by Matt Corbett
Audio DSP engineering team — agents (audio-dsp-architect, dsp-implementation-engineer) for the layer answering 'what processing architecture, at what latency, on what platform — and how do we make the audio callback real-time-safe and fast?': processing model (block vs sample-by-sample), latency & buffer budget, fixed vs float + denormals, algorithm approach (IIR biquads / FIR, FFT/STFT overlap-add, oversampling/anti-aliasing), plugin formats & frameworks (JUCE, VST3, AU/AUv3, AAX, CLAP, LV2), audio I/O (CoreAudio, ASIO, WASAPI, ALSA/JACK, Web Audio), lock-free parameter passing, spatial/binaural (HRTF), embedded DSP (CMSIS-DSP), SIMD, and measurement (null tests, THD+N, frequency response). skills, a knowledge bank (decision tree + 2026 patterns), and templates. Distinct from streaming-media-engineering (codecs/delivery), conversational-ai-voice-engineering (voice AI agents), and embedded-iot-engineering (general firmware) — this is the real-time signal-processing layer. Needs ravenclaude-core.
Claude Code3 Skills