Ppt Cinematic Animation logo

Ppt Cinematic Animation

Community
Cennyk-learner
ppt-cinematic-animation

把路演、答辩、竞赛、课堂展示 PPT 的静态页(也可以是一整份课堂稿)做成电影感的动画页:实拍质感底图 + 循环动图 + PowerPoint 原生动画和平滑切换,文字保持可编辑,全部做在页面里。内含从多轮真实返工里总结出的审美与协作原则、做过的动画手法库(含被否掉的)、发散创意的方法,以及"生图出成套同构底图 → Python 合成 → COM 组装 → 导出视频抽帧核对"的整条流程和踩过的坑。用户提到 PPT 要"做动画""做动图""让这页动起来""电影感""转场""平滑切换""聚光灯""宏大""机理演示""大屏",说某页"太平淡""AI感强""排版乱""像 AI 做的""字体不好看",或者要"几个创意方向""发散一下"时都应使用;即使只说"美化这页 PPT",只要目的是让页面在放映时有画面和节奏,也应使用。只做静态排版、整套 PPT 从零生成、或纯视频剪辑不属于本 skill。

Overview

PublisherCennyk-learner
Repositoryppt-cinematic-animation
Skill nameppt-cinematic-animation
Stars
3
Forks
0
Bundled files
47
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.

  • 47 bundled files

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

  • Open source

    Published by Cennyk-learner on GitHub. Read the source before you install it.

Installation

Install the Ppt Cinematic Animation 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/Cennyk-learner/ppt-cinematic-animation/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/Cennyk-learner/ppt-cinematic-animation.git \
  .claude/skills/ppt-cinematic-animation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ppt Cinematic Animation 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 Ppt Cinematic Animation 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 Ppt Cinematic Animation 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.

PPT 电影感动画页

把一页静态的 PPT 做成放映时"有戏"的一页:每点一下进入一幕,幕内几拍自动连播,画面是实拍质感的场景,光在讲事,字只留关键词。成品是可编辑的 .pptx,持续的运动用循环动图,转场、出字、画线和一次性的大动作用原生动画。

依赖:Windows + 微软 PowerPoint(COM)、Python(numpy、opencv-python-headless、python-pptx、Pillow,抓网页界面时要 playwright)、ffmpeg、一个能"以图改图"的生图工具(实测用 Codex CLI 的内置生图)。

这份 skill 怎么用

它由三样东西组成:

  1. 审美与协作原则(references/taste.md)。开工前通读。每一条都对应过一次整体返工,是默认的审美底线;用户当下说的话永远优先。
  2. 做过的手法和流程(style-library.md、pipeline.md、pitfalls.md、scripts/)。这是资产:省力,避坑,知道什么效果好、什么被否过。
  3. 你自己的想法。手法库是起点和参照,不是模板。新题目请先从内容出发自己想(references/ideation.md),参考一切可能的电影、设计、摄影和展陈,库里没有的画面才最值得做。
什么时候读哪份
开工前,以及拿不准某个画面好不好时references/taste.md
要出创意方向、写提案时references/ideation.md
选字体、排字,尤其是中文题材(画、历史、文化)references/typography.md
想看做过什么、哪些被否过references/style-library.md
开始生图、合成、组装时references/pipeline.md
动手写脚本前,以及出了怪问题时references/pitfalls.md
想先看一个完整跑通的例子examples/lighthouse/

审美底线(最短的版本)

  • 内容第一。 动画不能脱离这一页要讲的事;这一页只讲两件事,就围着这两件事做,再好的镜头不相干也删。字只留关键词。
  • 要真。 生成图的"AI 感"是最常见的返工原因。要新闻实拍的质感,再加一点电影的光影和气氛;至少一半画面是真实场景,抽象的数据空间和科技风不要。
  • 要有戏。 一幕里要有几种不同的动作,有明确的光;一张图加一个循环动作会显得平。但不要震动、闪白、冲击模糊,那是廉价的冲击。
  • 要点是主体。 承载要点的屏幕、设备、曲线、细节要大、要在主位。
  • 字要有题材的气质。 暗底金线、宽字距宋体、细体数字年份那一套一眼像 AI 模板。中文题材去下载书法、仿宋、篆书字体,用竖排、乌丝栏、印章,先出样张让对方挑字,见 typography.md。
  • 不加没要的东西。 没要求的字、进度条、装饰组件不要加;字要清楚、好看、不乱。
  • 不重复。 同一份稿里不要两次用同一种画面,页与页不复用素材。
  • PPT 负责让人看懂和相信,不负责举证。对照可以是示意的,但交付时说清哪些是示意。

怎么合作

返工几乎都来自理解偏差,不来自技术。所以顺序是固定的,除非用户明说"直接改":

  1. 问清。 先纠错、复述需求。问题编号,每个附上你的建议,让对方能一句话回答。
  2. 把手头的材料用一遍。 原 PPT、界面、照片、数据,先看完、点完。最有用的画面常常藏在材料里。
  3. 发散,提方向。 三到四个类型不同的方向,各写画面、参考、代价,给出你的推荐。写法见 ideation.md。
  4. 讲清每一拍。 选定方向后,把每一幕依次发生什么、点几下、多长时间讲出来,等确认。
  5. 先出样张。 新的画风、新的题材先出几张图看效果,通过了再全量做。
  6. 制作,导出,抽帧核对。 不要凭脚本推断"应该对了"。
  7. 如实汇报。 见最后一节。

