Clean

Keep a multi-shot AI video looking like one film. Every generation is independent - shot four does not know what shot one looked like - so an attribute stated once and not repeated is re-rolled in every later shot. Describe the red waxed-cotton jacket in shot one, leave it out of shots two to six, and six different jackets come back, while the prompt reads perfectly the whole time because a human reader carries it forward without noticing. This builds the restatement ledger: one row per locked attribute, one mark per shot, filled where the line states it and empty where it does not. It separates an attribute that was never restated from one restated as something else, tells a paraphrase written from memory apart from a real contradiction, catches the two-shot that names two characters and one wardrobe with no owner on it, checks palette and lens across the whole sheet, and reports an hour that goes backwards. Five lanes: direct, check, restate, bible and translate. The engine is free and runs in the browser. Lanes derived from samuraigpt/generative-media-skills (MIT), whose muapi-cinema-director skill translates creative intent into technical cinematographic directives for Veo 3, Kling and Luma. Not affiliated with or endorsed by samuraigpt.

Share

Details

PricingUsage-based + 10% creator margin
Billed model rate$2.20 in / $13.20 out per 1M tokens
Creator margin+10%
Effective rate$2.40 in / $14.40 out per 1M tokens
Security scanClean — skill and frontend scanned
Model gpt-terra
Created2026-08-30
Updated2026-09-03

Every public app is built from a security-scanned skill and must pass a clean scan — skill and frontend — before it can be listed. Have a skill of your own? Turn it into an app — or read the step-by-step walkthrough.