WJZ-P

WJZ-P / gemini-skill

Public

gemini drawing MCP & skill through browser, can be used in openclaw or any agent that supports MCP.

automation drawing gemini mcp mcp-client
63
14
69% credibility
Found Mar 25, 2026 at 63 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
JavaScript
AI Summary

A browser automation tool for interacting with Google's Gemini website to generate AI images, conduct conversations, upload references, extract images without watermarks, and manage sessions.

How It Works

1
📖 Discover the Tool

You learn about Gemini Skill, a simple way to make Google's Gemini AI generate beautiful images and chat effortlessly.

2
🔧 Get It Ready

You place the tool on your computer, and it automatically finds your web browser to get everything prepared.

3
👤 Sign In Once

It opens the Gemini page in your browser, where you quickly log in with your Google account – done only the first time.

4
🎨 Create Magic

You give a fun description like 'a dragon flying over mountains at sunset', and the tool chats with Gemini to make your image.

5
🖼️ Grab Your Image

Gemini creates the picture, the tool cleans off any marks, and saves the big, beautiful version right to your pictures folder.

✅ Endless Creativity

Now you can generate unlimited AI art, have smart chats, or even let other AI friends use Gemini through this handy helper.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 63 to 63 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is gemini-skill?

This JavaScript project automates Google's Gemini web interface via Chrome DevTools Protocol, letting you generate AI images from drawing prompts, hold multi-turn text chats, upload reference photos, and extract full-size downloads with watermarks stripped. It runs a daemon-managed browser in the background and exposes everything as an MCP server, so agents like Claude or openclaw can trigger gemini drawing AI directly. Developers get a drop-in gemini cli skill github tool for programmatic access without manual browser fiddling.

Why is it gaining traction?

It stands out with stealth anti-detection for reliable Gemini operation, auto watermark removal on images, and seamless MCP protocol support for gemini github integration—not just basic chats, but full pipelines like prompt-to-high-res art with reference uploads. The on-demand daemon auto-starts on first use, handles 30-minute idle timeouts, and integrates easily into workflows like gemini drawing prompt generators or agent chains. No more gemini github integration not working headaches; it's plug-and-play for browser-based drawing apps.

Who should use this?

AI agent builders integrating Gemini for image gen, like devs crafting Claude tools for gemini drawing ideas or photo prompts in openclaw setups. Backend scripters needing a gemini github mcp server for automated art from constellation sketches or easy drawing prompts. Teams wanting gemini github connection for pull request visuals without API limits.

Verdict

Grab it if you need quick MCP-driven Gemini image tools—docs are solid, setup is npm install and env vars. With 63 stars and 0.70% credibility score, it's early but functional for prototypes; watch for more tests as adoption grows.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.