3d-web-experience
You bring the third dimension to the web. You know when 3D enhances and when it's just showing off. You balance visual impact with performance. You make 3D accessible to users who've never touched a 3D app. You create moments of wonder without sacrificing usability.
36
21%
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/3d-web-experience/SKILL.mdQuality
Discovery
0%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 description reads as aspirational marketing copy rather than a functional skill description. It uses second-person voice ('You bring...', 'You know...') throughout, provides no concrete actions or tools, and lacks any explicit trigger guidance. It would be nearly impossible for Claude to reliably select this skill from a list of available skills.
Suggestions
Replace the aspirational second-person prose with third-person concrete actions, e.g., 'Creates interactive 3D scenes and models for web using Three.js/WebGL, implements 3D animations, renders .glb/.gltf assets.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about 3D web content, Three.js, WebGL, 3D models, 3D animations, or interactive 3D visualizations.'
Remove subjective filler phrases like 'moments of wonder' and 'just showing off' and replace with specific capabilities like 'camera controls, lighting, textures, model loading, and scene composition.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language like 'bring the third dimension to the web' and 'create moments of wonder' without listing any concrete actions such as creating 3D models, rendering scenes, implementing WebGL, or working with Three.js. | 1 / 3 |
Completeness | The description fails to clearly answer 'what does this do' with concrete capabilities and completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | The only relevant keyword is '3D' repeated in abstract phrases. It lacks natural trigger terms users would say like 'Three.js', 'WebGL', '3D model', '3D animation', 'rotate', 'scene', '.glb', '.gltf', or 'three-dimensional visualization'. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it could overlap with any web development, animation, visualization, or design skill. There are no distinct triggers that would help Claude differentiate this from other visual/web skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a reasonable breadth of 3D web development topics with some useful code snippets and a model optimization pipeline. However, it suffers from formatting issues (nested code fences inside Python blocks), lacks validation/feedback loops in workflows, includes unnecessary explanatory text that Claude already knows, and dumps all content into a single monolithic file without progressive disclosure.
Suggestions
Fix the nested code fence formatting — the outer ```python blocks incorrectly wrap inner JSX/bash/text code blocks, which would break parsing.
Add explicit validation checkpoints to the model pipeline (e.g., 'Verify output file size < 5MB', 'Load in browser and check for visual artifacts') and include error recovery steps.
Split detailed content (stack comparison, model pipeline, scroll patterns) into separate referenced files, keeping SKILL.md as a concise overview with links.
Remove the role description paragraph and capabilities bullet list — they add no actionable information. Start directly with the stack selection or a quick-start example.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary framing ('You bring the third dimension to the web...') and the capabilities list is a vague enumeration that doesn't add actionable value. The anti-patterns section explains obvious things ('Most traffic is mobile', 'Users think it's broken'). However, the code examples themselves are reasonably lean. | 2 / 3 |
Actionability | There are concrete code examples for Spline, R3F, scroll-driven 3D, and gltf-transform CLI commands, which is good. However, several code blocks are wrapped inside Python fenced blocks incorrectly (nested code fences), the decision tree is text art rather than executable logic, and some examples are incomplete (e.g., the RotatingModel mesh content is '...'). The anti-patterns section is descriptive rather than instructive. | 2 / 3 |
Workflow Clarity | The model pipeline has a numbered sequence (model → reduce → bake → export → compress → test), which is helpful. However, there are no explicit validation checkpoints or feedback loops — e.g., no step to verify the compressed output works correctly, no error recovery guidance if compression fails or the model exceeds size targets. | 2 / 3 |
Progressive Disclosure | The skill is a monolithic wall of text with no references to external files for detailed content. The stack comparison, model pipeline, scroll-driven 3D, and anti-patterns are all inline in one large document. There's no clear quick-start section separated from advanced content, and the 'Related Skills' section references other skills but doesn't link to supplementary detail files. | 1 / 3 |
Total | 7 / 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
- sickn33/antigravity-awesome-skills
- Commit
d739c8b
- 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.