burn-onnx-surgeon
Specializes in ONNX model import failures, unsupported operators, opset version mismatches, and dynamic shape issues. Use when burn-import fails or produces incorrect results.
cirq
Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip.
detecting-pointer-subtraction
Detects unsafe pointer subtraction operations that can lead to incorrect size calculations and integer underflow. Use when analyzing pointer arithmetic, size calculations, or investigating buffer sizing issues.
ebpf-packet-redirect
Implement packet redirection and routing in eBPF programs using bpf_redirect and bpf_redirect_neigh helpers. Includes source-based policy routing, map-based routing tables, load balancing, and CNF router patterns. Use when building routers, gateways, load balancers, or any CNF that needs to control packet forwarding paths.
rust-wasm-optimization
Optimize Rust code for WebAssembly compilation and runtime performance. Use when building WASM applications, optimizing binary size, or improving WASM runtime performance.
burn-backends
This skill should be used when the user asks about "Burn backend", "WGPU", "NdArray", "Candle", "LibTorch", "custom kernel", "CubeCL", "quantization", "WebAssembly", "no_std", or backend selection and extension.
typescript-patterns
Advanced types, strict mode, type safety
juce-audio-graphics-architect
Advanced JUCE audio DSP, real-time analysis, and interactive graphics for plugin development. Use when building AU/VST3 plugins, adding DSP chains (reverb/delay/physical modeling), implementing FFT or audio-reactive UI, integrating OpenGL/shader visuals or particle systems, or designing layered, animated JUCE interfaces with transparency and shadows. Prefer established third-party JUCE modules or GitHub libraries when they reduce custom code, with license and compatibility checks.
convert-python-rust
Convert Python code to idiomatic Rust. Use when migrating Python projects to Rust, translating Python patterns to idiomatic Rust, or refactoring Python codebases for performance, safety, and concurrency. Extends meta-convert-dev with Python-to-Rust specific patterns.
bb80-invariant-construction
Extract invariants from specification, encode in types/structure, enable single-pass construction.
python-expert
Expert-level Python development with Python 3.12+ features, async/await, type hints, and modern best practices
convert-c-cpp
Convert C code to idiomatic C++. Use when migrating C projects to C++, translating C patterns to modern C++ idioms, or refactoring C codebases into C++. Extends meta-convert-dev with C-to-C++ specific patterns covering all 8 pillars (Module, Error, Concurrency, Metaprogramming, Zero/Default, Serialization, Build, Testing).
convert-haskell-erlang
Convert Haskell code to idiomatic Erlang/OTP. Use when migrating Haskell projects to Erlang, translating pure functional patterns to fault-tolerant concurrent systems, or refactoring Haskell codebases into distributed Erlang applications. Extends meta-convert-dev with Haskell-to-Erlang specific patterns.
pennylane
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with PyTorch/JAX/TensorFlow. For hardware-specific optimizations use qiskit (IBM) or cirq (Google); for open quantum systems use qutip.
mithril-cache-agent
Build mithril-cache for torch.compile caching. Use when implementing content-addressable storage, cache keys, eviction, or framework hooks.
qiskit
IBM quantum computing framework. Use when targeting IBM Quantum hardware, working with Qiskit Runtime for production workloads, or needing IBM optimization tools. Best for IBM hardware execution, quantum error mitigation, and enterprise quantum computing. For Google hardware use cirq; for gradient-based quantum ML use pennylane; for open quantum system simulations use qutip.
mithril-checkpoint-agent
Build mithril-checkpoint compression for PyTorch models. Use when implementing byte grouping, compression pipeline, or checkpoint I/O.
convert-erlang-haskell
Translates Erlang concurrent functional code to Haskell pure functional code. Use when migrating BEAM-based systems, modernizing telecom infrastructure, or adopting stronger type systems. Extends meta-convert-dev with Erlang-to-Haskell specific patterns.
cpp-expert
Expert-level C++ development with modern C++20/23, STL, memory management, and performance
numerical-validation
Verify mathematical correctness and numerical accuracy after code changes
