three-best-practices

Three.js performance optimization and best practices guidelines. Use when writing, reviewing, or optimizing Three.js code. Triggers on tasks involving 3D scenes, WebGL/WebGPU rendering, geometries, materials, textures, lighting, shaders, or TSL.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/three-best-practices/SKILL.md

Quality

Content

61%Weight 40%Scale 1-5

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

The body is a well-organized, priority-ordered index of 120+ best-practice rules with a few useful inline code snippets, and it correctly assumes Claude's competence. Its main weakness is that almost all actionable detail is deferred to a `rules/` directory that is not present in the bundle, leaving the SKILL.md as a table of contents without the referenced payload.

Suggestions

Ship the referenced `rules/*.md` files (e.g. rules/setup-use-import-maps.md, rules/tsl-complete-reference.md) or remove the dangling references, since progressive disclosure depends on the linked payload actually existing.

Inline a few more executable examples for the highest-impact CRITICAL categories (memory disposal, render loop) so the skill is actionable even before the rule files are read.

Convert the 'How to Use' example-path code block into a short prose pointer or a tighter representative list to trim tokens that merely restate the rule IDs already shown above.

Dimension	Reasoning	Score
Conciseness	Mostly a lean, scannable reference: a priority table plus terse one-line rule summaries with prefixes, assuming Claude's competence without explaining basic concepts. Minor verbosity in a few headings and the inline 'How to Use' code block listing example rule paths.	4 / 5
Actionability	The body is primarily an index of rule names with one-line glosses rather than executable guidance; the four inline code snippets (import maps, disposal, TSL, mobile detection) are executable, but the bulk of 'rules' defer real instruction to external files, so most guidance is high-level rather than copy-paste ready.	3 / 5
Workflow Clarity	As a reference/lookup skill (not a destructive multi-step process), it has a clear structure: priority-ordered categories, a 'When to Apply' list, and a 'How to Use' pointer to rule files. No validation checkpoints are needed since it is non-destructive, and navigation is unambiguous.	4 / 5
Progressive Disclosure	The body references a `rules/` directory of per-rule markdown files (e.g. rules/setup-use-import-maps.md, rules/tsl-complete-reference.md) as the location of real detail, but no `rules/`, `references/`, `scripts/`, or `assets/` bundle directories exist, so the signaled one-level-deep references point to missing files and the overview is largely a stub.	2 / 5
	Total	13 / 20 Passed

Description

90%Weight 40%Scale 1-5

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, well-structured description with clear what/when guidance and comprehensive, natural trigger terms that map closely to what users would actually say when they need Three.js help. The only minor gap is that the named actions (writing/reviewing/optimizing) are somewhat broad rather than enumerating concrete operations.

Dimension	Reasoning	Score
Specificity	Names the domain (Three.js performance optimization and best practices) and several concrete actions ('writing, reviewing, or optimizing Three.js code'), but the actions are broad verbs rather than a comprehensive list of specific operations like dispose, merge, or compress.	4 / 5
Completeness	Explicitly answers both 'what' ('Three.js performance optimization and best practices guidelines') and 'when' ('Use when writing, reviewing, or optimizing Three.js code. Triggers on tasks involving...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including '3D scenes', 'WebGL/WebGPU rendering', 'geometries, materials, textures, lighting, shaders, or TSL' — these are exactly the terms users say when they need Three.js help.	5 / 5
Distinctiveness Conflict Risk	Clear niche (Three.js-specific performance/best practices) with distinct triggers like TSL, WebGPU, and shader terms that are unlikely to match other skills; minimal conflict risk.	5 / 5
	Total	19 / 20 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: zebbern/claude-code-guide
Path: skills/three-best-practices/SKILL.md
Commit: 9d252b3

Reviewed: 2 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.