hanzilihanziliCommunityยท7 Agent Skills Included

hanzi-browse

Browser automation in your real signed-in Chrome

Delegates web tasks to a sub-agent running in your own signed-in Chrome browser. Handles logins, form filling, posting, testing, and data extraction without brittle scripts or manual clicking. Ships 24 site playbooks for X, LinkedIn, Gmail, and more so tasks finish reliably on real websites.
npx skills add hanzili/hanzi-browse --all -g -y
Available:

Explains the platform architecture to your AI agent so it knows how the MCP server, Chrome extension, and workflow skills connect when executing browser tasks.

All Skills in This Repository (7)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install Hanzi Browse?โ–ผ

Run `npx skills add hanzili/hanzi-browse --all -g -y` in your terminal to install all skills globally for your agent.

What does Hanzi Browse do?โ–ผ

It lets your AI agent control your real signed-in Chrome browser to complete tasks like posting on social media, filling forms, testing web apps, and extracting data.

Which AI agents work with Hanzi Browse?โ–ผ

It works with Claude Code, Cursor, Codex, Gemini CLI, VS Code, and other MCP-compatible agents via a one-command setup.

Can it handle sites that require login?โ–ผ

Yes. Because it drives your actual Chrome with your existing sessions, it can access Gmail, LinkedIn, and other logged-in sites without sharing credentials.

Do I need coding skills to use it?โ–ผ

No. You describe the task in plain English and the sub-agent figures out the steps, clicks, and navigation on its own.

Related Repositories in Software Engineering

View All in Software Engineeringโ†’