Gestalt Ui logo

Gestalt Ui

Community
alpham8
gestalt-ui

Apply Gestalt principles of visual perception to UI design. Use when you need to: (1) group and organize UI elements effectively, (2) create intuitive visual relationships between components, (3) audit layouts for perceptual clarity, (4) design navigation, cards, forms, or dashboards that users understand instantly. Based on Gestalt psychology research applied to digital interfaces.

Overview

Publisheralpham8
Repositoryagentic-webdev
Skill namegestalt-ui
Stars
4
Forks
0
Bundled files
3
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by alpham8 on GitHub. Read the source before you install it.

Installation

Install the Gestalt Ui AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/alpham8/agentic-webdev/tree/master/skills/wondelai/gestalt-ui
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/alpham8/agentic-webdev.git /tmp/agentic-webdev
mkdir -p .claude/skills
cp -r /tmp/agentic-webdev/skills/wondelai/gestalt-ui .claude/skills/gestalt-ui
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gestalt Ui in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Gestalt Ui on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Gestalt Ui is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Gestalt Principles for UI Design

A framework for applying Gestalt psychology to interface design. Gestalt principles describe how humans automatically group, separate, and interpret visual elements -- use them intentionally to make interfaces self-explanatory.

Core Principle

Users don't see individual elements -- they see patterns and relationships. Every spacing decision, border, colour choice, and alignment communicates grouping, hierarchy, and meaning whether you intend it to or not. Gestalt principles are always active. The question is whether you're using them deliberately or accidentally.

Scoring

Goal: 10/10. When reviewing or designing interfaces, rate 0-10 based on deliberate application of Gestalt principles.

  • 9-10: Every grouping is intentional. Proximity, similarity, and common region work together. Visual relationships match semantic relationships perfectly.
  • 7-8: Most groupings are clear. Minor spacing inconsistencies or ambiguous element relationships in secondary areas.
  • 5-6: Groupings partially work but some elements feel disconnected or wrongly associated. Spacing is inconsistent.
  • 3-4: Significant grouping problems. Users must read labels to understand relationships because visual structure doesn't communicate them.
  • 1-2: No discernible visual grouping. Elements scattered without spatial logic. Users are lost.

The Gestalt Framework

1. Proximity -- The Primary Grouping Mechanism

Core concept: Elements positioned close together are perceived as related. Spacing is the most fundamental tool for communicating structure.

Why it works: The brain groups nearby elements automatically, before conscious thought. This is faster than reading labels or borders.

Key insights:

  • Related elements need less space between them than unrelated elements
  • A label must be closer to its input field than to the previous field
  • Section gaps should be noticeably larger than intra-section spacing
  • Equal spacing everywhere makes everything look equally related -- destroying hierarchy

Product applications:

ContextApplicationExample
FormsTighter spacing within field groups, larger gaps between groupsShipping address fields grouped tightly, separated from billing by 2x gap
NavigationClustered items in header menusPrimary nav items grouped, utility links (login, search) spatially separated
DashboardsRelated metrics grouped by proximityRevenue metrics clustered together, user metrics in a separate spatial zone
CardsContent within cards tightly spacedTitle-description-meta as a tight unit, action buttons slightly separated

Common mistake: Equal margins on all elements. If your form has identical gaps between every field, you've removed all visual grouping.

See: references/proximity-similarity.md

2. Similarity -- Visual Consistency Signals Function

Core concept: Elements sharing visual characteristics (colour, shape, size, weight, texture) are perceived as related and functionally equivalent.

Why it works: Once the brain identifies one element's meaning, it transfers that meaning to all visually similar elements. A blue underlined word learned as "clickable" makes all blue underlined words clickable.

Key insights:

  • All interactive elements of the same type must look identical (links, buttons, inputs)
  • Breaking similarity creates emphasis -- the Von Restorff Effect (see laws-of-ux skill)
  • Icon families must use uniform stroke weight, dimensions, and style
  • Typography hierarchy: same size and weight = same level of importance

Product applications:

ContextApplicationExample
NavigationConsistent link styling signals clickabilityAll nav links same colour, weight, and hover behaviour
ButtonsSame-level buttons share visual styleAll secondary actions use outlined style, all primary use filled
Data tablesConsistent cell styling signals data typeAll currency values right-aligned, same font, same colour
Status indicatorsConsistent badge/tag stylingAll "active" badges green, same size and shape

Critical rule: Breaking similarity must be intentional. A red item in a list of blue items demands attention -- use this for CTAs, errors, or critical actions, never accidentally.

See: references/proximity-similarity.md

3. Common Region -- Boundaries Create Groups

Core concept: Elements enclosed within the same boundary are perceived as grouped and related, even if they're otherwise dissimilar.

Why it works: Borders, backgrounds, and cards create explicit containers. Common region can override proximity -- items far apart but within the same card appear more related than close items in different cards.

