Video Storyboard Generator
视频分镜脚本生成器，支持头脑风暴、用户偏好记忆、15秒镜头规则、角色提示词生成、音效/BGM建议。用于生成带运镜指导、画面设计、旁白、角色描述的完整分镜脚本。支持极简版（内容描述）和专业版（详细运镜）。适用：教程、书籍介绍、评论、剧情、产品介绍、数据报告。当用户说"做分镜"、"分镜脚本"、"视频分镜"时使用。
Install
npx skills add OYYH-Apple/video-storyboard-generator --skill video-storyboard-generatorgit clone --depth 1 https://github.com/OYYH-Apple/video-storyboard-generator.git /tmp/video-storyboard-generator
mkdir -p ~/.claude/skills
cp -r /tmp/video-storyboard-generator/. ~/.claude/skills/video-storyboard-generatorPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Video Storyboard Generator
通过头脑风暴与用户共同确定视频需求，基于用户画像提供个性化建议，生成结构化的视频分镜脚本。
## 快速导航
> 📋 **新手推荐**: 查看 [`references/quick-reference.md`](references/quick-reference.md) 获取一页纸速查表
### 工作流程
- [阶段0: 用户画像加载（可选）](#阶段0用户画像加载可选)
- [阶段1: 视频类型识别与头脑风暴](#阶段1视频类型识别与头脑风暴)
- [阶段2: 段落结构设计](#阶段2段落结构设计)
- [阶段3: 镜头拆分](#阶段3镜头拆分时长时间规则)
- [阶段4: 逻辑检查](#阶段4逻辑检查与流畅度评估)
- [阶段5: 生成分镜脚本](#阶段5生成分镜脚本)
- [阶段6: 文件保存](#阶段6文件保存)
- [阶段7: 更新用户画像](#阶段7更新用户画像)
### 技术参考
- [运镜类型参考](#运镜类型参考) - 基础运镜 vs 电影级运镜
- [画面布局参考](#画面布局参考) - 构图法则与景别系统
- [参考资产](#参考资产) - 所有reference文件索引
## 核心原则
**段落是主题驱动的，不是标准化的**：分镜的段落结构完全取决于视频主题和内容需求。
**需求需要共同探索**：用户可能对视频的具体表现形式不够清晰，需要通过头脑风暴一起确定。
**用户画像驱动个性化**：系统会记忆用户的偏好，在后续交互中提供更贴合用户喜好的建议。
**镜头时长规则**：默认单个镜头时长不得超过15秒（可自定义）。
**内容安全规范**：所有分镜内容必须符合安全标准，不包含暴力、血腥或不适描述。详见 `references/content-safety.md`。
## 工作流程
### 阶段0：用户画像加载（可选）
在开始任何交互前，检查用户画像文件是否存在：
- **Windows**: `C:\Users\[用户名]\.video-storyboard\user-profile.md`
- **macOS/Linux**: `~/.video-storyboard/user-profile.md`
- **统一表示**: `<用户主目录>/.video-storyboard/user-profile.md`
**如果画像文件存在：**
读取用户画像后，**必须询问用户**：
> "检测到您之前的使用偏好记录。是否使用之前的偏好设置？"
> - **是**：应用用户画像中的偏好设置作为推荐
> - **否**：忽略画像记录，使用默认设置
**如果画像文件不存在：**
使用默认设置，并在本次交互结束后询问是否保存偏好。
详见 `references/user-profile.md`。
---
### 阶段1：视频类型识别与头脑风暴
#### 识别视频类型
根据用户描述识别视频类型，详见 `references/video-types.md`。
#### 头脑风暴 - 需求澄清
根据视频类型进行针对性的头脑风暴，详见 `references/questions-by-type.md`。
**所有视频类型都需要确认：**
5. **镜头时长限制** - 单个镜头最长时长（根据视频总时长自动推荐）
- **短视频（≤60秒）**：建议单镜头≤12秒，按镜头数量规划
- 30秒视频 → 建议3-5个镜头Details
- Skill name
video-storyboard-generator- Repository
- OYYH-Apple/video-storyboard-generator
- License
- MIT
- Repo updated
- 17 March 2026
FAQ
What does the Video Storyboard Generator skill do?
