## Overview

The Wearables Device Access Toolkit provides three levels of AI assistance for developers:

1. **Git-native tool integrations** — SDK knowledge delivered directly from the DAT GitHub repos through plugins for <gk project="wdp_manual_dat_docs_connect_26">Muse Code, </gk>Claude Code or Codex, and through repo-native tool files.
2. **Live docs lookup** — The shared Wearables MCP server exposes `search_dat_docs` so your AI tool can search current DAT guides while it works. When your MCP client supports response formats, ask for Markdown output so headings, links, and code blocks stay intact.
3. **API reference endpoint** — The full API surface served via [llms.txt](https://llmstxt.org/) as a supplementary reference for on-demand queries.

For implementation work, use the GitHub-hosted DAT plugin or repo-native skills for coding patterns, then use MCP for current docs lookup. The plugin teaches the assistant how DAT projects are structured; MCP keeps the assistant grounded in the latest published guides.

Start by copying one of the prompts below into an AI coding tool. Each prompt includes the GitHub repo, setup guidance, MCP endpoint, MCP tool, and docs links so a fresh AI session knows where to start.

## Copy a starter prompt

Use these prompts to get started quickly. They are written to make the assistant install or use DAT's GitHub-hosted plugin or skills when available, enable MCP for live docs lookup, inspect your project first, use `search_dat_docs` for current docs, request Markdown-formatted results when available, and keep the first code change small.
<wearables-ai-prompts>
  <wearables-ai-prompt task="Build minimal iOS DAT integration">You are helping me build a Wearables Device Access Toolkit iOS integration. Assume you know nothing about this project yet.

Use these public sources before choosing APIs or editing code:
- DAT iOS GitHub repo: https://github.com/facebook/meta-wearables-dat-ios
- DAT AI overview: https://wearables.developer.meta.com/docs/develop/dat/ai-assisted/
- iOS integration guide: https://wearables.developer.meta.com/docs/develop/dat/build-integration-ios/
- DAT MCP setup: https://wearables.developer.meta.com/docs/develop/dat/ai-assisted-mcp/
- Wearables MCP endpoint: https://mcp.developer.meta.com/wearables
- MCP tool to call: search_dat_docs
- Preferred MCP result format: Markdown

If DAT guidance or live docs lookup is not installed in this AI tool yet, follow the DAT MCP setup page to install the iOS DAT GitHub plugin or repo-native skills and configure live docs lookup for my AI tool.

Using the Wearables MCP endpoint https://mcp.developer.meta.com/wearables, first call search_dat_docs for current iOS setup, registration, permissions, session lifecycle, MockDeviceKit, and camera guidance. Request Markdown-formatted results if the MCP client exposes an output format option.

Inspect this repository and identify the smallest working iOS integration slice for Wearables Device Access Toolkit. Add dependency setup, app registration, `Wearables.configure()`, and connection lifecycle code first, using the existing app structure. Call out any required Info.plist keys, bundle identifier assumptions, and local verification steps. Implement the smallest safe change and run the relevant local checks.</wearables-ai-prompt>
  <wearables-ai-prompt task="Build minimal Android DAT integration">You are helping me build a Wearables Device Access Toolkit Android integration. Assume you know nothing about this project yet.

Use these public sources before choosing APIs or editing code:
- DAT Android GitHub repo: https://github.com/facebook/meta-wearables-dat-android
- DAT AI overview: https://wearables.developer.meta.com/docs/develop/dat/ai-assisted/
- Android integration guide: https://wearables.developer.meta.com/docs/develop/dat/build-integration-android/
- DAT MCP setup: https://wearables.developer.meta.com/docs/develop/dat/ai-assisted-mcp/
- Wearables MCP endpoint: https://mcp.developer.meta.com/wearables
- MCP tool to call: search_dat_docs
- Preferred MCP result format: Markdown

If DAT guidance or live docs lookup is not installed in this AI tool yet, follow the DAT MCP setup page to install the Android DAT GitHub plugin or repo-native skills and configure live docs lookup for my AI tool.

Using the Wearables MCP endpoint https://mcp.developer.meta.com/wearables, first call search_dat_docs for current Android setup, registration, permissions, session lifecycle, MockDeviceKit, and camera guidance. Request Markdown-formatted results if the MCP client exposes an output format option.

Inspect this repository and identify the smallest working Android integration slice for Wearables Device Access Toolkit. Add Gradle dependency setup, manifest setup, app registration, `Wearables.initialize(...)`, and connection lifecycle code first, using the existing app structure. Call out any required manifest metadata, permission assumptions, and local verification steps. Implement the smallest safe change and run the relevant local checks.</wearables-ai-prompt>
  <wearables-ai-prompt task="Validate camera or Mock Device Kit behaviour">You are helping me validate Wearables Device Access Toolkit camera or MockDeviceKit behavior. Assume you know nothing about this project yet.

