Codex Phone Lab

Community

Kappaemme-git

codex-phone-lab

Build and iterate mobile apps that run on a real phone through Expo/React Native live preview. Use when Codex is asked to create a phone app, prototype an iPhone or Android app, run an app on a physical phone, show a QR code for Expo Go, set up a mobile dev workflow, or turn a prompt into a live mobile app without starting from Xcode/TestFlight/App Store distribution.

Overview

Publisher	Kappaemme-git
Repository	`codex-phone-lab`
Skill name	`codex-phone-lab`
Stars	95
Forks	13
Bundled files	5
License	MIT
Links	Skill source Repository

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.
5 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by Kappaemme-git on GitHub. Read the source before you install it.

Installation

Install the Codex Phone Lab AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/Kappaemme-git/codex-phone-lab/tree/main/skill
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.

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/Kappaemme-git/codex-phone-lab.git /tmp/codex-phone-lab
mkdir -p .claude/skills
cp -r /tmp/codex-phone-lab/skill .claude/skills/codex-phone-lab

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Codex Phone Lab 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 Codex Phone Lab 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 Codex Phone Lab 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.

Codex Phone Lab

Use this skill to turn a product prompt into a React Native/Expo app that the user can open on a physical phone with Expo Go. Optimize for a fast "prompt -> app -> phone" loop before considering simulator, native builds, TestFlight, or app store distribution.

Operating Model

Prefer this path unless the user explicitly needs native iOS/Android modules:

Check local prerequisites with scripts/doctor.sh.
If no mobile project exists, create an Expo app with scripts/new-expo-app.sh <app-name>. This defaults to expo-template-default@sdk-54 so it opens in the current Expo Go version used by this workflow.
Build the first usable screen quickly; do not create a landing page.
Start the phone preview with scripts/start-phone-preview.sh [lan|tunnel|local].
Keep the dev server running while editing. Use Metro/Expo logs to fix runtime errors.
Tell the user to install Expo Go, scan the QR, and keep the phone on the same network for LAN mode.
Iterate in small visible changes: edit, observe logs, reload, fix.

Project Detection

Before creating a new app, inspect the current directory:

package.json with expo dependency: treat as existing Expo app.
app.json, app.config.*, app/, or expo-router: treat as Expo app even if dependencies need install.
ios/ and android/ without Expo: ask only if the user needs Expo migration; otherwise keep existing stack.
Empty directory: create a new Expo app with the SDK 54 template.

Phone Preview

Use Expo Go for the first "wow" demo because it avoids App Store/TestFlight friction.

Use SDK 54 by default. The current Expo Go in this workflow rejects SDK 55 projects with "Project is incompatible with this version of Expo Go". Override only when the user's Expo Go is known to support a newer SDK:

bash
CODEX_PHONE_LAB_EXPO_TEMPLATE=expo-template-default@sdk-55 <skill-dir>/scripts/new-expo-app.sh my-app

Run:

bash
<skill-dir>/scripts/start-phone-preview.sh lan

Use tunnel when the phone is not on the same Wi-Fi or LAN mode cannot connect. Tunnel mode may ask Expo to install a tunneling dependency.

The user workflow:

Install Expo Go on the phone.
Run the preview command.
Scan the QR code from Expo Go or the phone camera.
Keep the terminal open; app edits refresh live.

App-Building Guidance

Make the first screen feel like a real app:

Use safe areas and mobile-sized layouts.
Build actual interaction: forms, lists, navigation, toggles, timers, mock data, or state.
Include loading, empty, and error states when the workflow implies them.
Keep typography compact enough for mobile.
Avoid web landing-page patterns, oversized hero sections, nested cards, and explanatory in-app text.
Prefer Expo Router for multi-screen apps when the template already includes it.

Distribution Decision

Choose the lightest route that matches the user's goal:

Fast prototype on user's phone: Expo Go QR.
App with custom native modules: Expo development build.
Beta users on iPhone: TestFlight via EAS/Apple Developer account.
Public release: App Store / Play Store submission.

Do not imply Expo Go is production distribution. It is a live development preview.

References

Read references/expo-phone-workflow.md when deciding between Expo Go, development builds, TestFlight, and app store release.

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 Codex Phone Lab AI skill do?

Why use Codex Phone Lab on TypingMind?

Because you install it once and use it with any model. Codex Phone Lab 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 Codex Phone Lab in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Kappaemme-git/codex-phone-lab/tree/main/skill. 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 Codex Phone Lab?

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 Codex Phone Lab?

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

Is the Codex Phone Lab AI skill free?

Yes. It is published on GitHub by Kappaemme-git 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

Discrawl

openclaw

OrganizationPopular

Discord archive: search, sync freshness, DMs, summaries, TUI, repo/release work.

Gitcrawl

GitHub archive: issue/PR search, sync freshness, duplicate clusters, current GitHub handoff, and Gitcrawl repo work.

Graincrawl

Granola archive: search, sync freshness, notes, transcripts, panels, SQL counts, and Graincrawl repo work.

Openclaw Changelog Update

openclaw

OrganizationPopular

Regenerate OpenClaw release changelog sections from git history before beta, stable, or extended-stable releases.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Codex Phone Lab

Operating Model

Project Detection

Phone Preview

App-Building Guidance

Distribution Decision

References

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now