Agent skill

Whiteboard Video

by trustfuture in trustfuture/simon-skills

手绘白板风"边画边讲"讲解视频出片 skill(Excalidraw 风格逐笔动画 + 火山引擎配音 + 烧录字幕 + 品牌水印与片尾卡 + 横竖两张封面 + 各平台发布文案)。当用户说"做一期白板视频 / 边画边讲 / 手绘讲解视频 / 用 excalidraw 做视频 / whiteboard video",或要在本仓库里新建一期、改场景、换贴纸或真实…

MITAuto-check: notesMedia & Creative

Install Whiteboard Video

skills CLI
$ npx skills add trustfuture/simon-skills --skill whiteboard-video -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install trustfuture/simon-skills whiteboard-video --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/trustfuture/simon-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/whiteboard-video .claude/skills/whiteboard-video && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
whiteboard-video
GitHub stars
374
Token cost
~1.8k tokens
SKILL.md length
556 words
Files
42 (incl. references, assets)
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

手绘白板风"边画边讲"讲解视频出片 skill(Excalidraw 风格逐笔动画 + 火山引擎配音 + 烧录字幕 + 品牌水印与片尾卡 + 横竖两张封面 + 各平台发布文案)。当用户说"做一期白板视频 / 边画边讲 / 手绘讲解视频 / 用 excalidraw 做视频 / whiteboard video",或要在本仓库里新建一期、改场景、换贴纸或真实…

  • Works in 7 steps: 立题与查证 → 写旁白(scenes.js) → 出 Logo 与贴纸 → …
  • Tasks that involve Diagrams
  • SKILL.md covers 硬规矩, 命令, 一期的流程 and 修改类请求怎么接, plus 1 more section
  • Calls ffmpeg

What it does

Whiteboard Video is an agent skill from trustfuture/simon-skills. 手绘白板风"边画边讲"讲解视频出片 skill(Excalidraw 风格逐笔动画 + 火山引擎配音 + 烧录字幕 + 品牌水印与片尾卡 + 横竖两张封面 + 各平台发布文案)。当用户说"做一期白板视频 / 边画边讲 / 手绘讲解视频 / 用 excalidraw 做视频 / whiteboard video",或要在本仓库里新建一期、改场景、换贴纸或真实 Logo、重出片、改字幕、出封面、写发布文案时使用。全链路本地:Playwright + ffmpeg + 火山 TTS + 本地 codex CLI 生图,不需要剪辑软件。

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 47 other files, including reference files and assets (for example `README.md`, `config.json` and `examples/2026-09-08 为什么懂很多道理还是没变化/README.md`).

It sits in Media & Creative, covering Diagrams, Video production and Text to speech and voice. It works with Excalidraw, FFmpeg, Playwright and Remotion. The repository describes itself as: 不露脸做视频账号的 AI skill 合集:调查长片 + 手绘白板讲解视频,一句选题出片、配音字幕、封面与各平台文案. The licence is MIT.

When your agent uses it

  • Tasks that involve Diagrams
  • Tasks that involve Video production
  • Tasks that involve Text to speech and voice

Example prompts

  • “做一期白板视频 / 边画边讲 / 手绘讲解视频 / 用 excalidraw 做视频 / whiteboard video”
  • “/whiteboard-video”

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. 立题与查证
  2. 写旁白(scenes.js)
  3. 出 Logo 与贴纸
  4. 画场景
  5. 封面
  6. 出片与验收
  7. 发布文案与标题

What it can do on your machine

Read from SKILL.md and the folder at commit 3ad0a25. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • ffmpeg

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Whiteboard Video loads about 1.8k tokens when it runs, and up to ~6.4k if it reads all its reference files. Until then it costs about 71 tokens; SKILL.md has 556 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:14
    1. **全链路本地。** 旁白走火山引擎语音合成(凭证在 `<仓库>/.env`,音色可以是官方音色或你自己的声音复刻),语速默认 1.2 倍原生合成;贴纸走本地 `codex` CLI 生图;真实 Logo 走 Wikimedia Co
  • NoteMentions a .env fileSKILL.md:92
    | 换声线 / 换曲 | `.env` 的 `VOLC_TTS_VOICE` 或 config `tts.voice`(声音复刻音色配 `resourceId: volc.megatts.default`)/ `assets/bgm.mp3

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from trustfuture/simon-skills at commit 3ad0a25, republished under its MIT licence (© trustfuture). 556 words, ~1,787 tokens.

