Agent skill · design visual · sickn33
lookdev-auto
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.
Why this skill is useful
Adds a structured automation workflow for visual tuning that leverages vision models to optimize rendering parameters, which the AI wouldn't reliably generate on its own.
What it needs
Requires antigravity, claude-code, codex-cli, cursor, gemini-cli installed locally. About 3k tokens when loaded. Last updated 2026-08-07. 44,571 stars on the source repository.
What this skill does
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 automated counterpart to lookdev when there's no human to sit the loop. Source: connerkward/lookdev-auto-skill (MIT). Visual eval loop — let a vision/video model tune what only an eye can judge When the target is "does this LOOK/FEEL right" (not a number you can minimize), a vision model (image) or video-understanding model (motion/timing) can be the judge in a tight optimize loop. Worked reference: the screenstudio-alternative skill (iteration.py) (tuned zoom-animation feel via fal-ai/video-understanding). The loop 1. Render N labeled variants into ONE artifact. Vary the parameter(s) across a small spread. Annotate each variant's params ON the artifact (burn the label in: "A · 2.2Hz · ζ0.5"). Images → a labeled grid/contact sheet. Video/motion → a labeled sequence (label card or burned-in overlay before/over each clip) so the model can compare temporally. 2. One model call, structured output. Send the single artifact with an explicit rubric (define what "good" means — and what "too much"/"too little" look like). Ask for per-variant ratings + concrete suggested new values as JSON: {"ratings":{"A":n,...},"bestsofar":"X","suggest":[[p1,p2],...]}. 3. Coarse → fine. Round 1 = wide spread to locate the region. Round 2 = render the model's suggestions (+ carry the current best) into one artifact; ask it to pick the single best. Usually converges in 2 rounds. 4. Stop when sufficient — best rates high and suggestions cluster. Apply the winner. Token / quality / step reductions (do these) One artifact per round, not one call per variant. The biggest saver — a 6-variant round is 1 upload + 1 inference, not 6. Montage/grid beats a loop of single calls. Burn params onto the artifact. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills sickn33/lookdev-auto--c590c4