Script To Storyboard logo

Script To Storyboard

Community
SwotAtmk
script-to-storyboard

将完整的剧本、故事大纲或小说片段拆解为细化到单镜的中文分镜脚本,覆盖镜头号、景别、机位运镜、画面描述、台词、音效、时长标注,并为每个镜头附可直接用于图片或视频生成的提示词。支持抖音竖屏短视频与横屏影视微电影两种形态,按剧本气质自动判断或向用户确认。当用户给出剧本/大纲/小说并要求「拆分镜」「做分镜脚本」「出分镜表」「storyboard」时使用。

Overview

PublisherSwotAtmk
Repositoryinfinite-creation
Skill namescript-to-storyboard
Stars
112
Forks
30
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 SwotAtmk on GitHub. Read the source before you install it.

Installation

Install the Script To Storyboard 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/SwotAtmk/infinite-creation/tree/main/skills/script-to-storyboard
  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/SwotAtmk/infinite-creation.git /tmp/infinite-creation
mkdir -p .claude/skills
cp -r /tmp/infinite-creation/skills/script-to-storyboard .claude/skills/script-to-storyboard
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Script To Storyboard 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 Script To Storyboard 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 Script To Storyboard 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.

剧本转分镜

把一份已经写完的剧本,翻译成导演能逐镜执行的分镜脚本。核心交付物是一份分镜脚本文档,不是图片或视频。

核心原则

思维引擎(因果链):

剧本 → 提炼叙事弧(起承转合/钩子反转) → 确定形态与平台 → 切分场次 → 逐镜拆解(景别+运镜+画面+台词+音效+时长) → 每镜附生成提示词 → 静默自检 → 交付分镜文档

一句话质量测试:把分镜文档直接交给一位没读过原剧本的导演,他不需要再问任何"这里发生了什么"的问题,就能开拍。 若某个镜头删掉后故事依然成立且不损失情绪,说明该镜头是冗余,应删除。

铁律:

  1. 分镜必须忠实于剧本,不擅自增删情节、不改人物动机;只做"翻译",不做"改写"。
  2. 台词原样搬运,不润色、不缩写。
  3. 每镜都有存在的理由:交代信息、推进情绪或制造节奏,三者必居其一。

输入

必需:

  • 剧本/故事大纲/小说片段(用户文字、上传文件或引用的画布文本节点,任一形式)

可选(缺失时只追问缺失项,剧本信息里能推断的不要重复问):

  • 画幅与平台:未指定时,先按剧本气质判断——对话密集、强钩子、生活化题材 → 9:16 竖屏短视频;场景宏大、多人物调度、电影感强 → 16:9 横屏影视;判断模糊时询问用户。
  • 总时长或集数:未指定时按叙事弧自动规划,单镜头默认 3-8 秒。
  • 每镜是否生成参考图:默认不生成,仅用户要求时执行。

输入诊断

拆分镜前逐项明确(剧本里已有答案的直接取用,没有的合理假设并在文档开头注明"默认假设"):

  1. 体裁:短剧 / 短视频剧情 / 微电影 / 广告剧情 / MV 叙事
  2. 画幅与平台:9:16 竖屏(抖音/快手)或 16:9 横屏(影视感/横屏平台)
  3. 叙事弧:钩子(前 3 秒)→ 铺垫 → 冲突/转折 → 高潮 → 结尾状态
  4. 场景清单:每个场景的地点、时间、光线条件
  5. 人物清单:出场人物、造型关键特征、相互关系(用于跨镜一致性提示词)
  6. 情绪曲线:每场戏的情绪温度,决定镜头密度与节奏
  7. 预估总时长与镜头总数(时长 ÷ 5 秒 ≈ 镜头数)
  8. 声音设计:台词、旁白、音效点、音乐进出
  9. 合规敏感点:涉及暴力、医疗、金融等表述在提示词中使用正向护栏措辞

工作流

第一步:通读与拆弧

通读剧本,提炼:一句话故事、叙事弧五段、场景清单、人物清单、情绪曲线。此步不输出给用户,仅内部完成。

第二步:切分场次

按地点或情绪转折切分场次,为每场标注:场景、时间、光线、在场人物、本场任务(信息/情绪/节奏)、预估时长。

第三步:逐镜拆解

每场内部按"本场任务"拆到单镜。每个镜头必须包含输出契约的全部字段。拆镜口诀:

