Ux Navigation logo

Ux Navigation

Organization
Uxcel-Lab
ux-navigation

Design or critique navigation systems — match the nav pattern (top bar, sidebar, tabs, hamburger, mega menu, bottom nav) to the information architecture, and apply wayfinding, header, breadcrumb, and pagination best practices. Trigger when the user asks to design or review navigation, menus, navbars, sidebars, tabs, breadcrumbs, headers, pagination, or asks "how should users move around" a site or app.

Overview

PublisherUxcel-Lab
Repositoryproduct-skills
Skill nameux-navigation
Stars
35
Forks
8
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 Uxcel-Lab on GitHub. Read the source before you install it.

Installation

Install the Ux Navigation 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/Uxcel-Lab/product-skills/tree/main/ux/components/navigation
  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/Uxcel-Lab/product-skills.git /tmp/product-skills
mkdir -p .claude/skills
cp -r /tmp/product-skills/ux/components/navigation .claude/skills/ux-navigation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ux Navigation 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 Ux Navigation 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 Ux Navigation 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.

Navigation Skill

How this skill behaves (read first)

This is a generative skill. The default failure modes: pattern-by-habit (a top bar with a hamburger regardless of IA depth, breadth, or platform), hidden essentials (core sections buried behind icons), and missing wayfinding (no "you are here" signals, so users dropped in by search are lost). Navigation is chosen by the structure of the content and how users move through it — not by what modern sites look like. This skill gates:

  1. Establish the IA shape and platform — these mostly decide the pattern.
  2. Apply the always-true core — system layering, wayfinding signals, visible essentials, interaction basics.
  3. Surface the pattern decisions (top bar vs. sidebar, hamburger, mega menu, tabs, breadcrumbs, pagination vs. infinite scroll) with trade-offs.

Then it hands off to ux-heuristics-audit, ux-accessibility-audit, ux-aesthetics-audit, and ux-microcopy-audit — and, as a multi-screen structure, to ux-information-architecture-audit.


Step 0 — Establish context before designing

Ask if not known; state the assumption if proceeding without an answer:

  • IA shape — how many top-level sections, how deep the hierarchy, and is it expected to grow? (Breadth/growth pushes toward vertical nav and mega menus; shallow + stable fits a top bar or tabs.)
  • Platform — desktop, mobile, or responsive? Mobile flips defaults: bottom nav for top destinations, single-breadcrumb, hamburger placement by OS convention.
  • Content-focused or task-based? Content apps (news, video) can minimize chrome and hide secondary nav; task apps (booking, fitness) need persistent, visible navigation.
  • Entry points — do users land deep via search/links? Then wayfinding signals (breadcrumbs, titles, URLs) matter far more than the homepage path.

The always-apply core (correct for almost every case)

Layer the navigation systems — each has a job

Global (main sections, consistent on every page) · local (within a section; inverted-L with global on top) · contextual (related links in/after content) · utility (login, search, language, account — top corner, familiar labels, text language names not flags) · footer (legal, sitemap, contact, social; a "fat footer" can carry rich secondary nav). Don't make one layer do another's job — breadcrumbs never replace global nav.

Always answer "where am I?"

  • Selected state in the nav — the current section is visually marked (color, underline, offset). Same for the active tab and current pagination page.
  • Breadcrumbs for deep hierarchies (see specs) so search-engine arrivals get context.
  • Descriptive HTML titles and clean, readable URLs (/blog/how-to-bake-cookies, not /page1) — the browser chrome is part of navigation.
  • Logo top-left, always clickable, always to the homepage — the universal reset button. Centered/right logos measurably hurt navigation.
  • Test it: show someone a deep page cold and ask "where are you on this site?" If they can't answer, the signals are too subtle.

Keep essentials visible

  • Never bury primary sections behind a hamburger when space allows. Hidden navigation is less discoverable; hamburgers are for genuinely secondary items.
  • Visible options beat hidden ones at every scale: prefer exposed tabs/links over dropdowns when count allows.

Interaction basics (non-negotiable)

  • Touch targets ≥44×44px, link text ≥16px, adequate spacing between links.
  • Activate menus on click, not hover-only — hover fails on touchscreens and keyboards. If using hover (mega menus): 0.5s intent delay, 0.1s display.
  • Caret/arrow icons signal submenus; grayed-out (not removed) unavailable options.
  • Icons accompany labels, not replace them — icon-only nav gets ignored or misread.
  • Frequent destinations within easy reach (Fitts's law — order menu items by real usage).
  • Sticky headers/menus on long pages so navigation never requires scrolling back up — kept compact so they don't eat the viewport.

The context-dependent decisions (surface, don't auto-apply)

DecisionApply whenAvoid / adapt whenDefault recommendation
Top bar vs. vertical sidebarTop bar: ≤7 stable sections, content-first sites. Sidebar: many/growing categories, B2B/enterprise/gov, apps — better scanning (attention leans left), drops into mobile unchangedSidebar eats horizontal space on small screens — plan breakpointsTop bar for shallow/stable; left sidebar for broad/growing IA
Hamburger menuSecondary options; mobile space constraintsHiding primary sections; desktop with room to expose themEssentials visible + hamburger for the rest; top-left on Android, per-platform elsewhere
Mega menuLarge catalogs needing 2-D scannable category panelsFew categories (a plain dropdown is calmer); uncontrolled hover triggersChunk into medium-granularity groups (card-sort informed), concise labels, don't cover the page
Tabs2–9 parallel content categories with short labels, same hierarchy levelSequential steps (use a progress tracker); >1 row of tabs (never stack rows)Fixed tabs on desktop; scrollable tabs for many categories on mobile
Bottom nav (mobile)3–5 global destinations needing one-handed reachMore than 5 (clutter); secondary actionsThe mobile default for top-level app navigation
BreadcrumbsDeep hierarchies (e-commerce, docs, large blogs); users land mid-siteFlat sites (1–2 levels) — pure noiseAdd at depth ≥3; on mobile, a single "up one level" link
Pagination vs. infinite scrollUsers need to refind items, compare, feel progress (catalogs, search results, archives) — finite pages aid decisions and conversionPure leisure feedsPagination for goal-driven browsing; infinite scroll only for ambient consumption
Gesture navigationEngaging mobile patterns (swipe actions) with onboarding cuesAs the only path to a function (undiscoverable)Gestures as accelerators on top of visible controls
Quick linksFrequently needed or hard-to-find content promoted site-wideDuplicating what global nav already exposesA small, curated set — not a second menu

