music-suggestion

Proactive music suggestion. Routed in by user-emotion-detection/SKILL.md (the router) on emotion.detected (camera) and speech_emotion.detected (voice) events when the synthesized mood is suggestion-worthy (sad/stressed/tired/excited/happy/bored) AND audio is idle AND cooldown is clear. Reads, decision, and writes share the same parallel batch in a single turn. Does NOT fire on motion.activity / [activity] events —…