Audioaccessorykit logo

Audioaccessorykit

CommunityPopular
dpearson2699
audioaccessorykit

Support automatic audio switching for paired third-party Bluetooth headphones or earbuds with AudioAccessoryKit. Use when a companion app registers an audio accessory, an app extension reports worn/removed placement or connected source-device changes, or AccessoryControlDevice capabilities and errors need handling. Do not use for general AVAudioSession routing, Bluetooth transport, or initial accessory pairing.

Overview

Publisherdpearson2699
Repositoryswift-ios-skills
Skill nameaudioaccessorykit
Stars
1.2K
Forks
61
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

    Published by dpearson2699 on GitHub. Read the source before you install it.

Installation

Install the Audioaccessorykit 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/dpearson2699/swift-ios-skills/tree/main/skills/audioaccessorykit
  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/dpearson2699/swift-ios-skills.git /tmp/swift-ios-skills
mkdir -p .claude/skills
cp -r /tmp/swift-ios-skills/skills/audioaccessorykit .claude/skills/audioaccessorykit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Audioaccessorykit 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 Audioaccessorykit 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 Audioaccessorykit 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.

AudioAccessoryKit

Automatic audio switching support and intelligent audio routing inputs for third-party audio accessories. Enables companion apps to register audio accessory configuration with the system, and app extensions to report placement and connected source changes that help the system switch audio output. Available iOS 26.4+ / iPadOS 26.4+.

Beta-sensitive. AudioAccessoryKit is new in iOS 26.4. Re-check current Apple documentation before relying on specific API details.

AudioAccessoryKit builds on top of AccessorySetupKit. The accessory must first be paired via AccessorySetupKit before it can be registered for audio features. The central type is AccessoryControlDevice, which registers a Configuration from the container app and applies ongoing configuration updates from the app extension.

Contents

Setup

Prerequisites

  1. Pair the accessory over Bluetooth using AccessorySetupKit. This yields an ASAccessory object.
  2. Import the frameworks where needed in the container app and extension:
swift
import AccessorySetupKit
import AudioAccessoryKit

Framework Availability

PlatformMinimum Version
iOS26.4+
iPadOS26.4+

In the current Xcode 26.6 toolchain, AudioAccessoryKit is present in the device SDK but not the iPhone Simulator 26.5 SDK. Use a physical-device destination for this target. If the rest of the app must build for Simulator, isolate target membership or guard the import and implementation with #if canImport(AudioAccessoryKit) and provide a simulator stub.

Session Management

Registering an Accessory

After pairing via AccessorySetupKit, register the accessory from the container app by passing an AccessoryControlDevice.Configuration that describes the capabilities and any initial state the accessory supports:

swift
let accessory: ASAccessory  // Obtained from AccessorySetupKit pairing

let configuration = AccessoryControlDevice.Configuration(
    devicePlacement: .offHead,
    deviceCapabilities: [.audioSwitching, .placement]
)

try await AccessoryControlDevice.register(accessory, configuration)

Registration activates the specified capabilities and gives the system the configuration it needs to participate in audio routing decisions.

Retrieving the Current Configuration

In the app extension, access the device's current configuration using the static current(for:) method:

swift
let device = try AccessoryControlDevice.current(for: accessory)
let currentConfig = device.configuration

This returns the AccessoryControlDevice instance associated with the paired ASAccessory. The device exposes both the accessory reference and the current configuration. Apple marks current(for:) as app-extension-only.

Updating Configuration

In the app extension, push configuration changes to the system with update(_:). Only update fields for capabilities that were declared during registration:

swift
let device = try AccessoryControlDevice.current(for: accessory)
var config = device.configuration

config.devicePlacement = .onHead
try await device.update(config)

Treat this as a gated write workflow: confirm registration declared the capability, copy and mutate device.configuration, then try await update(_:). The method returns no configuration value; update an app-side mirror only after the call succeeds. On failure, use the disposition in Error Handling. Apple marks update(_:) as app-extension-only.

Audio Switching

Automatic audio switching lets the system intelligently route audio output to the correct device based on placement and connected sources.

Enabling Audio Switching

Declare .audioSwitching during the canonical registration flow above. Include .placement and an initial placement only when the accessory can report ongoing placement changes.

Capabilities

Automatic switching commonly uses these AccessoryControlDevice.Capabilities:

CapabilityPurpose
.audioSwitchingDevice supports automatic audio switching
.placementDevice can report its physical placement

Combine capabilities as needed. Do not declare .placement unless the accessory can keep the system updated with real placement state.

Device Placement

Report the physical position of the accessory from the app extension to help the system make routing decisions. Update placement whenever the accessory detects a position change.

Placement Values

AccessoryControlDevice.Placement defines four cases:

PlacementMeaning
.inEarAccessory is seated in the ear (e.g., earbuds)
.onHeadAccessory is on the head (e.g., headband headphones)
.overTheEarAccessory is over the ear (e.g., over-ear headphones)
.offHeadAccessory is not being worn

Updating Placement

swift
config.devicePlacement = .inEar

Apply this mutation within the canonical current→copy→update sequence above.

Common transitions:

  • .offHead to .onHead or .inEar when the user puts on the accessory
  • .onHead or .inEar to .offHead when removed
  • Update promptly on every detected change for responsive audio routing

Connected Audio Sources

For accessories that connect to multiple Bluetooth devices simultaneously, inform the system from the app extension which devices are connected. This lets the system route audio from the appropriate source.