Download SKILL.mdSave it as .claude/skills/whiteboard-video/SKILL.md (or your agent's skills folder). This skill also uses 41 other files; get the full folder from GitHub.
name
whiteboard-video
description
手绘白板风"边画边讲"讲解视频出片 skill(Excalidraw 风格逐笔动画 + 火山引擎配音 + 烧录字幕 + 品牌水印与片尾卡 + 横竖两张封面 + 各平台发布文案)。当用户说"做一期白板视频 / 边画边讲 / 手绘讲解视频 / 用 excalidraw 做视频 / whiteboard video",或要在本仓库里新建一期、改场景、换贴纸或真实 Logo、重出片、改字幕、出封面、写发布文案时使用。全链路本地:Playwright + ffmpeg + 火山 TTS + 本地 codex CLI 生图,不需要剪辑软件。

whiteboard-video:白板讲解视频出片

工具就是本仓库(下文 <仓库>),CLI 是 <仓库>/bin/wb,参数全在 <仓库>/config.json。每期内容在 config.json 的 dirs.projects(默认 <仓库>/episodes/<日期 标题>/),中间产物与成片在 dirs.build(默认 <仓库>/build/<日期 标题>/)。

本文件只讲流程与规矩。细节按需翻:references/dsl.md(场景与封面 API)、references/scene-patterns.md(版式坐标)、references/stickers.md(贴纸、真实 Logo、真人漫画像)、references/publish.md(标题与发布文案);公共工序在同级的 ../video-common/:references/fact-check.md(查证)、references/compliance.md(合规)、references/delivery-qa.md(验收)。

硬规矩

  1. 全链路本地。 旁白走火山引擎语音合成(凭证在 <仓库>/.env,音色可以是官方音色或你自己的声音复刻),语速默认 1.2 倍原生合成;贴纸走本地 codex CLI 生图;真实 Logo 走 Wikimedia Commons 官方 SVG(wb logo);配乐放 assets/bgm.mp3,没有就出无配乐成片。改配置不改代码。
  2. 一处为主。 期目录就是工程目录,scenes.js 是唯一手写源(旁白、场景、封面都在里面);scenes/、旁白稿.md、字幕.srt、封面-*.png 是生成物,不手改、不外拷。README.md(资料来源)和 发布.md(文案)是人写的。视频不放进期目录:成片在 <dirs.build>/<期>/outputs/final.mp4,中间产物在同目录 work/,旁白稿.md 里自动带成片链接。
  3. 先旁白后画面。 旁白按 | 切 beat,每 beat 34 句配一组元素;68 个场景,成片 22.5 分钟(1.2 倍语速下约 500600 字)。
  4. 画布 1920×1080。y≥960 是字幕区,右上 320×130 是水印区,元素不进去;wb scenes 的 ⚠ 必须清零。
  5. 公司、产品、模型用真实 Logo;人物、器械、物件用贴纸;文字、箭头、框用 Excalidraw。 讲到具体公司时主角用官方 Logo(wb logo),不用生图拟人机器人代指,观众认不出是谁。讲到具体公众人物时用真人照片参考的漫画像(wb image ... --ref=照片 --likeness,见 references/stickers.md),不用通用小人代指。Excalidraw 画人很丑,人和物件一律出贴纸。
  6. 事实先查再写。 数字、日期、价格要有来源,写进期目录 README.md;估算值在旁白和文案里都标"据报道/估算"。查证动作见 ../video-common/references/fact-check.md。
  7. 品牌层自动带,不用每期写。 右上角手写水印(第一场景逐笔画入)、片尾品牌卡(5.5 秒,静音)、封面上的品牌标都由工具生成,名字、品牌色、slogan 在 config.json 的 brand;标题和点睛色优先用 C.brand。
  8. 交付四件套:成片 + 两张封面 + 发布.md,主用标题和视频号简介直接贴在回复里。

