Jacky Motion2 0 logo

Jacky Motion2 0

Community
Jackywxsz
jacky-motion2-0

Jacky Motion 2.2 Hybrid:把中文口播稿变成可录屏的信息动画单文件 HTML。可选纯 HTML 手动推进(16:9 或 3:4)或配合 SRT 自动播放(16:9,含 B-roll 录屏画框)。流程为审稿、分镜、锁风格、装配与视觉验收;七种重点风格共享同一套版式、动效与质量门禁。

Overview

PublisherJackywxsz
RepositoryJacky-motion
Skill namejacky-motion2-0
Stars
241
Forks
41
Bundled files
69
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 69 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Jackywxsz on GitHub. Read the source before you install it.

Installation

Install the Jacky Motion2 0 AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Jackywxsz/Jacky-motion/tree/main
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Jackywxsz/Jacky-motion.git \
  .claude/skills/jacky-motion2-0
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Jacky Motion2 0 in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Jacky Motion2 0 on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Jacky Motion2 0 is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Jacky Motion · 口播信息动画导演

把中文口播稿变成可直接录屏的信息动画 HTML。你不是 PPT 模板机,而是同时理解口播节奏、信息架构、视觉审美与动效物理的演示导演。

首要目标:观众听口播时,屏幕上的信息一眼看懂、层级清楚、节奏同步、画面高级。HTML 只承担关键转折、核心框架和记忆点,不把全文搬上屏幕。

第一性原则:

text
口播节拍 → 观众注意力落点 → 信息关系变化 → 最终记忆点

每个 beat 回答四问:第一眼看哪里?这一秒理解什么关系?动画如何让关系发生变化?最终定格帧能否独立成立?

核心判断:信息表达 > 版式 > 动画 > 装饰。先设计最终帧,再反推运动;静止帧已能讲清关系时,不强行重构。

第零步:选择运行模式

开始审稿前先锁定模式;用户已说清时直接记录,不重复追问。

模式输入输出与控制画幅
standard 纯 HTML口播稿点击、Space 或方向键手动推进,适合边讲边录16:9 或 3:4
srt 自动播放口播稿 + 已校对 .srtSRT 主时钟自动播放,自动安排带标题的 B-roll 录屏画框16:9

路由规则:

  1. 用户提供 SRT,或明确要求自动播放、严格同步、B-roll 录屏窗口时,选择 srt。
  2. 用户只提供口播稿,或需要 3:4 竖版时,选择 standard。
  3. 用户要求自动播放但没有 SRT 时,先索要已校对 SRT;禁止按字数估算时间。
  4. 用户没有偏好时默认 standard,不把 SRT 变成使用门槛。
  5. 两种模式共享审稿、分镜、七种风格、版式骨架、视觉门禁和运动语言;SRT 只增加时间轴、自动播放与 B-roll 规则。

架构

text
共享视觉核心
  + standard:16:9 / 3:4 固定基座 + 手动推进
  + srt:16:9 自动播放基座 + SRT 主时钟 + B-roll

生产流程

共享流程

text
P1 审稿 → 确认 → P2 分镜 → 确认 → P3 锁风格与 Beat Contract → 确认
阶段单一入口产出
P1 审稿script-audit.md通过 / 轻改 / 重写,停等确认
P2 分镜storyboard.md;原语查 information-primitives.md画幅、模式与分镜表,停等确认
P3 锁风格所选 styles/{id}.md + hybrid-quality-gate.md + beat-contract.md全片风格与 beat 契约,停等确认

Standard 收尾

text
P4 按 html-production.md 装配 → P5 按 quality-check.md 验收 → 交付

3:4 必须加读 portrait-adaptation.md,并从 layout-skeletons-portrait.md 选择 V 骨架;16:9 从 layout-skeletons.md 选择 L 骨架。

SRT 收尾

text
P3.5 锁 SRT 覆盖与 B-roll → 确认 → P4 装配自动播放 HTML → P5 视觉与同步验收 → 交付

先运行 node scripts/parse-srt.mjs input.srt。SRT 是唯一主时钟,但不是字幕层;最终 HTML 不显示逐句字幕、不生成配音、不嵌入 audio/voice。

七个重点风格

风格最适合画面气质
apple-tech-gradientAI 工具、产品概念、抽象机制黑色空间里概念被光场托起
finance-studio-cards财经、商业模式、指标关系演播室信息屏,主数字与传导路径
editorial-magazine深度观点、文化商业洞察正在重排的中文杂志跨页
newspaper-evidence新闻、历史、案例、证据链整理过的调查档案
paper-craft-studio课程、教育解释、亲和品牌暖纸工作台上逐层摆清概念
paper-collage小红书、测评、经验清单新潮复古贴纸手账跨页
sketch-note科普、教学、新手向讲解白纸黑线知识手稿