  • 交代用全景,情绪用特写:新场景首个镜头给全景定空间关系;情绪峰值给面部或物件特写。
  • 一个镜头只干一件事:不要让一个镜头同时推进两个动作。
  • 动作用切分,氛围用长镜:动作戏短镜头快切(2-4 秒),氛围铺垫可用 5-8 秒长镜。
  • 台词配反应:谁说话给谁镜头,台词的"杀伤力"用听者的反应镜头呈现。

第四步:写每镜生成提示词

为每个镜头写可直接用于图片/视频生成的提示词段落(字段见输出契约),要求:

  • 画面要素齐全:主体+动作+景别+机位/运镜+光线+色调+场景细节。
  • 人物外貌特征在每条提示词中完整重复,不写"同上一镜"。
  • 提示词中不出现镜头号、时间轴等元信息,只写画面内容。

第五步(可选):生成参考图

仅当用户要求时,用第四步的提示词为关键镜头生成参考图作为分镜示意;默认跳过此步。

第六步:静默自检后交付

按"静默自检"逐条核对,弱项直接重写,然后输出分镜文档。

输出契约

分镜文档结构(中文,Markdown):

markdown
# 《剧作名》分镜脚本

## 概览
- 形态:竖屏短视频 / 横屏影视 | 画幅:9:16 / 16:9
- 预估总时长:XX 秒 | 镜头总数:XX
- 叙事弧:钩子(S1) → 铺垫(S2) → 转折(S3) → 高潮(S4) → 结尾(S5)
- 人物关键特征(供跨镜一致性):姓名:外貌描述三句内
- 默认假设:此处列出第三步无法从剧本推断、已自行假设的项

## 第 X 场:场景名(地点·时间·光线)
本场任务:一句话 | 情绪:X/10 | 预估 XX 秒

### 镜头 X-1 | 景别 | 运镜 | 时长 X 秒
- 画面:具体可视的画面描述,谁在做什么、镜头怎么动、光线如何
- 台词/旁白:原剧本台词,标注说话人;无台词写"无"
- 音效/音乐:音效点与音乐进出
- 情绪与节奏:本镜在情绪曲线上的位置
- 生成提示词:主体 + 动作 + 景别 + 机位运镜 + 光线色调 + 场景细节(不写元信息,人物特征完整重复)

字段硬规则:

  • 景别只用五档:远景 / 全景 / 中景 / 近景 / 特写
  • 运镜从固定、推、拉、摇、移、跟、环绕、升降中选,一镜最多两种组合
  • 竖屏短视频:首镜 3 秒内出现钩子;横屏影视:允许 5-8 秒的空间铺垫开镜
  • 时长标注为整数秒,单镜 2-8 秒;总时长 = 各镜时长之和

静默自检

交付前逐条核对,不过关就重写,不向用户展示清单:

  1. 抽查 3 个镜头做"导演测试":只看分镜能否还原剧情,不回看剧本。
  2. 台词是否与剧本逐字一致。
  3. 每镜时长与总时长是否自洽,镜头数是否与预估匹配。
  4. 提示词是否可直接使用:无"上一镜""同前"等相对引用,人物特征完整。
  5. 竖屏/横屏判断与剧本气质是否匹配,首镜是否符合平台节奏(竖屏 3 秒钩子)。
  6. 敏感措辞是否已替换为正向护栏表述。
  7. 概览的"默认假设"是否全部列出。

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 Script To Storyboard AI skill do?

将完整的剧本、故事大纲或小说片段拆解为细化到单镜的中文分镜脚本,覆盖镜头号、景别、机位运镜、画面描述、台词、音效、时长标注,并为每个镜头附可直接用于图片或视频生成的提示词。支持抖音竖屏短视频与横屏影视微电影两种形态,按剧本气质自动判断或向用户确认。当用户给出剧本/大纲/小说并要求「拆分镜」「做分镜脚本」「出分镜表」「storyboard」时使用。

Why use Script To Storyboard on TypingMind?

Because you install it once and use it with any model. Script To Storyboard 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 Script To Storyboard in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/SwotAtmk/infinite-creation/tree/main/skills/script-to-storyboard. 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 Script To Storyboard?

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 Script To Storyboard?

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

Is the Script To Storyboard AI skill free?

Yes. It is published on GitHub by SwotAtmk 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 👇