Whiteboard Book Video Skill

白板火柴人拆书短视频工作流。用于把一本书或一段长内容做成 60-90 秒竖屏(9:16)白板手绘信息图风格的拆书口播短视频，并用 HyperFrames 在本地渲染无平台水印的最终成片。覆盖：拆书脚本与分镜表生成、白板火柴人信息图分镜图生成、口播配音生成(可选男声/女声)、背景音乐生成(可选活泼/沉稳/其他风格)、每个阶段与用户确认、HyperFrames 动效渲染+字幕卡点+音乐混音装配、成片交付。当用户提到"拆书视频""拆解一本书""白板风/火柴人信息图短视频""口播短视频""书评视频""把这本书做成视频"等需求时使用。

73 stars 15 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add nutllwhy/whiteboard-book-video-skill --skill whiteboard-book-video-skill

Manual install

git clone --depth 1 https://github.com/nutllwhy/whiteboard-book-video-skill.git /tmp/whiteboard-book-video-skill
mkdir -p ~/.claude/skills
cp -r /tmp/whiteboard-book-video-skill/. ~/.claude/skills/whiteboard-book-video-skill

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 白板火柴人拆书视频工作流

把一本书做成 60-90 秒竖屏白板手绘口播短视频。全流程分 6 个阶段，每个阶段产出后都要先向用户确认再进入下一阶段。**最终成片用 HyperFrames 本地渲染，不用云端视频生成模型**（本地渲染环节无平台水印，不消耗云端视频生成额度）。

## 总流程（每阶段产出 → 用户确认 → 下一步）

0. **选节奏模式（开跑前先问）**：问用户要「慢版」还是「高密版」（见下方"节奏模式"）。两种模式各有对应脚本/图片/渲染参数，用户也可自定义画面数。
1. **调研与脚本**：读懂书的核心内容 → 产出「调研报告 + 拍摄脚本」（含按所选模式生成的分镜表 + 口播逐字稿 + 每镜头生图提示词）。→ 用户确认脚本
2. **分镜图**：按白板火柴人信息图规范，根据所选节奏模式生成对应数量的竖屏图。→ 用户确认风格/图（含人设或火柴人讲师选择）
3. **口播配音**：按脚本逐字稿生成配音，先问用户要男声还是女声。→ 用户试听确认
4. **背景音乐**：生成 BGM，先问用户要活泼还是沉稳（或其他风格）。→ 用户确认
5. **渲染装配**：HyperFrames 逐步画出动效 + 词级字幕卡点 + BGM 侧链混音 → 无水印成片。
6. **交付**：拷贝到项目根目录，`present_files` 交付，留系列化建议。

## 节奏模式（用户在开跑前二选一，可自定义）

| 模式 | 画面数 | 每画面时长 | 口播字数 | 适合 |
|---|---|---|---|---|
| **慢版** | 约 6-8 画面 | 6-9s | 约 320-380 字 | 讲书逻辑/深度解读，节奏从容 |
| **高密版** | 约 16-20 画面 | 4-5s | 约 280-340 字 | 信息密度高、快节奏、防单调，适合短视频完播 |

- 两种模式都用同一套白板信息图风格与"逐步画出"动效，差异只在画面切分粒度与口播断句。
- 用户未表态时默认问一次；用户自定义画面数时按其要求生成。
- 渲染阶段：慢版直接每画面一镜；高密版可把相邻画面合并成"多小节一镜"（每镜内依次 reveal），减少渲染镜头数，具体见 `references/render-and-assemble.md`。

## 关键默认（可被用户覆盖）

- 画幅：竖屏 9:16，1080×1920；单张分镜图 1152×2048（9:16）。
- 时长：60-90 秒；镜头硬切 + 每镜"逐步画出"揭示动效（约 1.9s）。
- 配音时长 = 视频总时长（视频按配音长度铺）。
- 字幕：词级卡点（用 faster-whisper ASR 词级时间戳），白板便签风样式（白底黑边圆角、黑字、红高亮），高密版字幕更多更短、慢版字幕更少更长。
- 画面角色：默认角落简笔画火柴人讲师；若用户提供个人 IP 形象（AI 生成卡通头像），先征询是沿用 IP 当主角还是用火柴人。

