AI Animation Skills

Twelve skills that make an agent build single-file HTML animations: slides, protocol diagrams, architecture diagrams and demos for screen recording

  • 1,661 ★ on the repository
  • Last commit
  • MIT
Skill

Extended access

Why this level

  • The agent creates and writes HTML files, examples and templates in the project working folder
  • `dynamic-archify` runs a Node.js renderer, and `video-shot-demos` contains a headless screenshot checker for shots
  • Installing the whole repository adds an offline library of hundreds of megabytes to the skills directory
All reasons and checks

unclecheng-li/ai_animation

Install

Manual install

npx skills add https://github.com/Unclecheng-li/AI_Animation/tree/main/skills/ppt-animation

Installs a single skill. Replace the folder name with the one you need: flowchart, network-protocol-viz, dynamic-archify, scholar-notes, card-theater, video-shot-demos, stacked-data-cards, win11-ui-demos, swiss-shot-demos or ui2v-motions.

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • The agent creates and writes HTML files, examples and templates in the project working folder
  • `dynamic-archify` runs a Node.js renderer, and `video-shot-demos` contains a headless screenshot checker for shots
  • Installing the whole repository adds an offline library of hundreds of megabytes to the skills directory

This is third-party code. Review the repository files before installing.

What it does

AI Animation Skills is a set of twelve skills that make an agent build single-file HTML animations: presentations, diagrams and demo clips. Every `skills/<name>` folder holds a `SKILL.md` with instructions for the agent, a `README.md` for people, prompt notes in `references/` and templates in `assets/`. The agent picks a skill from the description of your task or from the name in your request. `ppt-animation` makes PPT-style slides with elements easing in step by step and five ready themes. `flowchart` draws educational diagrams and explanations of how models such as LSTM work, in CSS and SVG. `network-protocol-viz` shows TCP/IP, Ethernet frames, routing and DHCP. `dynamic-archify` builds architecture diagrams, data flows and state machines from text or Mermaid code, with motion along the lines and export to several formats. It comes with a Node.js renderer with JSON Schema validation and a manual SVG mode. `scholar-notes` formats notes as a handwritten notebook in two styles, and `card-theater` builds a 3D card carousel with a narrative sidebar. The rest are made for screen recording. `video-shot-demos` turns a storyboard into one HTML per shot, with 29 styles, camera moves and WebAudio sound effects. `phone-ui-demos` shows an app on a phone going through a lock screen, chats and settings. `win11-ui-demos` reproduces a Windows 11 desktop with a cursor and hints. `stacked-data-cards` lays argument cards into a stack along a timeline, `swiss-shot-demos` puts a chart in Swiss typography into every shot, and `ui2v-motions` keeps an offline copy of 1,262 GSAP animation packages with a lookup table by purpose. A video comes from recording the screen in full-screen mode.

Who it is for. For authors of technical videos, teachers and developers who need animated diagrams, presentations and demos in a single HTML file.

Good fit when

  • You need a 5–10 slide presentation with animation for a lesson or a video and prefer not to use PowerPoint
  • You want to show how a protocol works, such as the TCP handshake, with a step-by-step animation
  • Technical documentation needs an architecture diagram with moving data flows
  • A video script has to become a set of on-screen demos, one HTML per shot
  • You want to turn notes on a technical topic into an attractive page instead of a text file

Not a fit when

  • You need a finished video file: the skills output HTML and you record the screen yourself
  • You need editable slides in PPTX: the output is HTML pages
  • You need animation for a product interface: these are scripted demos for recording, not components to embed
  • You need a precise engineering diagram without animation: draw.io skills and similar diagram tools handle that

Example request

Make a ppt-animation presentation about the HTTP protocol, dark-tech theme, 5 pages

Limitations

  • The author tested the set only in WorkBuddy. For Claude Code, Cursor, Codex CLI and Gemini CLI the compatibility table says compatible, without a separate check.
  • The `ui2v-motions` folder is an offline copy of the ui2v.com repository with 9,669 files and 641 MB. Installing all skills with the whole-repository command includes it, so install the skills you need one by one.
  • The `dynamic-archify` renderer runs on Node.js. Without it only the manual SVG mode remains.
  • The license is MIT, and the author adds that the materials are for educational use only.
  • Skills install from the `main` branch and change with it. You can pin a version with a tag or commit link or a release archive. Some of the `SKILL.md` instructions are written in Chinese.

How to disable. Delete the folders of the skills you want to drop from the agent's skills directory: `.claude/skills/<name>/` in Claude Code, `.agents/skills/<name>/` in Cursor, `.codex/skills/<name>/` in Codex CLI. The finished HTML files sit wherever the agent saved them and do not depend on the skill: they open on their own.

FAQ

How do I make an animated HTML presentation with an AI agent?

The `ppt-animation` skill builds a single-file 16:9 presentation where page elements ease in one after another after each flip. There are dark-tech, warm newspaper, clean white, cyberpunk and dark gradient themes, with keyboard, scroll wheel and click navigation. The author's example request: "Make a ppt-animation presentation about the HTTP protocol, dark-tech theme, 5 pages".

How do I draw an architecture diagram with moving data flows?

`dynamic-archify` takes a natural language description or Mermaid code and builds one of five types: architecture, workflow, sequence, dataflow or state machine. The diagram is inline SVG with dark and light themes, flowing lines and particles. The renderer runs on Node.js with JSON Schema validation, and without Node there is a manual SVG mode.

