New Mac App logo

New Mac App

Community
daveebbelaar
new-mac-app

Create a native macOS SwiftUI app from a working template (Swift package, SwiftData, build script, icon script, snapshot mode, git), with no Xcode GUI. Use when the user wants to start a new Mac app or scaffold a macOS project.

Overview

Publisherdaveebbelaar
Repositorybama
Skill namenew-mac-app
Stars
952
Forks
136
Bundled files
29
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.

  • 29 bundled files

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

  • Open source

    Published by daveebbelaar on GitHub. Read the source before you install it.

Installation

Install the New Mac App 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/daveebbelaar/bama/tree/main/skills/start/new-mac-app
  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/daveebbelaar/bama.git /tmp/bama
mkdir -p .claude/skills
cp -r /tmp/bama/skills/start/new-mac-app .claude/skills/new-mac-app
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable New Mac App 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 New Mac App 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 New Mac App 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.

New Mac app

The template builds and runs as is. The first build proves the toolchain works before you write feature code.

What the template is

A Swift package with one executable target, plus a script that wraps the binary in a real .app bundle. An agent can read and edit every file.

text
<AppName>/
  Package.swift          macOS 26, Swift 6.2 tools, main-actor default isolation
  Info.plist.in          bundle id, name, icon, minimum macOS
  Icon/AppIcon.icon      the app icon: Icon Composer file, JSON plus SVG layers
  build.sh               swift build -> .app bundle -> codesign -> ~/Applications
  CLAUDE.md              build, check, and design rules for agents
  Sources/<AppName>/
    App.swift            window, menus, Settings, database location
    Models.swift         SwiftData models, sidebar pages, AppModel
    ContentView.swift    NavigationSplitView: sidebar, list, detail
    Snapshot.swift       APP_SNAPSHOT mode: PNG and layout file per page and Settings tab, light and dark
    UI/Theme.swift       accent colors, saved choice, accent tokens
    SettingsView.swift   Settings window: one tab per topic, sized to content
    UI/AppearanceSettings.swift  Settings: accent picker (mode follows the Mac)
    UI/WindowBehavior.swift  no focus ring on open, fit to content
    UI/Grid.swift        the 4 pt spacing scale, layout probes, grid overlay
  tools/
    grid-lint.sh         flags spacing numbers off the 4 pt grid
    check-layout.swift   checks the layout files from snapshot mode
    make_icon.sh         Icon/AppIcon.icon -> Resources/Assets.car + AppIcon.icns (actool)
    icon_review.sh       renders every icon look into one PNG (ictool)
    icon_sheet.swift     joins the renders for icon_review.sh

Steps

  1. Check the toolchain:

    bash
    swift --version            # Swift 6.2 or later
    sw_vers -productVersion    # 26.0 or later

    On macOS 15, set .macOS(.v15) in Package.swift and LSMinimumSystemVersion to 15 in Info.plist.in, and skip Liquid Glass APIs.

  2. Pick the name (one UpperCamelCase word) and bundle id (reverse DNS). If docs/BRIEF.md exists, use its name.

  3. Run the script with the parent folder. It copies the template, fills in the name and bundle id, runs git init, and commits. It keeps a folder that holds only a brief.

    bash
    "${CLAUDE_SKILL_DIR}/scripts/new-app.sh" Tasks com.yourname.tasks ~/Developer

    In a Dropbox or iCloud Drive folder the script can take minutes: run it in the background.

  4. Build the app and its icon, then open it:

    bash
    cd ~/Developer/Tasks && ./build.sh --open
  5. Run the checks the template ships with, then look at the snapshots (build-and-verify skill):

    bash
    swift test --scratch-path ~/Library/Developer/Tasks/test-build   # Kit unit tests
    tools/selftest.sh                                                # PASS per check, exit 0
    tools/snap.sh                                                    # sample data, light and dark PNGs
  6. If docs/BRIEF.md exists, rename Item to the brief's main type and the sidebar pages to the brief's pages. Nothing else: features go through improve-loop, one story at a time. Build, snapshot, commit.

When to switch to an Xcode project

The Swift package covers most personal apps. Switch to an XcodeGen project (project.yml -> generated .xcodeproj, built with xcodebuild) when the app needs App Intents for Shortcuts and Spotlight, an asset catalog, app extensions, or widgets. Keep project.yml in git and the .xcodeproj out of it. Put build output outside Dropbox with -derivedDataPath.

Signing

build.sh signs with the first "Apple Development" certificate in the keychain, or ad hoc without one. Permissions (Accessibility, Screen Recording, camera) are stored per signature and path. Ad hoc builds ask again after every rebuild. A free Apple ID makes a certificate in Xcode > Settings > Accounts > Manage Certificates. Install to the same path every time.

A CLI for agents

To let Claude Code, Codex, or scripts read and change the app's data, call the Skill tool with agent-cli. The app binary becomes its own CLI and sends each command to the running app, so the database keeps one writer and the window updates live.

When the build fails

  • cannot find 'X' in scope after adding a file: SwiftPM cached the file list. Run swift package clean --scratch-path ~/Library/Developer/<AppName>/build.
  • binary is older than ...: a file did not compile. Read the first errors.
  • Concurrency errors: call the Skill tool with swift-swiftui.

Done when the app opens from ~/Applications, the snapshots show every page in light and dark, and the first commit exists.

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 New Mac App AI skill do?

Create a native macOS SwiftUI app from a working template (Swift package, SwiftData, build script, icon script, snapshot mode, git), with no Xcode GUI. Use when the user wants to start a new Mac app or scaffold a macOS project.

Why use New Mac App on TypingMind?

Because you install it once and use it with any model. New Mac App 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 New Mac App in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/daveebbelaar/bama/tree/main/skills/start/new-mac-app. 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 New Mac App?

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 New Mac App?

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

Is the New Mac App AI skill free?

Yes. It is published on GitHub by daveebbelaar 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 👇