DSP & Analog Circuit Modeling (WDF, Biquads, Polyphase OS)
by blockie710
Design real-time audio algorithms, analog circuit emulations, and SIMD-optimized processing pipelines.
Secure checkout via Stripe
Works with the AI tools you already use
See it in action
You say
Generate a C++ Biquad low-pass filter using a Direct Form II topology. Optimize the processing loop for AVX2 and ensure it is real-time safe with denormal prevention.
Your agent does
// Biquad DFII with AVX2 Optimization
void process(float* data, int count) {
const __m256 v_dc_offset = _mm256_set1_ps(1e-25f);
// ... SIMD coefficients and state management ...
for (int i = 0; i < count; i += 8) {
__m256 x = _mm256_loadu_ps(&data[i]);
x = _mm256_add_ps(x, v_dc_offset); // Denormal prevention
// ... vectorized DFII logic ...
}
}
What you get
About this skill
The problem
Designing audio DSP algorithms requires balancing mathematical precision with strict real-time performance. Manual implementation often leads to denormal issues, CPU spikes from dynamic allocation, and inefficient processing loops that fail to use SIMD hardware.
What it does
- Generates Wave Digital Filter (WDF) structures for non-linear analog circuit emulation like diodes and tubes.
- Designs discrete-time filter topologies including Biquads and State Variable Filters (SVF).
- Implements polyphase FIR oversampling chains to eliminate aliasing in saturators.
- Produces SIMD-optimized C++ code targeting AVX2, AVX-512, and ARM NEON.
Frameworks & tools
C++ (C++17 or later), JUCE, SIMD (AVX/NEON), and standard DSP libraries.
Why this beats prompting it yourself
General LLMs often produce code with hidden "real-time safety" violations like memory allocation in the audio thread. This skill enforces strict audio processing constraints, including denormal prevention and branchless non-linearities, which are critical for stable plugin performance.
Use cases
- Emulate the transfer function and impedance of a vintage tube preamp.
- Build a high-performance 8x oversampling engine for a distortion effect.
- Vectorize an existing gain or filter loop using AVX2 intrinsics.
- Implement stable, high-order filters without the risk of numerical explosion.
Known limitations
Does not handle GUI/UX code or VST3/AU wrapper boilerplate. Focuses strictly on the signal processing core and mathematical modeling.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean today
- 30-day refund guarantee
- One-time purchase, yours forever
- Secure checkout via Stripe
Creator
7 skills on Agensi
Frequently Asked Questions
Popular in AI Agents & LLM Ops
agentic-workflow
A risk-aware, evidence-based engineering lifecycle protocol for robust agentic task execution and safety.
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.
prompt-engineer
Professional prompt engineering patterns for building robust, secure, and production-ready LLM applications.
codex-grade-coding
Turn your AI agent into a senior engineer with strict task classification and verification-driven coding protocols.