r3f-loaders

React Three Fiber asset loading - useGLTF, useLoader, Suspense patterns, preloading. Use when loading 3D models, textures, HDR environments, or managing loading states.

Quality

76%

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 ./.agents/skills/r3f-loaders/SKILL.md

Quality

Content

68%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 thorough, highly actionable R3F loaders cookbook with executable examples across formats and hooks, weakened by repetition across examples and a monolithic structure that belongs partly in separate reference files. Adding validation steps and splitting reference detail would lift the lower dimensions.

Suggestions

Add an explicit validation/feedback checkpoint after loading (e.g., check useProgress errors, confirm scene.traverse before use) to support fragile loading workflows.

Move the per-format API detail (OBJ/MTL/FBX/STL/PLY, drei hook catalog) into a references/ file and link to it, keeping SKILL.md as a concise overview.

De-duplicate the repeated Canvas/Suspense and import boilerplate across examples to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	Mostly efficient code-first reference, but it repeats boilerplate imports and wrapper components across many near-identical examples (useGLTF/useTexture/useFBX each re-show Canvas/Suspense patterns), and the inline section-per-format listing could be tightened without losing value.	3 / 5
Actionability	Nearly every section is copy-paste-ready executable TSX with real import paths, concrete URLs, and configuration options covering the common cases from basic loading through Draco, progress callbacks, and multi-format support.	5 / 5
Workflow Clarity	Sequences are clear for each loading scenario (preload -> use -> render) and the Suspense/Error Handling sections show a coherent order, but there is no explicit validation checkpoint for confirming assets loaded or errors surfaced before proceeding.	4 / 5
Progressive Disclosure	Well-organized with clear section headers and a single-level See Also, but the entire reference is a monolithic SKILL.md (~600 lines) with API-per-format detail that would be better split into reference files; no bundle files are provided to offload it.	3 / 5
	Total	15 / 20 Passed

Description

85%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 clear, well-triggered description that concretely names the relevant hooks and asset types and gives explicit 'Use when' guidance. Minor gains possible from adding file extensions like .glb/.hdr and framing actions as verbs.

Suggestions

Add common file extensions as trigger terms (e.g., '.glb', '.gltf', '.hdr', '.fbx') to match how users phrase model-loading requests.

Lead with verb-based actions (e.g., 'Loads and preloads 3D assets') to sharpen the specificity of capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions (useGLTF, useLoader, Suspense patterns, preloading), though each is a hook/API name rather than a fully fleshed action, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what ('React Three Fiber asset loading - useGLTF, useLoader, Suspense patterns, preloading') and when ('Use when loading 3D models, textures, HDR environments, or managing loading states') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user-facing terms like '3D models', 'textures', 'HDR environments', and 'loading states'; missing common synonyms or file extensions like .glb/.gltf/.hdr.	4 / 5
Distinctiveness Conflict Risk	Scoped to R3F-specific loader hooks with distinct triggers (3D models, HDR environments), minimizing overlap with general React or generic Three.js skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (613 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: AzizBelhassan/timeverse
Path: .agents/skills/r3f-loaders/SKILL.md
Commit: 9dc2cb4

Reviewed: ~15 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.