Harmonyos Device Automation

This gives Claude the ability to control HarmonyOS NEXT devices by running Midscene CLI commands that capture screenshots and execute touch actions based on what it sees. The workflow is deliberate: run one command, read the screenshot, decide the next move. No background execution, no chaining. Each action (tap, scroll, type, drag) takes about a minute because there's AI inference happening behind the scenes. You need API keys for vision models, and two-finger gestures won't work since HarmonyOS automation doesn't expose multi-touch. If you're testing apps on Huawei's new OS or need reproducible device automation without manually scripting every coordinate, this is the toolchain. Part of a larger Midscene suite that covers browsers, desktops, Android, and iOS.

skills.sh installs: 2.3K
GitHub stars: 321
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add web-infra-dev/midscene-skills --skill harmonyos-device-automation --agent claude-code

Installs into .claude/skills of the current project.

Files

HarmonyOS Device Automation

CRITICAL RULES — VIOLATIONS WILL BREAK THE WORKFLOW:

Never run midscene commands in the background. Each command must run synchronously so you can read its output (especially screenshots) before deciding the next action. Background execution breaks the screenshot-analyze-act loop.

Run only one midscene command at a time. Wait for the previous command to finish, read the screenshot, then decide the next action. Never chain multiple commands together.

Allow enough time for each command to complete. Midscene commands involve AI inference and screen interaction, which can take longer than typical shell commands. A typical command needs about 1 minute; complex act commands may need even longer.

Automate HarmonyOS NEXT devices using npx -y @midscene/harmony@1. Each CLI command maps directly to an MCP tool — you (the AI agent) act as the brain, deciding which actions to take based on screenshots.