AutoGineer
Generated banner for Engage SDK Integration
Generated logo for Engage SDK Integration

Engage SDK Integration

Android (Google)OfficialCreated by Google LLCDistributed by Android (Google)

  • Skill
  • Tool integration
  • Software development
  • Apache-2.0
  • No issues found
Download ZIP

From the author

Helps developers integrate, debug, and resolve Play Engage SDK implementation issues. Use when adding Engage SDK support, generating publishing code, mapping data classes to entities, or fixing SDK-related errors.
— the description by Google LLC

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill provides a structured workflow for Android developers to integrate the Play Engage SDK. It covers the end-to-end process, including identifying vertical-specific requirements, generating necessary boilerplate code, mapping local data models to Engage entities, and configuring broadcast receivers for data synchronization. The skill also includes a verification checklist and troubleshooting guidance to ensure a robust implementation.

What it does

  • Guides developers through vertical-specific Engage SDK integration steps.
  • Generates boilerplate code for constants, entity converters, request factories, and workers.
  • Assists in mapping local app models to required Engage entity schemas.
  • Provides instructions for both static and dynamic broadcast receiver registration.
  • Offers a self-verification checklist to ensure successful implementation.
  • Provides troubleshooting steps for common compilation and integration errors.

When to use it

  • When adding Play Engage SDK support to an Android application.
  • When generating publishing code for recommendation or continuation clusters.
  • When mapping existing local data classes to Engage-compatible entities.
  • When debugging SDK-related errors or implementation issues.

Advantages

  • Ensures adherence to mandatory SDK structure and entity requirements.
  • Reduces manual effort by providing standardized code templates.
  • Promotes best practices for background data synchronization.
  • Simplifies the complex process of vertical-specific configuration.

Usage examples

“How do I integrate the Engage SDK for my food delivery app?”
The agent will identify the food vertical, guide you through selecting the appropriate cluster types, and generate the required boilerplate classes like ItemToEntityConverter and EngageWorker.
“I am getting a background execution error with my broadcast receiver. How do I fix it?”
The agent will instruct you to implement dynamic registration for your EngageBroadcastReceiver and verify that the correct permissions are handled.
“How do I map my local restaurant data class to a StoreEntity?”
The agent will analyze your data class, compare it against the food schema, and generate the conversion logic for your ItemToEntityConverter.

Install

  1. Download the skill as a ZIP:

    https://autogineer.com/agent-skills/android/engage-sdk-integration/download

  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip engage-sdk-integration.zip -d .agents/skills

Documentation by Google LLC

This skill guides you through integrating the Play Engage SDK into an Android app. It ensures that the code follows the mandatory structure and uses the required Engage entities for each vertical.

Workflow

Follow these steps to assist the developer:

  1. Identify vertical and cluster:

    • Ask the developer which vertical their app belongs to based on references/schemas/.

    • Check if the integration is for TV or mobile. If the integration is for TV, read the TV-specific sections in patterns.md as well.

    • Use {VERTICAL}.md in the references/schemas/ directory to identify the corresponding Engage entities and the client class name. The client field in the JSON provides the full class name. For example, com.google.android.engage.food.service.AppEngageFoodClient.

    • Note: Initializing the client class requires a Context parameter. For example, AppEngageFoodClient(context).

    • Always refer to common.md for common entities.

    • Ask which cluster type they want to publish from the supported cluster types for that vertical.

    • Find the method to call from {VERTICAL}.md in the references/schemas/ directory for the specified cluster. Each method will specify the request it expects.

    • Get the request structure from requests.md and clusters from clusters.md. Then suggest and use sources to fill the fields in the request structure correctly, along with the required entities and clusters.

  2. Generate structured boilerplate code:

    • Create a new directory for all Engage-related code. Name the directory to match the naming convention of the existing codebase.

    • Generate the following classes using templates in patterns.md:

      • Constants: holds constant values such as attempt counts and publish types.

      • ItemToEntityConverter: converts the app's local models to Engage's Entity models.

      • ClusterRequestFactory: constructs the publish requests.

      • EngageWorker: handles the actual publishing and publish errors using WorkManager.

