card-theater

card-theater is a skill for Claude Code, Codex from Unclecheng-li/AI_Animation. It costs 94 tokens per session (1,965 once invoked), scanned A, original, MIT.

A tool for creating animated HTML presentations with a narrated sidebar and a rotating set of three-dimensional cards. The cards can show steps, concepts, or comparisons.

In plain words
What is it for?
Use it to present protocol flows, product features, technical concepts, and other material that benefits from card-by-card storytelling.
Why use it?
It gives step-by-step explanations a visual structure, so viewers can follow a process or compare modes without reading a static page.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to present protocol flows, product features, technical concepts, and other material that benefits from card-by-card storytelling.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/unclecheng-li/ai_animation/card-theater
About the project

AI Animation Skills is a collection of agent instructions and templates for generating single-file HTML animations, including presentations, diagrams, protocol visualizations, phone interfaces, and video-style scenes. People use the skills with AI coding agents to create animated web pages from descriptions or templates. The catalogue entries are the collection's individual generation workflows.

Unclecheng-li/AI_Animation · 1,270 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Unclecheng-li/AI_Animation --skill card-theater
Clone the repo
git clone --depth 1 https://github.com/Unclecheng-li/AI_Animation

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for card-theater

README.md
[![agentmods](https://agentmods.dev/badge/skills/unclecheng-li/ai_animation/card-theater/github.svg)](https://agentmods.dev/skills/unclecheng-li/ai_animation/card-theater)
Your own site
<a href="https://agentmods.dev/skills/unclecheng-li/ai_animation/card-theater"><img src="https://agentmods.dev/badge/skills/unclecheng-li/ai_animation/card-theater/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for card-theater

Your own site · 80×15
<a href="https://agentmods.dev/skills/unclecheng-li/ai_animation/card-theater"><img src="https://agentmods.dev/badge/skills/unclecheng-li/ai_animation/card-theater.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,965 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00094 $0.01965
Opus 5 $0.00047 $0.00983
Sonnet 5 $0.00019 $0.00393
Haiku 4.5 $0.00009 $0.00197

Measured 12d ago against content hash 001653bc39bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

card-theater scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/card-theater/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Card Theater Skill

你是什么

你是一个专门生成侧边栏叙事 + 3D 卡片轮播演示动画的专家。每次被激活,你会根据用户描述的主题,生成一个完整的单文件 HTML,用 3D 卡片轮播 + 侧边栏解说的方式逐步展示流程、概念或协议。

核心视觉特征:

  • 左侧叙事栏 — 标题 + 当前卡片的解说文字 + 关键要点提示
  • 右侧 3D 卡片舞台 — 玻璃拟态卡片以 Coverflow / 轨道 / 滚动方式排列
  • 模式切换 — 可动态插入/移除卡片(如"传输模式 ↔ 隧道模式")
  • 荧光笔高亮 — 选中卡片的关键字段被荧光笔划过动画高亮
  • 键盘 / 滚轮 / 点击 — 多种导航方式

与其他 Skill 的区别:

  • ppt-animation → 全屏翻页 PPT,每页独立,无 3D 卡片
  • flowchart → 节点 + 连线的流程图,无侧边栏叙事
  • card-theater → 侧边栏 + 3D 卡片轮播,重叙事感,适合"分步讲解 + 模式对比"

5 种内置模板

模板 文件 交互方式 视觉特点 适合场景
scroll-3d-tilt assets/scroll-3d-tilt.html 垂直滚动 + 鼠标 3D 倾斜 动态网格背景 + 单卡片居中 + 鼠标跟随 3D 透视 单页滚动型演示,沉浸感强
apple-aurora-track assets/apple-aurora-track.html 键盘 ←→ + 点击卡片 Apple 极光背景 + 液态玻璃卡片轨道 + 非选中卡片模糊后退 产品特性展示,高级感
coverflow-classic assets/coverflow-classic.html Swiper Coverflow + 键盘 + 滚轮 经典 3D Coverflow 旋转 + 侧边栏解说 + 荧光笔 协议流程分步讲解,最通用
coverflow-watermark assets/coverflow-watermark.html Swiper Coverflow + 键盘 + 滚轮 巨型水印图标 + 卡片内大段文字 + 极简侧边栏 内容密度高的技术讲解
coverflow-focus assets/coverflow-focus.html Swiper Coverflow + 键盘 + 滚轮 选中卡片展开详情 + 未选中仅显示标题 + 总结卡片 由浅入深的渐进式讲解

核心工作流

Step 1 — 确认主题与模板

从用户输入中识别要演示的主题。如不明确,询问:

  • "你想演示什么流程 / 协议 / 概念?"
  • "有几个步骤 / 卡片?"
  • "需要模式切换吗?(如传输模式 / 隧道模式)"

模板选择建议:

  • 用户未指定 → 默认 coverflow-classic(最通用)
  • 强调沉浸感 → scroll-3d-tilt
  • 强调高级感 → apple-aurora-track
  • 内容密度高 → coverflow-watermark
  • 渐进式讲解 → coverflow-focus

如果信息充足,直接生成。

Step 2 — 规划卡片内容

每张卡片包含以下要素:

卡片:
  序号: "01"
  标题: "应用数据"
  副标题: "Payload"            # mono 字体,带颜色
  图标: "fa-file-code"          # Font Awesome 图标名
  图标颜色: "#FFD60A"
  解说: "这是用户产生的原始明文数据..."  # 侧边栏叙述文字
  要点: "此时数据尚未被任何协议包裹"      # 侧边栏底部提示
  高亮文本: "CLEAR TEXT / HTTP"    # 荧光笔高亮内容
  高亮颜色: "#FFD60A"
  水印图标: "fa-file-code"       # coverflow-watermark 用

模式切换卡片(可选):

  • 用户可定义"模式A ↔ 模式B",切换时动态插入/移除卡片
  • 如 IPsec 的"传输模式"(4卡片)↔"隧道模式"(5卡片,多一张新 IP 头卡片)

Step 3 — 生成标准

Read the full file on GitHub · 134 lines

Files

What ships with it

9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 134 lines · 94 tokens per session scan A 001653bc39bc

Subscribe to this mod's changes

card-theater is a skill published in the GitHub repository Unclecheng-li/AI_Animation (1,270 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 1,965 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories