Seedance Prompter

Converts casual video requests into structured Seedance 2.0 prompts using an 8-element formula: subject, action, scene, lighting, camera movement, style, quality, and constraints. Built for product demos, cinematic single-shot videos, and ad creative where you need precise control over every visual element. The workflow intelligently asks 2-3 clarifying questions when needed (lens choice, mood, aspect ratio) rather than dumping a form on you, then outputs English prompts with Chinese term preservation. Includes a quality suffix template and checks for common mistakes like contradictory camera movements or missing watermark constraints. If you're describing multi-shot narratives or need 5-second TikTok clips with native audio, this will redirect you to the storyboard or HappyHorse skills instead. References a masterclass doc with 9-element variations and 117 tested prompts.

GitHub stars: 269
last updated: Jun 1, 2026

View on GitHub

Install

$ npx -y skills add cclank/lanshu-awesome-ai-video-kit --skill seedance-prompter --agent claude-code

Installs into .claude/skills of the current project.

Files

seedance-prompter

把用户的"我想要什么样的视频"转换成 Seedance 2.0 能理解的工程级指令。

何时不用此 skill

用户描述的是 5/10/15 秒紧凑短片 或 要原生带音频 → 用 happyhorse-prompter
用户已有提示词但效果不对 → 用 seedance-debugger
剧情复杂需要多镜头切换 → 用 seedance-storyboard

核心方法论：进阶公式

精准主体 + 动作细节 + 场景环境 + 光影色调 + 镜头运镜 + 视觉风格 + 画质 + 约束条件

详见 methodology/02-进阶公式.md。

工作流程

步骤 1：澄清需求（必要时）

如果用户只给了一两句话（"做个香水广告"），先问清楚以下要素中至少 3 项（不要问全部，挑最影响结果的）：

要素	示例问题
主体	"香水瓶什么样？玻璃透明还是磨砂？"
动作	"瓶子是静止展示还是旋转/喷雾？"
场景	"实景还是纯色背景？什么色？"
光影	"硬光戏剧感还是柔光高级感？"
镜头	"特写质感优先还是中景展示整瓶？"
风格	"电影感 / 商业广告 / 极简 / 复古？"
时长/比例	"竖屏短视频 / 横屏 / 多长？"