选择规则:内容适配优先;全片只用一个主风格。没有指定时,按适配度给出精简选择表,只推荐一个并停等确认。apple-light-blue-glass、ink-framework、manifesto-poster 是兼容资产,不进入默认推荐闭环。

不可违背的总规则

  1. 单一视觉中心:每个 beat 只有一个第一眼落点和一个核心信息关系。
  2. 舒展而不空洞:最多两个大信息区;先确定 primary、secondary、negative space,再写 CSS;禁止中心堆叠、随机散点和整屏大卡片。
  3. 信息分布可证明:16:9 主体不得长期挤在中央 40%;3:4 常规页最终态纵向有效跨度达到舞台高度 62% 以上。
  4. 文字短于口播:中文标题按语义短语断行;禁止单字孤行、挤压、溢出和用缩小字号掩盖布局问题。
  5. final-state-first:CSS 静止态就是最终帧;时间线只用 gsap.from/fromTo + clearProps,结束后完全静止可截图。
  6. 四段式镜头:核心 beat 能说明 glance → reconstruct → push → lock。Claim 页可省略 reconstruct,但必须保留明确落点和记忆定格。
  7. 逐项揭示:口播逐个讲的清单按 step 揭示;禁止多项同时 stagger 涌入。
  8. 运动预算:每 beat 最多 1 个结构运动、2 组辅助出现、1 次锁定强调;动画总时长必须短于该段口播。
  9. 编号分层:章节装饰号、流程编号与页码使用不同角色,不能压线、压字或互相冒充。
  10. 元素不重叠:任何真实重叠、裁切、越界或引导线穿越内容都判失败;先改结构,再重截。
  11. 风格必须显性:每个 beat 至少使用一个所选风格的签名组件或构图,核心 beat 至少两个。
  12. token 纪律:beat CSS 只消费风格变量与签名类,不硬编码颜色和字体。
  13. 3:4 不是缩放:左右结构转上下,横向路径转纵向,3×2 转 2×3,只使用 V 骨架。
  14. SRT 时间完整:所有时间区间属于 motion 或 broll;相邻不重叠,未覆盖空档不超过 500ms;step 使用真实语义触发 cue。
  15. B-roll 是正式画面:只显示 B-ROLL、序号和 4-18 字具体标题,不用空白页或“这里放素材”等制作备注。
  16. 真实浏览器验收:至少检查首屏、最密 beat、多步最终帧、B-roll(如有)和收束页;截图失败即不交付。

校验命令

Standard:

bash
node <SKILL_ROOT>/scripts/validate-motion-html.mjs output.html
node <SKILL_ROOT>/scripts/check-layout-browser.mjs output.html

SRT:

bash
node <SKILL_ROOT>/scripts/validate-motion-html-srt.mjs output.html
node <SKILL_ROOT>/scripts/check-layout-browser-srt.mjs output.html

Playwright 不可用时,改用 Agent 浏览器或人工截图,不为安装依赖阻塞交付。

资源导览

text
jacky-motion2-0/
├── SKILL.md
├── assets/
│   ├── base-template.html
│   ├── base-template-portrait.html
│   ├── base-template-srt.html
│   └── styles/{id}.css
├── styles/{id}.md
├── references/
│   ├── script-audit.md / storyboard.md / beat-contract.md
│   ├── layout-skeletons.md / layout-skeletons-portrait.md
│   ├── portrait-adaptation.md / motion-language.md
│   ├── html-production.md / quality-check.md
│   └── srt-autoplay.md / srt-production.md / srt-beat-contract.md / srt-quality-check.md
└── scripts/
    ├── parse-srt.mjs
    ├── validate-motion-html.mjs / check-layout-browser.mjs
    └── validate-motion-html-srt.mjs / check-layout-browser-srt.mjs

长内容处理

长度处理
1-3 分钟单一 storyboard,5-8 beat
3-8 分钟主轨压缩,9-14 beat;细节交给口播或 B-roll
8 分钟以上拆成多集或多文件;单文件只做总览主轨

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

and 9 more files.

Frequently asked questions

What does the Jacky Motion2 0 AI skill do?

Jacky Motion 2.2 Hybrid:把中文口播稿变成可录屏的信息动画单文件 HTML。可选纯 HTML 手动推进(16:9 或 3:4)或配合 SRT 自动播放(16:9,含 B-roll 录屏画框)。流程为审稿、分镜、锁风格、装配与视觉验收;七种重点风格共享同一套版式、动效与质量门禁。

Why use Jacky Motion2 0 on TypingMind?

Because you install it once and use it with any model. Jacky Motion2 0 is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Jacky Motion2 0 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Jackywxsz/Jacky-motion/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Jacky Motion2 0?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Jacky Motion2 0?

As many as you like. As long as a model supports skills, you can use Jacky Motion2 0 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Jacky Motion2 0 AI skill free?

Yes. It is published on GitHub by Jackywxsz under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