Data Manager API agent skills are portable, self-contained modules of
Data Manager API-specific knowledge, instructions, and workflows. Data Manager API agent
skills work with AI assistants that support the [open Agent Skills
standard](https://agentskills.io/home), including Google Antigravity and Claude Code.

These agent skills are designed to help AI assistants understand Data Manager API
best practices, configure tools, and execute workflows with higher accuracy and
lower token cost.

## Available skills

The Data Manager API team provides a [suite of
skills](https://github.com/google/skills/tree/main/skills/ads) for building with the
Data Manager API:

| Skill | Description |
|---|---|
| [`data-manager-api-setup`](https://github.com/google/skills/tree/main/skills/ads/data-manager-api-setup) | Guides developers through client library installation and authentication steps for setting up the Data Manager API. |
| [`data-manager-api-event-ingestion`](https://github.com/google/skills/tree/main/skills/ads/data-manager-api-event-ingestion) | Assists with implementing event and conversion ingestion for Google products using the Data Manager API. |
| [`data-manager-api-audience-ingestion`](https://github.com/google/skills/tree/main/skills/ads/data-manager-api-audience-ingestion) | Helps with creating user lists and managing audience data using the Data Manager API for use cases such as Customer Match. |

## Get started

Install the agent skills appropriate for your development environment.

### Install Data Manager API agent skills

In most cases, Data Manager API agent skills can be installed in your preferred
editor with a single command:

### Antigravity

Run the following command in your project's directory:

    npx skills add google/skills/skills/ads --agent=antigravity

### Claude Code

    npx skills add google/skills/skills/ads --agent=claude-code

### Codex

    npx skills add google/skills/skills/ads --agent=codex

### Cursor

You can install Data Manager API agent skills directly by adding the skill's
GitHub repository endpoint (for example, `https://github.com/google/skills`)
in your editor's settings under custom rules. For more details, see the
[Cursor documentation on installing skills from GitHub](https://cursor.com/docs/skills#installing-skills-from-github).

You can also install the skills using NPX:

    npx skills add google/skills/skills/ads --agent=cursor

### Other agents

For other AI assistants supporting the open Agent Skills standard, you can
install the skills using NPX:

    npx skills add google/skills/skills/ads

> [!NOTE]
> **Note:** **Important:** Agent skills are actively developed. To ensure your AI assistant always has the latest Data Manager API features, best practices, and security recommendations, be sure to regularly [update your
> skills](https://developers.google.com/data-manager/api/devguides/quickstart/agent-skills#update-skills).

### Update Data Manager API agent skills

You can get all available updates and clean up out-of-date skills by running the
`update` command:

    npx skills update --all

### Use Data Manager API agent skills

AI assistants are designed to use skills automatically whenever they detect that
a skill's description matches your current request. Globally installed skills
remain dormant in unrelated projects unless your prompt context matches
Data Manager API tasks.

Skills can also be manually invoked in the agent chat. For many agents, you can
use the `/` key to open a list of installed skills.

## Core components of a skill

Each agent skill is a specialized package that provides the AI assistant with
the following components:

- **Specialized instructions**: Detailed guidance for your AI assistant on how to perform specific tasks, such as setting up API access, formatting and hashing user data, and implementing ingestion workflows.
- **Best practices**: Standard integration recommendations defined by the Data Manager API team.
- **Reference documentation**: Client library setup guides, migration field mappings, and code samples included in the skills to provide the assistant with accurate, up-to-date references.

## Benefits of using skills

Agent skills extend an assistant's capabilities with specialized knowledge on
demand without the overhead of loading bulky instructions into every
conversation.

### Reduced token costs

Conventional AI integrations often load massive amounts of documentation
upfront, which consumes significant tokens and increases session costs. Agent
skills use **progressive disclosure** to minimize this overhead:

- The AI assistant initially only checks the skill's name and description to see if it is relevant to your request.
- The skill's full instructions and references are only added to the active context window when the assistant determines they're necessary for your specific task, saving context space.

### AI-guided implementation

Instead of manually searching through documentation, you can describe your
intent in natural language. Skills guide your AI assistant to help you with
Data Manager API tasks, such as the following:

- *Write a Python script to ingest Google Ads offline conversions using the Data Manager API.*
- *Migrate this Google Ads `OfflineUserDataJobService` code for Customer Match to the Data Manager API.*
- *How do I retrieve the processing status of a Data Manager API event ingestion request?*

## Next steps

- [Learn how to use agent skills with Antigravity](https://antigravity.google/docs/skills)
- [Learn how to use agent skills with Claude Code](https://code.claude.com/docs/en/skills)