Expo Router logo

Expo Router

OrganizationPopular
expo
expo-router

Framework (OSS). Navigation and routing for Expo Router. Covers file-based routes, groups and dynamic routes, folder organization, Link with previews and context menus, native Stack, page titles, modals and form sheets, NativeTabs, headers and toolbars, and header search bars.

Overview

Publisherexpo
Repositoryskills
Skill nameexpo-router
Stars
2.5K
Forks
146
Bundled files
7
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.

  • 7 bundled files

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

  • Open source

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

Installation

Install the Expo 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.
  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/expo/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/plugins/expo/skills/expo-router .claude/skills/expo-router
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Expo 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 Expo 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 Expo 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.

Expo Router Navigation

Navigation and routing for Expo Router apps. For screen styling, colors, controls, media, and visual effects, use the expo-native-ui skill; for motion and gestures, use expo-animation.

References

Consult these resources as needed:

references/
  route-structure.md     Route conventions, dynamic routes, groups, folder organization
  tabs.md                NativeTabs, migration from JS tabs, iOS 26 features
  toolbar-and-headers.md Stack headers and toolbar buttons, menus, search (iOS only)
  form-sheet.md          Form sheets in expo-router: configuration, footers and background interaction.
  search.md              Search bar with headers, useSearch hook, filtering patterns
  zoom-transitions.md    Apple Zoom: fluid zoom transitions with Link.AppleZoom (iOS 18+)

Code Style

  • Always use kebab-case for file names, e.g. comment-card.tsx
  • Always remove old route files when moving or restructuring navigation
  • Never use special characters in file names
  • Configure tsconfig.json with path aliases, and prefer aliases over relative imports for refactors.

Routes

See ./references/route-structure.md for detailed route conventions.

  • Routes belong in the app directory.
  • Never co-locate components, types, or utilities in the app directory. This is an anti-pattern.
  • Ensure the app always has a route that matches "/", it may be inside a group route.

Library Preferences

  • Color from expo-router for native semantic colors, not raw PlatformColor (type-safe, auto-adapts to light/dark). See expo-native-ui for the full color palette pattern.
  • In SDK 56+, never import from @react-navigation/* directly — use expo-router/react-navigation instead (covers @react-navigation/native, /core, /elements, /routers)

Behavior

  • Prefer Stack.SearchBar to add a search bar to a screen

Navigation

Link

Use <Link href="/path" /> from 'expo-router' for navigation between routes.

tsx
import { Link } from 'expo-router';

// Basic link
<Link href="/path" />

// Wrapping custom components
<Link href="/path" asChild>
  <Pressable>...</Pressable>
</Link>

Whenever possible, include a <Link.Preview> to follow iOS conventions. Add context menus and previews frequently to enhance navigation.

Stack

  • ALWAYS use _layout.tsx files to define stacks
  • Use Stack from 'expo-router/stack' for native navigation stacks

Page Title

Set the page title with Stack.Title:

tsx
<Stack.Title>Home</Stack.Title>

Context Menus

Add long press context menus to Link components:

tsx
import { Link } from "expo-router";

<Link href="/settings" asChild>
  <Link.Trigger>
    <Pressable>
      <Card />
    </Pressable>
  </Link.Trigger>
  <Link.Menu>
    <Link.MenuAction
      title="Share"
      icon="square.and.arrow.up"
      onPress={handleSharePress}
    />
    <Link.MenuAction
      title="Block"
      icon="nosign"
      destructive
      onPress={handleBlockPress}
    />
    <Link.Menu title="More" icon="ellipsis">
      <Link.MenuAction title="Copy" icon="doc.on.doc" onPress={() => {}} />
      <Link.MenuAction
        title="Delete"
        icon="trash"
        destructive
        onPress={() => {}}
      />
    </Link.Menu>
  </Link.Menu>
</Link>;

Link Previews

Use link previews frequently to enhance navigation:

tsx
<Link href="/settings">
  <Link.Trigger>
    <Pressable>
      <Card />
    </Pressable>
  </Link.Trigger>
  <Link.Preview />
</Link>

Link preview can be used with context menus.