Key insights:

  • Cards, panels, and bordered sections are common region in action
  • Background colour changes signal section boundaries
  • Common region is stronger than proximity -- use it to override spatial grouping when needed
  • Too many containers create visual noise; use sparingly and with purpose

Product applications:

ContextApplicationExample
FormsFieldsets with visible borders group related inputsAddress fields in a bordered fieldset, payment in another
DashboardsCards containing related metrics"Revenue" card with total, growth, and chart -- visually one unit
SettingsPanels separating configuration areasAccount settings panel, notification preferences panel, privacy panel
PricingPlan cards enclosing features, price, and CTAEach plan visually distinct as a complete unit

See: references/region-connectedness.md

4. Figure-Ground -- Focus vs Context

Core concept: Elements separate into figure (focal element) and ground (background/context). The brain must decide what's foreground and what's behind -- make this decision obvious.

Why it works: Stable figure-ground relationships direct attention. Unstable ones create confusion about what to focus on.

Key insights:

  • High-contrast elements become figure; low-contrast becomes ground
  • Smaller overlapping objects tend to be figure; larger ones ground
  • Shadows and elevation create clear figure-ground separation
  • Modal overlays use dimmed backgrounds to force figure-ground clarity

Product applications:

ContextApplicationExample
CTAsHigh-contrast button against neutral backgroundBright "Sign Up" button on a muted hero section
ModalsDimmed/blurred backdrop establishes overlay as figureDark scrim behind a confirmation dialog
CardsSubtle shadows lift content off the pageCard with box-shadow on flat background
NavigationSidebar visually distinct from main contentDarker sidebar, lighter content area

Ethical boundary: Never use ambiguous figure-ground to hide important information (dark patterns). Pricing, terms, and opt-outs must be clear figure elements.

See: references/figure-ground-closure.md

5. Closure -- The Brain Completes Patterns

Core concept: We fill in missing visual information to perceive complete shapes. Partial information is enough when the pattern is recognisable.

Why it works: The brain wants coherence. Showing "enough" lets users infer the rest without overwhelming them with visual detail.

Key insights:

  • Partially visible carousel items signal "more content available"
  • Progress bars use closure -- an incomplete fill implies a complete target
  • Truncated text with "..." signals expandable content
  • Dotted or dashed lines suggest boundaries without solid visual weight

Product applications:

ContextApplicationExample
CarouselsPartially visible cards at edgesNext card peeking 20% into view signals scrollability
ProgressIncomplete fills show remaining work"3 of 5 steps completed" with partial bar
ListsTruncated items signal more content"Showing 5 of 23 results" with fade-out
IconsSimplified shapes the brain completesAn incomplete circle still reads as "loading"

See: references/figure-ground-closure.md

6. Continuity -- Follow the Line

Core concept: Elements arranged on a line or curve appear related and sequential. The eye follows the path naturally.

Why it works: We continue perceiving shapes and paths beyond their visible endpoints. This creates flow and sequence.

Key insights:

  • Aligned elements along invisible grid lines create order and cohesion
  • Progress steppers guide users through sequences
  • Breadcrumbs follow a linear path showing hierarchy
  • Diagonal or curved layouts guide eye movement through content

Product applications:

ContextApplicationExample
WizardsStep indicators connected by a lineSteps 1-2-3-4 connected, showing progression
TimelinesChronological events along a vertical lineActivity feed with connecting timeline
BreadcrumbsLinear path showing navigation hierarchyHome > Category > Product
Grid alignmentElements aligned to invisible columnsDashboard widgets snapped to a 12-column grid

7. Uniform Connectedness -- The Strongest Grouping

Core concept: Visually connected elements are perceived as most strongly related. This is the most powerful Gestalt grouping principle.

Why it works: Explicit visual connections (lines, arrows, shared containers) create unambiguous relationships that override all other grouping cues.

Key insights:

  • Connecting lines don't need direct contact with elements -- visual alignment is sufficient
  • Stronger than proximity, similarity, and common region
  • Use for explicit relationships that must be unambiguous
  • Process flows, org charts, and data relationships benefit most

Product applications:

ContextApplicationExample
Process flowsLines connecting sequential stepsCheckout: Cart → Shipping → Payment → Confirm
Org chartsLines showing reporting relationshipsTree structure with connecting branches
Data vizLines connecting related data pointsLine charts, node graphs, dependency trees
FormsVisual connectors between conditional fields"If yes" → reveal connected sub-fields

See: references/region-connectedness.md

8. Common Fate -- Movement Creates Grouping

Core concept: Elements moving together or in the same direction are perceived as related, regardless of visual similarity or distance.

Why it works: Shared motion is a powerful grouping signal -- the brain assumes co-moving elements are part of the same system.

Key insights:

  • Animated hover states affecting multiple elements simultaneously group them
  • Parallax layers moving at the same speed appear related
  • Swiping a card group as a unit signals they belong together
  • Scroll-linked animations on multiple elements create perceived unity

Product applications:

ContextApplicationExample
Hover effectsRelated elements react together on hoverHovering a card highlights its image, title, and CTA simultaneously
LoadingGrouped skeleton placeholders shimmer togetherThree related cards pulsing in sync
Scroll effectsCo-moving elements during scrollHeader and subheader sliding up together
Drag and dropSelected items moving as a groupMulti-select files dragging together

9. Focal Points -- What Stands Out Gets Attention

Core concept: Elements with contrast, emphasis, or visual distinction capture attention. The eye is drawn to what differs from its surroundings.

