Agent Skills
› mtarcure/claude-vibe-squad
› interactive-audio-design
interactive-audio-design
GitHub用于设计游戏音频交互系统，包括自适应音乐、动态音效、空间音频及混音规则。根据游戏状态定义音频层级、过渡逻辑和触发参数，确保内存与语音限制合规，为下游集成提供蓝图。
触发场景
需要设计游戏内自适应音乐或动态音效系统
定义音频状态机、混音总线或语音资源预算
安装
npx skills add mtarcure/claude-vibe-squad --skill interactive-audio-design -g -y
SKILL.md
Frontmatter
{
"name": "interactive-audio-design",
"audience": "specialist",
"description": "Use when gameplay state must drive sound and music reactively—specify stems, crossfades, stingers, horizontal resequencing, sound-effect pools, round-robin variation, spatialization, bus ducking, voice limits, and memory or streaming ceilings. Stop at the reactive-system blueprint; downstream schema packaging, media generation, and runtime code are separate."
}
Interactive Audio Design
Design the interactive layer over generated audio assets: adaptive music, dynamic SFX systems, spatial audio, mix/ducking, and audio state machines.
Steps
- Derive audio states from the game state model (menu, explore, combat, etc.); define entry/exit and transition rules between them.
- Design adaptive music as layers/stems with transition behavior (crossfade, stinger, horizontal re-sequence) tied to state.
- Design the SFX system: sound pools, round-robin/randomization to avoid repetition, and spatialization rules.
- Define mix buses and ducking rules (e.g. duck SFX under dialogue) as deterministic parameters, not vibes.
- For each cue, specify trigger, parameters, and a memory/voice-count/streaming budget; name the middleware/runtime target.
- Hand rendering to the audio asset specialists and integration to
game-engineer; never self-clear voice-likeness.
Acceptance
- Every audio state has entry/exit + transition behavior; no unbounded voice count.
- Mix and ducking rules are deterministic and parameterized.
- Each cue names its trigger, parameters, and budget; middleware target stated.
版本历史
- d5262e2 当前 2026-09-11 11:16
