Turn a vague mental image into a professional, ready-to-use image-generation prompt by interviewing the user. Use this skill whenever the user wants to create or generate an image but isn't sure how to describe it, has a picture in their head but can't put it into words, asks for help writing or improving an image / AI-art prompt, or is unhappy with what a generator produced because the prompt was too vague. Conduct the interview in the user's own language and output an English prompt. If an image-generation tool is available, also generate candidate images and refine them with the user. Trigger even when the user doesn't say the word "prompt" — e.g. "I want to make an image of ...", "help me make a picture / logo / illustration / icon / poster", or "I want something like this but ...".
2026-06-22