MCP HubMCP Hub
Volver a habilidades

review-web-design

pjt222
Actualizado 2 days ago
8 vistas
17
2
17
Ver en GitHub
Pruebastestingdesign

Acerca de

Esta habilidad analiza diseños web en cuanto a maquetación, tipografía, color, espaciado, responsividad y coherencia de marca. Es útil para revisar maquetas antes del desarrollo, evaluar sitios implementados y realizar pruebas en diferentes puntos de ruptura. La habilidad acepta URLs, maquetas o capturas de pantalla y puede consultar guías de marca para ofrecer una retroalimentación exhaustiva.

Instalación rápida

Claude Code

Recomendado
Principal
npx skills add pjt222/agent-almanac -a claude-code
Comando PluginAlternativo
/plugin add https://github.com/pjt222/agent-almanac
Git CloneAlternativo
git clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/review-web-design

Copia y pega este comando en Claude Code para instalar esta habilidad

Documentación

Review Web Design

Eval web design → visual quality, consistency, cross-device.

Use When

  • Mockup|prototype pre-dev review
  • Implemented site|app design quality
  • Design review session feedback
  • Brand consistency multi-page
  • Responsive behavior across breakpoints

In

  • Required: Design (URL|mockup|screenshot|src)
  • Optional: Brand guidelines|design system
  • Optional: Target audience
  • Optional: Reference|competitor designs
  • Optional: Concerns

Do

Step 1: Visual Hierarchy

Guides eye → importance.

  • Focal point: Obvious entry per page?
  • Heading hierarchy: H1→H2→H3 logical?
  • Size contrast: Important > supporting?
  • Color contrast: CTAs prominent?
  • Whitespace: Separates groups?
  • Reading flow: F|Z pattern?
## Visual Hierarchy Assessment
| Page/Section | Focal Point | Hierarchy Clear? | Issues |
|-------------|-------------|-----------------|--------|
| Homepage | Hero section CTA | Yes | Secondary CTA competes with primary |
| Product page | Product image | Mostly | Price not prominent enough |
| Contact form | Submit button | No | Form title same size as body text |

→ Each page assessed.

If err: no mockups → live code via dev tools.

Step 2: Typography

  • Font selection: Right for brand+content?
  • Pairing: Heading+body complement (max 2-3 families)?
  • Scale: Consistent (1.25 maj 2nd, 1.333 4th)?
  • Line height: Body 1.4-1.6, headings 1.1-1.3
  • Line length: 45-75 chars (~66 optimal)
  • Weight: Used for hierarchy
  • Size: ≥16px body
/* Example well-structured type scale (1.25 ratio) */
:root {
  --text-xs: 0.64rem;    /* 10.24px */
  --text-sm: 0.8rem;     /* 12.8px */
  --text-base: 1rem;     /* 16px */
  --text-lg: 1.25rem;    /* 20px */
  --text-xl: 1.563rem;   /* 25px */
  --text-2xl: 1.953rem;  /* 31.25px */
  --text-3xl: 2.441rem;  /* 39.06px */
}

→ Typo consistent, readable, hierarchical.

If err: >3 families → consolidate.

Step 3: Color

  • Palette: Limited (3-5 + neutrals)?
  • Brand: Matches guidelines?
  • Contrast: WCAG AA (4.5:1 normal, 3:1 large)
  • Semantic: Consistent (red=err, green=ok)?
  • Color blind: Not sole means?
  • Dark/light: Both readable + brand consistent?
## Colour Assessment
| Usage | Colour | Contrast Ratio | WCAG AA | Notes |
|-------|--------|----------------|---------|-------|
| Body text on white | #333333 | 12.6:1 | Pass | Good |
| Link text on white | #2563eb | 5.2:1 | Pass | Good |
| Muted text on light gray | #9ca3af on #f3f4f6 | 2.1:1 | FAIL | Increase contrast |
| CTA button text | #ffffff on #22c55e | 3.1:1 | FAIL for small text | Use darker green or larger text |

→ Palette coherent + accessible + semantic.

If err: contrast checker tool (WebAIM).

Step 4: Layout + Spacing

  • Grid: Consistent (12-col, auto, custom)?
  • Spacing scale: Systematic (4|8px base, Tailwind)?
  • Alignment: To grid (no "almost")?
  • Density: Right for content?
  • Whitespace: Intentional?
  • Consistency: Similar = same spacing?
## Spacing Consistency Check
| Element Pair | Expected Gap | Actual Gap | Consistent? |
|-------------|-------------|------------|-------------|
| Section title to content | 24px | 24px | Yes |
| Card to card | 16px | 16px/24px | No — inconsistent |
| Form label to input | 8px | 4px/8px/12px | No — varies |

→ Systematic grid + spacing.

If err: inconsistent → adopt scale (Tailwind space-*).

