Storyboard Breaker logo

Storyboard Breaker

OrganizationPopular
chatfire-AI
storyboard-breaker

分镜拆解专业规范 — 将剧本拆分为可承载多个子镜头的分镜段落

Overview

Publisherchatfire-AI
Repositoryhuobao-drama
Skill namestoryboard-breaker
Stars
15.3K
Forks
2.8K
Bundled files
3
Links
Skill sourceRepository
  • 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.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by chatfire-AI on GitHub. Read the source before you install it.

Installation

Install the Storyboard Breaker 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.
  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/chatfire-AI/huobao-drama.git /tmp/huobao-drama
mkdir -p .claude/skills
cp -r /tmp/huobao-drama/backend/workspace/skills/storyboard-breaker .claude/skills/storyboard-breaker
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Storyboard Breaker 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 Storyboard Breaker 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 Storyboard Breaker 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.

分镜拆解指南

核心定义：分镜段落

一个分镜 = 一个 分镜段落（segment）= 一个视频生成任务。

  • 每个段落时长 8-15 秒，内部承载 2-4 个子镜头
  • 子镜头之间可以切镜：换景别、换角度、换拍摄对象，用硬切衔接
  • 子镜头之间不跨场景：一个段落只发生在一个场景内（scene_id 是段落级绑定）
  • 每个子镜头 2-6 秒，聚焦一个画面单元（一个动作、一个反应、一个特写）

拆分流程（四步）

  1. 调用 read_storyboard_context 读取剧本、角色、场景、道具、已有分镜摘要
  2. 节拍识别：先识别剧本的叙事节拍——剧本中的【开场】【触发】【高潮】【收尾】等标记，或叙事转折点（地点转移、规则揭示、情绪爆发、反转）。节拍边界强制切段，同一节拍内的子镜头优先归入同一段落，不把一条因果链（铺垫-发生-反应）切散到不同段落
  3. 总量锚定：目标总时长 = 剧本字数 ÷ 500字/分钟；段落数 ≈ 目标总时长 ÷ 12秒，允许 ±20% 浮动。不要明显超出或不足
  4. 段落内拆子镜头：按动作切换点、视角切换点、对象切换点切分子镜头，为每个段落补全完整字段后调用 save_storyboards 一次性保存

节奏分层时长

按段落功能确定时长，不要一刀切：

段落类型时长说明
过渡段8-10 秒赶路、空镜、环境建立、转场
叙事段10-15 秒常规剧情推进、对话
爆点段12-15 秒特写、规则揭示、情感爆发、反转；子镜头节奏放慢，单个子镜头可停留 4-6 秒

台词时长下限（硬规则）

段落时长 ≥ 段内台词与旁白总字数（写在 description 中的部分）÷ 4.5字/秒 + 2秒表演余量

装不下的台词必须拆到下一个段落，不允许把演不完的台词塞进一个段落。

镜头要素

  1. 镜头标题：3-5字概括段落核心内容（如"噩梦惊醒"）
  2. 时间：具体时分 + 光线描述
  3. 地点：场景完整描述 + 空间布局 + 环境细节
  4. 景别：段落内主导景别；多景别段落写组合，如"中景+特写"
  5. 角度：平视/仰视/俯视/侧面/背面
  6. 运镜：固定/推镜/拉镜/摇镜/跟镜/移镜（段落内不同子镜头可不同）
  7. 画面描述 description：按 【镜头1】…【镜头2】… 逐子镜头描述观众实际看到和听到的内容——画面（谁 + 具体动作 + 肢体细节 + 表情）写在前；该子镜头有台词时以「角色名说：「台词」」写在对应 【镜头N】 内，旁白写「旁白：内容」
  8. 画面结果 result：段落结尾的即时后果 + 视觉细节
  9. 氛围 atmosphere：光线 + 色调 + 声音 + 整体氛围
  10. 时长 duration：段落总时长 8-15 秒，且满足台词时长下限
  11. 场景关联：若能匹配已有场景，必须填写 scene_id
  12. 角色关联：填写 character_ids，绑定当前段落涉及的 0 到多个角色
  13. 道具关联：填写 prop_ids，绑定当前段落出现的关键道具（0 到多个）

场景关联规则

  • 优先使用 read_storyboard_context 返回的 scenes
  • location + time 可明确匹配时，必须回填正确 scene_id
  • 不要凭空生成不存在的场景 ID
  • 如果剧本内容明显落在已有场景中，不要重复创造新场景描述

角色绑定规则

  • character_ids 必须从 read_storyboard_context 返回的角色列表中选择
  • 一个段落可以没有角色，也可以绑定多个角色
  • 只要段落里有明确出场、被看见、发生动作或说话的角色，都应绑定进去
  • 纯环境段落、空镜、物件特写可以传空数组

道具绑定规则

  • prop_ids 必须从 read_storyboard_context 返回的道具列表（props）中选择
  • 道具被角色使用、交接、特写，或在画面中明显可见且对叙事有意义时，必须绑定到该段落
  • 道具特写段落（无角色）也应绑定道具，character_ids 可为空
  • 与剧情无关的背景物品、场景陈设不要绑定；没有道具出现的段落传空数组
  • 绑定的道具会作为视频生成的参考图（白底单品图），保证道具外观跨段落一致

质量要求

  • description 要适合人读，按子镜头详细描述观众实际看到和听到的内容；台词/旁白直接写在对应 【镜头N】 内
  • image_prompt 要突出单帧构图、角色外观、环境和光线（对应段落第一个子镜头）
  • bgm_prompt 和 sound_effect 用简洁短语即可，但不能空泛到只有“紧张”“悲伤”
  • 如需调整，调用 update_storyboard 修改具体段落

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 Storyboard Breaker AI skill do?

分镜拆解专业规范 — 将剧本拆分为可承载多个子镜头的分镜段落

Why use Storyboard Breaker on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/chatfire-AI/huobao-drama/tree/master/backend/workspace/skills/storyboard-breaker. 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 Storyboard Breaker?

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 Storyboard Breaker?

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

Is the Storyboard Breaker AI skill free?

It is published on GitHub by chatfire-AI. Check the repository for licensing terms. 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.

Related AI Skills

View all
sickn33 logo

Advogado Criminal

sickn33
CommunityPopular

Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal.

6.8K
46.5K
1 files
View
sickn33 logo

Advogado Especialista

sickn33
CommunityPopular

Advogado especialista em todas as areas do Direito brasileiro: familia, criminal, trabalhista, tributario, consumidor, imobiliario, empresarial, civil e constitucional.

6.8K
46.5K
2 files
View
wshobson logo

Cqrs Implementation

wshobson
CommunityPopular

Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.

4.2K
39.8K
1 files
View
Yeachan-Heo logo

Hud

Yeachan-Heo
CommunityPopular

Configure HUD display options (layout, presets, display elements)

3.5K
39.2K
Instructions
View

Set up your own AI workspace now

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