Set up the Android SDK and connect to Meta glasses for the first time.
This skill appears to be introductory documentation/prompt content, and the system marks it as prompt-only, with no declared keys or remote endpoints, so overall risk is low. The main caveat is that the README guides developers to integrate a third-party Android SDK, app permissions, and a GitHub Packages token, but those are normal development requirements of the integrated SDK rather than direct high-risk behavior of the skill itself.
The metadata states that the skill itself requires no keys or environment variables. The README mentions a GITHUB_TOKEN with read:packages scope only for fetching dependencies from GitHub Packages during development, which is a build-time credential rather than a runtime secret directly collected or exfiltrated by the skill.
No remote host is declared for the skill itself. The network-related items in the README mainly concern the Android app side, such as downloading artifacts from GitHub Maven and declaring INTERNET permission; there is no evidence that the skill itself sends user data to unknown or unrelated endpoints.
The objective checks mark it as prompt-only, indicating that the artifact itself is more like documentation than an executable tool. The material does not show the skill launching local processes, executing scripts, or requesting system capabilities beyond what is described.
There is no indication that the skill itself reads or writes local files, databases, clipboard contents, or account data. The references to local.properties, AndroidManifest, and app initialization code are developer-side integration steps and do not mean the skill automatically gains data access.
The source is an open-source GitHub repository with auditable code and some community adoption (289 stars), which are positive factors that lower risk. Although the license is undeclared and maintenance status is unknown, the available material shows no clear supply-chain red flags such as closed distribution, unknown origin, or obvious tampering.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "getting-started" skill from askskill: 1. Download https://raw.githubusercontent.com/facebook/meta-wearables-dat-android/main/plugins/mwdat-android/skills/getting-started/SKILL.md 2. Save it as ~/.claude/skills/getting-started/SKILL.md 3. Reload skills and tell me it's ready
Guide me to integrate the Meta glasses SDK into an existing Android project, including Gradle dependencies, required permissions, AndroidManifest setup, and a minimal runnable example.
A step-by-step integration guide with config snippets, permission list, and basic sample code.
I finished the basic setup, but my Android app cannot connect to Meta glasses. Give me a troubleshooting checklist covering SDK initialization, Bluetooth/permission checks, and connection verification.
An ordered troubleshooting checklist to identify issues in initialization, permissions, or the connection flow.
Create a starter sample project structure for Meta glasses Android development, explain the purpose of each file, and provide the core code flow for the first device connection.
A clear sample project skeleton with file explanations and the key code flow for the first connection.
Set up the Meta Wearables Device Access Toolkit in an Android app.
read:packages scopeIn settings.gradle.kts:
val localProperties =
Properties().apply {
val localPropertiesPath = rootDir.toPath() / "local.properties"
if (localPropertiesPath.exists()) {
load(localPropertiesPath.inputStream())
}
}
dependencyResolutionManagement {
repositories {
google()
mavenCentral()
maven {
url = uri("https://maven.pkg.github.com/facebook/meta-wearables-dat-android")
credentials {
username = ""
password = System.getenv("GITHUB_TOKEN") ?: localProperties.getProperty("github_token")
}
}
}
}
In libs.versions.toml:
[versions]
mwdat = "0.7.0"
[libraries]
mwdat-core = { group = "com.meta.wearable", name = "mwdat-core", version.ref = "mwdat" }
mwdat-camera = { group = "com.meta.wearable", name = "mwdat-camera", version.ref = "mwdat" }
mwdat-mockdevice = { group = "com.meta.wearable", name = "mwdat-mockdevice", version.ref = "mwdat" }
In app/build.gradle.kts:
dependencies {
implementation(libs.mwdat.core)
implementation(libs.mwdat.camera)
implementation(libs.mwdat.mockdevice)
}
AndroidManifest.xml<manifest ...>
<uses-permission android:name="android.permission.BLUETOOTH_CONNECT" />
<uses-permission android:name="android.permission.INTERNET" />
<application ...>
<meta-data
android:name="com.meta.wearable.mwdat.APPLICATION_ID"
android:value="0" />
<activity android:name=".MainActivity" ...>
<intent-filter>
<action android:name="android.intent.action.VIEW" />
<category android:name="android.intent.category.DEFAULT" />
<category android:name="android.intent.category.BROWSABLE" />
<data android:scheme="myexampleapp" />
</intent-filter>
</activity>
</application>
</manifest>
Use 0 for APPLICATION_ID in Developer Mode. Replace myexampleapp with your app's URL scheme.
import com.meta.wearable.dat.core.Wearables
class MyApplication : Application() {
override fun onCreate() {
super.onCreate()
Wearables.initialize(this)
.onFailure { error, _ -> error("Failed to initialize DAT: ${error.description}") }
}
}
import com.meta.wearable.dat.core.Wearables
import com.meta.wearable.dat.core.selectors.AutoDeviceSelector
fun connect(activity: Activity) {
Wearables.startRegistration(activity)
}
fun startSession() {
val session = Wearables.createSession(AutoDeviceSelector()).getOrElse { error ->
throw IllegalStateException(error.description)
}
session.start()
}
Observe registration and available devices:
lifecycleScope.launch {
Wearables.registrationState.collect { state ->
// Update registration UI
}
}
lifecycleScope.launch {
Wearables.devices.collect { devices ->
// Update the device list
}
}
import com.meta.wearable.dat.camera.addStream
import com.meta.wearable.dat.camera.types.StreamConfiguration
import com.meta.wearable.dat.camera.types.VideoQuality
val stream = session.addStream(
StreamConfiguration(videoQuality = VideoQuality.MEDIUM, frameRate = 24),
).getOrElse { error ->
…
Set up camera sessions, stream video, capture photos, and tune resolution.
Build a complete DAT app with sessions, camera streaming, and photo capture.
Manage session and stream state with pause, resume, and device monitoring.
Diagnose common issues, compatibility problems, and session or stream debugging cases.
Helps developers set up Meta AI app registration and device permission flows.
Build display-enabled interfaces with device selection, UI components, and media playback.
Set up the Meta glasses SDK and make your first connection.
Test and validate glasses features without physical hardware using MockDeviceKit.
Guide app registration with Meta AI and camera permission request flows.