Perception Router logo

Perception Router

Community
Deibler
perception-router

Use this skill whenever a design task involves visual perception, layout, hierarchy, grouping, scanning order, attention, color organization, or composition — regardless of framework, design system, or platform. Trigger when the user is laying out a screen, page, slide, poster, dashboard, mobile view, or print piece; choosing what to emphasize; deciding how things should group; picking type sizes, spacing, or color roles; reviewing why something "looks busy" or "feels empty"; or asking "where should the eye land first." Routes the model to the right perception principle in this plugin and surfaces the most-decisive ones for the surface in question. Framework-agnostic: applies to web, mobile, print, physical product, slide design, and information graphics alike.

Overview

PublisherDeibler
Repositoryuniversal-design-principles
Skill nameperception-router
Stars
9
Forks
3
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Perception Router 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/Deibler/universal-design-principles/tree/main/plugins/perception-and-hierarchy-principles/skills/perception-router
  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/Deibler/universal-design-principles.git /tmp/universal-design-principles
mkdir -p .claude/skills
cp -r /tmp/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/perception-router .claude/skills/perception-router
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Perception Router 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 Perception Router 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 Perception Router 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.

Perception & hierarchy — router

This plugin holds the principles that govern how the eye organizes a composition: what gets seen first, what groups with what, what reads as noise, what reads as quality. They are framework-agnostic; the same principle applies to a shadcn/ui card, a Material chip, a Figma slide, a poster, or a printed report.

How to route

Read the task and identify the principles that decide it. Most non-trivial perception tasks are dominated by 3–6 principles. Read those principles' skills in full; treat the rest as background.

Principles in this plugin

The list below is the full inventory of perception-related principles from Universal Principles of Design covered by this plugin. Each principle has its own skill (and where useful, sub-aspect skills) under skills/. Principles marked [full] have reference-grade skill files; the others are planned and will be added in subsequent passes.

Visual hierarchy and emphasis

  • hierarchy [full] — the ranking of importance among visible elements; size, weight, color, position.
    • Sub-skills: hierarchy-typographic, hierarchy-spatial, hierarchy-color-and-tone.
  • alignment — elements share an invisible axis; misalignment reads as disorder.
  • area-alignment — alignment by visual mass rather than bounding box.
  • signal-to-noise-ratio [full] — the ratio of meaningful information to decoration.
    • Sub-skills: snr-densification, snr-decoration-removal, snr-emphasis-economy.
  • highlighting — emphasis works only when sparing.
  • von-restorff-effect — the item that differs is remembered and noticed first.
  • red-effect — red attracts disproportionate attention; reserve for genuine urgency.
  • horror-vacui — the impulse to fill empty space; whitespace is a feature.
  • layering — distinct visual planes (z, elevation) reduce noise.
  • gutenberg-diagram — Z-pattern reading on uniform layouts.

Gestalt grouping

  • proximity [full] — nearby items are perceived as a group.
    • Sub-skills: proximity-form-fields, proximity-data-tables, proximity-navigation.
  • similarity — items that look alike are perceived as related.
  • closure — the eye completes incomplete shapes.
  • common-fate — elements moving together are perceived as related.
  • figure-ground-relationship — every composition has a focused figure and a recessive ground.
  • good-continuation — aligned edges read as connected.
  • uniform-connectedness — a shared region binds elements more strongly than proximity alone.
  • law-of-pragnanz — the eye prefers the simplest valid interpretation.
  • contour-bias — sharp angles feel hostile; rounded corners feel friendly.

Proportion, rhythm, and depth

  • golden-ratio — 1:1.618; useful as a starting proportion for hero compositions.
  • fibonacci-sequence — successive Fibonacci ratios produce natural-feeling spacing scales.
  • rule-of-thirds — split a composition into thirds; place focal points on intersections.
  • symmetry — bilateral, radial, or translational; stable but can feel static.
  • self-similarity — fractal repetition at multiple scales creates coherence.
  • cathedral-effect — high "ceilings" (whitespace) invite expansive thinking; low ones invite focus.
  • three-dimensional-projection — subtle depth cues (shadow, scale) clarify layering.

Typography and color

  • legibility — character distinctness; a property of typeface and rendering.
  • readability — sustained reading speed; a property of layout (length, leading, contrast).
  • color — hue, saturation, value; cultural meaning; accessibility.
  • gloss-bias — glossy surfaces read as desirable.
  • top-down-lighting-bias — humans assume light from above; shadows below = raised, shadows above = recessed.

Attention quirks

  • inattentional-blindness — focused users don't see unexpected elements.
  • threat-detection — sharp angles, snake-like shapes, angry faces detected fast.
  • orientation-sensitivity — vertical and horizontal lines processed faster than oblique.

Heuristic for which to read first

  • Designing a page or screen layout → hierarchy, alignment, proximity, signal-to-noise-ratio.
  • Reviewing a "busy" or "noisy" UI → signal-to-noise-ratio, highlighting, horror-vacui.
  • Form layout → proximity, alignment, good-continuation, gutenberg-diagram.
  • Data table or dashboard → hierarchy, signal-to-noise-ratio, legibility, gestalt similarity.
  • Marketing / hero surface → hierarchy, golden-ratio or rule-of-thirds, gloss-bias, cathedral-effect.
  • Empty / loading / error states → hierarchy, horror-vacui, figure-ground-relationship.
  • Brand / visual-identity decisions → contour-bias, color, symmetry, self-similarity.
  • Choosing color tokens → color, red-effect, top-down-lighting-bias, plus accessibility checks (see process-and-robustness-principles).

Working method

  1. Name the surface in concrete terms: "B2B SaaS settings page with three sections," not "settings page."
  2. Pick 3–6 decisive principles from the list above. Most surfaces are dominated by Hierarchy, Proximity, Alignment, and Signal-to-Noise.
  3. Read those skills. Each principle skill includes a definition, when-to-apply guidance, anti-patterns, and worked examples.
  4. Make the decision and name the trade-off. Most principles trade against another.

Cross-plugin pointers

  • For learnability (mental models, complexity, defaults, recognition), see cognition-and-learnability-principles.
  • For behavior (affordance, feedback, errors, control), see interaction-and-control-principles.
  • For brand and tone, see aesthetics-and-emotion-principles.
  • For accessibility and edge cases, see process-and-robustness-principles.

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 Perception Router AI skill do?

Use this skill whenever a design task involves visual perception, layout, hierarchy, grouping, scanning order, attention, color organization, or composition — regardless of framework, design system, or platform. Trigger when the user is laying out a screen, page, slide, poster, dashboard, mobile view, or print piece; choosing what to emphasize; deciding how things should group; picking type sizes, spacing, or color roles; reviewing why something "looks busy" or "feels empty"; or asking "where should the eye land first." Routes the model to the right perception principle in this plugin and s...

Why use Perception Router on TypingMind?

Because you install it once and use it with any model. Perception Router 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 Perception Router in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Deibler/universal-design-principles/tree/main/plugins/perception-and-hierarchy-principles/skills/perception-router. 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 Perception Router?

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 Perception Router?

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

Is the Perception Router AI skill free?

It is published on GitHub by Deibler. Check the repository for licensing terms. 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 👇