Use these public sources before choosing APIs or editing code:
- DAT iOS GitHub repo: https://github.com/facebook/meta-wearables-dat-ios
- DAT Android GitHub repo: https://github.com/facebook/meta-wearables-dat-android
- DAT AI overview: https://wearables.developer.meta.com/docs/develop/dat/ai-assisted/
- iOS integration guide: https://wearables.developer.meta.com/docs/develop/dat/build-integration-ios/
- Android integration guide: https://wearables.developer.meta.com/docs/develop/dat/build-integration-android/
- DAT MCP setup: https://wearables.developer.meta.com/docs/develop/dat/ai-assisted-mcp/
- Wearables MCP endpoint: https://mcp.developer.meta.com/wearables
- MCP tool to call: search_dat_docs
- Preferred MCP result format: Markdown

If DAT guidance or live docs lookup is not installed in this AI tool yet, identify whether this project is iOS or Android, tell me the matching install commands from the DAT GitHub repo, and follow the DAT MCP setup page for my AI tool.

Using the Wearables MCP endpoint https://mcp.developer.meta.com/wearables, first call search_dat_docs for current MockDeviceKit, camera streaming, permissions, and session lifecycle guidance. Request Markdown-formatted results if the MCP client exposes an output format option.

Inspect this repository and add the smallest validation path for DAT camera or Mock Device Kit behavior. Prefer a local test or manual check that does not require physical glasses when possible. Keep the implementation scoped to one platform first, document what is not covered, and run the relevant local checks.</wearables-ai-prompt>
</wearables-ai-prompts>

## Git-native tool integrations

The SDK GitHub repos ship the same public DAT guidance in several formats. Each tool gets the same core knowledge — setup guides, streaming patterns, MockDeviceKit testing, session lifecycle, permissions, debugging, and sample app guidance — in whatever format it expects.

<gk project="wdp_manual_dat_docs_connect_26" markdown="block">

| Tool | Public artifact | Recommended setup |
|------|-----------------|-------------------|
| Muse Code | `.muse-plugin/plugin.json` | Add the DAT GitHub repo as a marketplace, install the DAT plugin, then approve it |
| [Claude Code](https://docs.anthropic.com/en/docs/claude-code) | `.claude-plugin/marketplace.json` + plugin manifests | Add the DAT GitHub repo as a marketplace, then install the DAT plugin |
| Codex | `.codex-plugin/plugin.json` inside `plugins/` | Add the DAT GitHub repo as a marketplace, then add the DAT plugin |
| [GitHub Copilot](https://github.com/features/copilot) | `.github/copilot-instructions.md` | Auto-loaded by Copilot in VS Code |
| [Cursor](https://cursor.sh/) | `.cursor/rules/*.mdc` | Auto-loaded with glob-based triggers |
| [AGENTS.md](https://agents.md) | `AGENTS.md` | Portable fallback for tools that read `AGENTS.md` |

</gk>

<gk project="wdp_manual_dat_docs_connect_26" exclude="true" markdown="block">

| Tool | Public artifact | Recommended setup |
|------|-----------------|-------------------|
| [Claude Code](https://docs.anthropic.com/en/docs/claude-code) | `.claude-plugin/marketplace.json` + plugin manifests | Add the DAT GitHub repo as a marketplace, then install the DAT plugin |
| Codex | `.codex-plugin/plugin.json` inside `plugins/` | Add the DAT GitHub repo as a marketplace, then add the DAT plugin |
| [GitHub Copilot](https://github.com/features/copilot) | `.github/copilot-instructions.md` | Auto-loaded by Copilot in VS Code |
| [Cursor](https://cursor.sh/) | `.cursor/rules/*.mdc` | Auto-loaded with glob-based triggers |
| [AGENTS.md](https://agents.md) | `AGENTS.md` | Portable fallback for tools that read `AGENTS.md` |

</gk>

<gk project="wdp_manual_dat_docs_connect_26" markdown="block">

See the dedicated setup guides for each tool: [Muse Code](/docs/develop/dat/ai-assisted-muse/), [Claude Code](/docs/develop/dat/ai-assisted-claude-code/), [Codex](/docs/develop/dat/ai-assisted-codex), [GitHub Copilot](/docs/develop/dat/ai-assisted-github-copilot/), [Cursor](/docs/develop/dat/ai-assisted-cursor/), [AGENTS.md](/docs/develop/dat/ai-assisted-agents-md/).

</gk>

<gk project="wdp_manual_dat_docs_connect_26" exclude="true" markdown="block">

See the dedicated setup guides for each tool: [Claude Code](/docs/develop/dat/ai-assisted-claude-code/), [Codex](/docs/develop/dat/ai-assisted-codex), [GitHub Copilot](/docs/develop/dat/ai-assisted-github-copilot/), [Cursor](/docs/develop/dat/ai-assisted-cursor/), [AGENTS.md](/docs/develop/dat/ai-assisted-agents-md/).

