Produces a responsive layout specification with breakpoints, column grids per breakpoint, component behavior rules, and content priority ordering for multi-device interfaces.
SkillScore82Maintained
Automatic
◆Design & UX Review pack
Last verified 9/19/2026
What it changes
Passed 18 of 22 test cases with the skill, and 17 of 22 without it.
Without skill77%
With skill82%
Checks it passed that the model alone missed
Specifies captions or labels to be at least 14px.
Sets body font size to at least 16px across all breakpoints including xs.
Validates fluid clamp output values at both the minimum and maximum viewport boundary limits.
and 2 more in the full report
3 fixed15 passed either way2 still failing2 broke
Pass-rate lift
+5 pp
Tokens
+261%
Agent turns
0%
Response time
0%
Model gemini-3.6-flashMeasured 9/19/2026v118 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 3
Prompt
I need a complete developer handoff specification for making our e-commerce product detail page fully responsive across screen sizes. The desktop version has a sticky top nav, a multi-image gallery, product info with price and buy box, collapsible product details, customer reviews grid, and a related items carousel. Please create a self-contained responsive blueprint that defines our breakpoint tiers, grid layout settings per tier, a component behavior matrix with priority ratings, spatial ASCII diagrams for mobile, tablet, and desktop viewports, responsive typography and spacing token schedules, touch target guidelines, and implementation notes.
What was checked, without and with the skill
Checked
Without skill
With skill
Sets body font size to at least 16px across all breakpoints including xs.
Missed
Passed
Specifies captions or labels to be at least 14px.
Missed
Passed
Includes a dedicated touch target notes section specifying a minimum 44x44px interactive tap area for mobile.
Missed
Passed
case-01 · gemini-3.6-flash · 9/19/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md605 linessingle file
Responsive Layout Design
When to Use
Use this skill when:
User needs a complete multi-device layout specification covering breakpoint definitions, grid systems, component behavior rules, content priority ordering, typography scaling, and spacing tokens -- ready for developer or designer handoff
User wants to define how specific components (navigation, data tables, hero sections, card grids, forms, sidebars) reflow, collapse, reorder, or transform across screen widths
User is designing a new interface and needs to establish the responsive foundation before any visual design or CSS work begins
User has an existing single-device layout and needs to extend it to a full responsive specification covering mobile, tablet, and desktop breakpoints
User needs to audit or redesign an existing responsive layout that has specific failure points (text overflowing, images breaking, navigation collapsing poorly, tables truncating)
User wants to specify content priority ordering so development teams know what to hide, deprioritize, or restructure on smaller viewports
User is creating a design system or component library and needs standardized responsive behavior rules that apply consistently across many screens
Do NOT use when:
User wants a wireframe for a single specific device or viewport only -- use wireframe-specification instead, which produces screen-level layout artifacts without multi-breakpoint complexity
User wants to define transitions, animations, or micro-interactions that occur during viewport resize or between screen states -- use prototype-spec for motion and transition behavior
User wants to write the actual CSS, Sass, or media query code that implements the responsive layout -- use a software-development skill (the spec produced here is the input to that work, not a substitute for it)
User wants to map how users navigate between screens or pages across devices -- use user-flow-mapping, which handles navigation paths rather than layout structure
User wants a visual brand identity or style guide -- responsive layout specs are structural artifacts, not visual direction documents
User wants to design a native mobile app layout (iOS/Android) -- native apps use platform-specific layout systems (UIKit Auto Layout, Jetpack Compose) that differ fundamentally from viewport-based responsive web design
Process
Step 1: Establish Context and Design Direction
Before drawing any boxes, collect the five parameters that determine every subsequent decision:
Content type classification: Identify which layout archetype the screen belongs to. Each has different responsive priorities:
Reading content (articles, documentation, blogs): Line length control is paramount. Single-column prose is ideal on all devices. Sidebar is supplementary.
Task-oriented interfaces (dashboards, admin panels, forms): Desktop-first thinking. Data density matters. Mobile versions often need significant restructuring, not just reflow.
Commerce and conversion pages (product pages, landing pages, checkout): Mobile-first is essential -- over 60% of e-commerce traffic is mobile. CTA visibility and form usability on thumb-zone areas are critical.
Content grids (news feeds, portfolios, galleries): Column count reduction is the primary responsive strategy. Image cropping and aspect ratio management matter.
Mixed editorial (marketing pages, homepages): Each section may use a different responsive strategy. Treat each section as a separate layout unit.
Priority device and traffic profile: Ask the user where most traffic originates. Use this to determine design direction:
Greater than 60% mobile sessions: mobile-first layout (design mobile layout first, progressively enhance for larger screens)
Greater than 60% desktop sessions: desktop-first (design full layout first, gracefully degrade for smaller screens)
No data available: default to mobile-first. It is harder to add complexity than remove it.
Generate, edit, and extend videos with xAI's grok-imagine-video model. Use when the user wants to create a video from text, animate a still image, build a reference-driven video (virtual try-on, character consistency), edit an existing video, or extend one. Asynchronous — the script handles polling.