Capacitor App Creation logo

Capacitor App Creation

Organization
capawesome-team
capacitor-app-creation

Guides the agent through creating a new Capacitor app from scratch. Covers project scaffolding with the Capacitor CLI, configuring the app (appId, appName, webDir), adding native platforms (iOS, Android), and syncing. Includes decision points for Ionic Framework integration, live updates, and CI/CD setup. Do not use for upgrading existing Capacitor apps, migrating from other frameworks, or plugin installation.

Overview

Publishercapawesome-team
Repositoryskills
Skill namecapacitor-app-creation
Stars
54
Forks
1
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by capawesome-team on GitHub. Read the source before you install it.

Installation

Install the Capacitor App Creation 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/capawesome-team/skills/tree/main/skills/capacitor-app-creation
  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/capawesome-team/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/capacitor-app-creation .claude/skills/capacitor-app-creation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Capacitor App Creation 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 Capacitor App Creation 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 Capacitor App Creation 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.

Capacitor App Creation

Create a new Capacitor app from scratch, including project scaffolding, platform setup, and optional integrations.

Prerequisites

  1. Node.js 22+ installed. Verify with node --version.
  2. For iOS: macOS with Xcode 26.0+ installed. Install Xcode Command Line Tools: xcode-select --install.
  3. For Android: Android Studio 2025.2.1+ installed with Android SDK (API 24+).

Agent Behavior

  • Guide step-by-step. Walk the user through the process one step at a time. Never present multiple unrelated questions at once.
  • One decision at a time. When a step requires user input, ask that single question, wait for the answer, then continue.
  • Present clear options. Provide concrete choices (e.g., "Do you want to add the iOS platform? (yes/no)") instead of open-ended questions.

Procedures

Step 1: Check for Ionic Framework

Before creating the app, ask the user:

Do you want to use the Ionic Framework for UI components and theming? (yes/no)

If the user answers yes, stop this skill and switch to the ionic-app-creation skill instead. If no, continue with Step 2.

Step 2: Create the Web App

Ask the user which web framework they want to use. Present these options:

  1. Angular
  2. React
  3. Vue
  4. None (vanilla JS/TS or existing web app)

Based on the selection, scaffold the web project:

Angular
bash
npm install -g @angular/cli
ng new my-app
cd my-app

The default web asset directory for Angular is dist/my-app/browser. Adjust the directory name based on the actual project name.

React
bash
npm create vite@latest my-app -- --template react-ts
cd my-app
npm install

The default web asset directory for React (Vite) is dist.

Vue
bash
npm create vite@latest my-app -- --template vue-ts
cd my-app
npm install

The default web asset directory for Vue (Vite) is dist.

None (vanilla or existing web app)

If the user has an existing web app, confirm it meets these requirements:

  1. A package.json file exists at the project root.
  2. A build output directory exists (e.g., dist, www, build).
  3. An index.html file exists at the root of the build output directory.
  4. The index.html file contains a <head> tag (required for Capacitor plugins to work).

If the user wants a vanilla project:

bash
mkdir my-app && cd my-app
npm init -y
mkdir www

Then create www/index.html:

html
<!DOCTYPE html>
<html lang="en">
<head>
  <meta charset="UTF-8" />
  <meta name="viewport" content="width=device-width, initial-scale=1.0" />
  <title>My App</title>
</head>
<body>
  <h1>My App</h1>
</body>
</html>

The web asset directory is www.

Step 3: Install Capacitor

Navigate to the project root directory and install the Capacitor core packages:

bash
npm install @capacitor/core
npm install -D @capacitor/cli

Step 4: Initialize Capacitor

Run the Capacitor init command with the app name, app ID, and web asset directory:

bash
npx cap init <appName> <appID> --web-dir <webDir>
  • <appName>: Ask the user for the display name of the app (e.g., "My App").
  • <appID>: Ask the user for the app ID in reverse-domain format (e.g., com.example.myapp).
  • <webDir>: Use the web asset directory determined in Step 2 (e.g., dist, www, dist/my-app/browser).

