Most browser automation tools require a headless browser, separate logins, and a lot of code. In this exercise, your agent drives your real browser — the one you use every day, with all your tabs open and all your accounts logged in.
Pi has no built-in MCP client (covered in the Tools lesson), so this doesn’t go through a Chrome DevTools MCP server the way it might in some other tools. Instead, you’ll use the Faster Chrome DevTools skill — a dependency-free command-line tool that talks to Chrome’s DevTools Protocol directly. No MCP server, no Puppeteer, no Playwright.
Install the skill
npx skills add zeke/faster-chrome-devtools-skill --global --all --yesThen run /reload so Pi picks it up.
Enable remote debugging in Chrome
Navigate to this URL in Chrome and enable it:
chrome://inspect/#remote-debuggingChrome shows a permission prompt the first time the skill connects, so nothing happens silently.
The killer feature: your existing session
The reason this is powerful is that the skill drives your existing Chrome session. You’re already logged in everywhere. That opens up sites that were never designed to be automated — sites with no API, no CLI, and a complex authenticated UI:
- Extract information from a page behind a login
- Summarize a paywalled article you subscribe to
- Fill out a long form with your agent walking you through it
- Compare details across multiple open tabs
- Check a portal or dashboard that has no API
What you’ll do
You’ll start simple — list your open tabs and take a screenshot to verify the connection works. Then try reading a page’s content and summarizing it. After that, the exercise is open-ended: pick something you actually want to automate and do it.
If you ever need a clean session instead of your logged-in browser, the same skill can launch an anonymous local Chrome profile with no logins, or connect to a remote browser over Cloudflare Browser Run — worth knowing about, even if you don’t need it for this exercise.