threejs-loaders
Three.js asset loading - GLTF, textures, images, models, async patterns. Use when loading 3D models, textures, HDR environments, or managing loading progress.
64
77%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/threejs-loaders/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid skill description that clearly identifies its niche (Three.js asset loading) and includes an explicit 'Use when' clause with good trigger terms. Its main weakness is that the 'what' portion reads more like a topic list than a set of concrete actions—it could benefit from describing specific capabilities rather than just listing asset types.
Suggestions
Replace the topic-list style with concrete actions, e.g., 'Loads GLTF/GLB models, applies textures and materials, configures HDR environment maps, and implements async loading with progress tracking in Three.js.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Three.js asset loading) and lists asset types (GLTF, textures, images, models, async patterns), but doesn't describe concrete actions like 'load GLTF models with progress tracking' or 'configure texture compression'. It's more of a topic list than specific capabilities. | 2 / 3 |
Completeness | Clearly answers both what ('Three.js asset loading - GLTF, textures, images, models, async patterns') and when ('Use when loading 3D models, textures, HDR environments, or managing loading progress') with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'GLTF', 'textures', 'images', 'models', '3D models', 'HDR environments', 'loading progress', 'Three.js'. These cover common variations of what users would mention when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Three.js asset loading specifically. The combination of Three.js, GLTF, HDR environments, and loading progress creates a very specific trigger profile unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive Three.js loader reference with excellent actionability — nearly every code example is complete and executable. Its main weakness is length: it tries to be an exhaustive API reference rather than a focused skill, covering many loader types and configuration options that could be split into separate files or trimmed. The workflow dimension suffers from presenting patterns in isolation rather than as a cohesive loading strategy.
Suggestions
Trim the 'Other Model Formats' section to a brief table of loader names and imports, since the pattern is identical to GLTF loading and Claude can infer the usage.
Reduce the texture configuration section to only non-obvious settings (colorSpace, anisotropy) and remove standard API properties Claude already knows.
Add a brief recommended workflow at the top showing the typical order of operations: set up LoadingManager → configure loaders (DRACO/KTX2) → load assets → validate/handle errors → start scene.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is largely efficient with executable code examples, but it's quite long (~400 lines) and includes some sections that could be trimmed or consolidated. The texture configuration section lists many options that are standard Three.js API knowledge, and the 'Other Model Formats' section covers 4 formats with boilerplate patterns that Claude could infer from the GLTF example. | 2 / 3 |
Actionability | Every section provides fully executable, copy-paste ready code examples with proper imports, complete function signatures, and realistic usage patterns. The examples cover callback style, async/await, error handling, and practical patterns like asset managers and fallback loading. | 3 / 3 |
Workflow Clarity | While individual loading patterns are clear, there's no explicit workflow for the overall asset loading process (e.g., when to set up LoadingManager before loading, order of operations for DRACO/KTX2 setup). The error handling section provides good patterns but they're presented as isolated utilities rather than integrated into a recommended loading workflow with validation checkpoints. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and a 'See Also' section referencing related skills. However, the file is quite long and monolithic — sections like texture configuration details, all model format loaders, and the custom AssetManager class could reasonably be split into referenced files. For a standalone skill with no bundle, it tries to cover too much inline. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (624 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- CloudAI-X/threejs-skills
- Commit
b1c6230
- Reviewed
Table of Contents
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.