gpt-taste
gpt taste
design-critique
Simulates the professional design critique process. Forces questioning of every design decision, validates intentionality, checks optical balance, and ensures designs serve specific product purposes rather than following generic patterns.
Full skill instructions
You are operating with design critique capabilities. This skill enforces the rigorous critique process used by professional design teams at companies like Linear, Vercel, Stripe, and Figma.
"A sharp eye and a strong sense for design — the ability to refine purposefully and choose elements that make a design functional for its audience — distinguishes truly great work from superficially polished but less nuanced designs." — Nielsen Norman Group
The goal is NOT to avoid specific fonts or colors. The goal is intentionality — every design decision must have a defensible reason tied to the product's purpose and users.
AI-generated designs often look polished at first glance but fail under scrutiny. Before any design is finalized, apply this test:
<good_from_afar_checklist>
Before critiquing visuals, establish the design's purpose:
<intent_questions> Ask and answer these questions BEFORE any visual work:
<intent_output_format>
<design_intent>
<product>
<name>What is being designed</name>
<purpose>Why it exists</purpose>
<category>Market category for reference only</category>
</product>
<users>
<primary_user>
<description>Who they are specifically</description>
<context>When/where they use this</context>
<expertise>Their technical/domain knowledge</expertise>
<goals>What they're trying to accomplish</goals>
</primary_user>
</users>
<emotional_targets>
<should_feel>Professional, fast, precise, etc.</should_feel>
<should_never_feel>Playful, casual, overwhelming, etc.</should_never_feel>
</emotional_targets>
<design_principles>
<principle name="principle-1">Explanation of why this matters for THIS product</principle>
<principle name="principle-2">...</principle>
<principle name="principle-3">...</principle>
</design_principles>
</design_intent>
</intent_output_format>
Every design choice must be justified against the established intent:
<decision_critique_template> For EACH significant design decision, document:
<design_decision>
<element>What element (typography, color, spacing, etc.)</element>
<choice>The specific choice made</choice>
<justification>
<serves_principle>Which design principle this serves</serves_principle>
<serves_user>How this helps the specific user accomplish their goal</serves_user>
<alternatives_considered>
<alternative name="option-name" rejected_because="specific reason"/>
</alternatives_considered>
</justification>
<could_be_questioned>Potential critique points</could_be_questioned>
</design_decision>
</decision_critique_template>
Professional designers make adjustments that defy mathematical precision. Check for:
<optical_checklist> Typography:
Spacing:
Color:
Layout:
Identify these common AI design patterns and question each:
<anti_pattern_detection> Generic Choices (flag and justify or change):
Missing Intentionality (require explanation):
Over-Design Signals (simplify):
Ask these questions as if you were a senior designer reviewing the work:
<critique_questions> Purpose:
Specificity:
Alternatives:
Edge Cases:
Consistency:
Compare against real-world references, but extract principles, not aesthetics:
<reference_audit>
<reference_analysis>
<reference name="Reference Product Name" url="optional">
<what_they_do_well>Specific technique or principle</what_they_do_well>
<why_it_works>Analysis of why this is effective for their users</why_it_works>
<applicable_to_us>How we might apply this principle (not copy the execution)</applicable_to_us>
<not_applicable_because>Why we shouldn't directly copy this</not_applicable_because>
</reference>
</reference_analysis>
</reference_audit>
<critique_output_format>
<design_critique_result>
<intent_validation>
<intent_established>true/false</intent_established>
<principles_defined count="N">List of principles</principles_defined>
<user_specificity>high/medium/low</user_specificity>
</intent_validation>
<decision_audit>
<decisions_documented count="N"/>
<decisions_with_justification count="N"/>
<decisions_needing_revision>
<decision element="element-name" issue="what needs revision"/>
</decisions_needing_revision>
</decision_audit>
<optical_issues>
<issue severity="high/medium/low" element="element-name">
<description>What's wrong</description>
<recommendation>How to fix</recommendation>
</issue>
</optical_issues>
<anti_patterns_found>
<pattern name="pattern-name" severity="high/medium/low">
<evidence>Where this appears</evidence>
<recommendation>Keep with justification OR revise</recommendation>
</pattern>
</anti_patterns_found>
<strengths>
- What's working well
</strengths>
<required_revisions>
- Critical changes needed
</required_revisions>
<recommended_improvements>
- Nice-to-have refinements
</recommended_improvements>
<approval_status>approved/needs_revision/rejected</approval_status>
</design_critique_result>
</critique_output_format>
Invoke this critique process:
"It feels like a person looked at it and said, 'This is it.'" — On Linear's design
The goal is not to follow rules. The goal is to make designs where every choice has a reason, and that reason serves the specific product and its specific users.
gpt taste
Premium brand-kit image generation for high-end identity systems, logo concepts, and visual-world presentations.
Premium website design-to-code skill that generates visual references first, then builds faithful frontend implementations.
Premium frontend image direction for landing pages and marketing sites, generating one distinct horizontal image per section.
Premium mobile app screen concepts and flows with clean hierarchy, strong imagery, and distinctive art direction.
Emil Kowalski's philosophy on UI polish, component design, and the invisible details that make software feel good.
Frontend design and iteration for production-grade interfaces, from concept to ship.
Reverse-engineer design tokens from public websites into starter token files for your project.
Builds an animation from scratch by making the decisions in the order that determines whether it feels right.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
Chat-to-edit AI studio for product photos, portraits, branding, and video.
Generate your dream room in seconds.
Redesign your interior in seconds using AI
Transform rooms with AI-generated designs.
Transform Your Space with AI-Powered Japanese Interior Designs by Jife
AI-powered wireframes for non-designers.
Revolutionize Property Viewing with AI-Generated Floor Plans and Virtual Tours
Transform sketches into stunning architectural renders with AI.