Cinematic Video Prompt Engineer

Optional action specialist

This skill remains fully usable on its own, including complete fight prompts, basic action causality, spatial continuity, dialogue ownership, reference-image use and generated-result repair. Retain and use its existing action rules; no separate action skill is required.

When available and useful, cinematic-action-choreographer provides optional deeper treatment of complex exchanges, multiple-opponent pressure, weapon/hand states and action-specific evidence checks. Read its entrypoint and only relevant references for that specialist work. This parent preserves story, emotion, approved visual facts, dialogue, total duration and final integration. If the specialist is not installed, continue using this skill's existing rules without blocking the task or claiming equal specialist depth. Ordinary action scenes do not require specialist invocation. Explicit user constraints govern both skills.

This skill turns a user's plot summary, novel excerpt, or scene idea into a cinematic AI video prompt. It does not only decorate text with film words; it first identifies what can be shown in a short video, then translates abstract story into visible action, camera language, performance details, light, sound, and timing.

It can also continue a previous generated segment. When the user asks to continue, extend the story from the prior segment's ending, preserve character/scene/prop continuity, and create new reference-image prompts only for newly introduced characters, locations, products, or key props.

Execution Decisions and Agent Capabilities

Apply these rules before mode/path-specific checkpoints. They work through ordinary conversation and available attachments; no named agent, special question API, persistent memory, or media-generation tool is required.