For [video], use [approved assets] to make ten thumbnail concepts. Score each at real YouTube sizes against [inspiration channel] for clarity, curiosity, emotional pull, contrast, and accuracy. Take the top three, improve each one's weakest dimension, and rescore them under the same rubric. Keep iterating the strongest concept until it clears [quality threshold] or [budget] ends. Reject anything the video cannot deliver. Return the winner, two runners-up, previews, final scores, and rationale.
claude-code · codex
Use this when
Use this when a video topic and asset set are ready but the thumbnail needs several structured ideation and critique rounds before production.
How it runs
Define the video subject, approved assets, inspiration channel, quality threshold, budget, and five-part rubric.
Create ten distinct concepts, inspect them at real YouTube sizes, and score each one under the same conditions.
Select the top three, improve the weakest dimension of each, and rescore them.
Stop at the quality bar or budget, reject misleading concepts, and return the winner plus two runners-up.
Done when
✓ One accurate thumbnail clears the fixed quality threshold. The winner outscores the alternatives under the same conditions, remains legible at realistic sizes, and represents the video accurately.
Why it works
A varied first set creates real options, while a fixed rubric makes later rounds comparable. Scoring accuracy prevents curiosity from becoming a promise the video cannot keep.
Implementation note
Choose an inspiration channel whose audience and visual language are relevant. Evaluate the actual thumbnail crop at desktop and mobile sizes, and reject concepts that misrepresent the video's substance.
Point War Loops at an authorized URL or image. Capture it with a genuine browser and record the layout, styles, content, motion, and responsive behavior. Build a static Pencil mirror and a moving Forge version. Compare both with the source at desktop, tablet, and mobile sizes; repair only the weakest fidelity signals. Stop when every gate passes, progress stalls, or capture is blocked. Finish with the builds, spec, renders, scores, and remaining gaps.
Reduce the CSS styling code [site] sends to users without changing tested screens. First capture representative pages, sizes, themes, and interactions, and record the built CSS size. Treat coverage reports only as suggestions. Remove one declaration or rule, rebuild, and rerun screenshots and project checks. Keep it only if every screenshot is pixel-identical and built CSS is smaller; otherwise revert. Stop when no supported candidate remains, progress stalls, or approval is required. Return reduction, evidence, and untested states.
Before building, choose reference images, a scoring rubric, [visual threshold], and [budget]. Build the most realistic Boeing 747 you can from Three.js primitives, then create a rig that screenshots nine repeatable angles. After each change, render and score the same views, have a critic identify the weakest feature, and fix it without regressing stronger views. Keep the best version. Stop at the threshold, stalled progress, or budget. Finish with the model, nine renders, scores, remaining gaps, and run summary.