把复杂剧情/故事大纲拆分为 Seedance 2.0 的"镜头1/镜头2/镜头3"多分镜结构。每个分镜按 4 维度组织(运镜 + 主体动作与表情 + 位置/空间变化 + 音频)。用于"帮我把这个故事写成 Seedance 提示词"、"分镜脚本"、"多镜头视频"、"剧情复杂的视频"、"剧本转分镜"等触发场景。
npx skills add https://github.com/cclank/lanshu-awesome-ai-video-kit --skill seedance-storyboard
剧情 → 多镜头分镜。Seedance 内部把时间和空间解耦,复杂视频最理想的形态是时间轴化分镜。
loop-ready motion with seamless start and end frames详见 methodology/03-分镜时序.md。
镜头1、镜头2、镜头3 等标识,按事件发生顺序组织(先主后次)把用户给的剧情拆成 3-5 个关键节拍。每个节拍对应一个镜头。问自己:
如果用户提到要用参考图/视频,明确每个素材的"功能角色":
| 角色 | 作用 |
|---|---|
| 角色锚定 | 锁定角色外观(推荐:大头照 + 全身照) |
| 场景定调 | 锁定环境与风格 |
| 运镜参考 | 锁定镜头语言与动作节奏 |
| 节奏氛围 | 用音频控制情绪、音色 |
推荐配置:4-5 个素材,不要用满(过多会导致风格冲突)。
[素材分配 + 主体定义],参考 @视频X 的运镜方式(如有)。
镜头 1:[运镜] + [主体@素材N 的动作与表情] + [位置/空间] + [音频]。
镜头 2:[运镜切换] + [主体@素材N 的动作变化] + [位置变化] + [音频]。
镜头 3:[运镜] + [主体动作] + [位置] + [音频]。
[整体约束:风格/色调/质量/稳定性]
## 分镜脚本
\`\`\`
[完整分镜提示词]
\`\`\`
**镜头数**:N 个 · **推荐时长**:10-15 秒 · **比例**:[X:Y]
**镜头节拍分析**:
- 镜头 1(建立):[简述]
- 镜头 2(发展):[简述]
- 镜头 3(结尾):[简述]
**素材建议**:[告诉用户准备哪些参考素材]
用户输入:"女主在医院接到坏消息后崩溃"
节拍拆分:
输出:
将@图片1的中年女性定义为主角,故事场景设定在@图片2的医院走廊。整体运镜参考@视频1
的中景跟拍。
镜头 1:医院走廊白炽灯下,主角@图片1 靠在墙边低头看手机,肩膀放松,嘴角带着浅
浅的微笑回复信息。中景平稳跟拍,从侧面缓慢推近。窗外傍晚柔光,画面
色调温暖。<远处护士站的低语声和脚步回声>。
镜头 2:手机响起,她抬手接听,镜头切到面部特写。瞳孔瞬间放大,下颌线绷紧,呼吸
屏住三秒。她的手指无意识地攥紧手机壳。固定机位,焦点锁定在眼神变化上。
背景虚化,色调变冷。<电话听筒里隐约的机械嗓音 + 心跳声渐强>。
镜头 3:她快步走进走廊尽头的洗手间,背靠门缓慢滑坐到地上,双手抱住膝盖,肩膀
开始无声颤抖。镜头从上往下缓慢拉远,最后定格在她蜷缩成一团的全景。
荧光灯白光与瓷砖冷调。【背景音】只剩水龙头滴水声和压抑的抽泣。
全程画面高清电影纪实风,色调由暖转冷,光影柔和;人物面部稳定不变形,动作自然
流畅,无卡顿无闪烁;不要生成水印、Logo、字幕。
镜头数:3 个 · 推荐时长:12-15 秒 · 比例:16:9
镜头节拍分析:
素材建议:女主大头照 1 张 + 女主全身照 1 张(保 ID 一致) + 医院走廊场景图 1 张 + 中景跟拍参考视频 1 段。共 4 个素材,不要再加。
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.
Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.
Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.
Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.
Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.
Take cclank/seedance-storyboard from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.