Shader Design Engineering logo

Shader Design Engineering

Organization
memi-design
shader-design-engineering

Design, implement, and verify intentional real-time shader effects for WebGL2, WebGPU/WGSL, and SwiftUI/Metal, including dithering, color correctness, accessible fallbacks, profiling, and debugging.

Overview

Publishermemi-design
Repositorydesign-skills
Skill nameshader-design-engineering
Stars
7
Forks
0
Bundled files
7
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.

  • 7 bundled files

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

  • Open source

    Published by memi-design on GitHub. Read the source before you install it.

Installation

Install the Shader Design Engineering 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/memi-design/design-skills/tree/main/skills/shader-design-engineering
  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/memi-design/design-skills.git /tmp/design-skills
mkdir -p .claude/skills
cp -r /tmp/design-skills/skills/shader-design-engineering .claude/skills/shader-design-engineering
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Shader Design Engineering 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 Shader Design Engineering 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 Shader Design Engineering 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.

Shader Design Engineering

Build a shader only when it clarifies state, supports a visual system, communicates spatial change, or creates bounded delight. Treat the shader as product behavior with a fallback, not as decoration that can obscure content.

Workflow

  1. Inspect the rendering surface, deployment targets, existing renderer, asset licenses, design tokens, accessibility settings, and performance tooling.
  2. Write an effect contract: visual purpose, input and coordinate spaces, uniforms, textures, output color and alpha semantics, animation clock, quality tiers, fallback, and acceptance evidence.
  3. Choose the smallest compatible effect:
    • Use a color effect when output depends only on the current pixel.
    • Use a distortion effect when the shader changes sample coordinates.
    • Use a layer or texture effect only when neighboring samples are necessary.
    • Use a separate render pass only when the effect cannot fit the host framework's bounded effect API.
  4. Normalize coordinates explicitly. Keep pixel, normalized device, UV, view, and texture spaces named rather than relying on implicit conversions.
  5. Keep time and randomness controllable. Accept a clock and seed from the host so tests, reduced motion, screenshots, and replays remain deterministic.
  6. Perform lighting and interpolation in a documented working color space. Preserve premultiplied alpha when the host requires it, and convert only at known boundaries.
  7. Add dithering after the intended tone or color mapping and before final quantization. Match the technique to the artifact: ordered patterns for deterministic low-cost output, noise-shaped methods when visible structure is unacceptable.
  8. Provide reduced-motion, reduced-transparency, low-power, unsupported-platform, and renderer-failure behavior before polishing the full effect.
  9. Profile the target interaction with realistic content. Record frame time, GPU work, resolution, device, browser or OS, and quality tier.
  10. Verify the effect visually and structurally. Capture deterministic frames, inspect compilation and validation messages, exercise the fallback, and report any untested platform honestly.

Platform routing

Read only the reference needed for the selected surface:

SurfaceReference
WebGL2 and GLSL ESreferences/webgl2-glsl.md
WebGPU and WGSLreferences/wgsl-webgpu.md
SwiftUI and Metalreferences/swiftui-metal.md
Ordered, noise-based, or temporal ditheringreferences/dithering.md
Profiling, accessibility, and debuggingreferences/performance-accessibility-debugging.md

Use creative-rendering-audit when the requested outcome is an evidence-backed review rather than implementation.

Required handoff

Report:

  • effect purpose and non-goals;
  • platform, effect type, coordinate and color-space contract;
  • uniforms, textures, seed, clock, and quality tiers;
  • fallback and accessibility behavior;
  • source and asset provenance;
  • verification commands, rendered evidence, device, resolution, and measured frame budget;
  • compilation, runtime, or cross-platform checks that remain unverified.

Boundaries

  • Do not copy shader source, diagrams, or prose from link-only or restrictively licensed references.
  • Do not claim a visual match from static code inspection.
  • Do not hide content, focus, selection, or error state behind an effect.
  • Do not introduce uncontrolled time, device-dependent random state, or an unbounded sampling radius.
  • Do not ship a high-quality path without a behaviorally meaningful fallback.

Maintenance

Review platform and reference links at least every 180 days. Refresh lastResearchedAt, source URLs, and immutable reference revisions only after checking the referenced material. Run the repository validator; it flags malformed URLs and shader references that exceed the freshness window.

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 Shader Design Engineering AI skill do?

Design, implement, and verify intentional real-time shader effects for WebGL2, WebGPU/WGSL, and SwiftUI/Metal, including dithering, color correctness, accessible fallbacks, profiling, and debugging.

Why use Shader Design Engineering on TypingMind?

Because you install it once and use it with any model. Shader Design Engineering 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 Shader Design Engineering in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/memi-design/design-skills/tree/main/skills/shader-design-engineering. 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 Shader Design Engineering?

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 Shader Design Engineering?

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

Is the Shader Design Engineering AI skill free?

Yes. It is published on GitHub by memi-design 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 👇