命令

bash
W=<仓库>/bin/wb
$W new "<标题>"                          # 建期目录:scenes.js 模板 + 发布.md 模板
$W logo "<标题>" logo-x="Commons 文件名.svg" ... [--vs=x,y]   # 真实 Logo → assets/<name>.png;--vs 拼 "A VS B" 封面图;--search="词" 先看候选
$W image "<标题>" name="英文描述" ...     # 贴纸,一次 ≤4 张(四宫格同风格)→ assets/<name>.png
$W stills "<标题>"                       # 每 beat 静帧 → <后台>/<期>/work/frames/,逐张看
$W cover "<标题>"                        # 封面-4x3.png + 封面-3x4.png → 期目录
$W build "<标题>"                        # scenes → tts → render → mix → cover → clean,出 outputs/final.mp4 / 字幕.srt / 旁白稿.md

分步:scenes / tts / render [scene|99-brand] / mix [gain] / clean / open / list。wb build 出片后自动 clean:删 work/frames 静帧和 work/out 里已不在场景表的旧分段,各场景分段与 master 保留(单场景重渲、重混配乐要用)。期参数用标题子串(wb build 薄肌)。wb render <期> 03-xxx 只重渲一段并自动重拼 master,接 wb mix 即新成片;TTS 有缓存,只有改过的旁白会重配。

一期的流程

1. 立题与查证
  • 明确选题、观众、口吻(默认冷静科普口吻,账号口吻写进 references/publish.md)。
  • 搜 2~3 轮;官方页优先且读到全文,二手站数字只做线索。
  • 数字、日期、来源列进 README.md「资料来源」,口径("240 倍 = 6000 万 / 25 万")单列一节。
2. 写旁白(scenes.js)
  • 口语短句,每句一个信息点。数字用中文读法利于 TTS("三百美元");字幕用原文,所以阿拉伯数字也行,但 @、iOS 这类 TTS 会念歪的词要斟酌。
  • 结构:开场定义/反差 → 分解(三要素/两列对比/时间线)→ 怎么算/怎么做 → 数字与门槛 → 冷水/边界 → 一句话总结 + 评论区问题。
  • 每个 beat 都要有能画出来的东西,抽象句并入相邻 beat。按原速写即可,成片语速 1.2 倍。
3. 出 Logo 与贴纸
  • 先列本期出现的公司/产品/模型 → wb logo。 wb logo --search="<公司> logo" 看 Commons 候选,挑官方现行版(带年份的取最新),一期一条命令取齐:标志(logo-<名>,方形,放主视觉)+ 字标(logo-<名>-word,横长,当标签/表头);两家对比再加 --vs=a,b 出 logos-vs.png 当封面主图。来源自动记在 assets/logos.json,抄进 README「画面素材」。Commons 没有的,去官网 press kit / brand 页找 SVG,确认授权再下载。
  • 再列本期物件(人物、器械、设备、道具),wb image 一次 ≤4 张,英文描述写姿势/服装/颜色(Excalidraw 五色:pale yellow/blue/green/red/grey)。
  • 逐张看 assets/<name>.png:杂点、邻格残片、主体断块 → --single 单张重出;只是抠图问题 → --rekey。封面主角贴纸也在这一步出(公司题材封面用 Logo,不另出)。
4. 画场景
  • 抄 references/scene-patterns.md 的版式坐标再微调;贴纸 s.image(x, y, 'name', { h: 370, align: 'center' }),人形 360380 高;Logo 同样用 s.image:主视觉标志 h 260300,卡片/柱子里 h 100~130,字标当标签用 w。
  • 一屏 10~20 个元素;一个 beat 塞不下就删元素,别指望笔画得完(排期最多溢出到下一段前 35%,再多就整体压缩)。
  • wb stills 后逐张看静帧:重叠、越界、文字超宽、太挤。改到满意。
5. 封面
  • scenes.js 末尾 cover 函数:s.coverLayout({ ratio, title, sub, sticker }),build(__dirname, scenes, { cover });wb cover 出 4:3 与 3:4。
  • 标题 ≤2 行、每行 ≤8 字:第一行说对象,第二行说钩子(自动品牌色 + 马克笔高亮);副标放数字;贴纸用主角(公司题材传 sticker: 'logos-vs' 或单个 logo-x,宽图在竖版会自动按宽度缩)。
  • 看两张 png:文字没撞贴纸、高亮压在钩子行、品牌标在角上。
6. 出片与验收
  • wb build。抽 2~3 帧看(ffmpeg -ss <t> -i final.mp4 -frames:v 1 x.png):字幕在底、水印在右上、贴纸擦出正常;片尾看一眼 99-brand。
  • 看 字幕.srt 前几条:原文拼写、数字未拆。
  • 机器检查与交付边界按 ../video-common/references/delivery-qa.md。
  • README.md 写好,时长以 ffprobe 为准。
7. 发布文案与标题
  • 按 references/publish.md:5 个标题候选(数字反差 / 事件主语 / 结论前置 / 生活单位换算 / 提问)选 1 主用;视频号简介、小红书标题+正文+标签、B 站标题、公众号摘要、评论区置顶。
  • 数字与 README.md 一致;合规自查勾完(../video-common/references/compliance.md)。
  • 填 发布.md,交付四件套。
Show full SKILL.md (250 more words)Show less

