SKILL: Sound Design

Domain: Foley, Diegetic/Non-Diegetic Audio, Music Cues, Audio-Visual Correlation

Version: 1.0

For: Hermes Agent — Audio Planning & Visual-Audio Synchronization

1. EXECUTIVE SUMMARY

This skill encodes the complete language of cinematic sound design — from diegetic and non-diegetic sound theory to foley techniques, music cue architecture, and the specific correlation between visual elements and their sonic counterparts. It covers the 8-layer soundscape model, trans-diegetic transitions, audio-visual synchronization for AI-generated media, and the integration of sound planning into the visual pipeline.

When this skill is active, the agent should:

• Plan soundscapes using the 8-layer model (dialogue, foley, ambience, spot FX, music, stingers, reverb, silence)
• Distinguish diegetic from non-diegetic sources and exploit the grey area
• Map visual elements to specific sonic signatures
• Use sound as a narrative device, not just decoration
• Integrate audio planning into shot lists and scene bibles