Component specs (when the pattern is chosen)

Headers — logo top-left + meaningful section labels + at most one primary CTA (top-right). Don't overload: menu, logo, search, one CTA. Compact height; 16px+ text; 44px+ targets; padding so elements never touch edges; visually distinct from content (contrast or border). Responsive: collapses gracefully, secondary items into the hamburger — never the essentials.

Tabs — uniform look and behavior; selected tab clearly highlighted and visually connected to its content; unselected tabs visible (not disabled-looking); hover effect for interactivity; one row only; white space over vertical dividers; content transition direction matches tab direction (parenting principle); ≥12px vertical padding, 44px touch targets; concise labels ("Orders," not "Order History").

Breadcrumbs — show hierarchy, not browsing history; start at Home; current page last, styled distinct and not clickable; every other item a real, clickable page; familiar dividers (> / →); positioned top of page below the header, left-aligned (mirrored for RTL); subtle styling — it's secondary nav (but still ≥4.5:1 contrast); overflow menus truncate long trails (keep first + last visible); truncate long labels with tooltip access to full text.

Pagination — current page clearly marked; previous/next plus first/last (« ») controls; page counter ("Page 3 of 10"); smart truncation of long page lists (always show first, last, current); optional manual page input and items-per-page selector for data-heavy lists; controls at the bottom of the content, generous click areas, 4.5:1 contrast.


Validate the result (orchestration)

Hand-offs name each lens by its installable skill name. Invoke one only if that skill is installed; if it isn't, this skill's own core already carries these rules — proceed without it rather than blocking.

After generating or revising, hand the result to the audit lenses rather than declaring it done. These are candidate lenses — posture is set by docs/orchestration-policy.md, or route the whole thing through ux-design-review. Here, heuristics and microcopy are Tier A (auto-run); accessibility, aesthetics, information-architecture, and mobile-responsiveness are Tier B (offered) — under an existing design system aesthetics is suppressed and accessibility narrows to usage; mobile-responsiveness applies only on mobile. If the user invoked this skill for one specific thing, respect that scope.

  • ux-heuristics-audit (Tier A) — visibility of system status (selected states), match to mental models, consistency, recognition over recall.
  • ux-accessibility-audit (Tier B — offer; narrow under a design system) — keyboard operability of menus, touch targets, contrast, hover-dependence, focus order through nav.
  • ux-aesthetics-audit (Tier B — offer; suppress under a design system) — header/menu density, spacing rhythm, whether chrome overwhelms content.
  • ux-microcopy-audit (Tier A) — section/tab/breadcrumb label clarity and conciseness, descriptive titles.
  • ux-information-architecture-audit (Tier B — offer) — whether the category structure itself (grouping, depth, labels) matches user mental models; this skill places the nav, IA owns the structure.
  • ux-mobile-responsiveness-audit (Tier B — offer; applies only on mobile) — when the context is mobile: bottom nav, breakpoints, one-handed reach.

If the audits surface a conflict (e.g., brand wants a minimal icon-only sidebar vs. findability), resolve back toward the primary task: users must always know where they are, what's here, and how to get where they're going.


Common do/don't patterns

❌ Don't✅ Do
Hamburger-everything because it's cleanEssentials visible; hamburger only for secondary items
Pick top bar vs. sidebar by aestheticsDecide by IA breadth, growth, and platform
Breadcrumbs that record the user's click pathBreadcrumbs that mirror the site hierarchy
Hover-only dropdownsClick activation; hover with 0.5s intent delay as enhancement
Icon-only nav itemsIcons + text labels
Two rows of tabsOne row; scrollable tabs or restructure categories
No selected state anywhereCurrent section, tab, and page always marked
Centered logo linking nowhereLogo top-left, clickable, → homepage
Infinite scroll on a product catalogPagination — users need to refind and compare
Flags as language selectorsText labels in each language's own name
Ship without checkingHand off to heuristics + accessibility + aesthetics + microcopy

Source lessons (Uxcel)

Frequently asked questions

What does the Ux Navigation AI skill do?

Design or critique navigation systems — match the nav pattern (top bar, sidebar, tabs, hamburger, mega menu, bottom nav) to the information architecture, and apply wayfinding, header, breadcrumb, and pagination best practices. Trigger when the user asks to design or review navigation, menus, navbars, sidebars, tabs, breadcrumbs, headers, pagination, or asks "how should users move around" a site or app.

Why use Ux Navigation on TypingMind?

Because you install it once and use it with any model. Ux Navigation 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 Ux Navigation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Uxcel-Lab/product-skills/tree/main/ux/components/navigation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ux Navigation?

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 Ux Navigation?

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

Is the Ux Navigation AI skill free?

Yes. It is published on GitHub by Uxcel-Lab 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 👇