Setting Audio Source Identifiers

Provide the Bluetooth address of connected devices as Data:

swift
let primaryBTAddress = Data([0x12, 0x34, 0x56, 0x78, 0x9A, 0xBC])
config.primaryAudioSourceDeviceIdentifier = primaryBTAddress

let secondaryBTAddress = Data([0xAB, 0xCD, 0xEF, 0x01, 0x23, 0x45])
config.secondaryAudioSourceDeviceIdentifier = secondaryBTAddress

Update these identifiers when the Bluetooth connection state changes (new device connects, existing device disconnects), then call the canonical update(_:) sequence.

Configuration Properties

Automatic switching uses these configuration fields:

PropertyTypePurpose
deviceCapabilitiesCapabilitiesDeclared device capabilities
devicePlacementPlacement?Current physical placement
primaryAudioSourceDeviceIdentifierData?Primary connected Bluetooth device address
secondaryAudioSourceDeviceIdentifierData?Secondary connected Bluetooth device address

Feature Discovery

Querying Capabilities

In the app extension, inspect the device's declared capabilities through its configuration:

swift
let device = try AccessoryControlDevice.current(for: accessory)
let caps = device.configuration.deviceCapabilities

if caps.contains(.audioSwitching) {
    // Device supports automatic audio switching
}

if caps.contains(.placement) {
    // Device reports physical placement
}

Checking Placement

Read the current placement to determine if the accessory is being worn:

swift
let device = try AccessoryControlDevice.current(for: accessory)

if let placement = device.configuration.devicePlacement {
    switch placement {
    case .inEar, .onHead, .overTheEar:
        // Accessory is being worn
        break
    case .offHead:
        // Accessory is not being worn
        break
    @unknown default:
        break
    }
}

Error Handling

AccessoryControlDevice.Error covers failure cases during registration and updates:

ErrorCause
.accessoryNotCapableAccessory does not support the requested capability
.invalidRequestRequest parameters are invalid
.invalidatedDevice registration has been invalidated
.unknownAn unspecified error occurred

Handle errors from registration and update calls:

swift
let configuration = AccessoryControlDevice.Configuration(
    devicePlacement: .offHead,
    deviceCapabilities: [.audioSwitching, .placement]
)

do {
    try await AccessoryControlDevice.register(accessory, configuration)
} catch let error as AccessoryControlDevice.Error {
    switch error {
    case .accessoryNotCapable:
        // Accessory hardware does not support requested capabilities
        break
    case .invalidRequest:
        // Check registration parameters
        break
    case .invalidated:
        // Coordinate container-app registration again
        break
    case .unknown:
        // Log, surface, or propagate; Apple does not classify this as transient
        throw error
    @unknown default:
        throw error
    }
}

Do not infer that .invalidated or .unknown is transient. Correct invalid capabilities or request parameters, discard an invalidated handle and notify the container app to re-evaluate registration where appropriate, and surface unspecified errors. Load Error Recovery Patterns for the complete disposition and invalidation handoff.

Common Mistakes

DON'T: Register before pairing with AccessorySetupKit

Register only the ASAccessory returned by a completed AccessorySetupKit pairing.

DON'T: Declare placement capability without updating placement

If registration declares .placement, the extension must update placement on every detected transition using the canonical update sequence.

DON'T: Ignore connection state changes for multi-device accessories

Clear or replace primary and secondary source identifiers whenever Bluetooth connections change; stale identifiers reduce switching accuracy.

DON'T: Forget to handle the invalidated error

swift
// WRONG -- ignores invalidation, keeps using stale device reference
try await device.update(config)  // Throws .invalidated, unhandled

// CORRECT -- discard the handle and let the container re-evaluate registration
do {
    try await device.update(config)
} catch AccessoryControlDevice.Error.invalidated {
    await notifyContainerAppToReevaluateRegistration(accessory)
}

Review Checklist

  • Accessory paired via AccessorySetupKit before AudioAccessoryKit registration
  • Both AccessorySetupKit and AudioAccessoryKit imported
  • Container app calls register(_: _:) with AccessoryControlDevice.Configuration
  • App extension calls current(for:) and update(_:)
  • Capabilities in the registration configuration match actual hardware support
  • Updates only touch fields for capabilities declared during registration
  • .placement capability accompanied by ongoing placement updates
  • Placement transitions (on/off head) reported promptly
  • Audio source device identifiers updated on Bluetooth connection changes
  • All AccessoryControlDevice.Error cases handled, including @unknown default
  • update(_:) calls use try await and handle errors
  • Invalidated device references trigger container-app registration recovery
  • Deployment target set to iOS 26.4+ or iPadOS 26.4+

References

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 Audioaccessorykit AI skill do?

Support automatic audio switching for paired third-party Bluetooth headphones or earbuds with AudioAccessoryKit. Use when a companion app registers an audio accessory, an app extension reports worn/removed placement or connected source-device changes, or AccessoryControlDevice capabilities and errors need handling. Do not use for general AVAudioSession routing, Bluetooth transport, or initial accessory pairing.

Why use Audioaccessorykit on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dpearson2699/swift-ios-skills/tree/main/skills/audioaccessorykit. 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 Audioaccessorykit?

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 Audioaccessorykit?

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

Is the Audioaccessorykit AI skill free?

It is published on GitHub by dpearson2699. Check the repository for licensing terms. 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 👇