gemini

Control Gemini browser tabs and chats via MQTT WebSocket commands.

116|56|Updated Jan 18, 2026
One-click install
npx skills add https://github.com/Soul-Brews-Studio/oracle-skills-cli --skill gemini-soul-brews-studio
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini
Source: https://github.com/Soul-Brews-Studio/oracle-skills-cli/tree/main/src/skills/gemini
Command: npx skills add https://github.com/Soul-Brews-Studio/oracle-skills-cli --skill gemini-soul-brews-studio

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires mqtt, and includes scripts (resource) components.

What problem does it solve?

This Skill enables automated remote control of the Gemini browser using MQTT WebSocket, allowing precise tab management, chat interactions, and data retrieval from Gemini tabs.

Core Features & Use Cases

  • Tab control: Create, focus, and inject badges into Gemini tabs with MQTT commands.
  • Chat & transcribe: Send chat prompts and trigger transcription or deep research workflows.
  • Use Case: A developer wants to automate daily Gemini tasks—opening a tab, sending a chat to fetch information, and capturing results without manual clicks.

Quick Start

  • /gemini chat "Hello Gemini!"
  • /gemini new "Your message"
  • /gemini transcribe "https://youtube.com/watch?v=XpHMle5Vq80"

Frequently Asked Questions about gemini

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

FAQPage Schema
How do I automate Gemini chat tasks using MQTT?

You can automate Gemini chat tasks using MQTT by issuing WebSocket commands that control browser tabs, send chat prompts, and retrieve responses without manual clicks. This enables precise, multi-tab automation for real-time workflows.

Can I control multiple browser tabs with Gemini via MQTT?

Yes, you can control multiple browser tabs with Gemini via MQTT by creating, focusing, and injecting badges into specific tabs. This allows tab-precise actions for managing parallel chat and research workflows.

How do I transcribe audio or video URLs through Gemini automation?

You can transcribe audio or video URLs by sending a transcription command like /gemini transcribe followed by the URL. The automation triggers the workflow within the Gemini browser to capture the results.

Do I need an MQTT dependency to run browser automation for Gemini?

Yes, you need the mqtt dependency to run this browser automation for Gemini. The Skill relies on MQTT WebSocket connections to issue chat, tab management, and data retrieval commands remotely.

What is the best way to retrieve real-time responses from Gemini tabs?

The best way to retrieve real-time responses from Gemini tabs is by using MQTT WebSocket commands to target specific tabs. This approach captures chat outputs and transcription data directly from the active browser session.

Are there limitations when using MQTT for Gemini browser tab control?

MQTT browser tab control for Gemini relies on deterministic scripts and active WebSocket connections, meaning it requires a running browser environment and cannot operate offline or without the mqtt dependency installed.