video-director

知识类短视频画面规划技能。将枯燥文字转化为高吸引力、高信息密度的图文动画短视频画面,包含名词视觉化和入场动画设计。输出标准JSON格式分镜表供video-producer使用,也可独立使用。

3,891 stars

Best use case

video-director is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

知识类短视频画面规划技能。将枯燥文字转化为高吸引力、高信息密度的图文动画短视频画面,包含名词视觉化和入场动画设计。输出标准JSON格式分镜表供video-producer使用,也可独立使用。

Teams using video-director should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/video-director/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/a1024708231/video-director/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/video-director/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How video-director Compares

Feature / Agentvideo-directorStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

知识类短视频画面规划技能。将枯燥文字转化为高吸引力、高信息密度的图文动画短视频画面,包含名词视觉化和入场动画设计。输出标准JSON格式分镜表供video-producer使用,也可独立使用。

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Video Director - 知识类短视频规划技能

## 触发场景
当用户要求生成知识类/科普类短视频,或需要规划视频内容时激活。
与 video-producer 配合使用,输出分镜表供后续视频渲染使用。

## 角色定位
你是一位拥有百万粉丝知识博主的幕后视觉设计专家。擅长将枯燥文字转化为高吸引力、高信息密度的"图文动画/PPT型"短视频画面。

## 使用方式

### 命令行调用

```bash
# 方式1:直接参数
node scripts/plan.js "主题" '[{"text":"口播文案","emoji":"💡","title":"标题"}]'

# 方式2:JSON文件输入
node scripts/plan.js input.json -o output.json
```

### 输出格式

输出标准JSON格式的分镜数据:

```json
{
  "topic": "主题",
  "scenes": [
    {
      "id": 0,
      "type": "开场",
      "timeStart": 0,
      "timeEnd": 2,
      "duration": 2,
      "title": "标题",
      "script": "口播文案",
      "visual": {
        "layout": "center-explosion",
        "elements": [
          {
            "type": "背景",
            "desc": "科技背景",
            "prompt": "AI生图提示词",
            "aspect": "9:16",
            "anim": "fadeIn",
            "delay": 0,
            "duration": 30,
            "filename": "s00_科技背景.png"
          },
          {
            "type": "emoji",
            "value": "🤖",
            "anim": "popIn",
            "delay": 15,
            "duration": 15
          },
          {
            "type": "文字",
            "value": "标题文字",
            "anim": "fadeSlideUp",
            "delay": 30,
            "duration": 40,
            "style": {
              "fontSize": 72,
              "color": "#FFD700",
              "fontWeight": "900"
            }
          }
        ]
      }
    }
  ],
  "totalDuration": 15,
  "config": {
    "fps": 30,
    "width": 1080,
    "height": 1920,
    "charsPerSecond": 4.5
  }
}
```

---

## 核心能力:名词视觉化

### 名词 → 视觉元素

当脚本中提到**名词**时,必须匹配对应的视觉元素:

| 名词类型 | 视觉化方式 | 示例 |
|---------|-----------|------|
| **抽象概念** | emoji 图标 | 技能 → ⚡、目标 → 🎯 |
| **具体物品** | emoji / 简单图形 | 手机 → 📱、视频 → 🎬 |
| **人物/角色** | 圆形头像占位 | 张三 → 👤 |
| **数据/数字** | 高亮数字 | 100万 → **100万** |
| **动作/行为** | emoji + 文字 | 学习 → 📖、赚钱 → 💰 |
| **品牌/产品** | Logo占位 | OpenClaw → 🤖 |

### 视觉元素入场动画

每个出现的名词视觉元素必须有**入场动画**:

| 动画类型 | 效果 | 适用场景 |
|---------|------|----------|
| **pop-in** | 从小变大弹出 | emoji、图标 |
| **fade-slide-up** | 淡入上移 | 文字、数字 |
| **wobble** | 轻微晃动后稳定 | 强调重点 |
| **glow-pulse** | 发光脉冲 | 关键词、高亮 |
| **scale-bounce** | 弹跳放大 | 数字、标题 |

---

## 设计原则

### 1. 画面形式
- 默认竖屏(9:16)PPT/图文动画风格
- 深色背景 + 亮色文字
- 尺寸: 1080×1920

### 2. 视觉层级
- **标题层**:大字、醒目、吸引眼球
- **正文层**:清晰可读
- **装饰层**:点缀但不抢眼
- **名词层**:随口播出现、配合入场动画
- 每页只传达一个核心观点

### 3. 信息可视化
- 数据 → 图表
- 步骤 → 列表/流程图
- 对比 → 左右对照
- 关键词 → 放大/变色/加粗/色块底纹

### 4. 动画逻辑
- 遵循"声画同步"原则
- **分层入场动画顺序**:
  1. 先名词视觉元素(emoji/图标)出现
  2. 再标题文字淡入
  3. 最后正文描述出现
- 推荐动画:淡入上移、缩放弹出
- 风格简洁稳重,动画时长 0.3-0.5s

---

## 输出格式

输出一份【画面设计方案】表格:

| 序号 | 时间轴 | 口播文案 | 画面设计 | 名词视觉 | 动画设计 | 预估时长 |
|:----:|:------:|---------|----------|---------|----------|:--------:|
| 1 | 00:00-00:03 | 开头引入 | 中心爆炸式 | 🤖 ⚡ | pop-in + fade | 3秒 |
| 2 | 00:03-00:08 | 第一个要点 | 左文右图 | 🎯 | fade-slide-up | 5秒 |
| ... | ... | ... | ... | ... | ... | ... |

