What problem does it solve? Foundational image and video models like Midjourney, Sora, Runway, and DALL-E default to stereotypes, clone faces, gibberish cultural text, and inaccurate environments when depicting diverse human subjects. This Skill provides a rigorous prompt engineering methodology to counter those systemic biases and produce dignified, authentic representation. ## Core Features & Use Cases - Annotated Prompt Architectures: Builds prompts systematically across Subject, Action, Context, Camera, Style, and explicit negative constraints. - Negative-Prompt Libraries: Blocks AI artifacts such as clone faces, extra fingers, fake cultural symbols, and nonsensical non-English text. - Video Physics Definitions: Specifies temporal consistency for clothing, hair, and mobility aids in Sora and Runway generations. - Use Case: A creative team needs a video of a Black female executive leading a meeting in Nairobi. The Skill produces a structured prompt with accurate architecture, skin-tone-appropriate lighting, distinct background actors, and negative constraints against stock-photo tropes, plus a 7-point QA checklist for review. ## Quick Start Ask the inclusive visuals specialist to write a bias-resistant image or video prompt for your creative brief, specifying the subject, cultural context, and target platform.