      • EngagePublisher: orchestrates periodic and one-time jobs.

      • EngageBroadcastReceiver: listens for AppEngageService intents and starts a one-time publish job from EngagePublisher. Important : Implement both static registration and dynamic registration patterns, including the companion object register method inside the EngageBroadcastReceiver class.

  3. Suggest entity mapping:

    • Ask the developer to provide their local model schema (for example, a data class or a JSON snippet).

    • If they haven't provided one, share entities from {VERTICAL}.md in the references/schemas/ directory as a guide.

    • Once the local model is identified, suggest a mapping to the corresponding Engage entity.

    • Generate the conversion logic using the ItemToEntityConverter pattern in patterns.md and add it to the generated {ENGAGE_CODE_DIR}/ItemToEntityConverter.

  4. Suggest data source:

    • Ask the developer to provide the source of actual data you'll publish.

    • Once you identify the data source, use it to fetch the data in the app's local model schema.

    • Use {ENGAGE_CODE_DIR}/ItemToEntityConverter to convert this data to an Engage entity.

    • Use obtained Engage entity model data with {ENGAGE_CODE_DIR}/ ClusterRequestFactory to get cluster requests.

    • Call corresponding cluster publishing method obtained from {VERTICAL}.md in the references/schemas/ directory with the obtained request in previous step in {ENGAGE_CODE_DIR}/EngageWorker.

  5. Gradle and manifest updates:

    • Suggest updates to build.gradle and AndroidManifest.xml.

    • For mobile apps, use patterns.md.

    • For TV apps, use the TV-specific sections in patterns.md.

    • Provide the necessary implementation dependencies for build.gradle or build.gradle.kts from patterns.md.

    • Provide the <receiver> and <service> declarations for AndroidManifest.xml.

    • Note: Except for TV, there aren't any vertical-specific imports. For all other verticals, com.google.android.engage:engage-core:1.6.0 is sufficient.

  6. Debugging and verification:

    • Self-verification checklist : Before considering your work complete, you must verify that you've implemented all of the following:

      • [ ] Registered EngageBroadcastReceiver statically in AndroidManifest.xml (inside the <application> tag).

      • [ ] Registered EngageBroadcastReceiver dynamically by calling EngageBroadcastReceiver.register(context) in the Application class or main Activity class.

      • [ ] Implemented the register method in EngageBroadcastReceiver's companion object to handle dynamic registration.

      • [ ] Handled empty data lists in EngageWorker (for example, by deleting the cluster instead of publishing empty data).

    • Perform a Gradle sync.

    • If errors occur (such as import failures, namespace conflicts, or compile errors), read references/troubleshooting.md to resolve them.

    • Execute a Gradle compilation (./gradlew compileDebugUnitTestSources or ./gradlew assembleDebug). See references/troubleshooting.md for compile rules and warnings about fast-compilation shortcuts. Repeat this step until compilation is successful.

  7. User checklist: At the end of code generation, notify the user to go through this checklist to verify that the integration is complete and as intended:

    • [ ] Verify that all the Engage-related files are created in {ENGAGE_CODE_DIR}/:

      • Constants

      • ItemToEntityConverter

      • ClusterRequestFactory

      • EngageWorker

      • {cluster_type}Publisher

      • EngageBroadcastReceiver

    • [ ] Verify that app's local model is converted to Engage entity by populating the fields correctly in the model in {ENGAGE_CODE_DIR}/ItemToEntityConverter.

    • [ ] Verify that all image URIs in ItemToEntityConverter point to images matching the strict aspect ratio requirements of the vertical (for example, 16:9, 1:1, 2:3).

    • [ ] Verify that {ENGAGE_CODE_DIR}/EngageWorker uses the data source identified in Step 4.

    • [ ] Verify that EngageBroadcastReceiver.register(context) is called within the Application class or MainActivity to register the receiver dynamically.

    • [ ] Verify that AndroidManifest.xml contains the static <receiver> declaration for EngageBroadcastReceiver with the necessary intent actions.

    • Important : Explicitly instruct the developer to call EngageBroadcastReceiver.register(context) inside their custom Application class onCreate() (or their main activity onCreate()) to dynamically register the receiver. Stress that both static and dynamic registrations are required for the integration to function.

