Gestalt Ui Organisation logo

Gestalt Ui Organisation

Organization
dembrandt
gestalt-ui-organisation

Group controls with Gestalt principles so users see what belongs together. Use when laying out components, navigation, toolbars, forms or dashboards.

Overview

Publisherdembrandt
Repositorydembrandt-skills
Skill namegestalt-ui-organisation
Stars
169
Forks
21
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Gestalt Ui Organisation 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/dembrandt/dembrandt-skills/tree/main/skills/gestalt-ui-organisation
  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/dembrandt/dembrandt-skills.git /tmp/dembrandt-skills
mkdir -p .claude/skills
cp -r /tmp/dembrandt-skills/skills/gestalt-ui-organisation .claude/skills/gestalt-ui-organisation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gestalt Ui Organisation 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 Organisation 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 Organisation 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 UI Organisation

UI should be organised so that the visual structure communicates relationships — which commands, controls, and elements belong together — without requiring users to read labels or documentation.

Core Gestalt Principles for UI Layout

1. Proximity

Elements that are close together are perceived as a group.

  • Place related controls (e.g. Bold / Italic / Underline) close together with minimal gap between them
  • Separate unrelated groups with larger whitespace
  • Do not use lines or borders as the primary grouping mechanism — proximity alone should convey the relationship

Example: A toolbar with [Cut] [Copy] [Paste] grouped tightly, then a wider gap before [Undo] [Redo], communicates two distinct command groups without any visual divider.

Prefer whitespace over separator lines

Default to whitespace, not divider lines, for grouping. Most separators do work that spacing does better — they add noise and a "boxed-in" feel without adding information. Remove the majority and let proximity carry the grouping.

Caveat: a line takes almost no space, so removing it leaves groups too close. Removing separators usually means adding spacing — budget the whitespace (occasionally a subtle background or heading) rather than just deleting the line and leaving the layout cramped.

The need for a separator grows with distance

Elements packed tightly separate themselves; elements far apart need help. A compact table with short rows reads without any lines, because each row is already next to the one it belongs with. The same table at full width, or with tall rows, needs row lines or zebra striping, or the eye loses its place crossing the row.

So the question is not "lines or no lines" but how far the elements sit from each other. Pick the lightest device that bridges the gap, in this order: spacing, a subtle fill or stripe, a hairline, a boxed region. Set it per size: a wide table may carry row lines while its compact variant in a sidebar drops them.

Cause and effect stay close

Proximity also governs time: what a click produces should appear next to the click. When a left-hand menu opens content that starts at the far right, the eye crosses the whole screen for every selection, and the user re-orients each time.

  • Anchor content to the left edge of the pane, not the centre. Content begins where the menu ends.
  • Put the page title and primary action in the top-left of the pane, level with the selected menu row. The first landing point is then a short hop from the click.
  • On wide screens prefer three narrow columns (menu, list, detail) over one narrow menu and one wide field. Each step moves the eye one column, never the full width.
  • Highlight the selected row and let the content enter with a small motion from the left, so the movement leads the eye.
  • Do this the same way in every view. If one screen answers a click next to it and another answers far away, the user learns nothing they can reuse.

2. Similarity

Elements that look alike are perceived as related.

  • Use consistent colour, shape, size, and iconography within a functional group
  • Differentiate groups through visual contrast (shape, fill, size) — not just position
  • Primary actions and secondary actions should look visually distinct from each other

Example: Destructive actions (Delete, Remove) use a different colour than constructive actions (Save, Add), signalling different intent groups.

3. Common Region

Elements enclosed in a shared region are perceived as a group.

  • Use cards, panels, or background fills to enclose logically related content
  • Avoid wrapping unrelated elements in the same container
  • Nested regions should reflect nested logical hierarchy

A region needs no border — but a borderless one needs air. Enclosure can come from a border/fill or from whitespace alone. When a card has no border or background, generous internal padding and a clear gap to its neighbours are what make it read as one region; without a border doing that job, cut the air and separate cards collapse into one blur. Borderless is fine — cramped-and-borderless is not.

Example: Form sections grouped in bordered cards signal that fields inside each card form a logical unit.

4. Connectedness

Elements connected by lines or visual links are perceived as related.

  • Use connectors, lines, or flow arrows only when a genuine relationship exists
  • In navigation trees or node-based editors, visible connections should match data relationships exactly

5. Figure / Ground

Users distinguish foreground interactive elements from background context.

  • Interactive controls should have sufficient contrast against their background
  • Disabled or contextual information should visually recede (lower contrast, smaller weight)
  • Modals and overlays must clearly separate from the underlying content layer

6. Continuity

The eye follows smooth paths and lines.

  • Align related controls along a consistent axis (left edge, baseline, or centre line)
  • Avoid breaking alignment within a logical group
  • Grid-aligned layouts reinforce groupings through shared axis continuity

Review Checklist

When reviewing a UI layout for Gestalt compliance:

  • Can a new user identify which controls belong together without reading labels?
  • Is proximity used as the primary grouping signal (not only borders/lines)?
  • Do visually similar elements share a functional purpose?
  • Are unrelated groups separated by meaningful whitespace?
  • Does the result of a click appear near the click, in the same place on every view?
  • Have unnecessary divider lines been removed in favour of whitespace (with spacing added to compensate)?
  • Does visual hierarchy match interaction hierarchy (primary > secondary > tertiary)?
  • Are destructive or irreversible actions visually distinct from constructive ones?
  • Is the figure/ground contrast sufficient for all interactive elements?

Common Anti-Patterns

Anti-patternProblemFix
All buttons same size and colour regardless of functionSimilarity principle violated — implies all actions are equivalentDifferentiate primary, secondary, destructive visually
Related controls spread across distant areas of the screenProximity violated — user cannot perceive the relationshipCo-locate related controls
Menu on the left, content starting far rightThe eye crosses the screen on every selectionAnchor content left, title level with the selected row; add a middle column on wide screens
Overuse of divider lines to group elementsRelies on decoration rather than spatial logicUse whitespace and proximity instead
Identical whitespace between all elementsNo grouping signal — everything reads as a flat listApply 8pt/4pt spacing scale: tight within group, loose between groups
Mixed icon styles within one toolbarSimilarity broken — implies different functional familiesUse a single consistent icon set and weight per toolbar

Frequently asked questions

What does the Gestalt Ui Organisation AI skill do?

Group controls with Gestalt principles so users see what belongs together. Use when laying out components, navigation, toolbars, forms or dashboards.

Why use Gestalt Ui Organisation on TypingMind?

Because you install it once and use it with any model. Gestalt Ui Organisation 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 Organisation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dembrandt/dembrandt-skills/tree/main/skills/gestalt-ui-organisation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Gestalt Ui Organisation?

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 Organisation?

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

Is the Gestalt Ui Organisation AI skill free?

Yes. It is published on GitHub by dembrandt 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 👇