Image Generation

If you're spinning up marketing assets or need placeholder images for a UI, this handles the Gemini API calls with a structured prompt format that covers subject, style, lighting, mood, and composition. You pick from three Gemini models depending on whether you need speed or quality, and it generates 2-4 variants per request with metadata tracking. The multi-agent workflow validates prompts and enforces brand colors, which is honestly the most useful part if you're trying to keep visual consistency across a project. It's more opinionated than just hitting an image API directly, but that structure saves you from vague prompts that produce garbage output.

Install to Claude Code

npx -y skills add supercent-io/skills-template --skill image-generation --agent claude-code