Next AI Draw.io
draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand
让你的agent一键直出商业级产品宣传片:会作曲,能指着画面改。Commercial-grade launch films by your coding agent — point at the frame to change it.
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/alchaincyf-huashu-motion)在同一工作中把 AI 连到服务的 MCP
draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand
Create, inspect, validate, and save editable 3D building scenes with Pascal's MCP server.
Verified React chart generation: select, validate, repair, render, and inspect charts through MCP.
同类工作,排序与 Skill 列表相同
| 本项 huashu-motion | impeccable | diagram-design | frontend-slides | guizang-ppt-skill | |
|---|---|---|---|---|---|
| 作者 | alchaincyf | pbakaus | cathrynlavery | zarazhangrui | op7418 |
| Skill 数 | 1 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 2,879 | 113,042 | 68,296 | 32,579 | 30,091 |
| 最近代码更新 | 2026年11月16日 | 2026年11月19日 | 2026年11月19日 | 2026年6月24日 | 2026年10月30日 |
| 许可证 | MIT | Apache-2.0 | MIT | MIT | AGPL-3.0 |
alchaincyf 提供的 1 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
Claude CodeCodex
依据开发者 README 和 repo 中的文件夹
GitHub account alchaincyf (person), 3 years old
★ 2,879 stars · code last changed 2026年11月16日
1 scripts that can run on a computer: bin/om · program files you cannot read (binaries): bin/om
No internet calls found in the scripts
No hooks or writes to machine settings found
Checked automatically from the repo files at commit f09dd7a (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
第一步:你用哪个 AI?
选择你用的应用,本页只显示该应用的安装方法
Files are byte-for-byte the same as on GitHub at commit f09dd7a · View on GitHub ↗
1 scripts
Once uploaded it runs on Claude’s systems, not on your computer. No need to unzip
All 47 files · 292 KB
SKILL.md27 KBbin/om1 KBreferences/about-author.md10 KBreferences/colour.md9 KBreferences/contract.md8 KBreferences/craft.md3 KBreferences/depth.md8 KBreferences/director.md18 KBreferences/experience.md27 KBreferences/grammars.md7 KBreferences/library/README.md7 KBreferences/library/formats.md9 KBreferences/library/languages/3d-object.md2 KBreferences/library/languages/art-styles.md1 KBreferences/library/languages/card-montage.md4 KBreferences/library/languages/character.md2 KBreferences/library/languages/continuous-morph.md4 KBreferences/library/languages/cursor-demo.md4 KBreferences/library/languages/data-story.md2 KBreferences/library/languages/editorial-collage.md1 KBreferences/library/languages/flat-world.md1 KBreferences/library/languages/generative-field.md1 KBreferences/library/languages/hand-drawn.md1 KBreferences/library/languages/kinetic-type.md4 KBreferences/library/languages/liquid-glass.md1 KBreferences/library/languages/mechanism.md2 KBreferences/library/languages/modular-grid.md2 KBreferences/library/languages/photo-led.md1 KBreferences/library/languages/retro-digital.md1 KBreferences/library/languages/showreel.md3 KBreferences/library/languages/system-diagram.md1 KBreferences/library/languages/talking-head.md1 KBreferences/library/product-fit.md7 KBreferences/library/techniques.md20 KBreferences/music.md15 KBreferences/product-demo-continuity.md8 KBreferences/provenance.md2 KBreferences/punch-up.md7 KBreferences/rhythm.md12 KBreferences/scores/first-light.abc3 KBreferences/scores/four-rooms.abc4 KBreferences/scores/signal.abc4 KBreferences/sound.md14 KBreferences/talking-head.md10 KBreferences/verification.md2 KBreferences/visual-direction.md9 KBLICENSE1 KB+Create skillUpload a skillpick huashu-motion.zip
SettingsCapabilitiesCode execution and file creation
Turn on Code execution and file creation first (newer menus: Create and edit files) · personal plans: Settings → Capabilities · Team/Enterprise: an admin turns it on under Organization settings → Plugins & skills · every plan, including Free
Upload once; it works in claude.ai and Claude Desktop, and in recent Claude Code signed in with a Claude account (not with an API key)
Cowork and cloud sessions use the skills turned on in your claude.ai account, not ~/.claude/skills on your computer (Claude Desktop scheduled tasks run locally and still load it)
Checked against official docs 2026年11月12日 · Source: support.claude.com, support.claude.com, code.claude.com
复制这句话,粘贴到 Claude Code 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
重新打开 Claude Code,输入 /huashu-motion,或直接提出相关任务,Claude 会自动选用
Checked against official docs 2026年11月12日 · Source: code.claude.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
npx skills add alchaincyf/huashu-motion摘自开发者 README,会下载并运行开发者的代码
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/alchaincyf/huashu-motion.git /tmp/popnx-skill-alchaincyf-huashu-motion-f09dd7a && mkdir -p ~/.claude/skills && cp -R '/tmp/popnx-skill-alchaincyf-huashu-motion-f09dd7a/skills/huashu-motion' ~/.claude/skills/huashu-motionChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill
