DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to build Wear OS Compose UI with the wear-compose-m3 skill with Skills

Install the wear-compose-m3 skill so an agent can build Wear OS screens with Compose Material 3.

Who it is forDeveloper building a Wear OS app with Jetpack Compose who wants the agent to follow the Wear Compose Material 3 guidance.

The problemWear OS layouts and components differ from phone layouts, and the README names this skill as one covering a specific Wear workflow.

The outcomeThe agent writes or updates Wear OS Compose screens using the wear-compose-m3 skill instructions.

What you need first

  • Android CLI, documented at developer.android.com/tools/agents/android-cli
  • An AI agent that reads skills, such as Claude Code, Codex, or Gemini
  • An Android project to work on

Steps

  1. Install Android CLI from developer.android.com/tools/agents/android-cli.
  2. Run android skills add wear-compose-m3 --project=. in the Wear OS project root. (inferred, check the README)
  3. Open your agent in the project directory.
  4. Ask the agent to build or update one Wear OS screen with Compose Material 3.
  5. Run the Wear OS app on a watch emulator and check the new screen.

Prompt for your agent

Using the android/skills repository and its wear-compose-m3 skill, add a Wear OS screen to the project at <project path> with Compose Material 3. List the files changed. Verify by running the Wear OS app on an emulator and opening the new screen.

Caveat. The README does not describe what the wear-compose-m3 skill covers in detail, so confirm its guidance against the official docs before relying on it.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page