Reference materials

Files

references/android/guide/playcore/engage/tv/recommendations.md

This guide contains instructions for developers to integrate their recommended video content, using the Engage SDK, to populate recommendations experiences across Google surfaces, such as TV, mobile, and tablet.

Recommendation leverages the Recommendation cluster to show movies and TV shows, from multiple apps in one UI grouping. Each developer partner can broadcast a maximum of 25 entities in each recommendations cluster and there can be a maximum of 7 recommendation clusters per request.

Pre-work

[!IMPORTANT] Important: Express interest in developing with Engage.

Complete the Pre-work instructions in the Getting Started guide.

  1. Execute publishing on a foreground service.

  2. Publish recommendations data at most once daily, triggered by either of

    • User's first login of the day. (or)

    • When the user starts interacting with the application.

Integration

AppEngagePublishClient publishes the recommendation cluster. Use the publishRecommendationClusters method to publish a recommendations object.

Make sure to initialize the client and check for service availability as described in the Getting Started guide.

client.publishRecommendationClusters(recommendationRequest)
Upserting recommendation clusters

Clusters are logical grouping of the entities. The following code examples explains how to build the clusters based on your preference and how to create a publishing request and upsert all clusters.

The RecommendationClusterType determines how the cluster will be displayed.

// cluster for popular movies
val recommendationCluster1 = RecommendationCluster
  .Builder()
  .addEntity(movie1)
  .addEntity(movie2)
  .addEntity(movie3)
  .addEntity(movie4)
  .addEntity(tvShow)
  // This cluster is meant to be used as an individual provider row
  .setRecommendationClusterType(TYPE_PROVIDER_ROW)
  .setTitle("Popular Movies")
  .build()

// cluster for live TV programs
val recommendationCluster2 = RecommendationCluster
  .Builder()
  .addEntity(liveTvProgramEntity1)
  .addEntity(liveTvProgramEntity2)
  .addEntity(liveTvProgramEntity3)
  .addEntity(liveTvProgramEntity4)
  .addEntity(liveTvProgramEntity5)
 // This cluster is meant to be used as an individual provider row
  .setRecommendationClusterType(TYPE_PROVIDER_ROW)
  .setTitle("Popular Live TV Programs")
  .build()

// creating a publishing request
val recommendationRequest = PublishRecommendationClustersRequest
  .Builder()
  .setSyncAcrossDevices(true)
  .setAccountProfile(accountProfile)
  .addRecommendationCluster(recommendationCluster1)
  .addRecommendationCluster(recommendationCluster2)
  .build()

When the service receives the request, the following actions occur within one transaction:

  • Existing RecommendationsCluster data from the developer partner is removed.

  • Data from the request is parsed and stored in the updated RecommendationsCluster. In case of an error, the entire request is rejected and the existing state is maintained.

[!NOTE] Note: Publish APIs are upsert operations, replacing existing content; update entities by republishing the entire cluster. Only publish recommendations for adult accounts. Avoid using delete APIs followed by publish, as the latter inherently replaces content.

Cross-device sync

SyncAcrossDevices flag controls whether a user's recommendations cluster data is shared with Google TV and available across their devices such as TV, phone, tablets. In order for the recommendation to work, it must be set to true.

Obtain consent

The media application must provide a clear setting to enable or disable cross-device syncing. Explain the benefits to the user and store the user's preference once and apply it in publishRecommendations Request accordingly. To get the most out of cross-device feature, verify app obtains user consent and enables SyncAcrossDevices to true.

Delete the Engage data

To manually delete a user's data from the Google TV server before the standard 60-day retention period, use the client.deleteClusters() method. Upon receiving the request, the service deletes all existing Engage data for the account profile, or for the entire account.

The DeleteReason enum defines the reason for data deletion. The following code removes recommendations on logout.

