techdou

Whiteboard Video — Development skill for Claude Code

Development community

Whiteboard hand-drawn video generator Agent Skill — SRT to full whiteboard video, batch/single image to animation.

How to install Whiteboard Video

This entry records only its repository, not the path inside it, so there is no exact command to give. Open techdou/whiteboard-video and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Whiteboard Video does

Whiteboard hand-drawn video generator Agent Skill — SRT to full whiteboard video, batch/single image to animation. Multi-provider text-to-image support.

Alternatives in Development

  • Hand Drawn Styles — Claude Code skill:把内容套进内置手绘画风配方,产出可直接复制的生图提示词 930 ★
  • Media — Understand an audio / video / image file — Antigravity (agy/Gemini) transcribes and analyzes it, returning a t 284 ★
  • Post Everywhere — Publish one piece of content — text, image, or video — to every connected platform (or a chosen subset) in a s 212 ★

README

Whiteboard Video — 白板手绘视频生成器 | Whiteboard Hand-drawn Video Generator

[English](#english) | [中文](#中文)

**Provenance | 来源**:改编自 B 站 [YangAgent](https://space.bilibili.com/) 分享的白板动画生成思路,在原方案基础上扩展为三模式 + 多 provider 文生图架构。


English

A portable Agent Skill for generating **whiteboard hand-drawn animation videos**. Supports three modes: SRT subtitle → complete whiteboard video, batch images → multiple animations, or single image → one animation.

**Animation pipeline**: line-art drawing (hand-held pen progressively sketches black-and-white outlines) → coloring (hand-held pen paints along contours to restore the original image).

Mode Input Output Needs API Key
Full mode SRT subtitle file Merged whiteboard video (storyboard → text-to-image → animation → merge) ✅ (TTS/image API)
Batch mode Multiple images + duration array Multiple whiteboard animation clips ❌
Single mode One image One whiteboard animation video ❌

Supports 4 text-to-image providers (RunningHub / OpenAI-compatible / Replicate / Stability AI), switched via `.env` `IMAGE_PROVIDER`. See full Chinese docs below for usage.


中文

从 SRT 字幕一键生成完整白板动画视频,或把图片转成白板手绘动画。一个 skill 覆盖完整场景。

三种模式

模式 输入 输出 需要 API Key
完整模式 SRT 字幕文件 合并后的完整白板视频(分镜→文生图→动画→合并) ✅ RunningHub
批量动画 多张图片 + 时长数组 多个白板动画视频片段 ❌
单图动画 单张图片 一个白板动画视频 ❌

动画效果分两个阶段:**线稿绘制**(手持笔逐步画出黑白线稿)→ **上色**(手持笔沿轮廓涂色还原原图)。

安装配置

1. 放置 skill

将整个 `whiteboard-video/` 目录放到 Agent 的 skills 目录下:

.agents/skills/whiteboard-video/

2. 配置 API Key(仅完整模式需要)

完整模式需要文生图 API 来生成白板图片。支持 4 个平台,通过 `.env` 中的 `IMAGE_PROVIDER` 切换:

Provider 环境变量 适用平台
runninghub(默认) RUNNINGHUB_API_KEY RunningHub
openai OPENAI_API_KEY + OPENAI_BASE_URL OpenAI 官方 / 硅基流动 / OneAPI / New API 等所有 OpenAI Images API 兼容平台
`