#Control any platform with Skills

Agent Skills are a format for extending AI coding agents with specialized capabilities. Midscene provides Agent Skills that let AI coding tools (like Claude Code, Cline, etc.) drive UI automation through CLI commands — no MCP server setup required.

Unlike MCP integration, Skills work by running CLI commands directly in the terminal. The AI agent acts as the brain: it takes screenshots, analyzes the UI, and decides which actions to perform next.

#Supported platforms

#Installation

Make sure Node.js is installed, then run:

# General installation
npx skills add web-infra-dev/midscene-skills

# Claude Code
npx skills add web-infra-dev/midscene-skills -a claude-code

# OpenClaw
npx skills add web-infra-dev/midscene-skills -a openclaw

Skills repository: github.com/web-infra-dev/midscene-skills

#Model configuration

Midscene skills require a vision model with strong visual grounding capabilities. Configure the following environment variables — either as system environment variables or in a .env file in the current working directory (Midscene loads .env automatically):

MIDSCENE_MODEL_API_KEY="your-api-key"
MIDSCENE_MODEL_NAME="model-name"
MIDSCENE_MODEL_BASE_URL="https://..."
MIDSCENE_MODEL_FAMILY="family-identifier"

For supported models and configuration details, see Model strategy and Common model configuration.

#Use skills

In your AI chat assistant, you can use the following command to use skills:

Open photo app, see what is the first photo in the album.

#More

Please refer to the Skills Repository for more details.