How do I get a video if the skills make HTML?

Open the HTML full screen and record the screen. `video-shot-demos` is made for such recording: the clip starts from a black screen and has a virtual clock, hover hints, pause and replay. Each shot is one HTML file and the shot styles rotate.

How is `flowchart` different from `dynamic-archify`?

`flowchart` is lighter and aimed at educational and popular-science explainers in video, where it matters that the result looks good and reads clearly. `dynamic-archify` is aimed at technical documents and system reviews, where precision and export matter.

Can I install one skill instead of the whole set?

Yes. For a single skill the author gives a link like `npx skills add https://github.com/Unclecheng-li/AI_Animation/tree/main/skills/ppt-animation`, while the command without a path installs all twelve, including the heavy `ui2v-motions`.

Which agents can the skills be installed into?

The skill folder is copied into the agent's skills directory: `.claude/skills/` for Claude Code, `.agents/skills/` for Cursor, `.codex/skills/` for Codex CLI, `~/.workbuddy/skills/` for WorkBuddy. For Gemini CLI an extension manifest is listed.

Discussion

No questions or reviews yet.

Skills

Over 50 open skills for motion graphics, animation and video: kinetic typography, charts, explainers, TikTok and Reels, WebGL, Manim

SkillMinimal access1.1KRepository stars
Needs a VPN

A skill that turns an idea, a link or a screen recording into finished video: HeyGen avatar, b-roll, captions and quality checks

SkillBroad access326Repository stars

Five skills: recordable web presentations, web design, GPT Image 2 prompting, local knowledge base retrieval and articles

SkillExtended access13.4KRepository stars

A skill for Cursor, Claude Code and Codex: from a product name or URL it builds a 4K promo with music, voice-over and checks

SkillExtended access407Repository stars

A skill for promo films and kinetic type: idea and storyboard before the build, MP4 rendered through Chrome and ffmpeg, checked by six gates

SkillExtended access1.1KRepository stars

A skill that draws interactive isometric illustrations in SVG, with WebGL shaders and React output, explaining an idea as a working machine

SkillExtended access22.4KRepository stars

Comparison with similar tools

Entries that share the main search query, and how they differ.

EntryOfficialRepository starsMain difference
AI Animation Skills (this entry)no1,661
Awesome Seedanceno2,327prompts and cases for Seedance 2.5 and 2.0
Awesome Seedance 2 Promptsno2,187over 2000 prompts for the Seedance 2.0 video model
Awesome Gemini 3 Promptsno523selected prompts for Gemini with images

README in short

The repository holds twelve skill folders, a `SKILL_TEMPLATE.md` for new skills, interface mockups in `UI/`, the original prompts `prompt.md` and `original-prompt.txt`, a `package.json` and contribution rules. The description, in Chinese and English, opens with a gallery of previews for every skill, followed by detailed descriptions, three install routes, an agent compatibility table, sample requests and the directory structure. The `dynamic-archify` folder holds schemas, renderers, examples and tests.

README badge

Original SKILL.md

---
name: "flowchart"
description: "生成教育/科普类流程图、概念图、原理演示的动画 HTML 页面。用 CSS/SVG 绘制节点和连线,支持流动箭头、逐步出现、hover 高亮等动画效果。适合技术讲解、视频科普、PPT 配图场景。"
version: "0.2.0"
triggers:
  - "流程图"
  - "概念图"
  - "原理演示"
  - "示意图"
  - "神经网络演示"
  - "AI 模型可视化"
  - "flowchart"
  - "flow diagram"
---

# Flowchart Skill

## 你是什么

你是一个专门生成**教育/科普类流程图与原理演示动画**的专家。每次被激活,你会根据用户描述的概念、流程或模型,生成一个完整的单文件 HTML,用动画直观展示其工作原理和数据流动。

**与 `dynamic-archify` 的区别:**
- `flowchart` → 偏教育/科普,面向视频演示,轻量化,注重"好看 + 直观"
- `dynamic-archify` → 偏工程/架构,面向技术文档,专业级,注重"精确 + 可导出"

## 支持的图表类型

| 类型 | 说明 | 示例 |
|------|------|------|
| 流程图 | 步骤流程、决策分支、循环 | 攻击链、渗透流程、API 调用链 |
| 概念图 | 概念关系、知识结构、对比 | AI 模型对比、协议分层、架构分层 |
| 原理演示 | 模型/算法/协议的动态工作过程 | RNN 展开、LSTM 门控、TCP 握手 |
| 时序图 | 消息交互、请求响应、调用链 | 客户端-服务端交互、认证流程 |
| 对比图 | 两种/多种方案的并排对比 | RNN vs LSTM、HTTP vs HTTPS |
| 时间线 | 事件发展、版本演进、历史脉络 | 木马发展史、技术演进 |
| 系统概览 | 简化的系统架构、模块关系 | 微服务拓扑、网络拓扑(简化版) |

### AI/ML 模型可视化(经典子集)

本 Skill 保留了 AI/ML 模型可视化的完整能力,已有以下示例:

| 模型 | 动画重点 | 示例文件 |
|------|---------|---------|
| MLP | 前向传播、层间权重流动 | `assets/MLP.html` |
| RNN | 时间步展开、隐藏状态传递 | `assets/RNN.html` |

Report a problem

Foxx AIAI Animation Skills
Foxx AI

I am Foxx AI and I have already vetted this tool. Ask about install, setup or anything else, and I will keep it simple.