This creates a capacitor.config.ts file in the project root.

Step 5: Build the Web App

Before adding native platforms, build the web app so the output directory exists:

Angular
bash
ng build
React / Vue (Vite)
bash
npm run build
Vanilla

No build step needed if using a static www/ directory.

Step 6: Add Native Platforms

Ask the user which platforms to add:

Which platforms do you want to add? (android/ios/both)

Add Android
bash
npm install @capacitor/android
npx cap add android

This creates the android/ directory with a native Android project.

Add iOS
bash
npm install @capacitor/ios
npx cap add ios

This creates the ios/ directory with a native iOS project. By default, Capacitor 8 uses Swift Package Manager (SPM) for iOS dependency management.

Step 7: Sync the Project

Sync the web assets and native dependencies:

bash
npx cap sync

This copies the built web assets into each native platform project and installs native dependencies (Gradle for Android, SPM for iOS).

Step 8: Run the App

Run the app on a connected device or emulator/simulator:

Android
bash
npx cap run android

This prompts for a target device (emulator or physical device).

iOS
bash
npx cap run ios

This prompts for a target simulator or physical device.

Step 9: Post-Creation Options

After the app is running, ask the user:

Do you want to set up Live Updates for over-the-air updates? (yes/no)

If yes, refer the user to the capawesome-cloud skill for live update setup.

Then ask:

Do you want to set up CI/CD for native builds and app store publishing? (yes/no)

If yes, refer the user to the capawesome-cloud skill for CI/CD setup.

Error Handling

  • npx cap init fails with "already initialized": A capacitor.config.ts or capacitor.config.json file already exists. The project is already a Capacitor project. Delete the existing config file if re-initialization is intended.
  • npx cap add fails with "platform already exists": The android/ or ios/ directory already exists. Remove the directory first: rm -rf android or rm -rf ios, then re-run npx cap add.
  • npx cap sync fails with "could not find the web assets directory": The web app has not been built yet, or the webDir in capacitor.config.ts points to a non-existent directory. Run the web app build command first (e.g., npm run build, ng build).
  • iOS build fails with "no such module": Run npx cap sync ios to ensure SPM dependencies are resolved.
  • Android build fails with SDK errors: Verify that Android SDK is installed and ANDROID_HOME or ANDROID_SDK_ROOT environment variable is set. Open Android Studio SDK Manager to install missing SDK versions.
  • index.html missing <head> tag: Capacitor plugins inject scripts into the <head> tag. Ensure the index.html in the web asset directory contains a <head> element.

Related Skills

  • ionic-app-creation — Create a new Ionic app with UI components and theming instead of a plain Capacitor app.
  • capacitor-app-development — General Capacitor app development guidance after app creation.
  • capacitor-angular — Angular-specific patterns and best practices for Capacitor apps.
  • capacitor-react — React-specific patterns and best practices for Capacitor apps.
  • capacitor-vue — Vue-specific patterns and best practices for Capacitor apps.
  • capacitor-plugins — Install and configure Capacitor plugins after app creation.
  • capawesome-cloud — Set up live updates, native builds, and CI/CD for the app.

Frequently asked questions

What does the Capacitor App Creation AI skill do?

Guides the agent through creating a new Capacitor app from scratch. Covers project scaffolding with the Capacitor CLI, configuring the app (appId, appName, webDir), adding native platforms (iOS, Android), and syncing. Includes decision points for Ionic Framework integration, live updates, and CI/CD setup. Do not use for upgrading existing Capacitor apps, migrating from other frameworks, or plugin installation.

Why use Capacitor App Creation on TypingMind?

Because you install it once and use it with any model. Capacitor App Creation 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 Capacitor App Creation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/capawesome-team/skills/tree/main/skills/capacitor-app-creation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Capacitor App Creation?

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 Capacitor App Creation?

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

Is the Capacitor App Creation AI skill free?

Yes. It is published on GitHub by capawesome-team 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 👇