domains / families / software-engineering / lookdev-auto

lookdev-auto

authentic

Automated visual tuning: a vision or video model rates rendered variants in a loop. Render several labeled variants into one artifact, ask the model to rate them and suggest better values, render the suggestions, ask it to pick the best, repeat until good — the model is the eye, you run the loop.

When to use

• Use whenever "looks/feels right" is the success criterion and there's no cheap numeric metric — animation easing/timing, zoom/camera feel, color grade, layout/spacing, design params, render/encoder settings, prompt params. Use the automate…

When not to use

• A real numeric metric exists and correlates with quality → optimize that directly;
• The judgment is subjective-to-the-user (their taste, brand) → show them the variants
• One or two variants → just look yourself.
• Model ratings are probabilistic aesthetic judgments, not objective truth; keep a human review step for brand-critical or subjective work.
• Automated rounds can become expensive or slow when renders are heavy or many variants are explored.
• This skill needs screenshots, frames, or clips that expose the quality difference; it is weak for subtle motion, audio, copy nuance, or user-preference calls.

Skill page

Source