Axiom Watchos logo

Axiom Watchos

CommunityPopular
CharlesWiltgen
axiom-watchos

Use when building ANY watchOS app — app structure, independent apps, Watch Connectivity, Smart Stack widgets, complications, controls, RelevanceKit, background tasks, ClockKit migration.

Overview

PublisherCharlesWiltgen
RepositoryAxiom
Skill nameaxiom-watchos
Stars
1.2K
Forks
86
Bundled files
9
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.

  • 9 bundled files

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

  • Open source

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

Installation

Install the Axiom Watchos 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/CharlesWiltgen/Axiom/tree/main/axiom-codex/skills/axiom-watchos
  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/CharlesWiltgen/Axiom.git /tmp/Axiom
mkdir -p .claude/skills
cp -r /tmp/Axiom/axiom-codex/skills/axiom-watchos .claude/skills/axiom-watchos
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Axiom Watchos 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 Axiom Watchos 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 Axiom Watchos 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.

watchOS Development

You MUST use this skill for ANY watchOS-specific development including app structure, independent apps, Watch Connectivity, complications and Smart Stack widgets, controls, Live Activities on watch, background tasks, and ClockKit migration.

Auditors are skills here. Where this router says "Launch some-auditor agent", invoke the matching Codex skill instead — same procedure, no Claude Code agent required.

Available: axiom-modernize.

The ones that shell out — builds, tests, simulators, crash symbolication — need shell access to run.

Quick Reference

Symptom / TaskReference
App structure, independent apps, watchOS 26 submission requirementsSee skills/platform-basics.md
watchOS HIG, glanceable UX, navigation modelSee skills/design-for-watchos.md
Smart Stack widgets, complications, ClockKit→WidgetKit, RelevanceKitSee skills/smart-stack-and-complications.md
Controls on watch surfaces, Live Activities on watchSee skills/controls-and-live-activities.md
Watch Connectivity (WCSession), paired-device data transfer, Family SetupSee skills/watch-connectivity.md
Xcode won't install/launch/attach to a Watch; Watch missing or unavailable in Device Hub / devicectlSee skills/watch-device-diag.md
Background tasks, freshness scheduling, TN3135 networking limitsSee skills/background-and-networking.md
BGTaskScheduler migration, deprecated WK background scheduling OS27See skills/background-and-networking.md
Foundation Models / Private Cloud Compute on the watch OS27See skills/platform-basics.md
WatchKit→SwiftUI migration, ClockKit→WidgetKit migrationSee skills/modernization.md

Cross-Suite Routes

These topics overlap with watchOS development but live in separate suites:

SwiftUI (shared iOS/watchOS/macOS)
  • View state, data flow, @Observable → See axiom-swiftui
  • Navigation basics (NavigationStack) → See axiom-swiftui
  • Layout, animations → See axiom-swiftui
Design
  • General HIG, Liquid Glass, SF Symbols, typography → See axiom-design
Accessibility
  • General VoiceOver, Dynamic Type, WCAG → See axiom-accessibility
  • watchOS-specific (VoiceOver rotor on Digital Crown, AssistiveTouch, Double Tap) → See axiom-accessibility (skills/watchos-a11y.md)
Health and workouts
  • HealthKit, HKWorkoutSession, HKLiveWorkoutBuilder, WorkoutKit → See axiom-health
  • Workout recovery, multi-device coordination → See axiom-health (skills/workouts.md)
iOS-side widgets and App Intents
  • iOS/iPadOS widgets, configuration intents, App Intents → See axiom-integration
  • Live Activities on iPhone (initiation + ActivityKit) → See axiom-integration
Concurrency
  • Swift 6 concurrency, actors, Sendable → See axiom-concurrency
New-on-watch frameworks (27 releases)
  • Foundation Models depth (sessions, @Generable, tools, PCC) → See axiom-ai; watch scoping is in skills/platform-basics.md
  • Vision framework (new on watchOS 27) → See axiom-vision
  • NowPlaying / MusicUnderstanding (new on watchOS 27) → See axiom-media

Conflict Resolution

axiom-watchos vs axiom-swiftui: When building a watchOS SwiftUI app:

