Expo App Initialize logo

Expo App Initialize

Community
richkuo
expo-app-initialize

Scaffolds a new Expo React Native app with the tabs template, expo-router, react-native-mmkv, expo-dev-client, and expo-iap at their latest compatible versions using Bun, then runs prebuild and writes the project CLAUDE.md commands. Invoke only with /expo-app-initialize <project-name>.

Overview

Publisherrichkuo
Repositoryrk-skills
Skill nameexpo-app-initialize
Stars
50
Forks
8
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 richkuo on GitHub. Read the source before you install it.

Installation

Install the Expo App Initialize 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/richkuo/rk-skills/tree/main/skills/expo-app-initialize
  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/richkuo/rk-skills.git /tmp/rk-skills
mkdir -p .claude/skills
cp -r /tmp/rk-skills/skills/expo-app-initialize .claude/skills/expo-app-initialize
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Expo App Initialize 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 App Initialize 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 App Initialize 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 App Initialize

Create a production-ready Expo React Native app from the tabs template and configure it with the standard dependencies. Use Bun for every command. Never use npm, yarn, or npx; use bunx for one-off tools.

Project name: $ARGUMENTS. If that value is empty or starts with a dollar sign (Codex does not replace the placeholder), take the name from the invocation message. If no name was passed, ask the user for a project name before running anything.

Versions

Use the latest version of every package that is compatible with the project. Never copy a version number from memory or from this skill.

  • Create the project with create-expo@latest, so the app starts on the newest stable Expo SDK.
  • Before any install, read the project's Expo SDK and React Native versions from package.json. For each package that Expo does not track (react-native-mmkv, react-native-nitro-modules, expo-iap), check the latest published version, its required peer dependencies, and its documented minimum Expo SDK and React Native versions. Choose the newest version that supports the project's React Native version and architecture, and record it with every required peer dependency. If the chosen version is older than the latest, tell the user why.
  • Install every package with bunx expo install <package>. It selects the version that matches the project's Expo SDK for packages Expo tracks, and the latest version for others. Install the versions and peer dependencies that the check chose in the same command.
  • After installation, run bunx expo install --check and bunx expo-doctor. Fix every version mismatch they report before prebuild.

Workflow

Run each step in order and wait for it to finish before the next. If a step fails, stop and report the exact error with troubleshooting steps. Never continue after a failed step.

  1. Create the project: bunx create-expo@latest <project-name> --template tabs --yes, then work inside the new directory.
  2. Confirm expo-router is already in package.json. The tabs template includes it. Install it with bunx expo install expo-router only if it is missing.
  3. Check the packages that Expo does not track, as the Versions section describes. Record the chosen version and the required peer dependencies of each package.
  4. Install the dependencies: bunx expo install react-native-mmkv react-native-nitro-modules expo-dev-client expo-iap, plus every required peer dependency that step 3 found. Write a package as <package>@<version> when step 3 chose a version older than the latest.
  5. Run bunx expo install --check and bunx expo-doctor, and fix every version mismatch they report.
  6. Run prebuild as the final setup step: bunx expo prebuild. If the user asked for one platform only, run bunx expo prebuild --platform <android|ios>. On Windows, prebuild skips iOS with a warning; this is expected, so report it and continue.
  7. Write the commands section into CLAUDE.md in the project root. Never overwrite or remove template content, and never add a second # Project Commands section.
    • CLAUDE.md exists, as a file or as a symlink to AGENTS.md: append the commands section to it once.
    • CLAUDE.md is missing and AGENTS.md exists: create CLAUDE.md with @AGENTS.md as its first line, then the commands section. Do not change AGENTS.md.
    • Neither file exists: create CLAUDE.md with the commands section.

Ask the user only when they give a non-standard project location, when their requirements conflict with this setup, or when an error cannot be resolved automatically.

Verification

Before reporting completion, confirm:

  • The tabs template exists: app/(tabs) and app/_layout.tsx.
  • package.json lists every required dependency and peer dependency.
  • bunx expo install --check and bunx expo-doctor report no problems.
  • Prebuild finished with no errors, and the native directory of each platform that prebuild generated exists: android/ and ios/ by default, only android/ on Windows, or only the platform the user asked for.
  • CLAUDE.md contains the commands section exactly once, and AGENTS.md, if the template created it, keeps all of its template content.

Commands section

Read the scripts in package.json after prebuild, and write the bun run lines to match the scripts that exist.

markdown
# Project Commands

## Development
- `bun start` - Start the Expo development server
- `bun run ios` - Run on iOS simulator
- `bun run android` - Run on Android emulator
- `bun run web` - Run in web browser

### Build and Deployment
- `bunx expo prebuild --clean` - Clean and regenerate native code
- `bunx eas-cli build --platform android` - Build for Android using EAS
- `bunx eas-cli build --platform ios` - Build for iOS using EAS
- `bunx eas-cli build --platform android --auto-submit` - Build and auto-submit to Play Store

Report

Follow the Response Style section of the global guidelines. Include the project directory name, the Expo SDK version, and each installed package with its version and purpose:

  • expo-router: file-based routing.
  • react-native-mmkv: high-performance key-value storage.
  • react-native-nitro-modules: native module runtime that react-native-mmkv requires.
  • expo-dev-client: custom development builds and native code.
  • expo-iap: in-app purchases. Warn that Apple and Google store configuration is still required.

State any package that is not on its latest version, and why. Suggest bunx expo run:ios or bunx expo run:android as next steps.

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 App Initialize AI skill do?

Scaffolds a new Expo React Native app with the tabs template, expo-router, react-native-mmkv, expo-dev-client, and expo-iap at their latest compatible versions using Bun, then runs prebuild and writes the project CLAUDE.md commands. Invoke only with /expo-app-initialize <project-name>.

Why use Expo App Initialize on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/richkuo/rk-skills/tree/main/skills/expo-app-initialize. 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 App Initialize?

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 App Initialize?

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

Is the Expo App Initialize AI skill free?

Yes. It is published on GitHub by richkuo 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 👇