Expert in building 3D experiences for the web - Three.js, React Three Fiber, Spline, WebGL, and interactive 3D scenes. Covers product configurators, 3D portfolios, immersive websites, and bringing depth to web experiences.
67
59%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-3d-web-experience/SKILL.mdQuality
Discovery
54%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description has strong trigger terms with specific technology names and use cases that clearly define a 3D web development niche. However, it lacks an explicit 'Use when...' clause, which is a significant gap for skill selection. The actions described are more categorical than concrete, leaning toward domain description rather than actionable capabilities.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about 3D graphics on the web, Three.js scenes, React Three Fiber components, WebGL shaders, or building interactive 3D experiences.'
Replace vague phrases like 'bringing depth to web experiences' with concrete actions such as 'create 3D models, set up lighting and cameras, animate objects, configure materials and textures.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (3D web experiences) and lists some specific use cases like 'product configurators, 3D portfolios, immersive websites,' but the actions are more like categories than concrete actions (e.g., 'building' is the only verb, and 'bringing depth to web experiences' is vague). | 2 / 3 |
Completeness | Describes what the skill covers but has no explicit 'Use when...' clause or equivalent trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and since the 'what' is also somewhat vague ('bringing depth to web experiences'), this falls to a 1. | 1 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Three.js', 'React Three Fiber', 'Spline', 'WebGL', '3D', 'product configurators', '3D portfolios', 'immersive websites', and 'interactive 3D scenes'. These cover a good range of terms a user working with 3D web content would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | The 3D web development niche is quite distinct, and the specific technology names (Three.js, React Three Fiber, Spline, WebGL) make it very unlikely to conflict with other skills. This has a clear, well-defined domain. | 3 / 3 |
Total | 9 / 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.
The skill provides strong, actionable code examples across multiple 3D web technologies with good coverage of common patterns (loading, scroll, performance, fallbacks). Its main weaknesses are structural redundancy (duplicated headers, overlapping expertise/capabilities lists), lack of validation checkpoints integrated into workflows, and a monolithic structure that would benefit from splitting into referenced files.
Suggestions
Remove duplicated section headers (e.g., '3D Stack Selection' and '3D Model Pipeline' each appear twice) and consolidate the overlapping expertise/capabilities lists into a single concise section.
Integrate the validation checks directly into the relevant workflows as explicit checkpoints (e.g., after model compression, verify file size < 5MB before proceeding; after scene setup, verify WebGL fallback works).
Split detailed reference content (validation checks, collaboration/delegation triggers, detailed code examples) into separate bundle files and reference them from the main SKILL.md to improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill has significant redundancy — section headers are duplicated (e.g., '3D Stack Selection' appears twice, '3D Model Pipeline' appears twice), and the role description, expertise list, and capabilities list overlap heavily. The 'Limitations' and 'When to Use' sections contain boilerplate. However, the code examples themselves are reasonably lean. | 2 / 3 |
Actionability | The skill provides fully executable code examples for Spline, React Three Fiber, GLTF compression CLI commands, scroll-driven 3D, performance optimization patterns, and fallback strategies. Code is copy-paste ready with real imports and realistic usage patterns. | 3 / 3 |
Workflow Clarity | The model optimization pipeline has a clear numbered sequence, and the product configurator/immersive portfolio workflows list steps. However, there are no explicit validation checkpoints or feedback loops — the optimization pipeline says 'test file size' but doesn't specify what to do if it fails. The validation checks section lists issues but isn't integrated into the workflows as checkpoints. | 2 / 3 |
Progressive Disclosure | The content is structured with clear sections and headers, but it's a monolithic file with no references to external files despite being quite long (~200+ lines). The validation checks, collaboration workflows, and detailed code examples could be split into separate reference files. No bundle files exist to offload content to. | 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
431bfad
Table of Contents
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.