
Engage SDK Integration
FreeStreamline Play Engage SDK integration for Android apps.
Free · Opens the source repo
What Engage SDK Integration does
The Engage SDK Integration skill is designed to assist developers in seamlessly integrating the Play Engage SDK into their Android applications. This skill provides a structured approach to ensure compliance with the SDK's requirements across various verticals, such as food, health and fitness, shopping, and more. By guiding users through the process of identifying the appropriate vertical and cluster, it simplifies the complex task of setting up the SDK correctly.
To begin, developers will identify the vertical their app targets and the corresponding Engage entities. The skill then generates boilerplate code necessary for the integration, including essential classes like Constants, ItemToEntityConverter, and EngageWorker. This automation not only saves time but also reduces the likelihood of errors during the setup process. Additionally, the skill suggests data mapping strategies and assists in updating the Gradle and manifest files, ensuring that all dependencies and configurations are correctly set.
The debugging process is also streamlined, providing a clear resolution path for common integration issues. After the code generation, a user checklist ensures that all necessary components are created and configured properly, allowing developers to verify their integration step-by-step. This comprehensive approach makes the Engage SDK Integration skill particularly useful for developers looking to implement the Play Engage SDK efficiently and accurately, without missing critical setup steps.
Overall, this skill is an invaluable resource for Android developers aiming to enhance their applications with the Play Engage SDK, providing them with the tools and guidance needed to implement the SDK correctly and effectively.
When to use it
Use this skill when you need to integrate the Play Engage SDK into your Android app, especially across different verticals.
When not to use it
This skill is not suitable for integrations outside of the Play Engage SDK or for developers not working on Android applications.
What you can build with it
Integrating Engage SDK for a Food App
A developer working on a food delivery app can use this skill to integrate the Engage SDK, ensuring all necessary entities and requests are correctly set up.
Debugging Play Engage SDK Issues
When encountering errors during SDK integration, this skill provides a clear path for identifying and resolving common issues, streamlining the debugging process.
Setting Up for Multiple Verticals
If a developer is building an app that spans multiple verticals, this skill helps in managing the different requirements and entities needed for each integration.
How to install Engage SDK Integration
View source1. Install with the skills CLI
npx skills add android/skills/engage-sdk-integration --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by androidThis 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:
-
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}.mdin the references/schemas/ directory to identify the corresponding Engage entities and theclientclass name. Theclientfield in the JSON provides the full class name. For example,com.google.android.engage.food.service.AppEngageFoodClient. - Note: Initializing the client class requires a
Contextparameter. 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}.mdin 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.
-
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 fromEngagePublisher. Important : Implement both static registration and dynamic registration patterns, including the companion objectregistermethod inside theEngageBroadcastReceiverclass.
-
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}.mdin 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
ItemToEntityConverterpattern in patterns.md and add it to the generated{ENGAGE_CODE_DIR}/ItemToEntityConverter.
-
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}/ItemToEntityConverterto convert this data to an Engage entity. - Use obtained Engage entity model data with
{ENGAGE_CODE_DIR}/ ClusterRequestFactoryto get cluster requests. - Call corresponding cluster publishing method obtained from
{VERTICAL}.mdin the references/schemas/ directory with the obtained request in previous step in{ENGAGE_CODE_DIR}/EngageWorker.
-
Gradle and manifest updates:
- Suggest updates to
build.gradleandAndroidManifest.xml. - For mobile apps, use patterns.md.
- For TV apps, use the TV-specific sections in patterns.md.
- Provide the necessary
implementationdependencies forbuild.gradleorbuild.gradle.ktsfrom patterns.md. - Provide the
<receiver>and<service>declarations forAndroidManifest.xml. - Note: Except for TV, there aren't any vertical-specific imports. For all other verticals,
com.google.android.engage:engage-core:1.6.0is sufficient.
- Suggest updates to
-
Debugging:
- Perform a Gradle sync.
- If errors occur, follow this resolution order:
- Fix import errors. For package
com.google.android.engageor classes starting withAppEngage, verify the package name in the{VERTICAL}.mdin references/schemas/ directory or common.md. - Fix any other errors.
- Fix import errors. For package
- Execute a full Gradle build and resolve any remaining compilation issues. Repeat this step until the Gradle build is successful.
-
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}/:ConstantsItemToEntityConverterClusterRequestFactoryEngageWorker{cluster_type}PublisherEngageBroadcastReceiver
- [ ] 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
ItemToEntityConverterpoint to images matching the strict aspect ratio requirements of the vertical (for example, 16:9, 1:1, 2:3). - [ ] Verify that
{ENGAGE_CODE_DIR}/EngageWorkeruses the data source identified in Step 4. - [ ] Verify that
EngageBroadcastReceiver.register(context)is called within theApplicationclass orMainActivityto register the receiver dynamically. - [ ] Verify that
AndroidManifest.xmlcontains the static<receiver>declaration forEngageBroadcastReceiverwith the necessary intent actions. - Important : Explicitly instruct the developer to call
EngageBroadcastReceiver.register(context)inside their customApplicationclassonCreate()(or their main activityonCreate()) to dynamically register the receiver. Stress that both static and dynamic registrations are required for the integration to function.
- [ ] Verify that all the Engage-related files are created in
Reference materials
-
FAQ: Engage FAQ - Refer to this document for answers to frequently asked questions from developers.
-
Vertical-specific guides:
-
Vertical-specific schemas:
Frequently asked questions about Engage SDK Integration
Similar skills
WinMD API Search
Easily find and explore Windows desktop APIs.
WebMCPify
Transform any web app into an agent-ready platform.
Phoenix Tracing
Instrument LLM applications with OpenInference tracing.
Foundry Hosted Agent CopilotKit
Guidance for developing agentic web apps on Azure.
Power Automate Foundation
Connect AI agents to Power Automate seamlessly.
Power Automate Flow Builder
Efficiently build and deploy Power Automate flows programmatically.
