gemini-skill
Automate Gemini web for AI image generation and chat
All Skills in This Repository (2)
Pure Emerald Level IndicatorsFrequently Asked Questions
FAQPage SchemaHow to install gemini-skill?▼
Run `npx skills add WJZ-P/gemini-skill --all -g -y` in your terminal to install the skill globally for your AI agent.
How to generate images with Gemini using AI?▼
Once installed, just ask your agent to draw something. It calls the gemini_generate_image tool, which sends your prompt to Gemini, waits for the result, and saves the full-size image locally.
Does gemini-skill remove watermarks from images?▼
Yes. Downloaded images are automatically processed to remove the Gemini watermark before being saved to your output folder.
Do I need a Google account to use gemini-skill?▼
Yes. The browser it controls must be logged into a Google account, since Gemini requires sign-in. The skill includes a login check tool to verify your session.
Which AI clients work with gemini-skill?▼
Any MCP-compatible client works, including Claude Code, Cursor, and OpenClaw, since the skill runs as a standard MCP server over stdio.
Related Repositories in Design & Creative
View All in Design & Creative→
nextlevelbuilderui-ux-pro-max-skill
AI design intelligence for professional UI, brands, and presentations
shadcn-uiui
Build and customize beautiful React component libraries with AI
nexu-ioopen-design
Open-source AI design studio for decks, prototypes, images, and video