CtrlK
BlogDocsLog inGet started
Tessl Logo

threejs-loaders

Three.js asset loading - GLTF, textures, images, models, async patterns. Use when loading 3D models, textures, HDR environments, or managing loading progress.

62

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/threejs-loaders/SKILL.md

The canonical home for this skill is threejs-loaders in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

67%Scale 1-5

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, highly actionable Three.js loader reference with excellent executable code examples covering all major loader types and patterns. Its main weakness is that it's too long and monolithic — it tries to be both a quick-start guide and an exhaustive reference in a single file, which hurts conciseness and progressive disclosure. Splitting advanced topics (compression, alternative formats, error handling patterns) into separate files would significantly improve it.

Suggestions

Split alternative model formats (OBJ, FBX, STL, PLY) into a separate reference file like LOADERS-OTHER-FORMATS.md and link to it from the main skill

Move the custom AssetManager class, error handling patterns (retry, timeout, fallback), and loading from different sources into an ADVANCED-LOADING.md file

Keep the main SKILL.md focused on GLTF loading, TextureLoader, LoadingManager, and async/Promise patterns as the core quick-start content

DimensionReasoningScore

Conciseness

The skill is quite long (~400+ lines) and includes many loader variants (OBJ, FBX, STL, PLY) and patterns (retry, timeout, custom asset manager) that could be in separate reference files. Some sections like the custom AssetManager class and error handling patterns are verbose for a skill file. However, it avoids explaining what Three.js or loaders are conceptually, which is good.

3 / 5

Actionability

Every section provides complete, executable code examples with proper imports, callback handling, and realistic usage patterns. The code covers common cases (GLTF, textures, HDR), compression variants (Draco, KTX2, Meshopt), async patterns, error handling, and caching — all copy-paste ready.

5 / 5

Workflow Clarity

The content is well-sequenced from simple loading to advanced patterns (compression, async, caching, error handling). The LoadingManager section shows clear progress tracking. However, there's no explicit validation workflow — e.g., no guidance on verifying loaded models are correct or handling missing textures in GLTF files systematically. Since this is primarily a reference skill rather than a destructive/batch operation, the missing validation doesn't cap the score.

4 / 5

Progressive Disclosure

The skill is a monolithic document with all content inlined — texture configuration, multiple model formats, async patterns, caching, error handling, and performance tips all in one file. The 'See Also' references at the bottom are good but the bulk content (especially OBJ/FBX/STL/PLY loaders, the custom AssetManager, and error handling utilities) should be in separate reference files. No bundle files exist to offload this content.

2 / 5

Total

14

/

20

Passed

Description

82%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.

This is a solid skill description that clearly communicates its scope and provides explicit 'Use when' guidance. Its main weakness is that it lists asset types rather than concrete actions (e.g., 'parse', 'decode', 'cache'), making it slightly less specific about what operations it performs. The trigger terms and distinctiveness are strong.

Suggestions

Replace the noun list with action verbs: e.g., 'Loads and parses GLTF/GLB models, applies texture maps, configures HDR environment lighting, and manages async loading progress in Three.js.'

Add file extension variations to trigger terms: '.glb', '.gltf', '.hdr', 'environment map', 'HDRI' to improve matching on natural user queries.

DimensionReasoningScore

Specificity

Names the domain (Three.js asset loading) and lists asset types (GLTF, textures, images, models) plus mentions async patterns, but doesn't describe concrete actions like 'loads and parses GLTF files, applies texture maps, handles loading callbacks'.

3 / 5

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 explicit trigger phrases.

5 / 5

Trigger Term Quality

Includes good natural keywords like 'GLTF', '3D models', 'textures', 'HDR environments', 'loading progress'. Missing some variations like '.glb', '.gltf', 'environment maps', 'HDRI', 'texture loading', 'model import'.

4 / 5

Distinctiveness Conflict Risk

Very distinct niche - Three.js asset loading is specific enough to avoid conflicts with general 3D skills, general JavaScript skills, or other Three.js skills focused on rendering/animation. The trigger terms are clearly scoped to loading concerns.

5 / 5

Total

17

/

20

Passed

Validation

81%

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

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (646 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

9

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.