bb-browser

Automate browser tasks via JSON-RPC and Chrome DevTools Protocol.

Updated Apr 18, 2026
One-click install
npx skills add https://github.com/yiplee/go-bb-browser --skill bb-browser-yiplee
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bb-browser
Source: https://github.com/yiplee/go-bb-browser/tree/main/skills/bb-browser
Command: npx skills add https://github.com/yiplee/go-bb-browser --skill bb-browser-yiplee

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

bb-browser provides a Go-based browser automation workflow that connects a CLI to a local bb-browserd daemon via JSON-RPC to attach to an already-running Chrome instance through the Chrome DevTools Protocol, enabling persistent login context, page control, and scripted interactions.

Core Features & Use Cases

  • CLI and daemon architecture allows tab management, navigation, and snapshotting using JSON-RPC over HTTP.
  • Adapter scripts run in the page context via eval, reusing cookies and login state for automated tasks.
  • Fetch and network observation/interception support enables authenticated data access and mocked responses for testing.

Quick Start

Start bb-browserd with a running Chrome instance and control tabs and run adapters via the JSON-RPC API.

Frequently Asked Questions about bb-browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate browser tasks using Chrome DevTools Protocol in Go?

Browser automation using Chrome DevTools Protocol in Go is achieved by connecting a CLI to a local daemon via JSON-RPC to attach to a running Chrome instance. This enables persistent login context, page control, and scripted interactions through commands like tab_list and goto.

Can I reuse browser cookies and login state for automated web interactions?

You can reuse cookies and login state for automated web interactions by attaching to an already-running Chrome instance. Adapter scripts run directly in the page context via eval, leveraging the existing authenticated session for persistent page control.

What is the best way to manage browser tabs and navigation via JSON-RPC?

Managing browser tabs and navigation via JSON-RPC is handled through a CLI and daemon architecture. This setup allows you to execute tab management, open new tabs, and trigger page navigation over HTTP using the JSON-RPC API surface.

How do I intercept network requests and mock responses for browser automation testing?

Network request interception and mocked responses for browser automation testing are supported through built-in fetch and network observation features. This enables authenticated data access and allows you to simulate specific server responses during scripted interactions.

Does browser automation with Go and chromedp require a separate daemon process?

Browser automation with Go and chromedp uses a separate bb-browserd daemon process to connect to Chrome. This architecture allows the CLI to communicate via JSON-RPC, maintaining a persistent connection to the running Chrome instance for continuous page control.

Why use an already-running Chrome instance instead of launching a new browser for automation?

Using an already-running Chrome instance for automation preserves your persistent login context and existing cookies. This avoids re-authenticating during automated tasks and allows adapter scripts to execute directly within your active page environment.