Expo Overview logo

Expo Overview

OrganizationPopular
expo
expo-overview

Framework (OSS). Entry point and router for every Expo or EAS task. Load this skill first — before writing code and before choosing another expo-* / eas-* skill — when the request, PRD, or spec mentions Expo, EAS, Expo Go, or an expo-* package, or the project has an `expo` dependency in `package.json`. Within that gate it also covers app specs and designs to implement (tabs, stacks, maps, lists, navigation, building from a screenshot), and phrasings like 'implement a mobile app', 'make my app look native', 'add navigation', 'fetch some data', 'upgrade my SDK', 'add Expo to my existing native app', 'ship to the App Store', or 'I'm new to Expo, where do I start'. A fully specified request (SDK pinned, libraries named, layout given) still routes through here — the shared setup rules still apply. Do NOT load it when neither signal is present: a bare React Native project with no `expo` dependency is not Expo work. Detects the real goal, routes to the right expo-* / eas-* skill, and owns the shared setup rules.

Overview

Publisherexpo
Repositoryskills
Skill nameexpo-overview
Stars
2.5K
Forks
146
Bundled files
1
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.

  • 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 expo on GitHub. Read the source before you install it.

Installation

Install the Expo Overview 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-overview .claude/skills/expo-overview
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Expo Overview 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 Overview 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 Overview 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-overview — router & shared rules for Expo / EAS

Start Here — read before doing anything

Do not guess the skill from project files alone. Many Expo goals look similar from the filesystem but need different skills.

  1. Confirm this is Expo or EAS work — the request mentions Expo or EAS, or package.json has an expo dependency. Otherwise this skill does not apply. A native app using EAS for delivery qualifies without an Expo runtime.
  2. Read the user's goal — what outcome do they want, in plain terms?
  3. Classify it using the Skill Map below, translating casual phrasing to a goal.
  4. Confirm intent if ambiguous ("Sounds like you want to ship to the stores — that's eas-app-stores. Right?"), then load that skill's SKILL.md and follow it.
  5. Trust the leaf skill — it has its own detection logic and steps. Don't improvise.

Skill Map (by goal)

Match the goal to a category, then the skill, then load that leaf's SKILL.md.

Build the app

  • expo-project-structure — folder layout for a new Expo Router project: where screens, components, and config live (never restructure an existing app to match)
  • expo-native-ui — screens, styling, semantic colors, native controls, SF Symbols, media, layout
  • expo-router — navigation: file-based routes, tabs / stacks / modals / sheets, links, headers
  • expo-animation — motion and gestures: Reanimated worklets, Gesture Handler, screen transitions, sheet and press feedback, haptics, and fixing animation that stutters on device
  • expo-ui — native UI components via @expo/ui: BottomSheet, Picker, Slider, Switch, Menu, Button, FieldGroup (grouped form sections), List / ListItem, and more — real SwiftUI on iOS, Jetpack Compose on Android. The universal layer needs SDK 56+ and runs in Expo Go; the drop-in replacements (@gorhom/bottom-sheet, datetimepicker, …) and platform-specific layers also exist on SDK 55.
  • expo-design-system — one visual source of truth: design tokens (color, spacing, typography, radius, shadow, motion), reusable component conventions, and audits for drift (hardcoded colors, spacing, fonts)
  • expo-tailwind-setup — Tailwind / NativeWind styling
  • expo-data-fetching — network requests, React Query / SWR, caching, offline, route loaders
  • expo-dom — run web code or reuse a web library inside native
  • expo-web-to-native — migrate an existing web / React app to a native iOS / Android app

Component selection rule: whenever you need a UI component (list rows, bottom sheets, pickers, sliders, menus, buttons, segmented controls, toggles), consult expo-ui first to check whether @expo/ui has a native equivalent before reaching for a React Native built-in or a community library. Native @expo/ui components give the best platform fit, and on SDK 56+ the universal ones run in Expo Go with no custom build. Load expo-ui alongside expo-native-ui for any app that renders lists, detail sheets, or form controls. One exception: @expo/ui List renders native grouped rows (an iOS Settings screen), not a virtualized list — use FlatList / FlashList for large datasets.