// If the user logs out from your media app, you must make the following call
// to remove recommendations data from the current Google TV device, otherwise,
// the recommendations data persists on the current Google TV device until 60
// days later.
client.deleteClusters(
  DeleteClustersRequest.Builder()
    .setAccountProfile(accountProfile)
    .setDeleteReason(DeleteReason.DELETE_REASON_USER_LOG_OUT)
    .build()
)

// If the user revokes the consent to share data with Google TV, you must make
// the following call to remove recommendations data from all current Google TV
// devices. Otherwise, the recommendations data persists until 60 days later.
client.deleteClusters(
  DeleteClustersRequest.Builder()
    .setAccountProfile(accountProfile)
    .setDeleteReason(DeleteReason.DELETE_REASON_LOSS_OF_CONSENT)
    .build()
)

Create entities

The SDK has defined different entities to represent each item type. Following entities are supported for the Recommendation cluster:

  1. MediaActionFeedEntity

  2. MovieEntity

  3. TvShowEntity

  4. LiveTvChannelEntity

  5. LiveTvProgramEntity

Provide descriptions

Provide a short description for each entity; this description will be displayed when users hover over the entity, providing them with additional details.

Call to action text

Provide an optional call to action text for each entity. This text will be displayed to the user to encourage engagement.

Tags

Optionally provide a list of tags for each entity. Tags can be used for categorization and filtering.

Platform specific playBack URIs

Create playback URIs for each supported platform: Android TV, Android, or iOS. This allows the system to select the appropriate URI for video playback on the respective platform.

In the rare case when the playback URIs are identical for all platforms, repeat it for every platform.

// Required. Set this when you want recommended entities to show up on
// Google TV
val playbackUriTv = PlatformSpecificUri
  .Builder()
  .setPlatformType(PlatformType.TYPE_ANDROID_TV)
  .setActionUri(Uri.parse("https://www.example.com/entity_uri_for_tv"))
  .build()

// Optional. Set this when you want recommended entities to show up on
// Google TV Android app
val playbackUriAndroid = PlatformSpecificUri
  .Builder()
  .setPlatformType(PlatformType.TYPE_ANDROID_MOBILE)
  .setActionUri(Uri.parse("https://www.example.com/entity_uri_for_android"))
  .build()

// Optional. Set this when you want recommended entities to show up on
// Google TV iOS app
val playbackUriIos = PlatformSpecificUri
  .Builder()
  .setPlatformType(PlatformType.TYPE_IOS)
  .setActionUri(Uri.parse("https://www.example.com/entity_uri_for_ios"))
  .build()

val platformSpecificPlaybackUris =
  Arrays.asList(playbackUriTv, playbackUriAndroid, playbackUriIos)

// Provide appropriate rating for the system.
val contentRating = RatingSystem
  .Builder()
  .setAgencyName("MPAA")
  .setRating("PG-13")
  .build()
Poster images

Poster images require a URI and pixel dimensions (height and width). Target different form factors by providing multiple poster images, but verify all images maintain a 16:9 aspect ratio and a minimum height of 200 pixels for correct display of the "Recommendations" entity, especially within Google's Entertainment Space. Images with a height less than 200 pixels may not be shown.

val image1 = Image.Builder()
  .setImageUri(Uri.parse("http://www.example.com/entity_image1.png"))
  .setImageHeightInPixel(300)
  .setImageWidthInPixel(169)
  .build()

val image2 = Image.Builder()
  .setImageUri(Uri.parse("http://www.example.com/entity_image2.png"))
  .setImageHeightInPixel(640)
  .setImageWidthInPixel(360)
  .build()

// And other images for different form factors.
val images = Arrays.asList(image1, image2)
Recommendation reason

Optionally provide a recommendation reason which can be used by Google TV to construct reasons as to why to suggest a specific Movie or TV Show to the user.

//Allows us to construct reason: "Because it is top 10 on your Channel"
val topOnPartner = RecommendationReasonTopOnPartner
  .Builder()
  .setNum(10) //any valid integer value
  .build()

//Allows us to construct reason: "Because it is popular on your Channel"
val popularOnPartner = RecommendationReasonPopularOnPartner
  .Builder()
  .build()

//Allows us to construct reason: "New to your channel, or Just added"
val newOnPartner = RecommendationReasonNewOnPartner
  .Builder()
  .build()

