Найдите подходящую возможность для вашего агента.
Convert Haskell code to idiomatic Roc. Use when migrating Haskell applications to Roc's platform model, translating lazy pure functional code to strict platform-based architecture, or refactoring type class based designs to ability-based patterns. Extends meta-convert-dev with Haskell-to-Roc specific patterns.
Carbon language library development patterns including interoperability with C++, memory safety patterns, generic programming, build system integration, testing approaches, and documentation standards. Use when creating Carbon libraries, designing public APIs with safety and interoperability in mind, or porting C++ libraries to Carbon.
Convert C++ code to idiomatic Rust. Use when migrating C++ projects to Rust, translating C++ patterns to idiomatic Rust, or refactoring C++ codebases. Extends meta-convert-dev with C++-to-Rust specific patterns, including FFI-based gradual migration.
Detects integer overflow and underflow vulnerabilities in arithmetic operations used for buffer sizing or allocation. Use when analyzing calculations, size computations, or investigating integer wraparound issues.
Minimize allocations and cloning using references, Cow, and smart pointers. Use when optimizing hot paths or memory-constrained code.
Develop OpenFeature SDK implementations from the specification. Use when implementing the OpenFeature spec in a new language, extending existing SDKs with new features, building custom providers, or contributing to official SDK repositories.
Leverage iterator chains for efficient, lazy data processing without intermediate allocations. Use when processing collections.
Opaque Pointer Pattern pattern for C development
This skill should be used when creating custom factors for Zipline Pipeline. It provides patterns for implementing CustomFactor classes, handling windowed computations, multiple inputs/outputs, and efficient numpy operations.
Bridge Rust and Python using PyO3 with proper GIL handling and async compatibility. Use when integrating Python ML models or libraries.
AI hardware accelerators including GPUs, TPUs, custom silicon, and hardware-aware optimization strategies for ML workloads.
Edge deployment strategies including mobile optimization, embedded systems, TFLite, Core ML, and resource-constrained inference.
Python開発支援（FastAPI/Pydantic/uv）。 型ヒント、ruff、mypyでモダンPython開発をガイド。
Provides reverse engineering analysis support including function identification, data structure analysis, and behavior understanding. Use when analyzing unknown binaries, understanding program structure, or investigating binary behavior.
Fast code operations using Serena MCP (1-3s) for symbol search, memory read/write, and basic code editing in LoRAIro project
Convert Roc code to idiomatic Erlang. Use when migrating Roc projects to Erlang/OTP, translating functional patterns to process-based architectures, or refactoring Roc codebases. Extends meta-convert-dev with Roc-to-Erlang specific patterns.
Diagnoses Burn deep learning errors including tensor shape mismatches, backend panics, autodiff issues, and training failures. Use when encountering runtime errors, compilation failures, or unexpected behavior in Burn code.
Specializes in ONNX model import failures, unsupported operators, opset version mismatches, and dynamic shape issues. Use when burn-import fails or produces incorrect results.
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.
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.
