Cinematic Audiovisual Language

Bottom-Layer Reasoning

Apply the think-one-step-further mechanism as a lightweight check:

• Confirm this skill is solving the user's real intent, not only the surface request.
• Make the output immediately usable and name any unavoidable next action.
• Extract the reusable structure and, when aligned, propagate it to adjacent prompts, skills, checklists, or workflows.
• Add one guardrail for the most likely next failure while preserving this skill's primary workflow.

Purpose

Use this skill before adding visual spectacle. It turns an idea into a readable audiovisual sequence where every shot has a narrative function, a spatial logic, a camera choice, and a reason to cut.

If the sequence does not yet know what new information each shot contributes, why the next shot exists, or how visible behavior carries implied emotion, receive a shot-level information skeleton from $shot-information-progression first. That Skill owns viewer-knowledge delta and redundancy diagnosis; this Skill remains responsible for shot size, camera position/path, blocking, axis, continuity, sound-image grammar, and concrete cut mechanics.

If the scene already has a clear information skeleton but lacks a dominant key image or needs camera geography reverse-derived from an imagined frame, receive a master-shot blueprint from $master-shot-camera-planning. That Skill owns selection of the indispensable master images and their scene-level reverse derivation; this Skill validates and completes the general axis, continuity, camera-path, cut, and sound-image grammar.