If you're working with Three.js and want to use the new WebGPU renderer, this skill gets you up to speed with TSL, which lets you write shaders in JavaScript instead of raw GLSL or WGSL strings. It covers the basics like setting up node materials, compute shaders for things like particle systems, and post-processing pipelines. The examples are practical (there's a full Earth shader with atmosphere) and the docs explain the method chaining syntax that takes some getting used to. Honestly, TSL is still evolving and the official documentation is sparse, so having the core concepts, common patterns, and GPU device limits reference in one place saves a lot of digging through GitHub issues.

skills.sh installs
1.7K
GitHub stars
1.3K
last updated
Jul 14, 2026

Install

$ npx -y skills add dgreenheck/webgpu-claude-skill --skill webgpu-threejs-tsl --agent claude-code

Installs into .claude/skills of the current project.

Files

WebGPU Three.js with TSL

TSL (Three.js Shading Language) is a node-based shader abstraction that lets you write GPU shaders in JavaScript instead of GLSL/WGSL strings.

Quick Start

import * as THREE from 'three/webgpu';
import { color, time, oscSine } from 'three/tsl';

const renderer = new THREE.WebGPURenderer();
await renderer.init();

const material = new THREE.MeshStandardNodeMaterial();
material.colorNode = color(0xff0000).mul(oscSine(time));

Skill Contents

Documentation

  • docs/core-concepts.md - Types, operators, uniforms, control flow
  • docs/materials.md - Node materials and all properties
  • docs/compute-shaders.md - GPU compute with instanced arrays
  • docs/post-processing.md - Built-in and custom effects
  • docs/wgsl-integration.md - Custom WGSL functions
  • docs/device-loss.md - Handling GPU device loss and recovery
  • docs/limits-and-features.md - WebGPU device limits and optional features

Sponsors

Details

Repository
github.com/dgreenheck/webgpu-claude-skill
First seen
Jun 3, 2026

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs