muzilee-gemini-image-skills

Community

Automate Gemini web chat and image generation.

Authormu-zi-lee
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill removes repetitive browser operations needed to interact with Gemini for text and image workflows by coordinating a local daemon with a Tampermonkey worker that performs all page DOM actions.

Core Features & Use Cases

  • Chat text generation: Send a prompt, wait for completion, and return the final Gemini response text (e.g., summarize an article).
  • Image generation + reference uploads: Generate images from prompts, upload reference images, and download the latest preview image to local disk (e.g., create a poster style using mood references).
  • Model switching and task orchestration: Normalize model aliases (pro/quick/think), open new chats, and route tasks through a unified task-envelope protocol between Python and the browser worker.

Quick Start

Ask an agent to send the prompt and return a local image file path by running the image generate flow with output_mode preview.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: muzilee-gemini-image-skills
Download link: https://github.com/mu-zi-lee/muzilee-gemini-image-skills/archive/main.zip#muzilee-gemini-image-skills

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.