视频分镜脚本生成器，支持头脑风暴、用户偏好记忆、15秒镜头规则、角色提示词生成、音效/BGM建议。用于生成带运镜指导、画面设计、旁白、角色描述的完整分镜脚本。支持极简版（内容描述）和专业版（详细运镜）。适用：教程、书籍介绍、评论、剧情、产品介绍、数据报告。当用户说"做分镜"、"分镜脚本"、"视频分镜"时使用。
How do I install the Video Storyboard Generator skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add OYYH-Apple/video-storyboard-generator --skill video-storyboard-generator. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Video Storyboard Generator popular?
It lives in OYYH-Apple/video-storyboard-generator, which has 73 GitHub stars and 8 forks.
Related skills
Scout
68AgriciDaniel/youtube-scout
Scout a topic on YouTube. Searches YouTube Data API v3 for the most relevant videos, ranks them by views (or engagement, likes, recency, momentum, breakout), and writes a research workbook in the OWT-Social-Ads layout with Videos, Channels, and Summary sheets, plus optional Comments and Transcripts (hooks, replay hotspots) sheets. Can also append into an existing sheet. Use when the user says "scout <topic>", wants a spreadsheet of top YouTube videos on a topic, wants creator or hook research, or wants YouTube rows added to their social ads sheet.
Regional Culture Poster
69dacnay816y62-hub/regional-culture-poster
Convert Chinese provinces, municipalities, autonomous regions, cities, counties, ancient cities, and cultural regions into restrained contemporary posters led by one culturally transformed Chinese character. Supports direct one-shot final image generation and layered production. Use when the user asks for a 中国省域文化海报、城市文化海报、地域文化视觉、极简大字海报、地区系列海报、展览主视觉、出版或社交封面，requests 直接生成、一次成图、不合成、不要后期、direct generation, or wants cultural analysis, art direction, image prompts, rendered poster images, or a coherent batch series for places such as 北京、广东、福建、江南、岭南、巴蜀 or 关中.
Confluence
68SpillwaveSolutions/confluence-skill
Manage Confluence documentation with downloads, uploads, conversions, and diagrams. Use when asked to "download Confluence pages", "upload to Confluence", "convert Wiki Markup", "sync markdown to Confluence", "create Confluence page", or "handle Confluence images".
Watch Video
78Newuxtreme/watch-video-skill
SLASH-COMMAND-ONLY. Invoke ONLY when the user explicitly types the literal `/watch-video` slash command. Never auto-trigger on phrases like "watch this video," "summarize this video," "take notes on this video," or on a bare YouTube URL. For ad-hoc YouTube questions, fetch the transcript directly (YouTube page or yt-dlp) and skim — do not run this heavyweight pipeline.
Dear
69jiawei248/dear-skill
Use when the user wants to make a thoughtful digital gift for a specific person — a parent, partner, friend, colleague, anyone they care about. Triggered by inspiration, not schedule. Produces an expressive H5, generated image, or text artifact. Accepts context through three entries: a folder of raw material (screenshots, photos, chat exports, notes), a one-line brief, or zero-argument interactive intake.
Media Publish Check
71XshuiAi/media-publish-check
All-platform pre-publish audit and adaptation for creators publishing to 抖音/Douyin、小红书/Xiaohongshu、微信视频号/Weixin Video Accounts、快手/Kuaishou. Review videos, images, graphic posts, audio, articles, transcripts, subtitles, covers, livestream scripts, product claims, reposted material, and overseas content. Use when users need one Skill to check visible content, spoken claims, AI disclosure, sources, rights, commercial context, platform mentions, livestream commerce, or platform-specific release versions. Trigger on requests such as “能不能发”“发布前审核”“查违禁词/敏感词”“会不会限流”“检查口播/字幕/封面/导流/带货”“标注 AI/转载/演绎/广告/个人
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.