在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
把 huashu-motion 文件夹放到 ~/.agents/skills/huashu-motion
~ 是你的主文件夹($HOME)
不用终端:下载 ZIP,解压后把 huashu-motion 文件夹移到 ~/.agents/skills
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/alchaincyf/huashu-motion.git /tmp/popnx-skill-alchaincyf-huashu-motion-f09dd7a && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-alchaincyf-huashu-motion-f09dd7a/skills/huashu-motion' ~/.agents/skills/huashu-motionChecked against official docs 2026年11月15日 · Source: learn.chatgpt.com
不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill
想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/alchaincyf/huashu-motion.git /tmp/popnx-skill-alchaincyf-huashu-motion-f09dd7a && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-alchaincyf-huashu-motion-f09dd7a/skills/huashu-motion' ~/.agents/skills/huashu-motion复制这句话,粘贴到 Cursor 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
在 Cursor 的 Agent 聊天中输入 / 并选择 huashu-motion
Checked against official docs 2026年11月12日 · Source: cursor.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
git clone --depth 1 https://github.com/alchaincyf/huashu-motion.git /tmp/popnx-skill-alchaincyf-huashu-motion-f09dd7a && mkdir -p ~/.cursor/skills && cp -R '/tmp/popnx-skill-alchaincyf-huashu-motion-f09dd7a/skills/huashu-motion' ~/.cursor/skills/huashu-motion适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com
其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。
已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹
✓ 命令已检查 2026年11月17日
以下文字来自开发者的 repo,不是 PopNx MCP 的指令
显示前 8,000 个字符 · 在 GitHub 打开完整文件
---
name: huashu-motion
description: "Motion graphics, launch videos and explainers as editable code. A director picks the motion language for your product; you point at frames to change them. 动画、发布片、解说视频,指着画面改。"
metadata:
author: "花叔"
homepage: "https://github.com/alchaincyf"
repository: "https://github.com/alchaincyf/huashu-motion"
version: "0.5.1"
---
# huashu-motion
You are the director, designer and animator. The film is code: one composition (`index.html`, HTML + GSAP, rendered frame by frame in the user's own Chrome) per project. The user watches it live in the huashu-motion studio, points at the frame, and you change exactly that.
Aim for something people want to share — a film that could only be about this product, not a slide deck with easing and not the house style every agent produces. Working code is the starting line; the finished frames are the bar.
## Read this first
**The bar.** The film is the only thing judged. Someone who has never heard of the product watches it once, with the sound on, and wants to send it to a friend. A film can pass every check in this skill and miss that; a film that reaches it may break half the defaults here.
**Three tests, in the order films fail them:**
1. **Is it this product?** Its real interface, real output and real words, in its own colours. Cover the logo: could the film be about a competitor?
2. **Does the energy have a shape?** A hook inside 3 s, a burst, one stop, a peak, a landing. `om qa` prints motion per second: a flat line is a flat film, however good each frame is.
3. **Is any stretch a slide?** A thing on a ground with a caption under it is a slide, however well it eases in. Every stretch gets its own shot scale and its own move ([punch-up.md](references/punch-up.md) §3).
**Which job is this?**
| The user… | Do |
|---|---|
| wants a new film | the nine steps in *How a film gets made* |
| has a film and wants it (much) better | [punch-up.md](references/punch-up.md): diagnose with numbers, keep the idea and the words, rebuild the shots and the score |
| pointed at a frame | *Handling a comment*: that place, that time, nothing else |
| wants an overlay, a loop or a single shot | steps 3–6 and 8; the directions gate only if no style was given |
**What is fixed, and what is yours.** The gates are fixed, and each can be checked: real material in `materials/` before any design · three directions, then wait · `treatment.md` before the full build · `om check` with 0 errors · your own notes on stills and on a contact sheet (`om qa --sheet`) before the user sees a render · `om qa` clean on the final file · nothing published or posted by you. Everything between the gates is a default taken from films that worked. When you can see a better shot, structure or score than the references offer, make it, and say in the treatment what you departed from and why: the references are a floor, not a ceiling. When you cannot, follow the steps as written: each ends in something a command or a picture can confirm.
