3d Spatial logo

3d Spatial

Community
dylantarre
3d-spatial

Use when working in Blender, Unity 3D, Unreal Engine, Cinema 4D, VR/AR applications, or any three-dimensional animation work.

Overview

Publisherdylantarre
Repositoryanimation-principles
Skill name3d-spatial
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 3d Spatial 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/01-by-domain/3d-spatial .claude/skills/3d-spatial
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable 3d Spatial 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 3d Spatial 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 3d Spatial 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.

3D Spatial Animation

Apply Disney's 12 animation principles to 3D software, VR/AR, and spatial computing environments.

Quick Reference

Principle3D/Spatial Implementation
Squash & StretchLattice deformers, blend shapes
AnticipationIK/FK wind-ups, camera pre-motion
StagingCamera angles, lighting, depth
Straight Ahead / Pose to PoseLayered animation vs blocking
Follow Through / OverlappingBone chains, physics simulation
Slow In / Slow OutF-curve editing, animation curves
ArcIK handles, motion paths in 3D space
Secondary ActionCloth sim, particle systems, environment
TimingFrame timing, VR 90fps requirements
ExaggerationStylized deformation, pushed poses
Solid DrawingVolume preservation, silhouettes
AppealCharacter design, satisfying motion

Principle Applications

Squash & Stretch: Use lattice or mesh deformers for organic squash. Blend shapes for facial deformation. Scale bones in hierarchies. Always preserve volume—if Y compresses, X/Z expand.

Anticipation: IK rig wind-ups for character animation. Camera pulls back before push-in. Objects coil before release. VR: telegraph actions clearly for user comfort.

Staging: Camera angle sells the action. Three-point lighting directs focus. Depth of field isolates subjects. In VR, use spatial audio and lighting to guide attention.

Straight Ahead vs Pose to Pose: Block key poses first (pose to pose), then refine (spline). Use layered animation—body first, then overlapping elements. Procedural secondary motion is straight ahead.

Follow Through & Overlapping: Bone chains for tails, hair, capes. Physics simulation for cloth and particles. Delay child bones from parents. Jiggle deformers for organic follow-through.

Slow In / Slow Out: F-curves (Blender), Animation Curves (Unity), Graph Editor (Maya). Tangent handles control easing. Flat tangents = slow, steep = fast. Never leave curves linear.

Arc: Motion paths visible in 3D space. IK handles naturally create arcs. Check arcs from multiple camera angles. FK rotation creates inherent arcs in hierarchies.

Secondary Action: Cloth simulation responds to primary motion. Particles emit on impacts. Environment objects react to character. Facial animation supports body action.

Timing: Film: 24fps with motion blur. Games: 60fps minimum. VR: 90fps required (72-120fps). Frame timing affects perceived weight—heavy = slower, light = faster.

Exaggeration: Push poses beyond anatomical limits for style. Smear frames for fast motion. Exaggerated anticipation and follow-through. VR: be careful—exaggeration can cause discomfort.

Solid Drawing: Check silhouettes from all angles. Maintain volume during deformation. Strong poses read in profile. Avoid interpenetration and broken geometry.

Appeal: Character design serves animation needs. Weight and balance feel believable. Movement has personality. In VR, presence and comfort are paramount.

Software Techniques

Blender

python
# Add follow-through with driver
# On child bone, add driver to rotation
driver.expression = "var * 0.3"
driver.variables["var"].source = parent_bone.rotation

# Physics-based secondary
bpy.ops.object.modifier_add(type='CLOTH')
bpy.context.object.modifiers["Cloth"].settings.quality = 10

Unity

csharp
// Spring-based follow through
public class SpringFollow : MonoBehaviour {
    public Transform target;
    public float springStrength = 10f;
    public float damping = 0.5f;

    private Vector3 velocity;

    void Update() {
        Vector3 delta = target.position - transform.position;
        velocity += delta * springStrength * Time.deltaTime;
        velocity *= 1f - damping * Time.deltaTime;
        transform.position += velocity * Time.deltaTime;
    }
}

VR/AR Considerations

AspectRequirement
Framerate90fps minimum, 120fps preferred
MotionAvoid camera animation—user controls view
ComfortGradual acceleration, avoid sudden motion
ScaleAnimations must work at world scale
InteractionClear feedback for hand/controller input

Performance Notes

  • LOD (Level of Detail) for distant animations
  • Bake complex simulations when possible
  • GPU skinning for character meshes
  • Culling animations outside view frustum
  • VR: maintain framerate above all else

Frequently asked questions

What does the 3d Spatial AI skill do?

Use when working in Blender, Unity 3D, Unreal Engine, Cinema 4D, VR/AR applications, or any three-dimensional animation work.

Why use 3d Spatial on TypingMind?

Because you install it once and use it with any model. 3d Spatial 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 3d Spatial in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dylantarre/animation-principles/tree/main/skills/01-by-domain/3d-spatial. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use 3d Spatial?

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 3d Spatial?

As many as you like. As long as a model supports skills, you can use 3d Spatial with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the 3d Spatial 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 👇