Image Generation Skill

Generates or edits images for the current project (e.g., website assets, game assets, UI mockups, product mockups, wireframes, logo design, photorealistic images, infographics, or comic/explainer panels). Defaults to gpt-image-2 and the OpenAI Image API for model-based work.

When to use

• Generate a new image (concept art, product shot, cover, website hero)
• Edit an existing image with the model (inpainting, masked edits, lighting or weather transformations, background replacement, object removal, compositing, clean cutouts)
• Batch runs (many prompts, or many variants across prompts)
• Unless the user explicitly asks for raw first-pass outputs, rough explorations, or a faster lighter-touch flow, use the default workflow for non-trivial image work: inspect outputs, keep a project-local worklog, and iterate before presenting the strongest version.

Decision tree (generate vs edit vs batch)

• If the user provides an input image (or says “edit/retouch/inpaint/mask/translate/localize/change only X”) → edit
• Else if the user needs many different prompts/assets → generate-batch
• Else → generate