## 阶段细则（按需读取 references）

| 阶段 | 读哪个 reference | 要点 |
|---|---|---|
| 脚本 | `references/script-writing.md` | 钩子→痛点→核心观点→案例→行动→收尾；7 镜头分镜表+逐字稿 |
| 分镜图 | `references/image-prompt.md` | 白板/网格底、马克笔线条、红蓝黑三色、角落火柴人、30%+ 留白、单图高密度 |

Read the full skill on GitHub

Details

Skill name: whiteboard-book-video-skill
Repository: nutllwhy/whiteboard-book-video-skill
License: MIT
Repo updated: 4 September 2026

FAQ

What does the Whiteboard Book Video Skill skill do?

How do I install the Whiteboard Book Video Skill skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add nutllwhy/whiteboard-book-video-skill --skill whiteboard-book-video-skill. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Whiteboard Book Video Skill popular?

It lives in nutllwhy/whiteboard-book-video-skill, which has 73 GitHub stars and 15 forks.

Related skills

Notebooklm Video Research

BayramAnnakov/notebooklm-youtube-skill

Automate NotebookLM notebook creation from YouTube videos. Given a YouTube video URL, extract information about people featured in the video, research them online, create a new NotebookLM notebook with the video and research as sources, and generate an audio overview. Uses screenshot-first automation to reliably target UI elements.

Images, Video & Audio

Gpt Image 2

jiangmuran/claude-image

Use when generating, editing, composing, or iterating on images — illustrations for reports/web, posters with Chinese or English typography, pitch-deck slides, UI mockups, infographics, pixel art, game sprites, character reference sheets, app icons, logo concepts, photoreal product shots, or photo edits with precise local changes. Symptoms include the user asking for "图", "图片", "插图", "海报", "封面", "图标", "ppt素材", "游戏素材", "改图", "修图", "logo", "draw me", "make an image", "生成一张", or attaching an image they want modified. Calls the gpt-image-2 model (April 2026 release; near-perfect text rendering inc

Images, Video & Audio

Take One

talsiach/take-one

Turn a short request into a finished short film rendered from code, working like a studio team of twelve jobs (strategist, creative director, writer, voice director, art director, storyboard artist, cinematographer, composer, sound designer, editor, reviewer, social copywriter). For launch and product videos, explainers, music videos, brand and story films. It learns the brand from its site, pitches the best route first (code, real-looking pictures, moving shots from a video model) with prices, asks whether to run to a finished first take or work in stages, always asks before spending money, c

Images, Video & Audio15

Hinge Profile Optimizer

b1rdmania/hinge-profile-optimizer

Improve a Hinge dating profile through research-backed screenshot audits, photo selection and ordering, conversational discovery, prompt and caption writing, settings review, or post-launch troubleshooting. Use for a full profile rebuild or a focused request about photos, copy, positioning, match quality, or profile performance.

Images, Video & Audio11

Media Publish Check

XshuiAi/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

Images, Video & Audio14

Kiln

elithril/blender-kiln

Makes and fixes 3D assets in Blender, for games, the web and AR. Use when the user wants a 3D model, prop, character or GLB/glTF/FBX/USDZ file made — from a text brief, a reference image, a free marketplace (PolyHaven, Sketchfab) or AI generation — AND when they bring an existing 3D file to fix: too heavy or too many polygons (optimize, compress, LODs), broken normals, scale or origin, materials lost on glTF export, conversion between GLB, FBX and USDZ, texturing, rigging for animation, animating it (walk and idle cycles, text-to-motion, looping clips, articulated props), or inspection. Drives

Images, Video & AudioIn 2 lists

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.