Spatial Thinking logo

Spatial Thinking

Community
dylantarre
spatial-thinking

Use when animation involves depth, perspective, volume, or three-dimensional awareness—camera moves, character positioning, environmental interaction, or maintaining consistent spatial relationships.

Overview

Publisherdylantarre
Repositoryanimation-principles
Skill namespatial-thinking
Stars
84
Forks
12
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 dylantarre on GitHub. Read the source before you install it.

Installation

Install the Spatial Thinking 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.
  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/dylantarre/animation-principles.git /tmp/animation-principles
mkdir -p .claude/skills
cp -r /tmp/animation-principles/skills/02-by-thinking-style/spatial-thinking .claude/skills/spatial-thinking
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Spatial Thinking 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 Spatial Thinking 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 Spatial Thinking 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.

Spatial Thinking

Think like a sculptor working in time. Your characters exist in three-dimensional space, even on a 2D screen. Every frame is a frozen moment in a world with depth.

Core Mental Model

Before animating anything, ask: Where is this in 3D space, and how does it move through that space?

Animation is 4D: three spatial dimensions plus time. Characters have fronts and backs. Rooms have depth. Actions travel along vectors through real (imagined) environments.

The 12 Principles Through Dimension

Solid Drawing — The foundation of spatial thinking. Every object has volume. Turn it around in your mind. Know what the back looks like. Draw through forms, not around them.

Arcs — All movement happens in 3D space. An arm swinging traces a curve through depth, not just across the screen. Think spherical paths, not flat shapes.

Staging — Spatial composition. Where in the Z-axis is each element? Foreground, midground, background create depth. Overlap establishes position in space.

Squash & Stretch — Deformation happens in 3D. When a ball squashes, it spreads outward in all directions, not just sideways. Maintain volume in depth.

Anticipation — Movement into the screen reads differently than across it. Anticipation toward camera: foreshortening increases. Away: forms recede.

Follow Through & Overlapping Action — Trailing elements exist in 3D. Hair doesn't just swing left-right; it wraps around forms, falls with gravity, catches on shoulders.

Secondary Action — Supporting elements occupy their own spatial positions. A cape occupies the space behind a character. Spatial consistency sells reality.

Timing — Depth affects perceived timing. Objects moving toward/away from camera have different visual rhythms than horizontal movement. Foreshortening compresses distance.

Slow In & Slow Out — Acceleration reads differently in depth. Objects approaching camera grow rapidly at the end (looming effect). Factor Z-axis speed changes.

Exaggeration — Spatial exaggeration includes depth. Characters can lean impossibly far into frame. Environments can stretch beyond physical possibility while maintaining spatial logic.

Appeal — Dynamic spatial composition is appealing. Interesting angles, depth variation, and dimensional poses create visual interest.

Straight Ahead & Pose to Pose — 3D motion paths are easier to plan (pose to pose). Complex spatial action benefits from knowing key positions in space before animating between them.

Practical Application

Spatial Awareness Checklist:

  • Where is the floor? Characters need grounding.
  • Where is the light source? It defines form.
  • What overlaps what? Establish depth order.
  • What's the camera angle? Affects all foreshortening.
  • What exists off-screen? Implied space matters.

Common Spatial Errors:

  • Floating: Characters not connected to environment
  • Flattening: Losing depth in complex poses
  • Scale drift: Objects changing size unintentionally
  • Tangents: Edges aligning in ways that flatten depth
  • Perspective inconsistency: Elements not sharing the same spatial grid

When animation feels "flat":

  1. Add overlapping elements to establish depth
  2. Include Z-axis movement (toward/away from camera)
  3. Use perspective in posing (near hand bigger than far hand)
  4. Add environmental shadows grounding characters

When space feels "confusing":

  1. Simplify depth layers
  2. Establish clear foreground/background separation
  3. Use staging to clarify spatial relationships
  4. Add establishing shots before complex action

Thinking in Depth:

  • Turn poses 45 degrees in your mind
  • Imagine the camera orbiting your scene
  • Consider what's behind every surface
  • Track objects through continuous 3D paths

The Golden Rule

The screen is a window, not a canvas. You're not decorating a flat surface—you're revealing a world that extends in all directions. Every element occupies a position in that world. Honor the space.

Frequently asked questions

What does the Spatial Thinking AI skill do?

Use when animation involves depth, perspective, volume, or three-dimensional awareness—camera moves, character positioning, environmental interaction, or maintaining consistent spatial relationships.

Why use Spatial Thinking on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dylantarre/animation-principles/tree/main/skills/02-by-thinking-style/spatial-thinking. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Spatial Thinking?

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 Spatial Thinking?

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

Is the Spatial Thinking AI skill free?

Yes. It is published on GitHub by dylantarre 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 👇