Use this skill when users ask to generate, edit, or compose images with Nano Banana (Gemini image models), including text-to-image, image editing, multi-image composition, grounding, and output sizing/saving controls.
@google/genai) as the primary flow (multi-turn edits, grounding, advanced generationConfig).scripts\nanobanana-cli.js for quick single-turn generation/editing runs.curl; keep guidance in JS CLI/wrapper form.NANOBANANA_GEMINI_API_KEY with fallback GEMINI_API_KEY.gemini-3.1-flash-image-preview (allow env override via NANOBANANA_MODEL).minimal|low|medium|high), default High.--google-search when needed.nanobanana-output/, unless the prompt explicitly asks for another location.imageConfig.imageSize as string "512" in API calls (never numeric 512).references\image-generation-api.md for operational payload rules, model behavior, sizing, thinking, grounding, and limits.references\sources.md to verify source provenance and jump to upstream docs.node scripts\nanobanana-cli.js --prompt "..."-i/--image (up to 14).--google-search when prompt needs fresh web context.