Modal

Present a screen as a modal:

tsx
<Stack.Screen name="modal" options={{ presentation: "modal" }} />

Prefer this to building a custom modal component.

Sheet

Present a screen as a dynamic form sheet:

tsx
<Stack.Screen
  name="sheet"
  options={{
    presentation: "formSheet",
    sheetGrabberVisible: true,
    sheetAllowedDetents: [0.5, 1.0],
    contentStyle: { backgroundColor: "transparent" },
  }}
/>
  • Using contentStyle: { backgroundColor: "transparent" } makes the background liquid glass on iOS 26+.

Common route structure

A standard app layout with tabs and stacks inside each tab:

app/
  _layout.tsx — <NativeTabs />
  (index,search)/
    _layout.tsx — <Stack />
    index.tsx — Main list
    search.tsx — Search view
tsx
// app/_layout.tsx
import { NativeTabs } from "expo-router/unstable-native-tabs";
import { ThemeProvider, DarkTheme, DefaultTheme } from "expo-router/react-navigation";
import { useColorScheme } from "react-native";

export default function Layout() {
  const colorScheme = useColorScheme();
  return (
    <ThemeProvider value={colorScheme === "dark" ? DarkTheme : DefaultTheme}>
      <NativeTabs>
        <NativeTabs.Trigger name="(index)">
          <NativeTabs.Trigger.Icon sf="list.dash" md="list" />
          <NativeTabs.Trigger.Label>Items</NativeTabs.Trigger.Label>
        </NativeTabs.Trigger>
        <NativeTabs.Trigger name="(search)" role="search" />
      </NativeTabs>
    </ThemeProvider>
  );
}

Create a shared group route so both tabs can push common screens:

tsx
// app/(index,search)/_layout.tsx
import { Stack } from "expo-router/stack";
import { colors } from "@/theme/colors";

export default function Layout({ segment }) {
  const screen = segment.match(/\((.*)\)/)?.[1]!;
  const titles: Record<string, string> = { index: "Items", search: "Search" };

  return (
    <Stack
      screenOptions={{
        headerTransparent: true,
        headerShadowVisible: false,
        headerLargeTitleShadowVisible: false,
        headerLargeStyle: { backgroundColor: "transparent" },
        headerTitleStyle: { color: colors.label },
        headerLargeTitleEnabled: true,
        headerBlurEffect: "none",
        headerBackButtonDisplayMode: "minimal",
      }}
    >
      <Stack.Screen name={screen} options={{ title: titles[screen] }} />
      <Stack.Screen name="i/[id]" options={{ headerLargeTitleEnabled: false }} />
    </Stack>
  );
}

headerLargeTitleEnabled is the SDK 56+ option name; older SDKs use headerLargeTitle, which is deprecated upstream.

Submitting Feedback

If you encounter errors, misleading or outdated information in this skill, report it so Expo can improve:

bash
npx --yes submit-expo-feedback@latest --category skills --subject "expo-router" "<actionable feedback>"

Only submit when you have something specific and actionable to report. Include as much relevant context as possible. If an AI agent repeatedly failed or the user had to take over an Expo task, load the expo-skill-feedback skill and follow its eval-candidate flow instead of reusing the command above.

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 Expo Router AI skill do?

Framework (OSS). Navigation and routing for Expo Router. Covers file-based routes, groups and dynamic routes, folder organization, Link with previews and context menus, native Stack, page titles, modals and form sheets, NativeTabs, headers and toolbars, and header search bars.

Why use Expo Router on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/expo/skills/tree/main/plugins/expo/skills/expo-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 Expo 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 Expo Router?

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

Is the Expo Router AI skill free?

Yes. It is published on GitHub by expo 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 👇