Step 5: Responsive

BreakpointWidthRepresents
Mobile375pxiPhone SE / small phones
Mobile L428pxiPhone 14 / large phones
Tablet768pxiPad portrait
Desktop1280pxStandard laptop
Wide1536px+Desktop monitor

Per breakpoint:

  • Layout adapt: Reflows (stack mobile, side desktop)?
  • Touch targets: ≥44x44 mobile?
  • Text: Right size?
  • Images: Scale w/o distortion?
  • Nav: Mobile accessible?
  • No h-scroll
## Responsive Review
| Breakpoint | Layout | Touch Targets | Text | Images | Navigation | Issues |
|-----------|--------|---------------|------|--------|------------|--------|
| 375px | OK | OK | OK | Overflow on hero | Hamburger | Hero image clips |
| 768px | OK | OK | OK | OK | Hamburger | None |
| 1280px | OK | N/A | OK | OK | Full nav | None |
| 1536px | OK | N/A | Line length too long | OK | Full nav | Add max-width to content |

→ All breakpoints tested + documented.

If err: no tools → review CSS media queries.

Step 6: Brand Consistency

  • Logo: Right size, spacing, clear zone
  • Color: Matches spec (hex, not "close")
  • Typo: Matches guidelines
  • Tone: UI copy matches personality
  • Icons: Consistent set
  • Photo: Matches brand

→ Brand verified vs guidelines.

If err: no guidelines → note + assess internal consistency.

Step 7: Write Review

## Web Design Review

### Overall Impression
[2-3 sentences: overall quality, strongest and weakest aspects]

### Visual Hierarchy: [Score/5]
[Key findings with specific references]

### Typography: [Score/5]
[Key findings with specific references]

### Colour: [Score/5]
[Key findings with specific references]

### Layout & Spacing: [Score/5]
[Key findings with specific references]

### Responsive Design: [Score/5]
[Key findings with specific references]

### Brand Consistency: [Score/5]
[Key findings with specific references]

### Priority Improvements
1. [Most impactful change — specific and actionable]
2. [Second priority]
3. [Third priority]

### Positive Notes
1. [What works well and should be preserved]

→ Specific, visual-reference feedback + prioritized improvements.

If err: scoring arbitrary → pass|concern|fail.

Check

  • Visual hierarchy all major pages
  • Typo readable + consistent + scaled
  • Color contrast vs WCAG AA
  • Layout + spacing grid consistent
  • Responsive 3+ breakpoints
  • Brand vs guidelines (or internal)
  • Specific feedback w/ visual refs

Traps

  • Subjective no reason: "Don't like color" → not actionable. Explain why.
  • Ignore access: Must include WCAG contrast. Beautiful + excludes ≠ good.
  • Mockups only: Test responsive, hover, transitions — not static.
  • Prescribe: Describe problem, not specific fix.
  • No context: Banking ≠ gaming. Review against context.

  • review-ux-ui — usability + interaction + access
  • setup-tailwind-typescript — Tailwind CSS impl
  • scaffold-nextjs-app — Next.js scaffold

Repositorio GitHub

pjt222/agent-almanac
Ruta: i18n/caveman-ultra/skills/review-web-design
0
agentsagentskillsai-assisted-developmentclaude-codeskillsteams

Habilidades relacionadas

evaluating-llms-harness

Pruebas

Esta Skill de Claude ejecuta el benchmark lm-evaluation-harness para evaluar modelos de lenguaje en más de 60 tareas académicas estandarizadas como MMLU y GSM8K. Está diseñada para que los desarrolladores comparen la calidad de los modelos, realicen seguimiento del progreso del entrenamiento o reporten resultados académicos. La herramienta admite varios backends, incluidos modelos de HuggingFace y vLLM.

Ver habilidad

cloudflare-cron-triggers

Pruebas

Esta habilidad proporciona conocimiento integral para implementar Cron Triggers de Cloudflare y programar Workers mediante expresiones cron. Cubre la configuración de tareas periódicas, trabajos de mantenimiento y flujos de trabajo automatizados, manejando problemas comunes como expresiones cron inválidas y inconvenientes de zonas horarias. Los desarrolladores pueden utilizarla para configurar manejadores programados, probar activadores cron e integrar con Workflows y Green Compute.

Ver habilidad

webapp-testing

Pruebas

Esta habilidad de Claude proporciona un kit de herramientas basado en Playwright para probar aplicaciones web locales mediante scripts de Python. Permite verificación de frontend, depuración de interfaz de usuario, captura de pantallas y visualización de registros, mientras gestiona los ciclos de vida del servidor. Úsela para tareas de automatización de navegadores, pero ejecute los scripts directamente en lugar de leer su código fuente para evitar contaminación del contexto.

Ver habilidad

finishing-a-development-branch

Pruebas

Esta habilidad ayuda a los desarrolladores a completar el trabajo terminado verificando que las pruebas pasen y luego presentando opciones estructuradas de integración. Guía el flujo de trabajo para fusionar, crear PRs o limpiar ramas después de que se completa la implementación. Úsala cuando tu código esté listo y probado para finalizar sistemáticamente el proceso de desarrollo.

Ver habilidad