每一版的素材和成品都按版本另存,方便换回旧版或几个方向并排比较,做法见 pipeline.md 第 7 节。

硬约束:动图从进入这一页就开始走

PowerPoint 里的动图不等点击,也不等它"出现"。整套分工由此而来:

内容用什么做
持续的氛围(雨、雪、雾、灯的脉动、车灯流动、光束扫动)无缝循环的短动图,从哪一帧开始都一样
进页第一幕的过程动图可以,还可以只放一遍停在最后一帧
点击之后才发生、有先后顺序的过程每个状态一张透明图层,原生淡入或擦除按顺序切。不要做成一整条动图
状态之间的推进(干到湿、亮到灭、夜到晨)几个循环动图之间用原生叠化或雾转场
一次性的大动作(崩落、尘云、文件滑入、镜头推拉)透明图层 + 原生路径、缩放、淡出
画线、逐行出字、界面逐步变化同一位置叠几张只差一点的图,用擦除依次露出
跨页的镜头推进(从全景推到细节)平滑切换(Morph),两页放同名形状,见 pitfalls.md
所有文字原生文本框,方便之后改措辞;中文竖排用方向 4(列从右往左)
画面里的手迹、题字、印章扫描件转墨迹透明度、按列或按字切成图层,擦除"写"出来;印章用 typo.seal 画

流程一览

  1. 取出目标页。 用 python-pptx 抽成只有这一页的小文件当底稿,不要用 COM 打开几百 MB 的总稿。
  2. 生图。 一次任务出一整套同构图(基准图、它的编辑变体、分割蒙版、留白的屏幕或桌面)。写实的写法在 prompts/real_photo_head.txt,例子在 prompts/real_photo_examples.md。
  3. 合成。 scripts/render_tools.py 提供循环动图、透明图层、画线、光束与光照揭示、屏幕合成、抽帧这些通用函数;scripts/scene_tools.py 是讲画、讲历史常用的(无缝的雪、光从一点铺开、灰到彩色晕开、墨晕式转场、放大镜、老照片、局部上色、去水印);scripts/typo.py 画印章、手迹图层和乌丝栏;每一幕具体怎么合成按内容自己写。有真实界面的 HTML 时用 scripts/capture_page.py 把它跑起来逐帧截。
  4. 组装。 scripts/ppt_tools.ps1 是 COM 工具函数,scripts/build_page_example.ps1 是一页两幕的最小例子(配 scripts/demo_assets.py 不靠生图工具也能跑通);examples/lighthouse/ 是从生图到成品的完整例子。整份多页稿用 scripts/pptkit.py(同一套写法的 Python 版,带中文竖排、配乐、讲稿备注),流程见 pipeline.md 第 8、9 节。
  5. 核对。 导出放映视频,抽帧拼联系表,逐幕看顺序、时机、遮挡和字(scripts/export_slides.py check)。scripts/cap_show.py 可以在真实放映时后台截屏。

找真实素材用 scripts/fetch_images.py(图片搜索、Wikimedia Commons),比字体用 scripts/specimen.py。

交付时要说的

  • 成品文件在哪、几页、多大,预览视频在哪。
  • 每页点几下,每一下发生什么。
  • 上一轮的意见逐条对应到改了什么。
  • 核对是怎么做的:哪些是从导出视频的抽帧看到的,哪些没有在真实放映里点过。
  • 哪些内容是示意、是你拟的词,哪些取自用户的材料。
  • 需要用户定的事,编号列出,附你的建议。
  • 换电脑放映需要装哪些字体,附上字体文件。
  • 整份稿另交讲稿(写进备注栏,再出一份 docx,标明谁讲哪几页、每页几秒、哪里点击)。

Bundled files

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

Frequently asked questions

What does the Ppt Cinematic Animation AI skill do?

把路演、答辩、竞赛、课堂展示 PPT 的静态页(也可以是一整份课堂稿)做成电影感的动画页:实拍质感底图 + 循环动图 + PowerPoint 原生动画和平滑切换,文字保持可编辑,全部做在页面里。内含从多轮真实返工里总结出的审美与协作原则、做过的动画手法库(含被否掉的)、发散创意的方法,以及"生图出成套同构底图 → Python 合成 → COM 组装 → 导出视频抽帧核对"的整条流程和踩过的坑。用户提到 PPT 要"做动画""做动图""让这页动起来""电影感""转场""平滑切换""聚光灯""宏大""机理演示""大屏",说某页"太平淡""AI感强""排版乱""像 AI 做的""字体不好看",或者要"几个创意方向""发散一下"时都应使用;即使只说"美化这页 PPT",只要目的是让页面在放映时有画面和节奏,也应使用。只做静态排版、整套 PPT 从零生成、或纯视频剪辑不属于本 skill。

Why use Ppt Cinematic Animation on TypingMind?

Because you install it once and use it with any model. Ppt Cinematic Animation 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 Ppt Cinematic Animation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Cennyk-learner/ppt-cinematic-animation/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 Ppt Cinematic Animation?

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 Ppt Cinematic Animation?

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

Is the Ppt Cinematic Animation AI skill free?

Yes. It is published on GitHub by Cennyk-learner 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 👇