Browser Automation

This is vision-driven browser automation that works from screenshots instead of the DOM, powered by Midscene.js. It runs in headless Puppeteer by default, but can also connect to your existing Chrome via CDP or a browser extension to preserve login sessions. The skill handles clicks, form fills, scrolling, and multi-step workflows by analyzing what's actually visible on screen. One thing to know: it requires a vision model (Gemini, Qwen, Doubao) configured via environment variables, and commands run one at a time since each step involves AI inference on screenshots. Use this when you need to scrape data, test UI, or automate web tasks without wrestling with selectors or accessibility trees.

skills.sh installs: 5.4K
GitHub stars: 321
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Browser 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.

Always report task results before finishing. After completing the automation task, you MUST proactively summarize the results to the user — including key data found, actions completed, screenshots taken, and any relevant findings. Never silently end after the last automation step; the user expects a complete response in a single interaction.