webgpu-threejs-tsl

Comprehensive guide for developing WebGPU-enabled Three.js applications using TSL (Three.js Shading Language). Covers WebGPU renderer setup, TSL syntax and node materials, compute shaders, post-processing effects, and WGSL integration. Use this skill when working with Three.js WebGPU, TSL shaders, node materials, or GPU compute in Three.js.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

80%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A concise, actionable overview with strong runnable code snippets, but it lacks an explicit validated workflow and every bundle file it references is absent, undermining its progressive-disclosure structure.

Suggestions

Create the referenced bundle files (docs/*.md, examples/*.js, templates/*.js, REFERENCE.md) so the 'Skill Contents' navigation resolves, or remove paths that will not be provided.

Add a short validated workflow for at least one fragile operation (e.g. compute-shader setup with an init/check step) to lift workflow_clarity above 2.

Mark which 'Skill Contents' entries are required vs. optional so Claude knows what to load first.

Dimension	Reasoning	Score
Conciseness	Lean overview that never explains what Three.js or WebGPU is; every code snippet (Quick Start, node materials, method chaining, Fn()) earns its place. Not a 2 because there is no padded explanation of concepts Claude already knows.	3 / 3
Actionability	The Quick Start snippet is copy-paste runnable, and node materials, method chaining, and custom Fn() functions all give concrete executable code. Not a 2 because the examples are complete and specific rather than pseudocode.	3 / 3
Workflow Clarity	The body is well-organized but presents conceptual patterns and pointers rather than a sequenced multi-step procedure with validation checkpoints; there is no explicit workflow or feedback loop. Not a 1 because organization is clear, but not a 3 because no validated sequence is given.	2 / 3
Progressive Disclosure	The 'Skill Contents' section signals one-level-deep references to docs/, examples/, templates/, and REFERENCE.md, but all 14 referenced files are missing, so the disclosure structure is broken in practice. Not a 3 because the navigation leads to nonexistent files; not a 1 because the in-body structure and signaling itself is sound.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that clearly states concrete capabilities and provides an explicit 'Use this skill when' trigger. It is distinct from generic Three.js skills and unlikely to conflict.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities ('WebGPU renderer setup, TSL syntax and node materials, compute shaders, post-processing effects, and WGSL integration'), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers 'what' (the capabilities listed) and 'when' via the 'Use this skill when working with Three.js WebGPU, TSL shaders, node materials, or GPU compute in Three.js' clause. Not a 2 because the when-trigger is explicit, not merely implied.	3 / 3
Trigger Term Quality	Natural trigger terms a user would say ('Three.js WebGPU', 'TSL shaders', 'node materials', 'GPU compute') are present with good coverage; not just technical jargon. Not scored below 3 because it covers the common variations a user would voice.	3 / 3
Distinctiveness Conflict Risk	Clear niche (WebGPU/TSL within Three.js) with distinct triggers; unlikely to fire for unrelated skills. Voice is third person throughout, so no specificity penalty applies.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: dgreenheck/webgpu-claude-skill
Path: skills/webgpu-threejs-tsl/SKILL.md
Commit: af2319b

Reviewed: 13 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.