修改类请求怎么接

用户说做法
改某句旁白 / 加一段改 scenes.js → wb build(只重配改过的场景)
用了假机器人 / 要真 Logowb logo 取官方 SVG → scenes.js 把 s.image 名字换成 logo-* → wb stills → wb render && wb mix && wb cover
换贴纸 / 人物太丑wb image 重出 → wb stills → wb render && wb mix(封面用到的话再 wb cover)
画得太快/太慢、文字蹦出来config render.pen:speed 描边 px/s、charSeconds 每字秒数区间、minSeconds 单元素下限、gapSeconds 抬笔间隙 → wb render && wb mix
渲染太慢 / 机器吃紧config render.workers(默认 4 路,每路一个 Chromium;1 = 串行),出帧与路数无关、逐帧一致
语速快/慢config tts.speed(默认 1.2)→ wb build,全部场景自动重配、字幕同步
配乐大/小config bgm.gain → wb mix;临时试听 wb mix <期> 0.4
字幕字号/位置config captions.fontSize / baselineY → wb render && wb mix
水印位置/关掉/换 logoconfig brand.watermark.position/enabled、brand.logo(透明底 png)→ wb render && wb mix
片尾卡 slogan / CTA / 时长 / 不要config brand.slogan、brand.endCard.* → wb render <期> 99-brand && wb mix
封面文案 / 贴纸 / 画幅scenes.js 末尾 cover 函数 → wb cover;画幅 config cover.ratios,标签 cover.seriesTag(tag: '' 去掉)
标题 / 发布文案 / 换平台改 发布.md,不用重出片
在 Obsidian 里改了图wb render && wb mix 直接读 .excalidraw.md;增删元素会改逐笔顺序,结构性改动回 scenes.js
换声线 / 换曲.env 的 VOLC_TTS_VOICE 或 config tts.voice(声音复刻音色配 resourceId: volc.megatts.default)/ assets/bgm.mp3(换曲先 volumedetect 量电平再定 gain)
换账号品牌config brand.name/accent/slogan,其余不动

