "「主角/配角/反派」", "archetype": "「原型标签」", "trait": "「记忆点」"}
  ],
  "patterns": [
    "「可借鉴模式1」", "「可借鉴模式2」"
  ],
  "templates": [
    {"original": "「原文例句」", "abstract": "「抽象模板」", "scenario": "「适用场景」"}
  ],
  "diff_requirements": {
    "do_not_copy": ["「不可复制项」"],
    "replace_with": ["「替换建议」"],
    "adapt_to": "「适配方向」"
  }
}

字段说明:

  • hook.technique:从以下手法选最匹配的——身份反转/意外撞见/危机开场/金句/反常情境/震撼对话/倒计时/其他
  • structure.acts:始终填 5 幕(开场/展开/转折/高潮/收束),字数不足的短篇可将相邻幕合并,但保留 5 个条目
  • rhythm.segments:按自然段落标注,至少 3 条
  • characters:至少填主角和重要配角,archetype 用简短原型标签(如"嘴硬心软女主""外冷内热男主")
  • patterns:至少 3 条
  • templates:至少 5 条,覆盖开篇钩子/悬念铺设/情绪转折/对话推进/结尾收束
2b. 拆解报告.md

中文可读报告,固定章节:

markdown
# 拆解报告:《文章名》

## 基本信息
- 类型:言情
- 字数:约X万
- 叙事视角:

## 剧情概要(200-300字)

## 开场钩子分析

## 结构骨架

| 阶段 | 章节 | 功能 |
|------|------|------|

## 悬念设计

## 节奏控制

## 情绪曲线

## 人物塑造

## 结尾分析

## 可借鉴模式(≥3条)

## 差异化要求
- 不可重写:
- 替换建议:
- 适配方向:
2c. 节奏统计.md
markdown
# 节奏统计:《文章名》

## 全文节奏公式
钩(X字)→铺(X字)→展(X字)→转(X字)→爆(X字)→收(X字)

## 快/中/慢比例
- 快节奏(<500字/段):X段,占X%
- 中节奏(500-1500字/段):X段,占X%
- 慢节奏(>1500字/段):X段,占X%

## 段落明细
| 段号 | 起止位置 | 字数 | 节奏标签 | 情绪标签 | 功能 |
|------|---------|:----:|---------|---------|------|
2d. 句式模板.md
markdown
# 句式模板:《文章名》

至少 5 条,覆盖不同场景:

| 原文例句 | 抽象模板 | 适用场景 |
|---------|---------|---------|
| 「原文」 | 「模板」 | 「场景」 |

Step 3:写入文件

5 个文件全部输出到 短篇/参考书/{类型}/{文章}/:

├── 原文.md           — 清洗后的原文,UTF-8 无 BOM
├── 拆解报告.md        — 中文可读报告(2b 格式)
├── 拆解数据.json      — 结构化数据(2a 模板填充)
├── 节奏统计.md        — 段落级节奏量化数据(2c 格式)
└── 句式模板.md        — 可复用句式模板(2d 格式)

Step 4:验证

写入完成后,必须验证:

  • 原文.md 存在且非空
  • 拆解报告.md 存在且包含全部 11 个章节标题
  • 拆解数据.json 存在且包含全部必填字段(与 2a 模板对照)
  • 节奏统计.md 存在且含节奏公式
  • 句式模板.md 存在且 ≥5 条模板

缺少任一文件或字段 → 补充后重新验证。

Frequently asked questions

What does the Shortstory Deconstruct AI skill do?

拆解盐选短篇参考文,提取钩子设计、悬念铺设、节奏控制、收束手法等写作模式。触发词:拆这篇、拆解、分析这个短篇、做拆解、帮我把这篇拆了、提取模式

Why use Shortstory Deconstruct on TypingMind?

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

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

Which AI models can use Shortstory 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 Shortstory Deconstruct?

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

Is the Shortstory 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

Set up your own AI workspace now

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