mcpbeat Sign in

Sample App Guide Agent Skill

Building a complete DAT app with camera streaming and photo capture

1k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
500
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/facebook/meta-wearables-dat-ios --skill sample-app-guide

The instruction itself

9 sections, as written by the author

Sample App Guide (iOS)

Build an iOS DAT app with camera streaming and photo capture.

This walkthrough covers app setup, registration, streaming, and capture. Pair it with the CameraAccess sample.

Project setup

  • Create a new Xcode project (SwiftUI App)
  • Add the SDK via SPM: https://github.com/facebook/meta-wearables-dat-ios
  • Add MWDATCore, MWDATCamera, and MWDATMockDevice to your target
  • Configure Info.plist (see Getting Started)

App architecture

A typical DAT app has these components:

MyDATApp/
├── MyDATApp.swift              # App entry point, SDK init
├── ViewModels/
│   ├── WearablesViewModel.swift    # Registration, device management
│   └── StreamViewModel.swift # Streaming, photo capture
└── Views/
    ├── MainAppView.swift           # Navigation
    ├── RegistrationView.swift      # Registration UI
    └── StreamView.swift            # Video preview, capture button

SDK initialization

import MWDATCore

@main
struct MyDATApp: App {
    init() {
        do {
            try Wearables.configure()
        } catch {
            assertionFailure("Wearables SDK configuration failed: \(error)")
        }
    }

    var body: some Scene {
        WindowGroup {
            MainAppView()
                .onOpenURL { url in
                    Task {
                        _ = try? await Wearables.shared.handleUrl(url)
                    }
                }
        }
    }
}

Wearables ViewModel

import MWDATCore

@MainActor
class WearablesViewModel: ObservableObject {
    @Published var registrationState: String = "Unknown"
    @Published var devices: [DeviceIdentifier] = []

    private let wearables = Wearables.shared

    func observeState() {
        Task {
            for await state in wearables.registrationStateStream() {
                self.registrationState = "\(state)"
            }
        }
        Task {
            for await devices in wearables.devicesStream() {
                self.devices = devices.map { $0.identifier }
            }
        }
    }

    func register() async {
        try? await wearables.startRegistration()
    }

    func unregister() async {
        try? await wearables.startUnregistration()
    }
}

Stream ViewModel

import MWDATCamera
import MWDATCore

@MainActor
class StreamViewModel: ObservableObject {
    @Published var currentFrame: UIImage?
    @Published var streamState: String = "Stopped"
    @Published var capturedPhoto: Data?

    private let wearables = Wearables.shared
    private var deviceSession: DeviceSession?
    private var camera: Camera?
    private var stream: Stream?

    func startStream() async {
        let config = StreamConfiguration(
            videoCodec: .raw,
            resolution: .medium,
            frameRate: 24
        )
        let selector = AutoDeviceSelector(wearables: wearables)

        do {
            let deviceSession = try wearables.createSession(deviceSelector: selector)
            try deviceSession.start()
            // Wait for the device session to reach the started state
            for await state in deviceSession.stateStream() {
                if state == .started { break }
            }
            guard let camera = try deviceSession.addCamera(config: config) else { return }
            let stream = camera.stream
            self.deviceSession = deviceSession
            self.camera = camera
            self.stream = stream
        } catch {
            return
        }

        guard let stream else { return }

        _ = stream.statePublisher.listen { [weak self] state in
            Task { @MainActor in
                self?.streamState = "\(state)"
            }
        }

        _ = stream.videoFramePublisher.listen { [weak self] frame in
            guard let image = frame.makeUIImage() else { return }
            Task { @MainActor in
                self?.currentFrame = image
            }
        }

        _ = stream.photoDataPublisher.listen { [weak self] photoData in
            Task { @MainActor in
                self?.capturedPhoto = photoData.data
            }
        }

        stream.start()
    }

    func stopStream() {
        camera?.stop()
        deviceSession?.stop()
        stream = nil
        camera = nil
        deviceSession = nil
    }

    func capturePhoto() {
        stream?.capturePhoto(format: .jpeg)
    }
}

Testing with MockDeviceKit

Add mock device support to develop without glasses:

import MWDATMockDevice

func setupMockDevice() async {
    let mockDeviceKit = MockDeviceKit.shared
    mockDeviceKit.enable()

    guard let device = try? mockDeviceKit.pairGlasses(model: .rayBanMeta) else { return }
    device.don()

    if let videoURL = Bundle.main.url(forResource: "test_video", withExtension: "mov") {
        let camera = device.services.camera
        camera.setCameraFeed(fileURL: videoURL)
    }
}

func tearDownMockDevice() {
    MockDeviceKit.shared.disable()
}

Allowed dependencies

Your DAT app should only depend on:

  • MWDATCore — always required
  • MWDATCamera — for camera streaming
  • MWDATMockDevice — for testing (can be test-only dependency)

Other skills for the same job

different authors, same section of the catalogue
Canvas Design
by anthropics
vendor ×13

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

1388k tokens
Algorithmic Art
by anthropics
vendor ×10

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

15k tokens scripts
Image Enhancer
by frostant
×6

Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.

635 tokens
Video Downloader
by CommandCodeAI
×4

Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.

671 tokens
Histolab
by christophacham
×3

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

18k tokens
Omero Integration
by christophacham
×3

Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.

32k tokens
Pydicom
by christophacham
×3

Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.

13k tokens scripts
Transformers
by christophacham
×3

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.

13k tokens

How to use it

Copy the folder

Take facebook/sample-app-guide from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.