Apple Launch Film logo

Apple Launch Film

Community
charlie947
apple-launch-film

Rebuild an Apple-style Mac launch film entirely in code with Claude Code. A thin menu bar, the black notch growing into widgets one scene at a time, full-screen gradient wallpapers and one short caption per scene. No screen recording, no After Effects. Use when someone says "Apple-style launch", "Mac launch video", "notch animation", "make it look like an Apple keynote", "macOS UI launch film" or wants a product launch that looks like native Mac interface.

Overview

Publishercharlie947
Repositorymotion-graphics-skills
Skill nameapple-launch-film
Stars
428
Forks
62
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by charlie947 on GitHub. Read the source before you install it.

Installation

Install the Apple Launch Film 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/charlie947/motion-graphics-skills/tree/main/skills/apple-launch-film
  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/charlie947/motion-graphics-skills.git /tmp/motion-graphics-skills
mkdir -p .claude/skills
cp -r /tmp/motion-graphics-skills/skills/apple-launch-film .claude/skills/apple-launch-film
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Apple Launch Film 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 Apple Launch Film 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 Apple Launch Film 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.

Apple-style launch film, built in code

Every pixel of the Mac is drawn in code: the menu bar, the notch, the widgets and the wallpapers. One HTML file with window.seek(seconds), exported to MP4.

Before you start: read brand.md and MOTION.md if they exist. If not, run brand-intake first, or ask for hex codes, a font and a logo file. Never call a result on-brand without them.

Pairs with a free skill (not mine) that turns Apple's design guidelines into rules Claude follows. Install it once:

npx skills add emilkowalski/skills --skill apple-design

Step 1: Ask for five things, then wait

  1. The product name and its one line, word for word.
  2. The facts list. Every feature, number and requirement the film may show. Nothing else goes on screen.
  3. The scenes. 6 to 8, each one feature plus one short caption. Example: "Your voice lives here."
  4. A reference (optional): a real Mac launch film or frames of one, in a folder called ref. It sets the look only.
  5. Size and length. Default 1920 x 1080, 30fps, about 2.5 seconds a scene.

Step 2: Build brief (paste into Claude Code)

Use the apple-design skill. [If ref/ exists: Match the LOOK of the reference in ref/. Read every frame first. Do not copy its words or its product name.]

It is a launch film for [PRODUCT]: the black MacBook notch at the top centre grows into Apple-style widgets, one scene at a time. Each scene has its own full-screen colour-gradient wallpaper and one centred caption below the notch, with the last word or two tinted a lighter shade of the wallpaper colour. It opens with the notch expanded and the word "hello" handwritten in a white script line, like the Mac hello screen.

Use only these facts, and add no others:
[FACTS LIST]

Scenes, about 2.5 seconds each:
[1. Notch expanded on black, "hello" handwritten.]
[2..n. Wallpaper colour, what the notch opens into, the caption.]
[Last. Black: the notch closes to its resting shape. Caption: PRODUCT and its one line.]

Size [WIDTH] x [HEIGHT], 30fps. The frame is a Mac screen: a thin macOS menu bar across the top with the notch in the middle of it. System fonts (-apple-system, Helvetica Neue fallback).

Build it as one self-contained HTML file with window.seek(seconds) that draws any exact frame. Capture one frame from each scene [and compare it side by side with the matching reference frame]. Fix what differs, and check the motion against the apple-design skill.

What I learned the hard way

  • Name the notch in words. Given the same brief, one model drew a whole laptop instead. "The notch at the top centre of the screen" is the anchor.
  • Springs, not tweens. The notch looks right when width and height spring on their own curves, open soft and close without overshoot.
  • Work motion out from the start of the film. If the notch reopens before it has finished closing, it carries on from where it is. A per-scene tween jumps.
  • Compare against the reference, scene by scene. Side-by-side frames caught a "hello" that sat off-centre and too big, a chunky progress bar that should be thin ticks, and a prompt jammed into the menu bar.
  • Keep the menu bar short. A full menu of words gets cut in half by wide widgets. Five items is plenty.
  • Widgets add no claims. Placeholder text is grey lines. Any UI word the facts list did not give you (button labels, a clock time) gets listed back for approval.

Step 3: Check and export

Would a stranger believe it is a real Mac for the first second? Is every word on screen from the facts list? Add a reduced-motion setting that swaps springs for quick fades.

Export with HyperFrames (free, open source): npx skills add heygen-com/hyperframes, then npx hyperframes render. For a vertical cut, hand the MP4 to reel-export.

Frequently asked questions

What does the Apple Launch Film AI skill do?

Rebuild an Apple-style Mac launch film entirely in code with Claude Code. A thin menu bar, the black notch growing into widgets one scene at a time, full-screen gradient wallpapers and one short caption per scene. No screen recording, no After Effects. Use when someone says "Apple-style launch", "Mac launch video", "notch animation", "make it look like an Apple keynote", "macOS UI launch film" or wants a product launch that looks like native Mac interface.

Why use Apple Launch Film on TypingMind?

Because you install it once and use it with any model. Apple Launch Film 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 Apple Launch Film in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/charlie947/motion-graphics-skills/tree/main/skills/apple-launch-film. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Apple Launch Film?

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 Apple Launch Film?

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

Is the Apple Launch Film AI skill free?

Yes. It is published on GitHub by charlie947 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 👇