Engage Sdk Integration logo

Engage Sdk Integration

OrganizationPopular
android
engage-sdk-integration

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.

Overview

Publisherandroid
Repositoryskills
Skill nameengage-sdk-integration
Stars
7.4K
Forks
484
Bundled files
28
LicenseApache-2.0
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.

  • 28 bundled files

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

  • Open source

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

Installation

Install the Engage Sdk Integration 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.
  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/android/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/play/engage-sdk-integration .claude/skills/engage-sdk-integration
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Engage Sdk Integration 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 Engage Sdk Integration 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 Engage Sdk Integration 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.

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).
      • [ ] Used --no-daemon for all Gradle compilations.
    • 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. You must run ./gradlew compileDebugUnitTestSources --no-daemon or ./gradlew assembleDebug --no-daemon. 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

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 Engage Sdk Integration AI skill do?

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.

Why use Engage Sdk Integration on TypingMind?

Because you install it once and use it with any model. Engage Sdk Integration 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 Engage Sdk Integration in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/android/skills/tree/main/play/engage-sdk-integration. 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 Engage Sdk Integration?

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 Engage Sdk Integration?

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

Is the Engage Sdk Integration AI skill free?

Yes. It is published on GitHub by android under the Apache-2.0 license. 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 👇