//Allows us to construct reason: "Because you watched Star Wars"
val watchedSimilarTitles = RecommendationReasonWatchedSimilarTitles
  .Builder()
  .addSimilarWatchedTitleName("Movie or TV Show Title")
  .addSimilarWatchedTitleName("Movie or TV Show Title")
  .build()

//Allows us to construct reason: "Recommended for you by ChannelName"
val recommendedForUser = RecommendationReasonRecommendedForUser
  .Builder()
  .build()

val watchAgain = RecommendationReasonWatchAgain
  .Builder()
  .build()

val fromUserWatchList = RecommendationReasonFromUserWatchlist
  .Builder()
  .build()

val userLikedTitle = RecommendationReasonUserLikedTitle
  .Builder()
  .setLikedTitleName("Movie or TV Show Title")
  .build()

val generic = RecommendationReasonGeneric.Builder().build()
Display time window

If an entity should only be available for a limited time, set a custom expiration time. Without an explicit expiration time, entities will automatically expire and be erased after 60 days. So set an expiration time only when the entities need to be expired sooner. Specify multiple such availability windows.

val window1 = DisplayTimeWindow
  .Builder()
  .setStartTimestampMillis(now() + 1.days.toMillis())
  .setEndTimestampMillis(now() + 30.days.toMillis())
  .build()

val window2 = DisplayTimeWindow
  .Builder()
  .setEndTimestampMillis(now() + 30.days.toMillis())
  .build()

val availabilityTimeWindows: List<DisplayTimeWindow> = listOf(window1, window2)
DataFeedElementId

If you have integrated your Media catalogue or Media action feed with Google TV, you need not create separate entities for Movie or TV Show and instead you can create a MediaActionFeedEntity which includes the required field DataFeedElementId. This Id must be unique and must match with the ID in Media Action Feed as it helps to identify ingested feed content and perform media content lookups.

val id = "dataFeedElementId"
MovieEntity

Here's an example of creating a MovieEntity with all the required fields:

val movieEntity = MovieEntity.Builder()
  .setName("Movie name")
  .setDescription("A sentence describing movie.")
  .addPlatformSpecificPlaybackUris(platformSpecificPlaybackUris)
  .addPosterImages(images)
  // Suppose the duration is 2 hours, it is 72000000 in milliseconds
  .setDurationMillis(72000000)
  .setCallToActionText("Watch Now")
  .addTag("Action")
  .build()

You can provide additional data such as genres, content ratings, release date, recommendation reason and availability time windows, which may be used by Google TV for enhanced displays or filtering purposes.

val genres = Arrays.asList("Action", "Science fiction")
val rating1 = RatingSystem.Builder().setAgencyName("MPAA").setRating("pg-13").build()
val contentRatings = Arrays.asList(rating1)
//Suppose release date is 11-02-2025
val releaseDate  = 1739233800000L
val movieEntity = MovieEntity.Builder()
  ...
  .addGenres(genres)
  .setReleaseDateEpochMillis(releaseDate)
  .addContentRatings(contentRatings)
  .setRecommendationReason(topOnPartner or watchedSimilarTitles)
  .addAllAvailabilityTimeWindows(availabilityTimeWindows)
  .build()
TvShowEntity

Here's an example of creating a TvShowEntity with all the required fields:

val tvShowEntity = TvShowEntity.Builder()
  .setName("Show title")
  .setDescription("A sentence describing TV Show.")
  .addPlatformSpecificPlaybackUris(platformSpecificPlaybackUris)
  .addPosterImages(images)
  .setCallToActionText("Watch Now")
  .addTag("Drama")
  .build()

Optionally provide additional data such as genres, content ratings, recommendation reason, offer price, season count or availability time window, which may be used by Google TV for enhanced displays or filtering purposes.

val genres = Arrays.asList("Action", "Science fiction")
val rating1 = RatingSystem.Builder()
  .setAgencyName("MPAA")
  .setRating("pg-13")
  .build()
val price = Price.Builder()
  .setCurrentPrice("$14.99")
  .setStrikethroughPrice("$16.99")
  .build()
val contentRatings = Arrays.asList(rating1)
val seasonCount = 5
val tvShowEntity = TvShowEntity.Builder()
  ...
  .addGenres(genres)
  .addContentRatings(contentRatings)
  .setRecommendationReason(topOnPartner or watchedSimilarTitles)
  .addAllAvailabilityTimeWindows(availabilityTimeWindows)
  .setSeasonCount(seasonCount)
  .setPrice(price)
  .build()
MediaActionFeedEntity

