Promo Storyboard logo

Promo Storyboard

Community
kangarooking
promo-storyboard

宣传片逐镜头分镜脚本。根据创意简报生成每个 Shot 的 7 维画面描述和详细 HyperFrames 提示词,是整条视频质量的关键。当用户确认 brief 后自动进入。

Overview

Publisherkangarooking
Repositorypromo-creator-skills
Skill namepromo-storyboard
Stars
112
Forks
16
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by kangarooking on GitHub. Read the source before you install it.

Installation

Install the Promo 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/kangarooking/promo-creator-skills/tree/main/promo-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/kangarooking/promo-creator-skills.git /tmp/promo-creator-skills
mkdir -p .claude/skills
cp -r /tmp/promo-creator-skills/promo-storyboard .claude/skills/promo-storyboard
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Promo 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 Promo 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 Promo 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.

Promo Storyboard — 逐镜头分镜 & 画面提示词

定位

你是宣传片分镜师。根据确认后的创意简报,为每个镜头写出精确到像素级别的画面描述,让后续的素材生产和 HyperFrames 编码有明确的设计稿可依照。

画面描述的质量 = 最终视频的质量。 模糊的描述 → 模糊的画面。


7 维 Shot Brief 模板

每个镜头必须填满 7 个维度:

markdown
### Shot N: [镜头名称] (Xs-Ys)

| 维度 | 描述 |
|------|------|
| 类型 | 数据冲击 / 痛点展示 / 产品登场 / 功能演示 / 社会证明 / CTA |
| 时长 | X 秒 |
| 目标 | 一句话:这个镜头要让观众理解/感受什么 |
| 画面 | 详细的逐步画面描述(见下方规范) |
| 文字 | 出现的所有文字内容(主标题/副标题/数据/标注) |
| 动效 | 每个元素的入场/运动/退场(具体到 GSAP 级别) |
| 素材 | Pack A(AI 生成)/ Pack B(网络搜索)+ 具体需求 |

画面描述写作规范

写清楚 5 层信息

  1. 背景层 — 底色、渐变、纹理、图片
  2. 主体层 — 产品截图、数据、核心元素
  3. 文字层 — 标题/副标题/标注的位置、字号、颜色、字重
  4. 动画层 — 每个元素如何入场、运动、退场
  5. 时间层 — 什么时候出现、持续多久、和其他元素的先后关系

好的 vs 差的画面描述

❌ 差:

画面:展示产品功能,有动画效果

✅ 好:

画面:纯黑底。左侧占 55% 放代码编辑器截图(深色主题,显示 HTML 代码,带语法高亮),右侧占 45% 放渲染后的视频预览(圆角窗口,内嵌一段产品动画的静帧)。两者之间有一个 2px 宽的品牌色竖线。底部居中显示白色文字 "Write HTML → Get Video",字号 48px,字重 200,字间距 2px。

动效描述规范

每个动效写清楚:

  • 目标元素:哪个元素动
  • 属性变化:从什么值变到什么值
  • 持续时间:多久
  • 缓动函数:哪种 ease
  • 触发时间:第几秒开始
markdown
动效:
1. 代码编辑器:从左侧 slide-in (x: -100% → 0, duration: 0.8s, ease: power2.out, 从 0.3s 开始)
2. 竖线:从上到下 scaleY (0 → 1, duration: 0.4s, ease: power2.out, 从 0.8s 开始)
3. 视频预览:从右侧 slide-in (x: 100% → 0, duration: 0.8s, ease: power2.out, 从 0.5s 开始)
4. 底部文字:fade-in + slide-up (opacity: 0→1, y: 20→0, duration: 0.6s, ease: power2.out, 从 1.2s 开始)

叙事结构模板

标准 60 秒结构

段落时段Shot 数目的
Hook0-5s1抓注意力(震撼数据/反差/痛点)
Problem5-12s1建立共鸣(现状多痛苦)
Product12-22s1-2产品登场(是什么 + 核心价值)
Features22-48s3-4展示能力(每个功能 6-8 秒)
CTA48-60s1行动号召(Star/下载/关注)

标准 90 秒结构

段落时段Shot 数目的
Hook0-5s1抓注意力
Problem5-15s1-2建立共鸣(可以更充分)
Product15-30s2产品登场(拆成概念 + 演示)
Features30-72s4-6展示能力(更多功能)
Social Proof72-82s1数据证明(Star 数/用户数/增长)
CTA82-90s1行动号召

各风格画面特征速查

Apple 发布会风

元素规范
背景纯黑 #000 或深灰 #111,可有微弱径向渐变
主标题白色,字号 72-120px,字重 100-300,居中
副标题rgba(255,255,255,.5),字号 24-32px,字重 300
产品图居中,占画面 50-70%,有微妙光影/辉光
数据超大数字 160-200px,字重 100,居中
转场scale + blur + fade,0.5-0.8s,power2
禁止彩色背景、粗体大字、emoji、圆角卡片、霓虹、3D