Why it works: Focal points require a baseline of similarity -- without uniform surrounding elements, nothing can stand out. Contrast is relative.

Key insights:

  • A highlighted CTA only works if surrounding elements are visually quieter
  • Larger text draws attention to key information
  • Colour contrast makes specific elements stand out
  • Unique shapes among uniform elements attract the eye
  • If everything is emphasised, nothing is emphasised

Product applications:

ContextApplicationExample
CTAsContrasting colour on primary actionBlue "Submit" button among grey secondary buttons
PricingRecommended plan visually distinct"Popular" plan larger, different colour, highlighted border
AlertsProminent styling for important messagesRed banner for errors among neutral content
DataKey metric highlightedDashboard KPI in large, bold font; supporting data in standard size

10. Pragnanz (Simplicity) -- Simple Wins

Core concept: People perceive complex arrangements in the simplest possible form. We prefer clear, ordered, symmetrical structures because they require less cognitive effort.

Why it works: Simpler interpretations are processed faster and feel safer. This is the meta-principle underlying all other Gestalt principles.

Key insights:

  • Clean, uncluttered interfaces are processed faster
  • Break complex information into simple, scannable components
  • Favour straightforward iconography over detailed illustrations
  • When in doubt, simplify -- if users must think about the structure, it's too complex

Product applications:

ContextApplicationExample
NavigationHierarchical organisation over flat listsCategorised menu instead of 40 links
IconsSimple, recognisable shapesMagnifying glass for search, not a detailed binoculars illustration
LayoutsClean grids over chaotic arrangementsUniform card grid instead of scattered elements
OnboardingStep-by-step over all-at-onceWizard with 4 clear steps instead of one overwhelming form

Principle Interactions

Gestalt principles don't work in isolation. They interact, reinforce, and sometimes conflict.

Reinforcement (Stronger Together)

CombinationEffect
Proximity + SimilarityElements that are close AND look alike are very strongly grouped
Common Region + ProximityCards with tight internal spacing -- double grouping signal
Continuity + Uniform ConnectednessSteps connected by a line AND aligned -- maximum sequence clarity
Figure-Ground + Focal PointsHigh-contrast CTA on dimmed background -- maximum attention

Conflicts (Resolution Required)

ConflictResolution
Proximity suggests group A, but Similarity suggests group BCommon Region overrides both -- use a container
Uniform Connectedness creates unwanted associationIncrease spacing (Proximity) AND change styling (Similarity) to counteract
Closure implies content exists but it doesn'tRemove the visual cue -- don't show a partial card if there's nothing to scroll to

Common Mistakes

MistakeWhy It FailsFix
Equal spacing everywhereRemoves all visual grouping -- everything looks equally relatedUse a spacing scale: tighter within groups, looser between
Too many containers/bordersVisual noise, every element screams "I'm a group"Use proximity and whitespace first; add borders only when needed
Inconsistent interactive stylingUsers can't predict what's clickableAudit all links, buttons, and interactive elements for visual consistency
Ambiguous figure-groundUsers don't know where to focusIncrease contrast on focal elements; dim/blur backgrounds
Accidental similarityUnrelated elements look alike, implying false relationshipsVary colour, size, or shape to differentiate distinct element types

Quick Diagnostic

QuestionIf NoAction
Can you tell which elements are grouped without reading labels?Spacing doesn't communicate structureAdjust proximity: tighter within groups, larger gaps between
Do all interactive elements of the same type look the same?Inconsistent similarityAudit and unify link, button, and input styling
Is there one clear focal point per screen/section?Everything competes for attentionReduce visual weight on secondary elements; increase on primary
Do cards/containers have clear internal hierarchy?Flat visual weight inside containersApply figure-ground and size contrast within cards
Can users predict what happens when they interact with an element?Weak signifiersStrengthen similarity with other interactive elements of the same type

Reference Files

Further Reading

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Gestalt Ui AI skill do?

Apply Gestalt principles of visual perception to UI design. Use when you need to: (1) group and organize UI elements effectively, (2) create intuitive visual relationships between components, (3) audit layouts for perceptual clarity, (4) design navigation, cards, forms, or dashboards that users understand instantly. Based on Gestalt psychology research applied to digital interfaces.

Why use Gestalt Ui on TypingMind?

Because you install it once and use it with any model. Gestalt Ui is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Gestalt Ui in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/alpham8/agentic-webdev/tree/master/skills/wondelai/gestalt-ui. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Gestalt Ui?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Gestalt Ui?

As many as you like. As long as a model supports skills, you can use Gestalt Ui with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Gestalt Ui AI skill free?

Yes. It is published on GitHub by alpham8 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