threejs-loaders

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

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

The canonical home for this skill is threejs-loaders in CloudAI-X/threejs-skills

Quality

Content

78%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.

A comprehensive, highly actionable reference for Three.js loaders with executable code throughout. The main weakness is its monolithic single-file structure, which inlines ~620 lines that could be progressively disclosed via reference files.

Suggestions

Move the long-tail per-format details (OBJ/MTL, FBX, STL, PLY, the full AssetManager class) into reference files under references/ and link to them from a leaner SKILL.md.

Deduplicate repeated import lines across snippets to reduce token cost and tighten conciseness.

Add a short 'typical loading workflow' sequence (load -> configure -> add to scene -> dispose) near the top to give an explicit end-to-end flow.

Dimension	Reasoning	Score
Conciseness	Mostly efficient code-first content that assumes competence, with minor redundancy (TextureLoader and GLTFLoader imports repeated across many snippets) that could be trimmed.	4 / 5
Actionability	Copy-paste ready, executable code covers all common cases — GLTF, textures, HDR/EXR, Draco, KTX2, OBJ/MTL, FBX, STL, PLY, async/Promise wrappers, caching, and error handling.	5 / 5
Workflow Clarity	Well-organized sections with the async and error-handling examples showing feedback patterns; as a reference/catalog skill it lacks an explicit end-to-end loading sequence but none is strictly required for non-destructive loading.	4 / 5
Progressive Disclosure	A single ~620-line file with good section headers but no bundle files or one-level-deep references; content such as the full AssetManager class and per-format details is inlined rather than split into separate reference files.	3 / 5
	Total	16 / 20 Passed

Description

88%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, specific description with concrete capabilities and an explicit Use-when clause covering the main loading scenarios. Minor improvements possible by adding common file extensions (.glb, .hdr) to the trigger terms.

Suggestions

Add file extensions to the trigger clause (e.g., '.glb', '.gltf', '.hdr', '.exr') so Claude matches when users reference specific file types.

Consider naming 'progress tracking' explicitly in the when-clause to better match the 'managing loading progress' phrasing users might say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — "GLTF, textures, images, models, async patterns" and "HDR environments" — giving comprehensive coverage of asset-loading actions.	5 / 5
Completeness	Explicitly states both the what ("Three.js asset loading - GLTF, textures, images, models, async patterns") and the when ("Use when loading 3D models, textures, HDR environments, or managing loading progress").	5 / 5
Trigger Term Quality	Natural trigger phrases like "loading 3D models, textures, HDR environments" are present, but file extensions (.glb/.gltf/.hdr/.exr) and a few synonyms are omitted.	4 / 5
Distinctiveness Conflict Risk	The Three.js asset-loading niche is clear and triggers are specific to 3D loading, though minor overlap risk exists with sibling skills like threejs-textures.	4 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 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
referenced_paths_exist	Referenced path issues: 3 missing, 1 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: calesthio/OpenMontage
Path: .agents/skills/threejs-loaders/SKILL.md
Commit: 1bab711

Reviewed: about 20 hours 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.