## The tool
```sh
OM="<this skill's folder>/bin/om" # or: npx huashu-motion (same commands)
$OM grab <folder|url> <dir> # the product's real material into <dir>/materials/: screenshots, logo, images, its colours and type
$OM new <dir> # contract-ready starter project
$OM studio <dir> --no-open & # live preview + direct edits + comments (prints the URL)
$OM inbox <dir> --wait --timeout 540 # block until the user comments, claim it, print context
$OM look <id> <dir> # PNGs of the frame the user commented on + a close-up of the spot
$OM done <id> <dir> --note "…" # tell the user what changed (shown in the studio)
$OM set key=value <dir> # change a variable's value in index.html
$OM sound <dir> # music + effects from the scenes, OM.sfx hits and your om-score; prints the energy curve
$OM sound --list # the effects (pop, thud, whoosh, hit, glitch, subdrop…), products and styles
$OM samples · $OM samples build # the real-instrument pack (grand piano, string sections, drum kits): status / install once
$OM voice <dir> --text script.txt # narration + word cues (OM.cue) + subtitles; or --audio <your recording>
$OM render <dir> # → <dir>/out/<name>-vN.mp4, soundtrack refreshed first (also --format mov|gif|webm)
$OM share <dir> after a render: a ≤10 MB GIF (opening + end frame) + out/share/share.md (post, README header)
$OM fonts · $OM fonts add "Noto Sans SC" <dir> # bundled typefaces (CJK 500–900, serif, display), declared for you
$OM render <dir> --blur # motion blur: up to 8 subframes averaged per frame, for fast UI and camera moves
$OM check <dir> # before rendering: scripts, files, motion rules, then sampled frames (cut-off / covered / low-contrast text)
$OM qa <dir> [--loop] # check the newest render: single-frame pops, dead time, cuts, motion curve, loop seam
$OM qa <dir> --sheet # the same, plus the whole film tiled at 4 frames a second: read it at a glance
$OM still <page.html|dir> --at 0,2.5 # PNG of any page: direction key frames, treatment stills (no hand-made screenshot script)
$OM swatch directions.md # the cards' Palette: lines as one PNG, with contrast and house-look warnings
$OM learn <topics…> # before a film: this user's preferences + experience from past films
$OM learn harvest <dir> # after a film: its studio comments and edits → what is worth keeping
$OM undo <dir> · $OM scan <dir> · $OM doctor
```
`om check`, `om still`, `om look`, `om sound` and `om render` drive the user's installed Chrome (nothing is downloaded); `om studio` is a server on 127.0.0.1. If your sandbox blocks starting a browser or a local server (e.g. Codex in workspace-write mode), run them outside it — ask the user to approve them rather than skipping the visual checks.
`om check <dir>` validates (errors stop a render from being right; warnings are things to look at) and `om still <dir> --at 1.2,3.4` saves frames to look at. Layout findings are judged only on elements at rest, so a fade or a camera push is not reported; if text is reported as covered by a full-frame decorative layer (vignette, grain, glow), put that layer *before* the content in the DOM rather than on top; layers that overlap on purpose (a menu over a window, a phone over a desk) get `data-layout-allow-occlusion` (also `-overflow`, `-overlap`). Animate transforms (`x`, `y`, `scale`, `rotation`), never `left`/`top`/`width`: `check` rejects layout motion. Keep exactly one composition `*.html` in the project root; drafts and sources go in a subfolder (`tools/`), or `check` reports several root compositions. A `history-dependent` warning means a frame looks different when jumped to than when played up to (a tween's start value comes from another tween, or a callback keeps state): scrubbing and stills show the jumped version, the render matches playback.
## How a film gets made
1. **Direct it.** Run `om learn <topics>` first (e.g. `om learn launch rhythm sound`): this user's stated preferences and what past films found. Then read [director.md](references/director.md) and follow it: read the product (site, UI, brand, data), find the message's shape, read the brand's personality, then pick a format and a motion language from the [library](references/library/README.md). Ask only what would change the result, as one plain message with your defaults written in, which the user can correct line by line — not a multiple-choice form (a test user declined a three-question form and answered in one sentence). **Always settle narration (口播)** unless already decided: none (music + effects), a system voice reading a script you write (`om voice --text`), their own recording / cloned voice (`om voice --audio`), or the footage's own sound when the提问、分享技巧或报告无法使用。按“有帮助”数量排序。