agentleFS
nisarthnisarth/claude-skills-store/skills/design/design-critique/SKILL.md

design-critique

Skill1 starsChanged 7 months agoMITView on GitHub

Get structured design feedback on usability, hierarchy, and consistency. Trigger with "review this design", "critique this mockup", "what do you think of this screen?", or when sharing a Figma link or screenshot for feedback at any stage from exploration to final review. Trigger phrases: "review this design", "design critique", "critique this mockup", "feedback on this UI", "what do you think of this screen", "design review", "is this design good", "improve this design", "design feedback", "UX review"

42 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use color-system, presentation-design and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • launchapp-devSkill

    color-system

    Build a comprehensive color system with palette generation, semantic mapping, and accessibility compliance.

    Also in 3 projects that use this

  • ArnavPuriSkill

    presentation-design

    Design slide decks as HTML/CSS (custom or reveal.js): slide layouts on a fixed 16:9 canvas, presentation typography, slide charts, builds and transitions, speaker notes, and PDF export. Use for decks presented or shared from the browser; for native .pptx files use a PowerPoint-specific tool. Trigger phrases: "presentation", "slide deck", "slides", "pitch deck", "keynote", "reveal.js", "slide design", "presentation template", "speaker notes"

    Also in 3 projects that use this

  • brianciouSkill

    ux-writing

    UX writing guidelines for reviewing and optimizing interface copy. Use when the user asks to review, improve, or rewrite UI text including button labels, error messages, onboarding flows, or any interface copy. Apply when auditing microcopy for web apps, mobile apps, or any digital product requiring clear, user-centered communication.

    Also in 5 projects that use this

  • jpoindexterSkill

    design-system-audit

    Audit code for design system violations - grid spacing, tokens, existing components

    Also in 3 projects that use this

  • agentes100xSkill

    brand-identity

    Proporciona la fuente única de verdad para lineamientos de marca, tokens de diseño y voz/tono. Usa esto para mantener consistencia visual y de comunicación.

    Also in 3 projects that use this

  • nandanosqlSkill

    design-brief

    Create a design brief that clearly communicates the product context, user needs, constraints, and success criteria to the design team — bridging PM requirements and design execution.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 36 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do similar elements look and behave the same way?

    line 49
  2. Distinctive:

    Do labels, buttons, and headings communicate what they do?

    line 56
  3. Distinctive:

    When a systematic evaluation is needed, check against:

    line 119
  4. Distinctive:

    Response: Check step count (can any be combined?), progress indication (does the user know where they are?), validation approach (inline vs.

    line 139
  5. Distinctive:

    Ask before assuming: If something looks intentional but problematic, ask about the reasoning before suggesting a change.

    line 149
  6. Distinctive:

    Prioritize feedback: Not everything is equally important.

    line 150
  7. Distinctive:

    Test your assumptions: If you think something will confuse users, frame it as a hypothesis: "Users might not notice the secondary action …

    line 153

“Common” is measured: kept by at least 6 in 10 of the 36 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Design Critique

Provide structured, actionable design feedback covering usability, visual hierarchy, consistency, and user experience. Calibrate depth and tone to the design stage.

Workflow

Step 1: Understand the Context

Before critiquing, clarify:

  1. Design stage: Exploration, wireframe, high-fidelity, or final review?
  2. Target user: Who is this designed for?
  3. Goal of the screen/flow: What should the user accomplish?
  4. Specific concerns: Any areas the designer wants focused feedback on?
  5. Constraints: Brand guidelines, technical limitations, design system in use?

Adjust feedback depth to the stage:

  • Exploration: Focus on concept and approach, not pixels
  • Wireframe: Focus on layout, flow, and information architecture
  • High-fidelity: Focus on visual design, micro-interactions, edge cases
  • Final review: Focus on polish, consistency, and production readiness

Step 2: Evaluate Across Dimensions

Usability

  • Can the user accomplish their primary task without confusion?
  • Is the most important action the most prominent?
  • Are there unnecessary steps or friction points?
  • What happens on error, empty state, or edge case?
  • Is the flow recoverable (can users go back, undo, correct mistakes)?

Visual Hierarchy

  • Where does the eye go first? Is that the right place?
  • Are primary, secondary, and tertiary actions visually distinct?
  • Is there enough contrast between elements at different hierarchy levels?
  • Does the layout guide the user through a logical sequence?
  • Is there too much competing for attention?