Ship & operate

  • eas-app-stores — build and submit iOS/Android apps (Expo and other React Native projects, plus existing native apps), TestFlight, versions, and store metadata
  • eas-hosting — deploy the web bundle to EAS Hosting; also author Expo Router API routes (+api.ts handlers) and their environments / domains
  • eas-workflows — EAS Workflow YAML and CI/CD pipelines
  • eas-simulator — run and drive the app on a remote iOS / Android simulator on EAS cloud
  • expo-dev-client — custom development builds
  • eas-update — configure, publish, test, and debug compatible over-the-air updates
  • eas-update-insights — OTA update health: crash rate, adoption, payload size
  • eas-observe — startup / launch / TTI performance with EAS Observe

Extend natively

  • expo-module — native modules and views (Swift / Kotlin) with the Expo Modules API
  • expo-brownfield — embed Expo / React Native screens in native SwiftUI/UIKit or Android apps; isolated artifacts and integrated builds
  • expo-app-clip — iOS App Clip target (AASA, smart app banner)

Maintain & learn

  • expo-upgrade — upgrade the Expo SDK and fix dependency conflicts
  • expo-examples — canonical, version-matched integration examples (Stripe, Clerk, Supabase, …)
  • expo-skill-feedback — send feedback on an Expo skill or on Expo itself; enable / disable the anonymous usage telemetry

Translating vague asks

Some everyday phrasings don't obviously map to a skill name — translate before routing:

  • "Make it look native" → grouped controls / settings forms = expo-ui; screens, styling = expo-native-ui; motion = expo-animation; navigation = expo-router.
  • "Make the screens consistent" / "clean up the styling" / "set up a theme or design tokens" → expo-design-system.
  • "It looks AI-generated" / "too generic, not native" → expo-design-system (named native-slop tells + audit), with expo-native-ui for the platform idioms.
  • "Ship it" / "get an .ipa or .apk" / "release to the stores" / "put my Swift app on TestFlight" → eas-app-stores (build + submit, TestFlight, versions, store metadata).
  • "I'm new / where do I start" → scaffold first (see Shared setup rules), then route by goal.

Shared setup rules

Apply the rules that match the project and the requested task.

  • Native app using EAS for delivery? Route to eas-app-stores; its references/native-ios.md covers SwiftUI/UIKit on iOS. Keep the existing native project. Apply EAS auth/linking below; Expo scaffolding, SDK, and package-install rules do not apply to this path.
  • Starting a new Expo app? Start one the standard way before routing to a feature skill: npx create-expo-app@latest, laying out folders per expo-project-structure. Then classify the user's goal and route.
  • Detect the SDK version before giving version-specific advice: read the expo version in package.json (and app.json / app.config.{js,ts}). Many APIs and defaults differ by SDK.
  • Read the docs for that SDK, not latest. Use the version-pinned URL, e.g. https://docs.expo.dev/versions/v56.0.0/sdk/ui/ on SDK 56 instead of https://docs.expo.dev/versions/latest/sdk/ui/ — the latest pages track the newest SDK and can document APIs the project does not have yet.
  • Moving to a newer SDK is its own task — load expo-upgrade instead of bumping versions by hand.
  • Managed vs. bare/prebuild: the presence of committed ios/ and android/ directories means native projects exist (prebuild or bare). Config-plugin and native-setup steps differ — note which one the project is in.
  • Install packages with npx expo install <pkg>, not raw npm/yarn/pnpm add, so versions stay compatible with the project's SDK.
  • EAS auth & linking (only needed for build/submit/update/observe/workflows): check login with eas whoami, log in with eas login. A project is linked when extra.eas.projectId exists in the app config; create it with eas init if missing.

When to skip the router hop

  • Only when the user explicitly named a specific expo-* / eas-* skill → load that skill directly.
  • A fully-specified task (SDK version pinned, file layout given, libraries named) is not a reason to skip: the shared rules above still apply — check them, then route to the matching leaf skill.

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-overview" "<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 Overview AI skill do?

Framework (OSS). Entry point and router for every Expo or EAS task. Load this skill first — before writing code and before choosing another expo-* / eas-* skill — when the request, PRD, or spec mentions Expo, EAS, Expo Go, or an expo-* package, or the project has an `expo` dependency in `package.json`. Within that gate it also covers app specs and designs to implement (tabs, stacks, maps, lists, navigation, building from a screenshot), and phrasings like 'implement a mobile app', 'make my app look native', 'add navigation', 'fetch some data', 'upgrade my SDK', 'add Expo to my existing nativ...

Why use Expo Overview on TypingMind?

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

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

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 Overview?

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

Is the Expo Overview 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 👇