3d Four Seasons logo

3d Four Seasons

CommunityPopular
MengTo
3d-four-seasons

Add coordinated spring, summer, fall, and winter states to a 3D scene, blending foliage, sunlight, sky, ground materials, snow, and particles without rebuilding the world. Use for seasonal controls, architectural walkthroughs, and outdoor scenes with four-season transitions.

Overview

PublisherMengTo
RepositorySkills
Skill name3d-four-seasons
Stars
6.1K
Forks
717
Bundled files
2
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.

  • 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 MengTo on GitHub. Read the source before you install it.

Installation

Install the 3d Four Seasons 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/MengTo/Skills.git /tmp/Skills
mkdir -p .claude/skills
cp -r /tmp/Skills/agent-skills/3d/3d-four-seasons .claude/skills/3d-four-seasons
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable 3d Four Seasons 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 Four Seasons 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 Four Seasons 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 Four Seasons

Keep one recognizable place across all four seasons. Each season should change several mutually consistent visual cues while preserving camera state and interactions.

Author the seasonal identity

Inventory deciduous trees, evergreens, exposed surfaces, sheltered surfaces, lights, sky, and existing weather. Use species and climate appropriate to the project; the table is a temperate-scene starting point.

SeasonFoliage and groundLight and atmosphereMotion
SpringFresh foliage; blossom on appropriate speciesSoft warm daylight; gentle hazeSparse petals or young leaves
SummerDense deep greens; full ground coverStronger daylight; readable shaded greensRestrained leaf drift and breeze
FallSpecies-specific amber, red, and brown; litterLower warm sun; golden hazeMore falling leaves
WinterBare deciduous branches; retained evergreens; exposed snowCool sky fill; pale sun; warm interiorsOptional sparse snow; little leaf drift

Choose particle effects only when they serve the scene. A seasonal selector does not require a storm or a full weather simulator.

Share one state

Use a four-component blend in the order [spring, summer, fall, winter]. Accept autumn as an alias for fall, then normalize to one internal key. The weights start nonnegative and sum to one.

js
const presets = {
  spring: [1, 0, 0, 0], summer: [0, 1, 0, 0],
  fall: [0, 0, 1, 0], winter: [0, 0, 0, 1],
};
const weights = [0, 1, 0, 0];
let target = presets.summer;
function setSeason(name) {
  const key = name === 'autumn' ? 'fall' : name;
  if (!Object.hasOwn(presets, key)) return false;
  target = presets[key];
  return true;
}
function stepSeason(dt, reducedMotion = false) {
  const a = reducedMotion ? 1 : 1 - Math.exp(-1.4 * Math.min(Math.max(dt, 0), 0.05));
  for (let i = 0; i < 4; i++) weights[i] += (target[i] - weights[i]) * a;
}

Feed the same state into material uniforms, sky, sun/fill lighting, particle density, and optional ambient audio. A new selection should redirect the current blend, not queue another animation or reset to summer. Resolve each result from authored base values and weights; repeatedly tinting last frame's color causes drift.

Change foliage and snow convincingly

Use species-specific color palettes and stable per-instance IDs. Gradually thin deciduous foliage for winter using a deterministic threshold or dither. Preserve evergreen coverage. Apply matching visibility and wind rules to shadow/depth materials so absent leaves do not cast summer shadows.

For inexpensive settled snow, combine winter weight with upward-facing world-space geometric normals and an exposure mask:

text
snow = winterWeight * smoothstep(0.3, 0.85, worldNormal.y) * exposure

Blend toward a pale, rough snow material. Upward normal alone also whitens sheltered tables and indoor floors; tag exposed objects or supply shelter masks. A material overlay does not add thickness or change silhouette. Add selective snow-cap geometry only for close-up edges where depth matters. Keep falling snow intensity separate from settled coverage if the scene models accumulation and melt.

Keep the transition responsive

Preallocate particle pools and reuse materials/geometry. Change uniforms rather than recompiling shaders or rebuilding the world. Preserve existing material hooks when extending shaders and use stable program cache keys; match the installed renderer's shader chunks instead of assuming an old injection point exists.

Keep season independent of time of day and weather. Derive a final lighting state from those inputs once, so several controllers do not overwrite the same sun or fog values. Refresh expensive environment maps at controlled state changes, with caching where possible.

Use keyboard-accessible controls with a visible selected state and updated accessible labels. Under reduced motion, apply the chosen seasonal appearance immediately and retain a composed still scene. Pause continuous animation while hidden.

Verify

Capture all four seasons from the same camera. Each should be recognizable without its label. Rapidly switch spring → winter → summer → fall mid-transition and check for color drift, stale shadows, allocation spikes, and lost camera controls. Verify snow exposure indoors/outdoors, evergreen retention, particle count, and desktop/mobile rendering.

Read REFERENCES.md. Seijaku demonstrates shared uSeason weights, setSeason, snowInject, foliage thinning, and seasonal light tinting. Full snowfall physics and climate simulation are extensions, not claims about that implementation.

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 3d Four Seasons AI skill do?

Add coordinated spring, summer, fall, and winter states to a 3D scene, blending foliage, sunlight, sky, ground materials, snow, and particles without rebuilding the world. Use for seasonal controls, architectural walkthroughs, and outdoor scenes with four-season transitions.

Why use 3d Four Seasons on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/MengTo/Skills/tree/main/agent-skills/3d/3d-four-seasons. 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 3d Four Seasons?

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 Four Seasons?

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

Is the 3d Four Seasons AI skill free?

Yes. It is published on GitHub by MengTo 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 👇