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.

Quality

55%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/3d-web-experience/SKILL.md

The canonical home for this skill is 3d-web-experience in sickn33/agentic-awesome-skills

Quality

Content

72%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.

The content is a strong, code-rich reference: actionable examples across the main 3D-web stacks, clear decision guidance, and good section structure. Its main weakness is workflow rigor — the optimization/compression pipelines are listed as steps but lack validation checkpoints for irreversible batch operations.

Suggestions

Add explicit validation/feedback checkpoints to the 3D Model Pipeline, e.g. after compression verify file size and that the GLB still loads before shipping.

Make placeholder snippets runnable: replace `<mesh ref={ref}>...</mesh>` and `scene="https://prod.spline.design/xxx/..."` with complete minimal examples or a clear placeholder convention.

Drop the redundant opening paragraph that restates the YAML description to trim tokens.

Dimension	Reasoning	Score
Conciseness	The body is code-forward and tight — decision trees, comparison tables, and executable snippets carry most of the weight — with only minor padding such as the opening 'You bring the third dimension...' restating the description, fitting the 'efficient; minor instances that could be trimmed' anchor above the 3-anchor's 'mostly efficient but includes some unnecessary explanation'.	4 / 5
Actionability	It provides multiple copy-paste-ready blocks (Spline, R3F, gltf-transform compression, ScrollControls, GSAP) plus a concrete decision tree, matching the 'mostly executable guidance; concrete code with minor gaps' anchor; it stops short of 5 because some snippets (e.g. `<mesh ref={ref}>...</mesh>`) are placeholders rather than fully runnable.	4 / 5
Workflow Clarity	Sequences like the 3D Model Pipeline (1-6) and format selection give a clear order, but destructive/batch operations (draco compression, poly-count reduction, model optimization) have no validation checkpoints or feedback loops, so per the destructive/batch cap workflow_clarity cannot exceed 3 even though the 4-anchor's sequence is otherwise present.	3 / 5
Progressive Disclosure	No bundle files exist and the skill is a single well-organized file with clear section headers (Capabilities, Patterns, Anti-Patterns, Related Skills); per the under-50-references guideline this satisfies the 'well-organized sections' condition for a top score without external references.	5 / 5
	Total	16 / 20 Passed

Description

37%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.

The description is a stylistic value-statement rather than a functional trigger: it conveys tone about 3D on the web but names no concrete actions and provides no 'Use when' guidance. It would rarely be selected from a natural user request because it lacks the keywords users actually say.

Suggestions

Rewrite in third person naming concrete actions, e.g. 'Builds and optimizes 3D web experiences using Three.js, React Three Fiber, and Spline.'

Add an explicit trigger clause: 'Use when the user asks for 3D scenes, WebGL, product configurators, or interactive 3D on the web.'

Include natural trigger terms users say (Three.js, React Three Fiber, R3F, WebGL, GLB/GLTF, 3D model) rather than only '3D' and 'the web'.

Dimension	Reasoning	Score
Specificity	The description names the 3D-web domain but uses only abstract attitudinal statements ('You know when 3D enhances', 'You balance visual impact with performance') with no concrete actions, and it is written in second person, so it fits the 'names the domain but actions are minimal or generic' anchor rather than the 3-anchor which requires 1-2 concrete actions.	2 / 5
Completeness	A vague 'what' is present ('bring the third dimension to the web') but there is no explicit 'Use when...' trigger clause, so per the missing-trigger-cap guideline it cannot exceed 3, and the 4-anchor requires an explicit (if imperfect) 'when'.	3 / 5
Trigger Term Quality	It offers only the generic terms '3D' and 'the web'; none of the natural phrases a user would say (Three.js, WebGL, 3D model, product configurator) appear, matching the 'one or two generic keywords' anchor and falling below the 3-anchor's 'some relevant keywords'.	2 / 5
Distinctiveness Conflict Risk	The 3D-web niche is reasonably specific, but the generic, trigger-free phrasing means it could still overlap with adjacent frontend/animation skills, fitting the 'somewhat specific but could still overlap' anchor better than the more concrete 4-anchor.	3 / 5
	Total	10 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/3d-web-experience/SKILL.md
Commit: 731a928

Reviewed: 1 day 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.