Image Generation with Gemini 3.1 Flash

Foundational skill for generating and editing images using Google's Gemini 3.1 Flash Image Preview model. All graphic design skills reference this skill for the generation pipeline.

Prerequisites

pip install google-genai Pillow
export GEMINI_API_KEY="your-api-key"

Step 0: Load Brand Context

Read .agents/design-context.md if it exists and pull the hex colors, style archetype, and typography description into the prompt. If it doesn't exist, use the design-context defaults and tell the user the output isn't brand-matched yet. If the user has a logo or product photo, pass it as an --image reference rather than describing it — the model reproduces references far more faithfully than descriptions.