Here's an example of creating an MediaActionFeedEntity with all the required fields:

val mediaActionFeedEntity = MediaActionFeedEntity.Builder()
  .setDataFeedElementId(id)
  .setCallToActionText("Watch Now")
  .addTag("Action")
  .build()

Optionally provide additional data such as description, recommendation reason and display time window, which may be used by Google TV for enhanced displays or filtering purposes.

val mediaActionFeedEntity = MediaActionFeedEntity.Builder()
  .setName("Movie name or TV Show name")
  .setDescription("A sentence describing an entity")
  .setRecommendationReason(topOnPartner or watchedSimilarTitles)
  .addPosterImages(images)
  .build()
LiveTvChannelEntity

This represents a live TV channel. Here's an example of creating a LiveTvChannelEntity with all the required fields:

val liveTvChannelEntity = LiveTvChannelEntity.Builder()
  .setName("Channel Name")
  // ID of the live TV channel
  .setEntityId("https://www.example.com/channel/12345")
  .setDescription("A sentence describing this live TV channel.")
  // channel playback uri must contain at least PlatformType.TYPE_ANDROID_TV
  .addPlatformSpecificPlaybackUris(channelPlaybackUris)
  .setLogoImage(logoImage)
  .setCallToActionText("Watch Now")
  .addTag("News")
  .build()

Optionally provide additional data such as content ratings or recommendation reason.

val rating1 = RatingSystem.Builder()
  .setAgencyName("MPAA")
  .setRating("pg-13")
  .build()
val contentRatings = Arrays.asList(rating1)

val liveTvChannelEntity = LiveTvChannelEntity.Builder()
  ...
  .addContentRatings(contentRatings)
  .setRecommendationReason(topOnPartner)
  .build()
LiveTvProgramEntity

This represents a live TV program card airing or scheduled to air on a live TV channel. Here's an example of creating a LiveTvProgramEntity with all the required fields:

val liveTvProgramEntity = LiveTvProgramEntity.Builder()
  // First set the channel information
  .setChannelName("Channel Name")
  .setChannelId("https://www.example.com/channel/12345")
  // channel playback uri must contain at least PlatformType.TYPE_ANDROID_TV
  .addPlatformSpecificPlaybackUris(channelPlaybackUris)
  .setChannelLogoImage(channelLogoImage)
  // Then set the program or card specific information.
  .setName("Program Name")
  .setEntityId("https://www.example.com/schedule/123")
  .setDescription("Program Description")
  .addAvailabilityTimeWindow(
      DisplayTimeWindow.Builder()
        .setStartTimestampMillis(1756713600000L) // 2025-09-01T07:30:00+0000
        .setEndTimestampMillis(1756715400000L) // 2025-09-01T08:00:00+0000
        .build()
  )
  .addPosterImage(programImage)
  .setCallToActionText("Watch Now")
  .addTag("Sports")
  .build()

Optionally provide additional data such as content ratings, genres, or recommendation reason.

val rating1 = RatingSystem.Builder()
  .setAgencyName("MPAA")
  .setRating("pg-13")
  .build()
val contentRatings = Arrays.asList(rating1)
val genres = Arrays.asList("Action", "Science fiction")

val liveTvProgramEntity = LiveTvProgramEntity.Builder()
  ...
  .addContentRatings(contentRatings)
  .addGenres(genres)
  .setRecommendationReason(topOnPartner)
  .build()

[!NOTE] Note: If the additional fields are provided directly within the entity, these values will be prioritized. The locale, if provided in the Account Profile, will be used to fetch the remaining entity metadata from Google's database in the language consistent with the request.

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by
Google LLC
Publisher
Android (Google) (Official)
Distributed by
Android (Google)
Source
android/skills · play/engage-sdk-integration · commit bf68e2d
Licence
Apache License 2.0 (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE.txt)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Google LLC or Android (Google).

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download engage-sdk-integration.zip