Tencent/BrowserSkill

What it solves

BrowserSkill allows AI agents to interact with a user's web browser using their existing logged-in sessions. This removes the need for the agent to handle complex authentication or manage separate accounts, enabling it to perform tasks on internal sites or within authenticated workflows while the user remains in control.

How it works

The system consists of three main components: a CLI/daemon that manages the connection, a browser extension (Chrome or Edge) that provides the automation interface, and a "skill" (a set of instructions) that teaches an AI agent how to use the CLI. The agent sends commands via the CLI to the extension, which then executes actions in a separate "Agent Window" or a borrowed tab.

Who it’s for

It is designed for users of shell-capable AI agents (such as Cursor, Claude Code, or DeepSeek Harness) who want their agents to automate web-based tasks, read authenticated pages, or debug websites using real-time browser evidence.

Highlights

• Session Persistence: Uses the browser's current login state to access authenticated sites.
• Visible Automation: Tasks run in a dedicated Agent Window, allowing users to monitor progress or intervene for human-only steps like CAPTCHAs.
• Website Debugging: Captures network requests, response bodies, and console messages to help agents investigate bugs.
• Flexible Deployment: Supports local setups or remote connections where the agent runs on a server and the browser is on a local machine.
• Full-Page Capture: Ability to take long screenshots of entire web pages.
• Browser Profile Support: Bind tasks to specific browser profiles for different account sets.