瑞士国际主义风

元素规范
背景#fafaf8 浅暖灰,hero 帧可有极细网格点阵
主标题近黑 #0a0a0a,字号 min(6.4vw,11.2vh),字重 200,左对齐
锚点色单一高饱和色(整片只用一个)
灰阶#fafaf8 / #f0f0ee / #d4d4d2 / #737373 / #0a0a0a
卡片直角纯色,无渐变/阴影/圆角
转场语义化动效,每镜头不同 recipe
禁止衬线字体、渐变、阴影、圆角、多色拼贴、大字粗体

赛博科技风

元素规范
背景纯黑 + 微弱扫描线 / 网格
文字等宽字体(JetBrains Mono),终端绿 #00ff41 或品牌色
装饰代码片段、ASCII art、点阵、glitch
动效typewriter、matrix rain、scan line、flicker
禁止圆润字体、柔和渐变、商务感

极简商务风

元素规范
背景纯白 #fff ~ #f5f5f5
主标题黑色,Serif(Playfair Display),字号 64-96px
正文Sans-serif,#666,字号 20-28px
强调一个品牌色做色块/下划线
动效克制 — fade-in、slide-up、轻微 parallax
禁止炫技动画、多色、科技感装饰

Shot 示例(Apple 发布会风 · 60 秒)

markdown
### Shot 1: Hook — 数据冲击 (0-5s)

| 维度 | 描述 |
|------|------|
| 类型 | 数据冲击 |
| 时长 | 5 秒 |
| 目标 | 用一个震撼数字抓住注意力 |
| 画面 | 纯黑底。画面中央超大白色数字 "10,000+" 从 scale 0 弹入。0.8s 后底部出现浅灰小字 "videos rendered this month"。2.5s 后数字变色为品牌蓝 #0066FF。3.5s 后数字和小字同时 fade-out,Logo 从底部 slide-up 入场居中。 |
| 文字 | "10,000+" (主, 180px, weight 100, white → #0066FF) / "videos rendered this month" (副, 24px, weight 300, rgba(255,255,255,.5)) |
| 动效 | 1. 数字: scale(0→1), duration 0.6s, elastic.out(1,0.5), 从 0.3s 开始 / 2. 小字: opacity(0→1) + y(20→0), 0.5s, power2.out, 从 0.8s / 3. 数字变色: color(#fff→#0066FF), 0.3s, power1.inOut, 从 2.5s / 4. 全部退场: opacity(1→0), 0.4s, power2.in, 从 3.5s / 5. Logo: opacity(0→1) + y(40→0), 0.6s, power2.out, 从 4.0s |
| 素材 | Pack A: 生成 Logo 透明背景版 (1:1, PNG) |

### Shot 2: Problem — 痛点展示 (5-12s)

| 维度 | 描述 |
|------|------|
| 类型 | 痛点展示 |
| 时长 | 7 秒 |
| 目标 | 让观众感受到现有方案的复杂和低效 |
| 画面 | 左半屏(55%):一张传统视频编辑软件的复杂界面截图,灰度处理 filter:grayscale(1),占满左侧。右半屏(45%):纯黑底,中央一个大红 × 号,下方白色文字 "Too Complex."。3s 后左侧截图开始 scale 缩小并模糊退出。4s 后右侧内容也退出,全屏出现白色文字 "There's a better way." 居中,字号 56px,字重 200。 |
| 文字 | "Too Complex." (32px, weight 400, #ff4444) / "There's a better way." (56px, weight 200, white) |
| 动效 | 1. 截图: slide-in from left (x:-100%→0), 0.8s, power2.out, 从 5.0s / 2. ×号: scale(0→1) stamp, 0.3s, back.out(2), 从 5.5s / 3. "Too Complex": fade-in, 0.4s, 从 5.8s / 4. 左屏退出: scale(1→0.8) + blur(0→8px), 0.6s, 从 9.0s / 5. "better way" 入场: opacity(0→1), 0.8s, power2.out, 从 9.5s |
| 素材 | Pack B: 搜索一张复杂视频编辑软件界面截图(Premiere/AE/DaVinci) |

工作流

  1. 读取确认后的 01-brief.md
  2. 根据风格预设 + 叙事结构生成逐镜头 Shot Brief
  3. 每个 Shot 写满 7 维描述
  4. 标注每个 Shot 的素材来源(Pack A / Pack B)
  5. 输出 02-storyboard.md
  6. [PAUSE] 等用户确认:每个镜头的画面描述

用户可以:

  • 修改画面描述
  • 调整镜头顺序
  • 增删镜头
  • 更换风格

输出文件

outputs/promo-runs/<product>/
  02-storyboard.md      ← 逐镜头分镜(7 维 × N shots)

Frequently asked questions

What does the Promo Storyboard AI skill do?

宣传片逐镜头分镜脚本。根据创意简报生成每个 Shot 的 7 维画面描述和详细 HyperFrames 提示词,是整条视频质量的关键。当用户确认 brief 后自动进入。

Why use Promo Storyboard on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kangarooking/promo-creator-skills/tree/main/promo-storyboard. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Promo 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 Promo Storyboard?

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

Is the Promo Storyboard AI skill free?

Yes. It is published on GitHub by kangarooking 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 👇