film-storyboard-skill
Converts scripts into visual storyboard prompts using a three-step breakdown process.
Install
mkdir -p .claude/skills/film-storyboard-skill && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16175" && unzip -o skill.zip -d .claude/skills/film-storyboard-skill && rm skill.zipInstalls to .claude/skills/film-storyboard-skill
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
影视分镜生成技能。将剧本转化为可用于 AI 出图的分镜提示词。采用分层渐进式流程:节拍拆解 → Beat Board(九宫格)→ Sequence Board(四宫格)。Key capabilities
- →Break down scripts into narrative anchors (Beat Breakdown)
- →Generate nine-grid Beat Board prompts for AI image generation
- →Create four-grid Sequence Board prompts for detailed actions
- →Ensure character and scene consistency across generated images
- →Integrate visual style and cinematography terms into prompts
How it works
The skill converts scripts into storyboard prompts for AI image generation using a layered, progressive workflow. It breaks down narrative beats, generates nine-grid prompts, and then expands them into four-grid sequence prompts, ensuring consistency.
Inputs & outputs
When to use film-storyboard-skill
- →Convert script into storyboard
- →Generate visual prompts for a film scene
- →Maintain character consistency in AI imagery
About this skill
影视分镜生成技能
必读
../../references/00-first-principles.md../../references/08-camera-and-cinematography.md../../references/09-storyboard-methodology.md
技能说明
影视分镜生成技能,将剧本、故事梗概或分场大纲转化为可用于 AI 出图的分镜提示词。采用分层渐进式流程:先进行节拍拆解识别叙事锚点,再生成 Beat Board 九宫格提示词,最后为每个锚点生成 Sequence Board 四宫格提示词展开段落动作。四宫格生成时以九宫格对应格作为参考图片(垫图),确保人物与场景一致性。
输入
- 剧本/梗概/分场文本
- 视觉风格(默认:真人风格,可被用户覆盖)
输出
beat-breakdown.md— 节拍拆解表beat-board.md— Beat Board 九宫格提示词(9格)sequence-board.md— Sequence Board 四宫格提示词(每个 Beat Anchor 一组,共 9 组 36 格)
执行流程
第一步:生成节拍拆解表
理解输入:
- 读取用户提供的剧本/梗概/分场文本
- 确认视觉风格(默认:真人风格,可被用户覆盖)
节拍拆解:
- 识别叙事曲线的关键拐点
- 创建 beat-breakdown.md,将节拍拆解表写入
第二步:生成 Beat Board 九宫格提示词
读取上游产物:
- 读取 beat-breakdown.md
生成 Beat Board 提示词:
- 将 Beat Anchor 转化为九宫格提示词
- 提示词采用叙事描述式,参考
references/11a-seedance-prompt-methodology.md的模板与示例 - 创建 beat-board.md,将九宫格提示词写入
第三步:生成 Sequence Board 四宫格提示词
读取上游产物:
- 读取 beat-board.md
生成 Sequence Board 提示词:
- 为每个 Beat Anchor 生成一组四宫格提示词
- 必须继承九宫格对应格的人物/场景/光色描述
- 提示词采用叙事描述式,参考
references/11a-seedance-prompt-methodology.md的模板与示例 - 创建 sequence-board.md,将四宫格提示词写入
分镜核心原则
一致性优先原则
- 四宫格提示词必须继承九宫格对应格的人物/场景/光色描述
- 发生变化必须显式说明原因
连贯性检查原则
- 参考
references/09-storyboard-methodology.md连贯性与剪接相关规则
工程约束原则
- 九宫格用于"选点与定锚",生成后作为四宫格的参考图片(垫图)
- 四宫格生成时,使用九宫格对应格作为参考图片输入
节拍拆解(Beat Breakdown)
目的
识别叙事曲线的关键拐点,为分镜提供叙事锚点。
输出格式
| Beat Anchor | 叙事目的 | 情绪 | 时长估算 |
|---|---|---|---|
| B1 | [叙事目的] | [情绪] | [时长] |
| B2 | [叙事目的] | [情绪] | [时长] |
| ... | ... | ... | ... |
| B9 | [叙事目的] | [情绪] | [时长] |
拆解原则
- 识别 9 个关键拐点(Beat Anchor)
- 每个 Beat Anchor 对应一个叙事目的和情绪
- 时长估算用于后续动态提示词生成
Beat Board 九宫格提示词
目的
为 9 个 Beat Anchor 生成九宫格提示词,用于 AI 出图。
输出格式
## Beat Board 九宫格提示词
请生成一张 3×3 九宫格布局的电影分镜图像。每个格子代表一个关键叙事节点(Beat Anchor),所有格子必须保持视觉风格统一。请按照以下规范生成。
### 视觉规范
整体风格:[描述整体美术风格]
色彩基调:[描述全片色彩倾向]
材质质感:[描述关键材质表现要求]
### 宫格布局
第1行:格1-3 / 第2行:格4-6 / 第3行:格7-9
### Panel Breakdown(分镜拆解)
格1——【B1: [叙事目的]】
视角:[完整叙事描述:景别、环境、人物、动作、光线、色调、氛围,融合为流畅段落]
重点:[这个格子的核心视觉元素]
格2——【B2: [叙事目的]】
视角:[完整叙事描述]
重点:[核心视觉元素]
...(共 9 格)
提示词写法原则
