Orchestrate audio team: audio-director + sound-designer + technical-artist + gameplay-programmer for full audio pipeline from direction to implementation.
This is the Codex-adapted version of the original workflow. Use only .codex/ runtime assets when following it.
Arguments: [feature or area to design audio for]
When this skill is invoked, orchestrate the audio team through a structured pipeline.
Decision Points: At each step transition, use request_user_input to present
the user with the subagent's proposals as selectable options. apply_patch the agent's
full analysis in conversation, then capture the decision with concise labels.
The user must approve before moving to the next step.
Read the argument for the target feature or area (e.g., combat,
main menu, forest biome, boss encounter).
Gather context:
design/gdd/ for the featuredesign/gdd/sound-bible.md if it existsassets/audio/Use the spawn_agent tool to spawn each team member as a subagent:
subagent_type: audio-director — Sonic identity, emotional tone, audio palettesubagent_type: sound-designer — SFX specifications, audio events, mixing groupssubagent_type: technical-artist — Audio middleware, bus structure, memory budgetssubagent_type: gameplay-programmer — Audio manager, gameplay triggers, adaptive musicAlways provide full context in each agent's prompt (feature description, existing audio assets, design doc references).
Spawn the audio-director agent to:
Spawn the sound-designer agent to:
Spawn the technical-artist agent to:
Spawn the gameplay-programmer agent to:
Compile the audio design document combining all team outputs.
Save to design/gdd/audio-[feature].md.
Output a summary with: audio event count, estimated asset count, implementation tasks, and any open questions between team members.