What problem does it solve? Video sound design often fails because scripts are written for the eye, music is chosen without testing against the edit, and licensing risks are ignored until a platform mutes or claims the video. This Skill provides a single decision framework for everything the audience hears, from VO delivery direction to copyright-safe audio sourcing. ## Core Features & Use Cases - Ear-Written VO Rules: Converts visual scripts into spoken-cadence narration with delivery direction covering voice selection, model temperament, emotion tags, and pronunciation calibration. - BGM and SFX Layering Discipline: Defines a four-criterion BGM selection process, a five-word SFX vocabulary (whoosh, impact, riser, sparkle, transition), relative frame-pinning, loudness layering, and anti-machine-gun repetition techniques. - Copyright Red Lines: Enforces licensed-source selection, paid-tier commercial rights, Content ID risk awareness, AI disclosure requirements, and attribution archiving. - Use Case: When producing a product promo video, use this Skill to write the voiceover for the ear, pick a tech-house BGM that matches the edit's energy curve, pin SFX to beats relative to shot starts, and archive license proof before publishing. ## Quick Start Ask the agent to design the sound for your video by defining the voiceover script, BGM direction, and SFX layers according to this Skill's decision framework.
