Kinetic Reel logo

Kinetic Reel

Community
jumpersun
kinetic-reel

用代码制作或修改动态文字主导的产品介绍、技术成果展示、作品集与片头,结合 Canvas 排版、three.js 画面、节拍配乐和 MP4 输出。适用于 kinetic typography 或 motion reel,不用于角色叙事水彩动画。

Overview

Publisherjumpersun
Repositoryframecraft-skills
Skill namekinetic-reel
Stars
4
Forks
0
Bundled files
24
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.

  • 24 bundled files

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

  • Open source

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

Installation

Install the Kinetic Reel 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/jumpersun/framecraft-skills/tree/main/skills/kinetic-reel
  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/jumpersun/framecraft-skills.git /tmp/framecraft-skills
mkdir -p .claude/skills
cp -r /tmp/framecraft-skills/skills/kinetic-reel .claude/skills/kinetic-reel
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kinetic Reel 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 Kinetic Reel 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 Kinetic Reel 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.

动态排版短片

以 Canvas 2D、three.js、WebGL 后期和程序合成配乐制作可编辑短片。所有路径相对于本 SKILL.md 所在目录;解析真实 skill 目录后执行脚本,不依赖 Claude API 或固定模型。

准备与分镜

先确认受众、主要信息、时长、比例、语言和事实来源,沿用已有输入与授权。继续修改时复用已有作品项目。

  1. 运行 bash <skill-dir>/scripts/new_project.sh --check。需要 Node ≥22.12、npm、rsync、Chrome、ffmpeg;优先选择已有合适运行时,用本次命令的 PATH 和 CHROME_PATH 指定,不修改用户默认环境。
  2. 运行 bash <skill-dir>/scripts/new_project.sh <new-project-dir>,目标必须不存在。--skip-install 仅复制模板。依赖安装在作品目录;Skill 模板不存 node_modules 或渲染输出。
  3. 阅读 style-guide.md;制作音频时再读 sound.md。需要长片组织方式时参考 work-reel-26,按其说明修正示例导入路径。
  4. 写项目 STORYBOARD.md:各章节时间预算、事实来源、贯穿装置、每个镜头的标题、视觉动作、转场和声音。先展示分镜,再按已有制作授权继续,不额外引入审批。

项目和中间结果放工作区,projectless 聊天默认用 work/;最终交付放 outputs/。默认 1920×1080,竖屏要重排 HUD、文字、场景与安全区域。

内容与实现

  • 画面中的真实数字和成果来自提供的材料,保留适用范围;示意数据标 SCHEMATIC,不编造指标。
  • reel/cues.js 维护镜头开始 S、事件 hits、章节 CH、时长 dur;画面和音效读取同一时间轴。模板按 120 BPM 编写,改节奏要同步检查 cues.js 的 B、score.mjs 的 BEAT 和细分音符,不能只改 bpm 字段。
  • reel/reel.js 每个镜头一函数:背景 → three.js 图层 → 排版与机制图 → HUD;在 SCENES 和 TR 注册镜头与转场。
  • 每帧只依赖 t,使用确定随机数,支持并行和乱序渲染。保持图形圆角、半径与合成器参数的边界保护。
  • 每个镜头呈现一个具体过程,例如任务路由、状态变化或检索融合。大字给结论,动画解释过程。
  • 默认保留醒目大字、黑/奶油/荧光绿配色和节拍切换;按用户品牌和语言调整。中文受众可用中文主标题,选匹配的中文字体并按实际字宽重新排版;CJK 列表须覆盖画面中文字。
  • 文字避开 HUD 与底部进度条。转场从观众注视的元素出发,以缩放、虹膜、推移等保持连续。
  • 配乐是程序合成电子音乐,不生成演唱或旁白。必要的旁白由用户提供或使用当前环境另有授权的音频能力。

检查、配乐与编码

bash
node render.mjs --sheet=1,4,7,10,13,15.5 --cols=3 --w=640 --out=out/check/sheet.jpg
node render.mjs --stills=10.4 --out=out/stills
node render.mjs --strip=13.8:14.5 --out=out/check/transition.jpg
node music/score.mjs
ffmpeg -y -i music/score.wav -af "highpass=f=30,equalizer=f=250:t=q:w=1:g=-2,loudnorm=I=-14:TP=-1.2:LRA=8" -c:a aac -b:a 192k assets/score.m4a
node render.mjs --frames --workers=4 --fps=30
node render.mjs --encode --out=out/reel.mp4

使用 Codex 的 view_image 或可用图片工具检查每个镜头、密集文字与每类转场的渲染结果。按实际交付尺寸确认中文可读、数字不碰撞、转场不空帧,修正后再检查。

--frames 按源码、画面资产、渲染设置生成缓存签名;画面输入变化后旧生成帧失效,未变化可续跑。--range=a:b 用于区间渲染,签名变化后仍需补齐全片;--force 强制重画选定区间。--encode 检查完整序列并继承帧率与音频路径,可用 --audio=... 覆盖;改帧率须重新渲染。只有配乐文件变化时可直接重新 encode,不必重画。

Google Fonts 当前是网络依赖。网络受限或要求稳定交付时,将字体和许可放项目 assets/fonts、改用本地 @font-face 并核对加载结果;不要默认已离线。渲染速度以本机抽样结果为准。

交付前用 ffprobe 检查尺寸、帧率、时长与音轨,用 ffmpeg 完整解码;声音可用频谱和分段 RMS 辅助检查,不能把这些检查当成试听。注明是否完整观看和实际试听,并交付视频、必要的源码及素材来源。模板回归检查:node --test <skill-dir>/scripts/test-render.mjs。

仅当用户要求网页片头时阅读 site-intro,按需适配自动播放、跳过、静音和 HTTP Range;制作视频本身不包含发布网站。前端手测优先用 Codex 内置浏览器,遵守会话浏览器约定。上游来源与迁移差异见 provenance.md。

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 Kinetic Reel AI skill do?

用代码制作或修改动态文字主导的产品介绍、技术成果展示、作品集与片头,结合 Canvas 排版、three.js 画面、节拍配乐和 MP4 输出。适用于 kinetic typography 或 motion reel,不用于角色叙事水彩动画。

Why use Kinetic Reel on TypingMind?

Because you install it once and use it with any model. Kinetic Reel 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 Kinetic Reel in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jumpersun/framecraft-skills/tree/main/skills/kinetic-reel. 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 Kinetic Reel?

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 Kinetic Reel?

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

Is the Kinetic Reel AI skill free?

It is published on GitHub by jumpersun. Check the repository for licensing terms. 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 👇