Quick Reference: The Core Multimodal Prompt Skeleton
Memorize a compact prompt skeleton that works across image, audio, and document tasks.
What are the four parts of a dependable multimodal prompt skeleton? Job, Evidence, Criteria, Output. State the task, label the attached evidence, name the evaluation standard, and specify the output shape. When should you add another modality? Modalities are evidence channels, not prestige badges. JECO What does JECO remind you to include? “I sent the screenshot, so the prompt can stay vague.” The image is only the evidence. The prompt still has to assign the job, the standard, and the output. Common objection A teammate assumes the attachment does the prompting work. Your reply It reminds the team that modalities…
Sign up free — one personalized lesson every day, matched to your role and goals.
Already have an account? Sign in