Mobile App Developer logo

Mobile App Developer

Community
happycapy-ai
mobile-app-developer

End-to-end mobile app development and publishing using Expo + EAS. Covers project scaffolding, asset preparation, peer-dep / lock-file troubleshooting (development.md), web preview with phone frame and Expo Go QR code (preview.md), AND automated build + submit to TestFlight / App Store (publishing.md), with full automation via Apple ASC API Key (no Mac, no Xcode, no 2FA required). Use when the user wants to build, test, preview, publish, or automate the release pipeline of a React Native / Expo iOS or Android app.

Overview

Publisherhappycapy-ai
RepositoryHappycapy-skills
Skill namemobile-app-developer
Stars
138
Forks
30
Bundled files
3
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.

  • 3 bundled files

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

  • Open source

    Published by happycapy-ai on GitHub. Read the source before you install it.

Installation

Install the Mobile App Developer 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/happycapy-ai/Happycapy-skills.git /tmp/Happycapy-skills
mkdir -p .claude/skills
cp -r /tmp/Happycapy-skills/skills/mobile-app-developer .claude/skills/mobile-app-developer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mobile App Developer 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 Mobile App Developer 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 Mobile App Developer 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.

mobile-app-developer

End-to-end playbook for shipping an Expo / React Native app — from scaffolding to TestFlight / Play Store — fully automated from a Linux sandbox.

When to Trigger

Trigger this skill when the user wants to:

  • Scaffold or modify a React Native / Expo project
  • Run / test / debug the app locally (Expo Go, dev client, simulator)
  • Generate a web preview page with phone frame + Expo Go QR code
  • Configure EAS Build (cloud build) for iOS or Android
  • Publish to TestFlight (iOS internal testing) or Google Play Internal Testing
  • Submit to App Store / Play Store public release
  • Set up ASC API Key auth (bypass Apple 2FA)
  • Replace icons / splash screens for store compliance
  • Diagnose EAS build failures (peer deps, lock files, credentials, fingerprint, etc.)

Do NOT trigger for: pure native iOS/Android (no Expo), Flutter, Cordova/Capacitor, KMP/Compose Multiplatform.

Skill Layout

This skill is split into focused documents. Read the relevant one(s) on demand — do NOT preload all.

FileRead when…
development.mdSetting up project, installing deps, configuring app.json, preparing icons/splash, running on simulator/device, fixing peer-dep / lock-file errors, managing env vars / secrets
publishing.mdConfiguring eas.json submit profile, ASC API Key / Play Service Account, running build + submit, diagnosing submit failures, App Store / Play Store metadata checklists
preview.mdGenerating a web preview page with phone frame + Expo Go QR code. Uses Expo Web (react-native-web) static export for browser preview and Expo dev server for real-device QR scanning

If the user's task spans multiple (e.g. "build a new Expo app and ship it to TestFlight"), read development.md first, then publishing.md.

Default Tech Stack

LayerChoice
FrameworkExpo (latest stable — check https://docs.expo.dev/versions/latest/ before scaffolding)
Build / DistributionEAS Build + EAS Submit (Expo cloud)
Auth (Apple)App Store Connect API Key (.p8) — bypasses 2FA
Auth (Google)Play Console Service Account JSON
Auth (Expo)Personal Access Token via EXPO_TOKEN

Hard Preconditions

Before starting any build or publish work, confirm with the user:

  • Expo account + EXPO_TOKEN (https://expo.dev/accounts//settings/access-tokens)
  • For iOS:
    • Apple Developer account (paid, $99/year)
    • ASC API Key: .p8 file + Issuer ID + Key ID (role ≥ App Manager; ≥ Admin to create certs)
    • Apple Team ID + ASC App ID + Bundle Identifier
  • For Android:
    • Google Play Console account ($25 one-time)
    • Service Account JSON key (created in Play Console → API access)
    • Package name + Play Console app already created
    • First AAB must be uploaded manually to Play Console before automation works

If anything is missing, ask the user before proceeding. Do not guess.

Sandbox Requirements

The sandbox/CI must have:

bash
node --version       # >= 18
npm --version        # >= 9
convert -version     # ImageMagick — for icon/splash conversion
expect -v            # for first-time non-interactive credential setup
curl --version       # for fetching build logs

Quick check:

bash
for cmd in node npm convert expect curl; do
  command -v $cmd >/dev/null 2>&1 && echo "[OK] $cmd" || echo "[MISSING] $cmd"
done

If anything is missing, install before continuing (apt-get install imagemagick expect).

Architecture Recommendation

PhaseAI/API key locationWhy
Internal testing (TestFlight / Play Internal)OK to call AI Gateway directly from clientSpeed of iteration; risk is bounded by closed tester pool
Public releaseMUST proxy through your own backendEmbedded keys can be extracted from any IPA/AAB

Useful URLs

Notes

  • All commands tested on Linux. macOS users get extra options (local Xcode, simctl) which this skill avoids for portability.
  • Treat .p8 files and Service Account JSONs like passwords. Always gitignore (*.p8, *-service-account.json).
  • This skill assumes EAS cloud build. Local builds (expo prebuild + native toolchain) are out of scope.

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 Mobile App Developer AI skill do?

End-to-end mobile app development and publishing using Expo + EAS. Covers project scaffolding, asset preparation, peer-dep / lock-file troubleshooting (development.md), web preview with phone frame and Expo Go QR code (preview.md), AND automated build + submit to TestFlight / App Store (publishing.md), with full automation via Apple ASC API Key (no Mac, no Xcode, no 2FA required). Use when the user wants to build, test, preview, publish, or automate the release pipeline of a React Native / Expo iOS or Android app.

Why use Mobile App Developer on TypingMind?

Because you install it once and use it with any model. Mobile App Developer 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 Mobile App Developer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/happycapy-ai/Happycapy-skills/tree/main/skills/mobile-app-developer. 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 Mobile App Developer?

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 Mobile App Developer?

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

Is the Mobile App Developer AI skill free?

Yes. It is published on GitHub by happycapy-ai 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 👇