已知坑

  • Logo:很多官网有验证页拦截,Logo 一律走 Commons API(wb logo),别去官网抓图。OpenAI 2025 字标最后的 "I" 就是一根竖条,不是被裁掉;Claude 星芒 SVG 边缘略锯齿,放大到 300 高以内看不出来。
  • 火山 TTS 偶尔只返回半段:tts-volc.mjs 按逐字数校验自动重试;全量重配 FORCE_TTS=1。缓存键含文本+音色+语速,改语速会全部重配。
  • 字幕文本必须用原文,TTS 词会把 @grok 写成 atgrok;字幕时间来自 TTS 逐字时间戳,改旁白必须重跑 tts。
  • SVG dash 在每个子路径 M 处重起,rough.js 又双描边:整条 path 一起 dashoffset 会"所有边同时长、每边描两遍"。渲染器已按子路径拆节点、双描边拆 A/B 层,别回退。
  • rough.js toPaths 不带 dasharray,虚线在 render.html 手动设。
  • 文本宽度是估算值,居中用 align:'center' 才准;左对齐长文本别超 1920。
  • Playwright 截图偶发 30s 超时,渲染器带 3 次重试;再挂重跑 wb render。
  • 不要并发跑 wb image:codex 没按指定路径落盘时会兜底抓"最近生成的图",并发会互相抓错。
  • 渲染整期约 35 秒(4 路并行,2.5 分钟片),wb build 全程约 40 秒(TTS 命中缓存时)。后台长任务不要用 &,用工具自带的后台运行。
  • 并行出帧靠两点,别动:render.html 的 seek() 每帧把底色矩形原地重插,强制整屏重画(否则 Chromium 只重画变化区域,帧会跟出帧顺序有关);每路单开一个 Chromium。改渲染器后用 render.workers=1 和 4 各出一遍,ffmpeg -f framemd5 对比必须 0 帧不同。
  • 用 require() 跑 templates/scenes.js 会在 templates/ 下生成产物,别这么测;冒烟测试用 wb new。

© trustfuture, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 41 other files (references, assets) in skills/whiteboard-video of trustfuture/simon-skills.

  • SKILL.md
  • .env.example
  • .gitignore
  • README.md
  • assets/fonts/OFL.txt
  • assets/fonts/Xiaolai-Regular.ttf
  • assets/sample-covers.jpg
  • assets/sample-preview.gif
  • assets/sample-preview.mp4
  • bin/wb
  • config.json
  • examples/2026-09-08 为什么懂很多道理还是没变化/README.md
  • examples/2026-09-08 为什么懂很多道理还是没变化/assets/panicked.png
  • examples/2026-09-08 为什么懂很多道理还是没变化/assets/reader.png
  • examples/2026-09-08 为什么懂很多道理还是没变化/assets/stepper.png
  • … and 27 more

Open the folder on GitHubat commit 3ad0a25

Compare with similar skills

Whiteboard Video next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Whiteboard Video compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Whiteboard Video this skilltrustfuture/simon-skills374—~1.8kAutomated safety check: NotesMIT
Whiteboard Video Factorywwwzhouhui/skills_collection283—~4.9kAutomated safety check: NotesNone
Immersive Short Videoxrkseek/XRK-AGT140—~1kAutomated safety check: PassMIT
Motion Adfabricioctelles/skills106—~4.1kAutomated safety check: PassApache-2.0
Render Mosaic Grid Revealgooseworks-ai/goose-skills1.2k—~1.1kAutomated safety check: PassMIT
Render Model Comparison Gridgooseworks-ai/goose-skills1.2k—~930Automated safety check: PassMIT

Similar skills

  • Whiteboard Video Factory

    wwwzhouhui/skills_collection

    手绘白板风"边画边讲"讲解视频出片 skill(Excalidraw 逐笔动画 + 火山/小米/edge-tts 配音 + 烧录字幕并逐段跟读高亮 + 品牌水印与片尾卡 + 三张封面 4:3 / 3:4 / 9:16 + 各平台发布文案:视频号 / 小红书 / 抖音 / B 站 /…

    283 GitHub stars~4.9k tokensUpdated 3 days ago
    Media & CreativeAuto-check: notes
  • Immersive Short Video

    xrkseek/XRK-AGT

    Produce immersive vertical short videos (口播/科普/产品讲解) without AI-slop aesthetics.

    140 GitHub stars~1k tokensUpdated 8 days ago
    Media & CreativeAuto-check passed
  • Motion Ad

    fabricioctelles/skills

    Produce a short motion-graphics video ad — a 15s Facebook/Instagram/TikTok spot — as a rendered MP4.

