Skip to content
cccskills
FreePublished on GitHub

ai-smell-detector

Use to audit a generated or heavily templated interface for generic AI aesthetics, unjustified trend patterns, component-registry residue, vague copy, repetitive motion, novelty theater, or visual decisions that lack brand/UX rationale.

The English summary is being prepared. Showing the original description.

See how to install

Files included (2)

  • SKILL.md1.6 KB
  • agents/openai.yaml240 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

AI Smell Detector

Detect patterns, not forbidden shapes

The following are smells when repeated without a project-specific reason:

  • centered hero + generic eyebrow + two CTAs;
  • arbitrary bento/three-card feature grids;
  • gradient text and blue/purple glow as default “premium” styling;
  • glassmorphism with no material concept;
  • excessive pills/badges;
  • identical corner radius on every surface;
  • icon + heading + paragraph card repetition;
  • every section using the same fade-up reveal;
  • oversized vague claims with no evidence;
  • stock imagery with inconsistent lighting/crop;
  • generic font pairing with no typographic character;
  • floating decorative objects with no composition role;
  • 3D cursor/particles/parallax that communicate nothing.

Test each suspicious decision

Ask:

  1. What user/brand/content purpose does this serve?
  2. Would the design lose meaning if it were removed?
  3. Is this repeated because of a system or because it was an easy default?
  4. Does the choice appear in the references as a principle or as a copied fashion cue?
  5. Is there a more specific expression of the same intent?

Output

Classify each smell as: keep, adapt, replace, or remove, with the reason. Avoid redesigning merely to be unusual.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Use for release-level accessibility and performance review, including WCAG 2.2 AA, keyboard/focus, target size, reduced motion, semantic controls, Core Web Vitals, images/fonts/JavaScript, and animation or 3D performance budgets.

The English summary is being prepared. Showing the original description.

Lrinvl1203/world-class-web-design-os8Updated Oct 2, 2026

Use when a website needs a strong visual point of view, distinct concept routes, composition, typography, color/materiality, imagery direction, spatial rhythm, or a memorable signature idea.

The English summary is being prepared. Showing the original description.

Lrinvl1203/world-class-web-design-os8Updated Oct 2, 2026

Use when deciding whether to implement UI from native HTML/CSS, accessible primitives, shadcn-style source components, or visual component registries such as 21st.dev, Aceternity, React Bits, Motion Primitives, Magic UI, or Animate UI.

The English summary is being prepared. Showing the original description.

Lrinvl1203/world-class-web-design-os8Updated Oct 2, 2026

Use after substantial web projects or repeated design defects to convert evidence into reusable skill improvements through root-cause analysis, regression scenarios, and controlled proposals without silently changing the core OS.

The English summary is being prepared. Showing the original description.

Lrinvl1203/world-class-web-design-os8Updated Oct 2, 2026

Use when the design concept calls for Three.js or React Three Fiber 3D, WebGL/WebGPU, Rive, Spline, Theatre.js, SVG, canvas, shaders, particle systems, or other immersive creative-web techniques.

The English summary is being prepared. Showing the original description.

Lrinvl1203/world-class-web-design-os8Updated Oct 2, 2026

Use as an independent design-review pass after rendering a website; evaluates macro, meso, micro craft, applies the Design Quality rubric, identifies root causes, and prioritizes changes without defending the implementation intent.

The English summary is being prepared. Showing the original description.

Lrinvl1203/world-class-web-design-os8Updated Oct 2, 2026

See all skills by Lrinvl1203

Report a problem with this skill