3d-web-experience
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 (Three.js, React Three Fiber, WebGL, Spline) that create a distinctive niche. However, it lacks an explicit 'Use when...' clause, which significantly hurts completeness. The actions described are more categorical ('covers', 'bringing depth') rather than concrete, and 'bringing depth to web experiences' is vague filler.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Three.js, React Three Fiber, WebGL, 3D rendering, or building interactive 3D scenes for the web.'
Replace vague phrases like 'bringing depth to web experiences' and 'covers' with concrete actions such as 'Creates 3D product configurators, builds interactive 3D portfolios, implements WebGL shaders, and sets up React Three Fiber scenes.'
Remove the word 'Expert in' which is a self-referential claim; use third-person action verbs instead (e.g., 'Builds 3D experiences for the web...').
| 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 vague compared to 'create interactive 3D product configurators'). 'Bringing depth to web experiences' is fluffy. | 2 / 3 |
Completeness | Describes what it 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 the 'what' portion is also somewhat vague ('covers' and 'bringing depth'), so this falls to 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', 'interactive 3D scenes'. Good coverage of both library names and use-case terms. | 3 / 3 |
Distinctiveness Conflict Risk | The focus on 3D web technologies (Three.js, React Three Fiber, Spline, WebGL) creates a clear niche that is unlikely to conflict with general web development or other skills. The specific library names serve as strong distinguishing triggers. | 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.
This skill provides solid, actionable code examples across multiple 3D web technologies with good coverage of common patterns (model loading, scroll integration, performance optimization, fallbacks). Its main weaknesses are structural redundancy (duplicated headers and overlapping Expertise/Capabilities sections), lack of validation checkpoints in multi-step workflows, and a monolithic structure that could benefit from splitting detailed content into referenced files.
Suggestions
Remove the duplicated section headers (e.g., '### 3D Stack Selection' immediately followed by '## 3D Stack Selection') and consolidate the overlapping 'Expertise' and 'Capabilities' lists into a single concise section.
Add explicit validation/verification steps to the model pipeline (e.g., 'Verify output file size with `ls -lh output.glb`; if > 5MB, increase Draco compression or reduce texture resolution and re-run').
Split detailed code examples and the validation checks into separate referenced files (e.g., PATTERNS.md, VALIDATION.md) to keep SKILL.md as a concise overview with clear navigation links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill has some redundancy — the 'Expertise' and 'Capabilities' sections largely duplicate each other, and the role description is fluffy ('You create moments of wonder'). The pattern headers are repeated (e.g., '### 3D Stack Selection' followed by '## 3D Stack Selection'). 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, and fallback strategies. The code is copy-paste ready with real imports and realistic patterns. | 3 / 3 |
Workflow Clarity | The model pipeline has a clear numbered sequence but lacks explicit validation checkpoints — there's no 'verify the output works' step after compression, no feedback loop for when file size exceeds targets. The product configurator and immersive portfolio workflows are listed but lack validation steps. The optimization pipeline is a numbered list without verification gates. | 2 / 3 |
Progressive Disclosure | Content is organized into logical sections with clear headers, but everything is inline in one large file with no references to external files for deeper content. The validation checks, collaboration triggers, and detailed code examples could be split out. The delegation triggers section provides good cross-references to other skills though. | 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 | |
- Repository
- boisenoise/skills-collections
- Commit
636b862
- 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.