design-critique

Obtén retroalimentación estructurada de diseño sobre usabilidad, jerarquía y consistencia. Actívalo con "revisa este diseño", "critica este mockup", "¿qué opinas de este…

npx skills add https://github.com/anthropics/knowledge-work-plugins --skill design-critique

/design-critique

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Get structured design feedback across multiple dimensions.

Usage

/design-critique $ARGUMENTS

Review the design: @$1

If a Figma URL is provided, pull the design from Figma. If a file is referenced, read it. Otherwise, ask the user to describe or share their design.

What I Need From You

  • The design: Figma URL, screenshot, or detailed description
  • Context: What is this? Who is it for? What stage (exploration, refinement, final)?
  • Focus (optional): "Focus on mobile" or "Focus on the onboarding flow"

Critique Framework

1. First Impression (2 seconds)

  • What draws the eye first? Is that correct?
  • What's the emotional reaction?
  • Is the purpose immediately clear?

2. Usability

  • Can the user accomplish their goal?
  • Is the navigation intuitive?
  • Are interactive elements obvious?
  • Are there unnecessary steps?

3. Visual Hierarchy

  • Is there a clear reading order?
  • Are the right elements emphasized?
  • Is whitespace used effectively?
  • Is typography creating the right hierarchy?

4. Consistency

  • Does it follow the design system?
  • Are spacing, colors, and typography consistent?
  • Do similar elements behave similarly?

5. Accessibility

  • Color contrast ratios
  • Touch target sizes
  • Text readability
  • Alternative text for images

How to Give Feedback

  • Be specific: "The CTA competes with the navigation" not "the layout is confusing"
  • Explain why: Connect feedback to design principles or user needs
  • Suggest alternatives: Don't just identify problems, propose solutions
  • Acknowledge what works: Good feedback includes positive observations
  • Match the stage: Early exploration gets different feedback than final polish

Output

## Design Critique: [Design Name]

### Overall Impression
[1-2 sentence first reaction — what works, what's the biggest opportunity]

### Usability
| Finding | Severity | Recommendation |
|---------|----------|----------------|
| [Issue] | 🔴 Critical / 🟡 Moderate / 🟢 Minor | [Fix] |

### Visual Hierarchy
- **What draws the eye first**: [Element] — [Is this correct?]
- **Reading flow**: [How does the eye move through the layout?]
- **Emphasis**: [Are the right things emphasized?]

### Consistency
| Element | Issue | Recommendation |
|---------|-------|----------------|
| [Typography/spacing/color] | [Inconsistency] | [Fix] |

### Accessibility
- **Color contrast**: [Pass/fail for key text]
- **Touch targets**: [Adequate size?]
- **Text readability**: [Font size, line height]

### What Works Well
- [Positive observation 1]
- [Positive observation 2]

### Priority Recommendations
1. **[Most impactful change]** — [Why and how]
2. **[Second priority]** — [Why and how]
3. **[Third priority]** — [Why and how]

If Connectors Available

If ~~design tool is connected:

  • Pull the design directly from Figma and inspect components, tokens, and layers
  • Compare against the existing design system for consistency

If ~~user feedback is connected:

  • Cross-reference design decisions with recent user feedback and support tickets

Tips

  1. Share the context — "This is a checkout flow for a B2B SaaS" helps me give relevant feedback.
  2. Specify your stage — Early exploration gets different feedback than final polish.
  3. Ask me to focus — "Just look at the navigation" gives you more depth on one area.

Más skills de anthropic

access
anthropic
Gestiona el acceso a canales de Discord: aprueba emparejamientos, edita listas permitidas, configura políticas de DM/grupo. Úsalo cuando el usuario pida emparejar, aprobar a alguien, verificar quién está permitido…
official
session-report
anthropic
Generar un informe HTML explorable del uso de la sesión de Claude Code (tokens, caché, subagentes, habilidades, prompts costosos) a partir de las transcripciones de ~/.claude/projects.
official
build-mcp-server
anthropic
Esta habilidad debe usarse cuando el usuario solicite "construir un servidor MCP", "crear un MCP", "hacer una integración MCP", "envolver una API para Claude", "exponer herramientas a…
official
cookbook-audit
anthropic
Auditar un cuaderno de Anthropic Cookbook basado en una rúbrica. Úsalo siempre que se solicite una revisión o auditoría de un cuaderno.
official
handle-complaint
anthropic
Gestiona una queja entrante de cliente de principio a fin: extrae el contexto, redacta una respuesta y sugiere una solución operativa. Acepta un correo electrónico o ID de ticket opcional…
official
use-case-triage
anthropic
Determinar rápidamente si una actividad de procesamiento necesita una PIA, una DPIA obligatoria del GDPR, o puede continuar — detecta conflictos con la política de privacidad y dirige al…
official
board-minutes
anthropic
Redacta actas de reuniones de la junta o comité en el formato de su organización. Detecta automáticamente las próximas reuniones de la junta y comités desde su calendario, solicita la agenda y…
official
renewal-tracker
anthropic
Muestra los contratos con fechas límite de cancelación próximas y advierte antes de que se cierren las ventanas de notificación, trabajando desde un registro de renovaciones mantenido. Úsalo cuando el usuario pregunte…
official