firefox-bidi

Inspect and automate live Firefox pages via WebDriver BiDi.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/bugabinga/pi-ext --skill firefox-bidi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: firefox-bidi
Source: https://github.com/bugabinga/pi-ext/tree/main/skills/firefox-bidi
Command: npx skills add https://github.com/bugabinga/pi-ext --skill firefox-bidi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Debugging or interacting with web pages often requires inspecting real browser state (DOM, console/network events, and screenshots) that can’t be reliably reproduced from text alone.

Core Features & Use Cases

  • Inspect page structure with semantic snapshots: Generate a compact, agent-friendly view of visible interactive elements for navigation and reasoning.
  • Extract HTML and evaluate expressions: Pull full page HTML or targeted selector HTML, and run safe JavaScript expressions against a specific browsing context.
  • Drive interaction with reliable clicks and typing: Click by CSS selector or accessible text, click at coordinates as a visual fallback, type into the focused element, and repeatedly load more content.
  • Diagnose console and network issues: Subscribe to BiDi console events and network responses (and optionally use experimental RDP for closer DevTools Console parity).
  • Manage a Firefox instance: Reuse a managed Firefox profile/process across commands, or connect to an existing BiDi-enabled Firefox using environment configuration.

Quick Start

Run the skill to list contexts and auto-start a managed Firefox if needed, then choose a context prefix for subsequent inspect and interaction commands.

Frequently Asked Questions about firefox-bidi

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

FAQPage Schema
How do I extract HTML and inspect DOM elements in a live Firefox browser?

To extract HTML and inspect DOM in a live Firefox browser, the skill uses WebDriver BiDi to pull full page HTML, extract targeted selector HTML, and generate semantic snapshots of visible interactive elements for navigation and reasoning.

Can I capture console and network errors during Firefox automation?

Yes, you can capture console and network errors during Firefox automation by subscribing to WebDriver BiDi console events and network responses. Optional experimental RDP provides closer DevTools Console parity for deeper diagnostics.

Do I need Node.js to use WebDriver BiDi for browser debugging?

Yes, you need Node.js 22+ execution to use WebDriver BiDi for browser debugging. You also need a configure a BiDi WebSocket endpoint and maintain a persistent state/profile directory for deterministic CLI-driven operations.

What is the best way to automate clicking and typing in a web page using Firefox?

The best way to automate clicking and typing in Firefox is using WebDriver BiDi to click by CSS selector or accessible text, click at coordinates as a visual fallback, type into focused elements, and repeatedly load more content.

How do I take screenshots for visual verification during web page debugging?

You can take screenshots for visual verification during web page debugging by driving a live Firefox instance via WebDriver BiDi to capture the current browser state, ensuring reliable verification that text extraction alone cannot provide.

Can I reuse an existing Firefox profile when running automated WebDriver BiDi commands?

Yes, you can reuse an existing Firefox profile when running automated WebDriver BiDi commands. The skill manages a persistent profile directory across commands or connects to an existing BiDi-enabled Firefox using environment configuration.