Swiss Shot Demos

CommunityPopular

Unclecheng-li

swiss-shot-demos

制作"瑞士国际主义风格（Swiss Style）+ 图表驱动"的视频分镜演示动画——纸灰底/炭黑墨/发丝线/唯一强调橙的编辑部级排版，每页用匹配内容的可视化图表（时间线/循环环/流程链/对照表/点阵计数/热力矩阵…）代替文字堆砌，一镜一 HTML，电影化播放器全屏录屏即成片。只要用户提到：瑞士风格演示页、Swiss Style 动画、图表驱动的分镜演示、把口播稿做成可视化动画、信息图风格演示动画、或要求把一批演示页从暗色油光改成瑞士风/杂志编辑风——就用本 Skill。内容完全开放不设限：技术教程、产品发布、安全科普、知识叙事皆可。与 video-shot-demos（风格轮换体系）同底盘，但本 Skill 全系列统一一套瑞士设计语言，靠图表类型与版式变化制造镜头差异。

Overview

Publisher	Unclecheng-li
Repository	`AI_Animation`
Skill name	`swiss-shot-demos`
Stars	1.6K
Forks	123
Bundled files	350
License	MIT
Links	Skill source Repository

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.
350 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by Unclecheng-li on GitHub. Read the source before you install it.

Installation

Install the Swiss Shot Demos AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/Unclecheng-li/AI_Animation/tree/master/skills/swiss-shot-demos
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.

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/Unclecheng-li/AI_Animation.git /tmp/AI_Animation
mkdir -p .claude/skills
cp -r /tmp/AI_Animation/skills/swiss-shot-demos .claude/skills/swiss-shot-demos

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Swiss Shot Demos 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 Swiss Shot Demos 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 Swiss Shot Demos 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.

瑞士风格图表驱动演示动画（Swiss Style · 一镜一 HTML）

把视频分镜做成编辑部级排版 + 可视化图表的演示动画：纸灰底、炭黑墨、发丝线、灰阶明度阶梯、每页唯一强调橙；每个镜头的主体是一张与内容匹配的"图表"（时间线、循环环、流程链、双列对照、点阵计数、热力矩阵、泳道、嵌套剖视……），而不是文字堆砌。一镜一 HTML，电影化底盘（黑场起手/虚拟时钟/镜头推拉/WebAudio 音效），全屏录屏即成片。

反模式就是本 Skill 的诞生理由：AI 默认生成的演示页永远是"乌漆墨黑+油光锃亮"（黑底+霓虹发光+渐变光斑）——本系统全面禁用，改用瑞士国际主义的平面克制：白纸、墨字、一根发丝线、一点橙。

创作哲学

图表优先：拿到任何一段口播，先问"这是什么图"——流程→链/泳道，循环→环，对比→双列/slopegraph，数量→点阵/计数，时间→时间线，结构→嵌套/分层，分布→热力矩阵。文字只做标题/标签/结论条，主体图形区 ≥55% 面积。
明度即数据：灰阶阶梯 L1-L7 承载全部层级（重要=最黑），彩色只留一个橙 #F5572F 标"本页唯一主角"（最大数字/结论/焦点节点/警示）。
排版即力量：Inter 大字排版（主标题 64-120px、断言数字 120-260px·800-900、eyebrow 15px uppercase tracking .14em）+ 88px 页边距 + 12 列网格 + 非对称布局（左重右轻）。
克制是美德：禁 glow/霓虹 text-shadow、径向光斑、光泽渐变、vignette、扫描线、颗粒、大模糊阴影。允许：平面色块、1-2px 发丝线、虚线、反白（墨底纸字）、细网格。
动画快进快停：quarticOut/cubicOut 缓动；入场三式 pop/fade/draw；禁弹跳闪烁发光。节拍动画一律 cue+tws（可暂停可冻结），纯装饰才用 CSS animation。
每镜头 15-45s；口播不上屏（cue 注释对齐时间戳）；数字不许编（白名单纪律）。

Token 纪律（硬性）

禁止通读 assets/template.html 与 assets/examples/ 下任何成片页。模板 cp 复制后 grep -n "改这里\|DUR=" 拿行号，只读标记区；成片页卡壳时 grep 定位后窗口读 ≤80 行。
知识优先取 references/ 四份浓缩文档（swiss-system 设计正本 / chart-skill-bridge 三技能融合选型 / chart-vocabulary 内建图表词汇 / production-spec 生产纪律）。