  1. Use axiom-watchos for watch-specific patterns: glanceable UI, constrained navigation, Digital Crown focus, Smart Stack placement
  2. Use axiom-swiftui for cross-platform SwiftUI: state management, layout primitives, animations
  3. Both may apply: A watchOS NavigationStack with complications needs axiom-watchos for complication surfaces and axiom-swiftui for NavigationStack basics

axiom-watchos vs axiom-integration: For widgets and Live Activities:

  1. Use axiom-watchos for watch complications, Smart Stack placement, watch-side Live Activity presentation, RelevanceKit
  2. Use axiom-integration for iOS/iPadOS widgets, core ActivityKit API, App Intents

watch-device-diag vs watch-connectivity: Two independent connections fail in ways that look identical. Decide which before writing any code:

  1. Use watch-device-diag for the Mac/Xcode → Watch link (CoreDevice): install, launch, LLDB attach, a Watch that is missing or unavailable
  2. Use watch-connectivity for the iPhone app ↔ watchOS app link (WCSession): transfer-API choice, delivery semantics, background-task completion
  3. When unsure, start with watch-device-diag. Run the app without the debugger attached — if it behaves correctly, the fault is the tunnel and no WCSession change will help. Redesigning WCSession to compensate for a broken debugger tunnel is the most expensive mistake in watchOS work
  4. isReachable == false is not a transport failure — it is the expected value across ordinary lifecycle transitions and routes to watch-connectivity, not here

axiom-watchos vs axiom-health: For workouts on Apple Watch:

  1. Use axiom-watchos for watch-specific presentation: Always On display, Smart Stack placement, background mode coordination
  2. Use axiom-health for HKWorkoutSession lifecycle, HKLiveWorkoutBuilder, recovery, multi-device mirroring

Decision Tree

dot
digraph watchos {
    start [label="watchOS development task" shape=ellipse];
    what [label="What area?" shape=diamond];

    start -> what;
    what -> "skills/platform-basics.md" [label="app structure, independent apps, submission"];
    what -> "skills/design-for-watchos.md" [label="watch HIG, glanceable UX"];
    what -> "skills/smart-stack-and-complications.md" [label="complications, Smart Stack, RelevanceKit"];
    what -> "skills/controls-and-live-activities.md" [label="controls, watch Live Activities"];
    what -> "skills/watch-connectivity.md" [label="WCSession, paired-device transfer"];
    what -> "skills/watch-device-diag.md" [label="Xcode can't reach the Watch"];
    what -> "skills/background-and-networking.md" [label="background tasks, BGTaskScheduler, networking limits"];
    what -> "skills/platform-basics.md" [label="Foundation Models / PCC on watch"];
    what -> "skills/modernization.md" [label="WatchKit/ClockKit migration"];
    what -> "axiom-health" [label="workouts, HealthKit, WorkoutKit"];
    what -> "axiom-swiftui" [label="general SwiftUI patterns"];
    what -> "axiom-accessibility" [label="VoiceOver rotor, AssistiveTouch"];
    what -> "axiom-integration" [label="iOS-side widgets, App Intents"];
}

Resources

WWDC: 2021-10003, 2022-10133, 2023-10138, 2023-10029, 2023-10309, 2024-10098, 2024-10157, 2024-10205, 2025-334

Docs: /watchos-apps/building_a_watchos_app, /watchos-apps/creating-independent-watchos-apps, /watchconnectivity, /widgetkit/creating-accessory-widgets-and-watch-complications, /widgetkit/converting-a-clockkit-app, /relevancekit, /technotes/tn3135-low-level-networking-on-watchos, /technotes/tn3157-updating-your-watchos-project-for-swiftui-and-widgetkit

Skills: axiom-swiftui, axiom-design, axiom-accessibility, axiom-health, axiom-integration, axiom-concurrency, axiom-ai, axiom-vision, axiom-media

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 Axiom Watchos AI skill do?

Use when building ANY watchOS app — app structure, independent apps, Watch Connectivity, Smart Stack widgets, complications, controls, RelevanceKit, background tasks, ClockKit migration.

Why use Axiom Watchos on TypingMind?

Because you install it once and use it with any model. Axiom Watchos 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 Axiom Watchos in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/CharlesWiltgen/Axiom/tree/main/axiom-codex/skills/axiom-watchos. 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 Axiom Watchos?

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 Axiom Watchos?

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

Is the Axiom Watchos AI skill free?

Yes. It is published on GitHub by CharlesWiltgen 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 👇