Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From nanobanana
Generate images from text prompts with optional --count (1-8), --styles, --variations, --format, and --seed controls. Calls Nano Banana tool and displays output from ./nanobanana-output/.
npx claudepluginhub lucklyric/cc-dev-tools --plugin nanobananaHow this command is triggered — by the user, by Claude, or both
Slash command
/nanobanana:generate <prompt> [--count=N] [--styles="style1,style2"] [--variations="var1,var2"]This command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
# Nano Banana: Generate Image Parse the user's input and call the `generate_image` MCP tool. ## Arguments User input: $ARGUMENTS ## Instructions 1. Extract the main prompt (text before any options) 2. Parse any options from the input: - `--count=N` (1-8, default: 3) → maps to `outputCount` - `--styles="style1,style2"` → maps to `styles` array. Valid: photorealistic, watercolor, oil-painting, sketch, pixel-art, anime, vintage, modern, abstract, minimalist - `--variations="var1,var2"` → maps to `variations` array. Valid: lighting, angle, color-palette, composition, mood, season,...
/nano-bananaGenerates or edits images using Google's Gemini Image model. Accepts a prompt and optional image path for editing.
/gemini-imageGenerates images from text descriptions using Google Gemini AI. Interactively selects model (e.g., gemini-3.1-flash-image-preview) and aspect ratio (e.g., 1:1). Requires GEMINI_API_KEY and Python 3.
/generateGenerates a complete wiki for the current repo as a VitePress site with catalogue, onboarding guides, pages, dark-mode Mermaid diagrams, and citations.
/generateGenerates typed API clients, schemas, and SDKs from OpenAPI specs using Kubb. Optionally accepts a spec file path or config flags.
/generateGenerates ADVPL/TLPP code for TOTVS Protheus: functions, classes, MVC structures, REST APIs, web services, entry points, reports, and more via <type> [name] [--module].
Share bugs, ideas, or general feedback.
Parse the user's input and call the generate_image MCP tool.
User input: $ARGUMENTS
--count=N (1-8, default: 3) → maps to outputCount--styles="style1,style2" → maps to styles array. Valid: photorealistic, watercolor, oil-painting, sketch, pixel-art, anime, vintage, modern, abstract, minimalist--variations="var1,var2" → maps to variations array. Valid: lighting, angle, color-palette, composition, mood, season, time-of-day--format=grid|separate → maps to format (default: separate)--seed=123 → maps to seed (integer)generate_image with the parsed parameters. Default outputCount to 3 if not specified../nanobanana-output/ and present the most recent image(s) to the user using the Read tool/generate a sunset over mountains, photorealistic
/generate a cute robot mascot --count=5 --styles="pixel-art,modern"
/generate abstract wallpaper --variations="color-palette,mood" --count=2