Consistency

  • Do similar elements look and behave the same way?
  • Does this follow the design system or established patterns?
  • Are spacing, typography, and color usage consistent with the rest of the product?
  • Would a user who knows the rest of the product recognize this as part of it?

Content and Copy

  • Is the language clear and concise?
  • Do labels, buttons, and headings communicate what they do?
  • Is there jargon the user might not understand?
  • Are error messages helpful and actionable?

Edge Cases

  • What happens with no data? Too much data?
  • What about very long text, long names, or international content?
  • How does this work on mobile, small screens, or with touch input?
  • What about first-time vs. returning users?

Step 3: Structure the Feedback

Organize feedback by priority:

### Design Critique: [Screen/Flow Name]
Reviewed: [Date] | Stage: [Exploration/Wireframe/Hi-Fi/Final]

#### What Works Well
- [Positive 1]: [Why it is effective]
- [Positive 2]: [Why it is effective]

#### Critical Issues (Must Fix)
1. **[Issue]**: [What is wrong and why]
   - **Impact**: [How this affects the user]
   - **Suggestion**: [Specific recommendation]

2. **[Issue]**: [What is wrong and why]
   - **Impact**: [How this affects the user]
   - **Suggestion**: [Specific recommendation]

#### Improvements (Should Consider)
1. **[Issue]**: [What could be better]
   - **Suggestion**: [Recommendation]

2. **[Issue]**: [What could be better]
   - **Suggestion**: [Recommendation]

#### Minor Polish (Nice to Have)
- [Observation]: [Suggestion]
- [Observation]: [Suggestion]

#### Questions
- [Question about intent, constraint, or trade-off]

Step 4: Provide Actionable Suggestions

For each piece of feedback:

  • Be specific. "The CTA is not prominent enough" is vague. "The primary CTA blends with secondary buttons because it uses the same fill color at the same size. Try using a larger size and the brand accent color to differentiate."
  • Explain the why. Connect feedback to user impact, not personal preference.
  • Suggest, do not dictate. Offer a direction, not the only solution.
  • Reference patterns. Point to existing patterns in the product or industry standards.

Feedback Frameworks

The "I Like, I Wish, What If" Method

  • I like: What is working and should be preserved
  • I wish: What could be improved
  • What if: Alternative approaches worth exploring

The Nielsen Heuristics Lens

When a systematic evaluation is needed, check against:

  1. Visibility of system status
  2. Match between system and real world
  3. User control and freedom
  4. Consistency and standards
  5. Error prevention
  6. Recognition over recall
  7. Flexibility and efficiency of use
  8. Aesthetic and minimalist design
  9. Help users recognize, diagnose, and recover from errors
  10. Help and documentation

Examples

Example 1: Landing Page

User: "Review this landing page mockup." Response: Evaluate the visual hierarchy (is the value prop clear above the fold?), CTA prominence (can you find the primary action in 3 seconds?), content flow (does the page answer who, what, why, how in order?), and trust signals (social proof, security, credibility).

Example 2: Form Design

User: "Critique this multi-step form." Response: Check step count (can any be combined?), progress indication (does the user know where they are?), validation approach (inline vs. on-submit), error recovery (can users go back without losing data?), and field labeling (visible labels, not placeholders only).

Example 3: Dashboard

User: "Feedback on this analytics dashboard." Response: Assess information density (is it overwhelming or just right?), hierarchy (what is the most important metric and is it prominent?), scannability (can users get the key message in 5 seconds?), and actionability (can users act on what they see?).

Best Practices

  1. Start with what works. Acknowledging strengths builds trust and helps the designer understand what to preserve. Feedback that is only negative is demoralizing and less effective.
  2. Separate opinion from principle. "I don't like blue" is preference. "Blue on blue creates a contrast ratio below 3:1" is a design principle. Lead with principles.
  3. Ask before assuming. If something looks intentional but problematic, ask about the reasoning before suggesting a change. There may be a constraint you do not know about.
  4. Prioritize feedback. Not everything is equally important. Label feedback as critical, important, or nice-to-have so the designer knows where to focus.
  5. Critique the design, not the designer. Say "the layout creates visual competition between elements" not "you made the layout too busy."
  6. Consider the full flow. A screen that looks odd in isolation may make sense in context. Ask to see the surrounding screens before flagging inconsistencies.
  7. Test your assumptions. If you think something will confuse users, frame it as a hypothesis: "Users might not notice the secondary action because..." This invites discussion rather than defensiveness.
  8. Follow up. Good critique leads to iteration. Offer to review the next version to close the feedback loop.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.