skills.rest
thiansit
thiansitCOMMUNITY
Explore all skills by this author →
GitHub

gemini

Control Gemini browser tabs via MQTT WebSocket for messaging and automation.

Updated Aug 27, 2026
Search Tags:#transcription#gemini#mqtt#browser-automation#deep-research#mosquitto#tab-precision
One-click install
npx skills add https://github.com/thiansit/LuPang --skill gemini-thiansit
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini
Source: https://github.com/thiansit/LuPang/tree/main/.claude/skills/gemini
Command: npx skills add https://github.com/thiansit/LuPang --skill gemini-thiansit

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Provides deterministic, programmatic control of a Gemini browser tab so users can send messages, automate workflows, and extract responses without manual tab interaction.

Core Features & Use Cases

  • Tab Management: create_tab, list_tabs, focus_tab and inject_badge for reliable tab targeting.
  • Chat & Automation: send chat messages to a specific tab, select model (fast/thinking/pro), execute scripts, and retrieve text/html/state.
  • Media & Research: YouTube transcription, Deep Research automation, and end-to-end smooth-flow demos for researcher or content workflows.

Quick Start

Send the message "Hello Gemini!" to the active Gemini tab using the gemini skill.

Frequently Asked Questions about gemini

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

FAQPage Schema
How do I automate Gemini browser interactions using MQTT?▼

You can automate Gemini browser interactions by sending scripted commands via an MQTT WebSocket broker to target specific browser tabs, send chat messages, and extract responses deterministically.

What is needed to control Gemini tabs via MQTT WebSocket?▼

To control Gemini tabs via MQTT WebSocket, you need a Gemini Proxy Extension v2.8.8+ and a Mosquitto MQTT broker configured with both TCP and WebSocket listeners.

Can I use MQTT to extract YouTube transcriptions from a Gemini tab?▼

Yes, you can use MQTT commands to execute YouTube transcription and Deep Research automation directly within a targeted Gemini browser tab without manual interaction.

How do I target a specific browser tab for Gemini chat automation?▼

You target a specific browser tab for Gemini chat automation by using tab management commands like create_tab, list_tabs, and focus_tab to ensure precise message delivery.

What MQTT topics are used for scripting Gemini browser commands?▼

Scripting Gemini browser commands uses the claude/browser/command, claude/browser/response, and claude/browser/status MQTT topics to send instructions and retrieve execution feedback.

Does Gemini MQTT automation support selecting different AI models?▼

Yes, Gemini MQTT automation supports model selection, allowing you to switch between fast, thinking, and pro models programmatically during your chat and research workflows.

Related Skills

Explore More Software Engineering Skills→
heman1033p-createheman1033p-create

gemini

Controls Gemini browser tabs via MQTT WebSocket commands for chat, research, and transcription.

Community
Intermediate
costiashcostiash
4

transcription-helper

Transcribe local videos and YouTube content into timestamped transcripts using gpt-4o-transcribe.

Community
Advanced
Soul-Brews-StudioSoul-Brews-Studio
116

gemini

Control Gemini browser tabs and chats via MQTT WebSocket commands.

Official
Advanced
richardnguyen0715richardnguyen0715

scrapling

Scrape static and JavaScript-rendered web content with stealth and Cloudflare bypass.

Community
Advanced