Breakdown logo

Breakdown

Community
artemnovitckii
breakdown

Makes a 3D exploded-view animation for a reel. A phone floats on a dark studio backdrop, comes apart layer by layer (glass, screen, frame, board and battery, back), and each part gets a thin leader line and a label. Use when the user runs /breakdown or asks for an exploded view, a "what's inside" teardown or a labelled 3D breakdown of a device.

Overview

Publisherartemnovitckii
Repositoryclaude-animation-skills
Skill namebreakdown
Stars
147
Forks
21
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

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

Installation

Install the Breakdown 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/artemnovitckii/claude-animation-skills/tree/main/skills/breakdown
  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/artemnovitckii/claude-animation-skills.git /tmp/claude-animation-skills
mkdir -p .claude/skills
cp -r /tmp/claude-animation-skills/skills/breakdown .claude/skills/breakdown
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Breakdown 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 Breakdown 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 Breakdown 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.

/breakdown

┌──────────────────────┐
│ PHONE / EXPLODED VIEW│  mono header
│   ▱▱▱▱▱▱ ──── 01 Glass
│   ▱ 9:41 ▱ ── 02 Screen
│   ▱▱▱▱▱▱ ──── 03 Frame │  layers lift apart, the phone turns slowly
│   ▱▱▱▱▱▱ ──── 04 Board │  leader lines draw out to the labels
│   ▱▱▱▱▱▱ ──── 05 Battery
│   ▱▱▱▱▱▱ ──── 06 Back  │
└──────────────────────┘

First use

This skill's folder is the "Base directory" Claude Code shows when it loads it.

bash
SKILL_DIR="<base directory of this skill>"
KIT=$(python3 -c 'import os,sys;print(os.path.realpath(os.path.join(sys.argv[1],"..","..","kit")))' "$SKILL_DIR")
[ -s "$KIT/node_modules/three/build/three.module.js" ] || bash "$KIT/setup.sh"

Needs ffmpeg and Node. It renders with WebGL in headless Chrome.

Steps

  1. Labels. Ask what the breakdown is for. The model is a phone, so the labels are the user's take on its six layers, top first: the cover glass, the display, the frame, the logic board, the battery and the back. Labels can be literal ("Battery / 3,582 mAh") or a joke ("Battery / never enough").
  2. Spec. Write <name>.breakdown.json (below).
  3. Build. Run python3 "$SKILL_DIR/build.py" <spec.json>. A 3D render takes about 1.5 minutes, most of it HyperFrames waiting on WebGL (a sub_timeline_readiness_timeout warning is normal). Run with --snap 3.8 first to check the labels.
  4. Check the sheet: every label sits right of the phone and inside the red frame, and the numbers run 01 to 06 from top to bottom.
  5. Hand over the mp4 path.

Spec

json
{
  "title": "Phone", "subtitle": "Exploded view",
  "labels": [["Cover glass", "toughened · 0.6 mm"], ["OLED display", "6.3 in · 120 Hz"], ["Titanium frame", "grade 5 · 7.8 mm"],
             ["Logic board", "3 nm chip · 8 GB"], ["Battery", "3,582 mAh"], ["Back glass", "matte · magnet ring"]],
  "time": "9:41", "date": "Saturday 1 November", "accent": "#F08A5D"
}
  • labels: exactly 6, top layer first, each ["Name", "short note"]. Names up to about 16 characters, notes about 22. ["", ""] hides a label. The numbers are added in screen order.
  • title / subtitle: the header, shown in capitals.
  • time / date: what the lock screen shows.
  • accent: label numbers, leader dots and the battery stripe (hex).
  • hold (optional): extra seconds at the end. out (optional): the output path.

Another object

The spec changes words, not shapes. For another flat, layered object (a tablet, a laptop lid, a card wallet, a smartwatch), copy "$SKILL_DIR/template.html" next to the spec and add "template": "template.html" to the spec. In the copy:

  • PW, PL, PR set the outline (width, length, corner radius). slab(w, l, r, thickness, material) makes one rounded layer, and tex(w, h, draw) paints a canvas texture onto it (see the battery and the screen).
  • Each part(y) is one layer; y is how high it floats when exploded. Y0 holds the heights when assembled, and ORDER says which layer leaves first.
  • ANCHORS says where each label's leader line starts: [part index, [x, y, z] on that part]. Check with --snap 1.0,3.8 after every change: assembled at 1.0, exploded and labelled at 3.8.

Taste

  • Six labels at most, short and plain. Notes are facts or one dry joke, never slogans.
  • Keep the dark backdrop and the right-hand label column; the text stays clear of the phone.

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 Breakdown AI skill do?

Makes a 3D exploded-view animation for a reel. A phone floats on a dark studio backdrop, comes apart layer by layer (glass, screen, frame, board and battery, back), and each part gets a thin leader line and a label. Use when the user runs /breakdown or asks for an exploded view, a "what's inside" teardown or a labelled 3D breakdown of a device.

Why use Breakdown on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/artemnovitckii/claude-animation-skills/tree/main/skills/breakdown. 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 Breakdown?

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 Breakdown?

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

Is the Breakdown AI skill free?

It is published on GitHub by artemnovitckii. 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 👇