</gk>

### Setup

Start from the DAT GitHub repo for your platform when using <gk project="wdp_manual_dat_docs_connect_26">Muse Code, </gk>Claude Code or Codex.

<gk project="wdp_manual_dat_docs_connect_26" markdown="block">

Muse Code, iOS:

```bash
export MUSE_EXPERIMENTAL_PLUGINS=1
muse plugins marketplace add mwdat-ios-marketplace https://github.com/facebook/meta-wearables-dat-ios
muse plugins install mwdat-ios@mwdat-ios-marketplace
muse plugins approve mwdat-ios
```

Muse Code, Android:

```bash
export MUSE_EXPERIMENTAL_PLUGINS=1
muse plugins marketplace add mwdat-android-marketplace https://github.com/facebook/meta-wearables-dat-android
muse plugins install mwdat-android@mwdat-android-marketplace
muse plugins approve mwdat-android
```

</gk>

Claude Code, iOS:

```bash
claude plugin marketplace add facebook/meta-wearables-dat-ios
claude plugin install mwdat-ios@mwdat-ios-marketplace
```

Claude Code, Android:

```bash
claude plugin marketplace add facebook/meta-wearables-dat-android
claude plugin install mwdat-android@mwdat-android-marketplace
```

Codex, iOS:

```bash
codex plugin marketplace add facebook/meta-wearables-dat-ios
codex plugin add mwdat-ios@mwdat-ios-marketplace
```

Codex, Android:

```bash
codex plugin marketplace add facebook/meta-wearables-dat-android
codex plugin add mwdat-android@mwdat-android-marketplace
```

Then follow the [DAT MCP setup instructions](/docs/develop/dat/ai-assisted-mcp/) to enable live docs lookup for your coding tool.

For tools that use repo-native checked-in files instead of plugin manifests, use:

```bash
./install-skills.sh copilot
./install-skills.sh cursor
./install-skills.sh agents
```

### What the config covers

All surfaces receive the same SDK knowledge, covering:

- **Getting started** — Dependencies, project setup, and first integration
- **Session lifecycle** — Connecting, reconnecting, and managing device sessions
- **Camera streaming** — Resolution selection, frame rates, and photo capture
- **Permissions** — Requesting and handling device permissions
- **MockDeviceKit** — Testing without physical hardware
- **Debugging** — Common issues, Developer Mode, version compatibility
- **Sample app guide** — Building a complete DAT app from scratch

## API reference endpoint (llms.txt)

As a supplement to the GitHub-hosted integrations, the SDK provides an [llms.txt](https://llmstxt.org/) endpoint with the full API surface. The GitHub integrations cover patterns and best practices; the endpoint covers the API reference.

### Endpoints

| Endpoint | Description |
|----------|-------------|
| [wearables.developer.meta.com/llms.txt](https://wearables.developer.meta.com/llms.txt) | Index of available documentation sections with links |
| [wearables.developer.meta.com/llms.txt?full=true](https://wearables.developer.meta.com/llms.txt?full=true) | Full API reference content in a single document |

The index endpoint follows the [llms.txt specification](https://llmstxt.org/) and returns a lightweight listing of documentation sections. The `?full=true` variant returns the complete API reference inline, which is what most AI tools need to write code.

### What's included

The endpoint serves API reference documentation for both iOS (Swift) and Android (Kotlin) platforms, covering:

- `MWDATCore` — App registration, device discovery, session management, and telemetry
- `MWDATCamera` — Camera access, resolution and frame rate selection, and photo capture
- `MWDATMockDevice` — Simulated device for testing without physical hardware

## Tips for effective use

- **Start with the GitHub-hosted integration** — Use the <gk project="wdp_manual_dat_docs_connect_26">Muse Code, </gk>Claude Code or Codex plugin when your tool supports it. Use the repo-native file installs for Copilot, Cursor, or `AGENTS.md` readers. This gives the assistant DAT-specific coding patterns, setup flow, and test guidance.
- **Use MCP for live docs lookup** — Follow the [DAT MCP setup instructions](/docs/develop/dat/ai-assisted-mcp/) for your coding tool. Ask your AI tool to call `search_dat_docs` before choosing SDK APIs and request Markdown-formatted results when the client supports response formats.
- **Add the API reference when you need specifics** — If your AI tool can't find a particular method signature or parameter type, point it at the llms.txt endpoint for the full API surface.
- **Be specific in your prompts** — Mention the platform (iOS or Android) and the module you're working with (`MWDATCore`, `MWDATCamera`, or `MWDATMockDevice`).
- **Combine with the guides** — For deeper integration patterns and lifecycle management, point your AI tool at the [integration overview](/docs/develop/dat/build-overview/) and platform-specific integration guides ([iOS](/docs/develop/dat/build-integration-ios/), [Android](/docs/develop/dat/build-integration-android/)).