Cognition Router logo

Cognition Router

Community
Deibler
cognition-router

Use this skill whenever a design task involves cognition, mental models, learnability, complexity reduction, defaults, memory, scanning, or comprehension — regardless of framework or platform. Trigger when the user is designing forms, settings, onboarding, dashboards with many widgets, complex tables, navigation IA, search experiences, or any flow that has many options or asks the user to learn something new. Trigger when the user mentions "too complex," "too many options," "users keep getting confused," defaults, labels, copy, mental models, progressive disclosure, autocomplete, or ergonomics. Routes the model to the right cognition principle in this plugin.

Overview

PublisherDeibler
Repositoryuniversal-design-principles
Skill namecognition-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 Cognition 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/cognition-and-learnability-principles/skills/cognition-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/cognition-and-learnability-principles/skills/cognition-router .claude/skills/cognition-router
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cognition 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 Cognition 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 Cognition 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.

Cognition & learnability — router

This plugin holds the principles that govern how easily a user can understand, learn, and remember an interface. They are framework-agnostic and apply equally to web apps, mobile apps, desktop software, control panels, in-car displays, and printed forms.

Principles in this plugin

Each principle has its own skill (with sub-aspect skills where useful). Principles marked [full] have reference-grade skill files; the rest are planned and will be added in subsequent passes.

Complexity reduction

  • hicks-law [full] — decision time grows with the log of the number of options.
    • Sub-skills: hicks-law-menus, hicks-law-defaults, hicks-law-pricing.
  • 80-20-rule — 80% of usage flows through 20% of features; design the default for the 80%.
  • chunking — group items into ~4±1 chunks so working memory can hold them.
  • performance-load — total cognitive + kinesthetic effort to do a task; minimize both.
  • progressive-disclosure — show only what's needed now; reveal advanced controls on demand.
  • satisficing — users pick the first acceptable option, not the optimal one.
  • ockhams-razor — among solutions that work, prefer the simplest.

Mental models and recognition

  • mental-model — users come with a model of how the system works; design to match it.
  • recognition-over-recall — recognizing is easier than remembering; show options.
  • visibility — features that aren't visible aren't used.
  • mapping — controls map onto what they affect.
  • constancy — visual properties remain stable across state changes.
  • iconic-representation — pictures are recognized faster than words but only when conventional.
  • mimicry — borrow successful familiar patterns rather than invent.
  • rosetta-stone — pair a known referent with a novel concept.

Chunking, scanning, and memory

  • inverted-pyramid — most important info first, then supporting detail.
  • five-hat-racks — five ways to organize: Location, Alphabet, Time, Category, Hierarchy.
  • advance-organizer — a structural preview before content (TOC, breadcrumbs).
  • serial-position-effects — first and last items are remembered best.
  • stickiness — memorable, concrete content earns repeat use.
  • storytelling — narrative encodes meaning more memorably than bullets.
  • picture-superiority-effect — images outlast text in memory.
  • mnemonic-device — explicit memory aids reduce recall cost.
  • propositional-density — meaning per visible mark; high density reads as polished.

Wayfinding and navigation

  • wayfinding [full] — orienting, choosing routes, monitoring progress, recognizing destinations.
    • Sub-skills: wayfinding-physical-spatial-metaphors, wayfinding-search-and-recovery, wayfinding-breadcrumbs-and-context.
  • progressive-disclosure [full] — show what's needed now; tuck the rest behind explicit affordances.
    • Sub-skills: progressive-disclosure-defaults-and-tucking, progressive-disclosure-disclosure-affordances.

Consistency and encoding

  • consistency — same things look and behave the same.
  • cognitive-dissonance — contradictions between expectation and behavior cost trust.
  • confirmation-bias — users notice what confirms their model and ignore what doesn't.
  • comparison — comparison is easier than evaluation.
  • depth-of-processing — interactive engagement yields better memory than passive reading.
  • priming — exposure shapes how a subsequent stimulus is processed.
  • framing — how information is framed changes the choice users make.
  • modularity — break complex systems into independent, recombinable units.
  • redundancy — multiple independent signals make critical info reliable.

Heuristic for which to read first

  • Designing a long form or settings page → chunking, progressive-disclosure, hicks-law, mental-model.
  • Picking defaults → satisficing, 80-20-rule, hicks-law-defaults, framing.
  • Picking an icon set → iconic-representation, recognition-over-recall, mimicry.
  • Designing a dashboard → propositional-density, chunking, inverted-pyramid.
  • Onboarding → mental-model, advance-organizer, depth-of-processing, storytelling.
  • Search / navigation IA → wayfinding, recognition-over-recall, five-hat-racks, visibility.
  • "Users keep getting lost" → wayfinding, wayfinding-breadcrumbs-and-context, wayfinding-search-and-recovery.
  • Settings / forms feel overwhelming → progressive-disclosure, chunking, hicks-law.
  • Reviewing a confusing flow → mental-model, cognitive-dissonance, consistency.

Cross-plugin pointers

  • For visual layout and grouping, see perception-and-hierarchy-principles.
  • For behavior (errors, undo, target sizing, feedback), see interaction-and-control-principles.
  • For aesthetic and tonal decisions, see aesthetics-and-emotion-principles.
  • For accessibility, 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 Cognition Router AI skill do?

Use this skill whenever a design task involves cognition, mental models, learnability, complexity reduction, defaults, memory, scanning, or comprehension — regardless of framework or platform. Trigger when the user is designing forms, settings, onboarding, dashboards with many widgets, complex tables, navigation IA, search experiences, or any flow that has many options or asks the user to learn something new. Trigger when the user mentions "too complex," "too many options," "users keep getting confused," defaults, labels, copy, mental models, progressive disclosure, autocomplete, or ergonom...

Why use Cognition Router on TypingMind?

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

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

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

Is the Cognition 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 👇