    106 GitHub stars~4.1k tokensUpdated 5 days ago
    Media & CreativeAuto-check passed
  • Render Mosaic Grid Reveal

    gooseworks-ai/goose-skills

    Render a 'mosaic-grid-reveal' video from a config — a real-DOM FULL-BLEED N×N mosaic of real product tiles that pops in one tile at a time (scatter order, ease-out-back overshoot), the grid clears…

    1.2k GitHub stars~1.1k tokensUpdated today
    Media & CreativeAuto-check passed
  • Render Model Comparison Grid

    gooseworks-ai/goose-skills

    Render a 'model comparison grid' video from a config — a fal-style "same prompt, N contenders" showcase — a dark real-DOM stage where per beat a monospace prompt fades in centered, docks to a small…

    1.2k GitHub stars~930 tokensUpdated today
    Media & CreativeAuto-check passed
  • Render Photo Grid Card

    gooseworks-ai/goose-skills

    Render a 'photo-grid promo card' video from a config — a real-DOM card with a FIXED header/footer and a CONTINUOUSLY SCROLLING 2-row grid of MIXED tiles (video clips, product/lifestyle stills…

    1.2k GitHub stars~664 tokensUpdated today
    Media & CreativeAuto-check passed

More from trustfuture/simon-skills

  • Investigation Video

    trustfuture/simon-skills

    制作或精修不露脸商业与消费调查视频,覆盖选题、事实核查、10分钟以上叙事、真实动态素材、配音字幕、CTA,以及AI封面和各平台发布文案。按当前请求执行阶段,保留已确认稿件和品牌;不自动公开发布。

    374 GitHub stars~1.3k tokensUpdated 15 days ago
    Auto-check passed
  • Video Common

    trustfuture/simon-skills

    各账号视频流水线共用的四道工序(事实核查与来源台账、AI 封面比例验收、平台文案机制、成片机器验收与交付边界、合规自查)。不直接触发;由各账号 skill(如本仓库的 investigation-video-skill)在对应环节引用。音色、字幕样式、品牌、时长、口吻、平台集合都不在这里,留在各账号 skill。

    374 GitHub stars~239 tokensUpdated 15 days ago
    Auto-check passed

Questions about Whiteboard Video

What does Whiteboard Video do?

手绘白板风"边画边讲"讲解视频出片 skill(Excalidraw 风格逐笔动画 + 火山引擎配音 + 烧录字幕 + 品牌水印与片尾卡 + 横竖两张封面 + 各平台发布文案)。当用户说"做一期白板视频 / 边画边讲 / 手绘讲解视频 / 用 excalidraw 做视频 / whiteboard video",或要在本仓库里新建一期、改场景、换贴纸或真实…. Whiteboard Video is an agent skill from trustfuture/simon-skills.

When should I use Whiteboard Video?

Whiteboard Video fits situations like: tasks that involve Diagrams; tasks that involve Video production; tasks that involve Text to speech and voice.

How do I install Whiteboard Video in Claude Code?

Run `npx skills add trustfuture/simon-skills --skill whiteboard-video -a claude-code`. Or copy the skill folder (skills/whiteboard-video in trustfuture/simon-skills) into .claude/skills/whiteboard-video in your project. Claude Code loads it when a task matches its description.

How do I install Whiteboard Video in Codex?

Run `npx skills add trustfuture/simon-skills --skill whiteboard-video -a codex`. Or copy the skill folder (skills/whiteboard-video in trustfuture/simon-skills) into .agents/skills/whiteboard-video in your project. Codex loads it when a task matches its description.

Can I use Whiteboard Video in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add trustfuture/simon-skills --skill whiteboard-video -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/whiteboard-video, .gemini/skills/whiteboard-video, .github/skills/whiteboard-video and .opencode/skills/whiteboard-video in your project.

What does Whiteboard Video need to run?

Going by SKILL.md and its folder, Whiteboard Video needs the command-line tools its instructions call (ffmpeg).

Does Whiteboard Video access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Whiteboard Video safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Whiteboard Video use?

Whiteboard Video is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Whiteboard Video use?

About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.6k tokens, read only when the agent opens those files.

What are the alternatives to Whiteboard Video?

Skills that share tags, products or a category with Whiteboard Video: Whiteboard Video Factory (wwwzhouhui/skills_collection, 283 stars), Immersive Short Video (xrkseek/XRK-AGT, 140 stars), Motion Ad (fabricioctelles/skills, 106 stars) and Render Mosaic Grid Reveal (gooseworks-ai/goose-skills, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Whiteboard Video?

trustfuture (a GitHub user) maintains it in trustfuture/simon-skills, which has 374 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 24, 2026.

Source: trustfuture/simon-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.