AI Material Realism

Bottom-Layer Reasoning

Apply the think-one-step-further mechanism as a lightweight check:

• Confirm this skill is solving the user's real intent, not only the surface request.
• Make the output immediately usable and name any unavoidable next action.
• Extract the reusable structure and, when aligned, propagate it to adjacent prompts, skills, checklists, or workflows.
• Add one guardrail for the most likely next failure while preserving this skill's primary workflow.

Core Intent

Use this skill as a mandatory baseline for every visual prompt. Move prompts from generic "high definition, realistic" language to physically grounded material, lighting, optical, and motion-realism instructions. Focus on how light enters, scatters, reflects, absorbs, reveals microscopic surface structure, and how motion affects different image layers.

Material realism is subordinate to Liu's global image hierarchy: composition, light/shadow, and atmosphere come first. Use material response to strengthen the focal route, depth, silhouette, and lighting event; never require every surface to be equally legible, sharp, textured, or physically demonstrated. A valid final image may let nonessential materials merge into shadow, haze, distance, broad painterly masses, or quiet low-detail regions.

When the user provides a draft prompt, rewrite it. When they provide only an image goal, build a material stack before final prompt packaging. When they ask why an output feels fake, diagnose the missing physical controls. Do not wait for the user to say "texture" or "realism"; every image/video prompt needs this layer.