工作流

第 0 步 · 分镜表：通读素材（口播稿带时间戳/大纲/分镜脚本），拆成 镜头|时长|图表主视觉(选型)|页面分类(A 信息动效 / B 拟真仿真) 分配表给用户确认。页面分类决定策略：A 类全瑞士+图表最大化；B 类（真机/软件界面仿真）保留仿真本体、只把舞台底/页头/标注/角注/结论条瑞士化。素材复制（勿读内容）：

bash
cp -r "assets/examples/vulnclaw-tutorial/Shark-GIF" <输出目录>/    # 大肥鱼 GIF（角色位）

第 1 步 · 逐页实现：cp assets/template.html <输出目录>/shot-x-x_名称.html → grep 定位 → 只改【改这里】区：eyebrow+大标题+主图表（从 chart-vocabulary 选型）+ cue 表。底盘/瑞士 tokens/组件库不动。

图表技能桥接（主视觉选型时优先查 references/chart-skill-bridge.md）：内置 diagram-design（14 型概念示意图，MIT）与 archify（5 型工程图，MIT）于 assets/chart-skills/，lieflat-charts（63 型数据图表法典，NC 许可需自行安装）——按"有数字→lieflat / 讲关系→diagram-design / 讲系统→archify / 轻量示意→内建"匹配选择，外部图并入时按桥接文档做 Swiss 换肤（tokens 覆盖/去交互/cue 驱动）。读型文档按需单读，勿通读 gallery。

第 2 步 · 质检：底盘自带 QA 钩子——URL 加 #auto,t=毫秒 起播后冻结在该时刻，直接无头截图（无需改文件）：

bash
& "C:\Program Files (x86)\Microsoft\Edge\Application\msedge.exe" --headless --disable-gpu --hide-scrollbars --window-size=1920,1080 --virtual-time-budget=4500 --screenshot="_qa\p_t6000.png" "file:///C:/路径/shot-x-x.html#auto,t=6000"

每页 ≥4 时间点（开场/中段/高潮/结尾）+ 控制台零错误。审美四问逐页过：① 纸底/墨字/发丝线系统一致？② 无残留发光/渐变/油光？③ 大字层级与网格成立、主视觉 ≥55%？④ 图表词汇真实落位且与内容匹配？

第 3 步 · index 总览：按章节分组的调度板（同瑞士系统），列每镜时长/图表类型/分类标签。

交付标准

黑场「启动播放」起手；1920×1080 自适应；HUD 底部唤出（进度条墨色）；可暂停重播；DUR 精确
瑞士 tokens 唯一正本（纸 #F0EFEB/墨 #1C1C1A/橙 #F5572F/灰阶阶梯）；Inter+Noto Sans SC+IBM Plex Mono 三件套
主体图形区 ≥55%；eyebrow→大标题→图表三件套结构；橙每页 ≤3 处、只标一个主角
图表词汇与内容匹配（见 chart-vocabulary 选型表）；零发光/渐变/光斑
cue 注释=口播原句+时间戳；口播不上屏；数字白名单不编造
大肥鱼 1-2 次（纸底气泡：白底+1px 墨边+黑字+橙关键词）；角注出处；QA 四问全过

Bundled files

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

and 140 more files.

Frequently asked questions

What does the Swiss Shot Demos AI skill do?

Why use Swiss Shot Demos on TypingMind?

Because you install it once and use it with any model. Swiss Shot Demos 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 Swiss Shot Demos in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Unclecheng-li/AI_Animation/tree/master/skills/swiss-shot-demos. 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 Swiss Shot Demos?

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 Swiss Shot Demos?

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

Is the Swiss Shot Demos AI skill free?

Yes. It is published on GitHub by Unclecheng-li 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

Accessibility

affaan-m

CommunityPopular

WCAG 2.2 レベル AA 標準を用いてインクルーシブなデジタルプロダクトを設計・実装・監査します。Web 用のセマンティック ARIA および Web・ネイティブプラットフォーム（iOS/Android）のアクセシビリティトレイトを生成するために使用します。

Archify

Validated interactive HTML diagrams, upstream-maintained.

Auteur

Design and build cinematic, award-level web pages.

Concept Diagrams

Generate flat, minimal educational SVG visuals as HTML.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

瑞士风格图表驱动演示动画（Swiss Style · 一镜一 HTML）

创作哲学

Token 纪律（硬性）

工作流

交付标准

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now