- 叙事描述式:用完整段落描述,不要关键词堆叠
- 具体化:所有描述必须具体到可视化的程度
- 摄影术语融入自然语言
- 情绪通过视觉细节传达,不要抽象描述
Sequence Board 四宫格提示词
目的
为每个 Beat Anchor 生成一组四宫格提示词,展开段落动作。
输出格式
## Sequence Board 四宫格提示词
### B1 四宫格展开
请生成一张 2×2 四宫格布局的电影分镜图像。这组四宫格展开 Beat Anchor B1 的段落动作,所有格子必须保持视觉风格统一,并与九宫格格1保持一致。请按照以下规范生成。
**参考图片**:九宫格格1(作为垫图输入)
#### 视觉规范
继承九宫格格1的:[人物外观、场景环境、光线色调]
#### 宫格布局
第1行:格1-2 / 第2行:格3-4
#### Panel Breakdown(分镜拆解)
格1——【[动作描述]】
视角:[完整叙事描述:景别、人物、动作、光线、色调、氛围]
重点:[核心视觉元素]
格2——【[动作描述]】
视角:[完整叙事描述]
重点:[核心视觉元素]
格3——【[动作描述]】
视角:[完整叙事描述]
重点:[核心视觉元素]
格4——【[动作描述]】
视角:[完整叙事描述]
重点:[核心视觉元素]
---
### B2 四宫格展开
...(共 9 组)
提示词写法原则
- 必须继承九宫格对应格的人物/场景/光色描述
- 发生变化必须显式说明原因
- 叙事描述式,不要关键词堆叠
- 具体化,所有描述必须具体到可视化的程度
成功标准
- 节拍拆解识别 9 个关键拐点,每个有明确的叙事目的和情绪
- Beat Board 九宫格提示词包含所有必需元素(景别、环境、人物、动作、光线、色调、氛围)
- Sequence Board 四宫格提示词继承九宫格对应格的人物/场景/光色描述
- 所有提示词采用叙事描述式,不使用关键词堆叠
- 所有描述具体到可视化程度
- 视觉风格统一,光影逻辑自洽
- 四宫格生成时使用九宫格对应格作为参考图片(垫图)
- 每个提示词可直接用于 AI 出图工具生成分镜
When not to use it
- →When the output is not intended for AI image generation
- →When a non-layered, non-progressive workflow is preferred
Limitations
- →The skill generates film storyboards.
- →The skill converts scripts into storyboard prompts for AI image generation.
How it compares
This skill automates the conversion of scripts into AI-ready storyboard prompts using a structured, multi-stage process that maintains visual consistency, unlike manual prompt creation or single-stage generation.
Compared to similar skills
film-storyboard-skill side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| film-storyboard-skill (this skill) | 0 | 3mo | No flags | Intermediate |
| applying-brand-guidelines | 8 | 8mo | Review | Beginner |
| baoyu-xhs-images | 20 | 2mo | No flags | Beginner |
| meme-factory | 5 | 6mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
applying-brand-guidelines
anthropics
This skill applies consistent corporate branding and styling to all generated documents including colors, fonts, layouts, and messaging
baoyu-xhs-images
JimLiu
Generates Xiaohongshu (Little Red Book) infographic series with 10 visual styles and 8 layouts. Breaks content into 1-10 cartoon-style images optimized for XHS engagement. Use when user mentions "小红书图片", "XHS images", "RedNote infographics", "小红书种草", or wants social media infographics for Chinese platforms.
meme-factory
davila7
Generate memes using the memegen.link API. Use when users request memes, want to add humor to content, or need visual aids for social media. Supports 100+ popular templates with custom text and styling.
baoyu-comic
JimLiu
Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and sequential image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".
brand-strategy
jeremylongshore
A 7-part brand strategy framework for building comprehensive brand foundations. Trigger with phrases like "create brand strategy", "build brand brief", "define brand positioning", "brand messaging", "audience architecture", "brand truth", or "go-to-market brand plan".
baoyu-cover-image
JimLiu
Generates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining 9 color palettes and 6 rendering styles. Supports cinematic (2.35:1), widescreen (16:9), and square (1:1) aspects. Use when user asks to "generate cover image", "create article cover", or "make cover".