---

## 时长预估规范

### 配音时长预估
- 普通语速:每秒约 4-5 个中文字符
- 快节奏:每秒约 6-7 个字符
- 慢节奏:每秒约 3 个字符

### 场景时长分配
- 开场(黄金3秒):2-3秒
- 重点内容:5-8秒
- 过渡内容:3-5秒
- 结尾号召:2-3秒

### 帧数计算
```
帧数 = 时长(秒) × 30 (FPS)
```

---

## 名词视觉化示例

### 示例:OpenClaw 技能系统

```
口播:"OpenClaw 是你的 AI 助手,但它的能力取决于「技能」"

名词提取:
- OpenClaw → 🤖
- AI 助手 → 🤖
- 技能 → ⚡

视觉化设计:
| 名词 | 视觉元素 | 入场时机 | 动画 |
|------|---------|---------|------|
| OpenClaw | 🤖 | 0s | fade-in |
| 技能 | ⚡ | 0.5s | pop-in |
```

---

## 工作流程

1. **分析脚本** - 提取核心观点和逻辑结构
2. **识别名词** - 找出所有需要视觉化的名词
3. **匹配视觉** - 为每个名词分配 emoji/图标/图形
4. **规划动画** - 设计入场顺序和动画类型
5. **预估时长** - 根据文字量预估配音时长
6. **拆解分镜** - 将脚本拆解为若干"关键画面"
7. **输出表格** - 完整的画面设计方案

---

## 视觉元素建议

### 常用 Emoji
🎯 💡 🔥 ⭐ ✅ 📱 🎬 🔧 ⚡ 💪 📖 💰 🚀 🌟 📌 🎓 💡

### 色系规范
- 背景:深色(#0f0f23 或渐变)
- 主文字:白色或亮色
- 强调色:#FFD700(金)、#00D4FF(青)、#FF6B6B(红)
- 辅助色:#888、#ccc(灰度)

---

## 技术备注

生成视频时使用:
- `fontFamily: '"Noto Color Emoji", serif'` 支持 emoji
- `fonts-noto-cjk` 支持中文
- `fonts-noto-color-emoji` 支持彩色 emoji
- FPS: 30, 尺寸: 1080×1920

---

## 与 video-producer 配合

本技能输出分镜表,video-producer 负责:
1. 调用 TTS 生成实际配音
2. 获取实测时长
3. 渲染视频
4. 合并音视频

---
*本技能与 video-producer、remotion-video-toolkit 配合使用,实现短视频一键生成*

Related Skills

demo-video

3891
from openclaw/skills

Create product demo videos by automating browser interactions and capturing frames. Use when the user wants to record a demo, walkthrough, product showcase, or interactive video of a web application. Supports Playwright CDP screencast for high-quality capture and FFmpeg for video encoding.

Video Production

pentest-active-directory

3891
from openclaw/skills

Assess Active Directory identity attack paths including roasting, relay, and delegation abuse.

Security

seedance-video

3891
from openclaw/skills

Generate AI videos using ByteDance Seedance. Use when the user wants to: (1) generate videos from text prompts, (2) generate videos from images (first frame, first+last frame, reference images), or (3) query/manage video generation tasks. Supports Seedance 1.5 Pro (with audio), 1.0 Pro, 1.0 Pro Fast, and 1.0 Lite models.

recipe-video-extractor

3891
from openclaw/skills

Extract a structured cooking recipe from a shared video URL when the user sends `recipe <url>`. Prioritize caption/description and comments via browser automation, then use web search/fetch as fallback with clear source attribution.

json2video-pinterest

3891
from openclaw/skills

Generate Pinterest-optimized vertical videos using JSON2Video API. Supports AI-generated or URL-based images, AI-generated or provided voiceovers, optional subtitles, and zoom effects. Use when creating video content for Pinterest affiliate marketing, creating vertical social media videos, automating video production with JSON2Video API, or generating videos with voiceovers and subtitles.

arch-video-cut

3891
from openclaw/skills

Automatic Architecture Video Editing Workflow with Self-Learning Preferences

short-video-script-generator-pro

3891
from openclaw/skills

AI Short Video Script Generator, support TikTok/YouTube Shorts/Instagram Reels, auto generate hook, shots, voiceover, subtitles, BGM, CTA. $0.005 USDT per use.

ai-notes-of-video

3891
from openclaw/skills

The video AI notes tool is provided by Baidu. Based on the video download address provided by the user, it downloads and parses the video, and finally generates AI notes corresponding to the video (a total of three types of notes can be generated: document notes, outline notes, and image-text notes).

keevx-video-translate

3891
from openclaw/skills

Translate videos into a specified target language using the Keevx API. Supports audio-only translation, subtitle generation, and dynamic duration adjustment. Use this skill when the user needs to (1) Translate/dub a video (2) Translate a video from one language to another (3) Query the list of supported translation languages (4) Check the status of a video translation task. Keywords video translate, Keevx, dubbing.

keevx-image-to-video

3891
from openclaw/skills

Use the Keevx API to convert images to videos. Supports multiple models (V/KL), various resolutions (720p/1080p/4K), and audio generation. Use this skill when the user needs to: (1) Convert images to video (2) Generate video with Keevx (3) Create and query image-to-video tasks (4) Batch image-to-video conversion. Keywords: image to video, Keevx, video generation.

ai-video-prompt

3891
from openclaw/skills

AI视频Prompt构建专家。采用"首尾帧图片+视频"工作流,支持多段5秒视频拼接生成长视频(30秒/60秒)。先生成关键帧图片,再生成视频Prompt,确保段与段之间无缝衔接。针对即梦平台优化,支持全中文Prompt输出。

seeddance-ai-video

3891
from openclaw/skills

集成字节跳动SeedDance AI视频生成API,支持文本到视频、图片到视频等功能