3d Sky Background logo

3d Sky Background

CommunityPopular
MengTo
3d-sky-background

Create a camera-correct sky background for a 3D scene with a procedural atmosphere or panorama, horizon haze, aligned sunlight, and coherent environment lighting. Use for architectural skies, outdoor 3D backgrounds, golden hour, and day-to-night sky transitions.

Overview

PublisherMengTo
RepositorySkills
Skill name3d-sky-background
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 Sky Background 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-sky-background .claude/skills/3d-sky-background
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable 3d Sky Background 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 Sky Background 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 Sky Background 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 Sky Background

Build a sky that surrounds the world, with a readable horizon and lighting that belongs to the same atmosphere.

Choose the representation

Inspect the project's renderer, camera range, color pipeline, environment lighting, and existing assets. Use an existing licensed panorama when its cloud composition matters, a procedural sky when changing sun position matters, or a restrained hybrid. Keep the project's rendering backend and version; do not add a second renderer for the sky.

Keep three responsibilities explicit: the visible sky background, the reflection/ambient environment, and direct sun lighting. A background photograph alone does not light PBR objects. A PMREM environment does not supply a shadow-casting directional sun. See the PMREM documentation.

Build a stable surrounding sky

  • Use the engine's background facility, a fullscreen direction shader, or an inward-facing dome with depth writes disabled and fog disabled. A dome must fit inside the camera's clipping range and follow camera translation; it should retain world orientation as the camera rotates.
  • Derive color from the normalized viewing direction. Blend a pale warm horizon through a muted middle band into a cooler zenith. Keep the lower hemisphere compatible with the ground haze rather than leaving an exposed hard edge.
  • Use a shared sun direction for the visible disk, glow, directional light, and any sky-ray pass. A broad halo and a small disk are separate terms; avoid a large white blob.
  • Add distant silhouettes only when the composition needs depth. Keep them low contrast, with a hue and value close to the horizon.

Map a panorama deliberately

A true equirectangular sky wraps a full 360° horizontally and 180° vertically. Establish a consistent world-axis convention, rotate the texture so its photographed sun matches the scene sun, and inspect both the seam and zenith.

A wide landscape photograph is a partial panorama. Record its angular coverage and horizon position; do not stretch it indiscriminately over a sphere. Seijaku aligns a partial sky image around the sun and mirrors its back coverage. That is a composition-specific shortcut; repeated cloud shapes may be visible during a full orbit. Prefer a complete panorama for unrestricted cameras.

When a custom shader wraps longitude, a discontinuity at the seam can cause bad texture derivatives and a blurred stripe. Prefer continuous sampling coordinates with texture wrapping; otherwise supply corrected gradients appropriate to the shader version. Test the seam while orbiting, not only in the initial view.

Keep color and lighting coherent

Annotate display-referred color images as sRGB and keep lighting calculations in linear space. Apply tone mapping and output conversion once at the intended final stage. Do not copy a fitted inverse tone-map function from another project: Seijaku's fit is coupled to its custom final shader and exposure. Decide explicitly whether a photograph should be tone-mapped with the scene or composited through a separate display-referred path.

Provide a procedural gradient immediately, then load the sky asset asynchronously and blend it in. An asset error should leave a usable sky. Fit texture resolution to the visible angular coverage and target display; do not gate first interaction on an oversized sky image.

Generate a prefiltered environment when needed and reuse it. During a day/night or season transition, interpolate cached environments where supported or refresh at meaningful state changes. Rebuilding PMREM every frame can dominate the scene cost. Dispose superseded environment render targets without disposing textures still in use.

Day, dusk, and night

Use continuous weights for horizon/zenith colors, sun glow, fog tint, exposure, moon, and stars. Fade stars after the sky darkens. Preserve enough ambient illumination to read materials at night. Animate cloud movement slowly, pause when hidden, and retain a designed still sky for reduced motion.

Verify

  • A full orbit and vertical look reveal no seam, stretched clouds, dome edge, or camera translation parallax.
  • Sun direction, shadows, rays, and reflections agree at the intended hero view.
  • Day/dusk/night changes avoid flashes, double tone mapping, and mismatched fog.
  • The sky remains useful before its image loads and when that image fails.
  • Mobile and 2× rendering preserve the horizon and avoid unexpected environment rebuilds.

Read REFERENCES.md for source inspection and official APIs. Seijaku's relevant functions are makeSky, makeHills, makeStars, and its environment update path.

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 Sky Background AI skill do?

Create a camera-correct sky background for a 3D scene with a procedural atmosphere or panorama, horizon haze, aligned sunlight, and coherent environment lighting. Use for architectural skies, outdoor 3D backgrounds, golden hour, and day-to-night sky transitions.

Why use 3d Sky Background on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/MengTo/Skills/tree/main/agent-skills/3d/3d-sky-background. 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 Sky Background?

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 Sky Background?

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

Is the 3d Sky Background 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 👇