Provide architecture-specific GPU optimization advice for NVIDIA GPUs (Ampere, Hopper, Ada). Use when discussing GPU architecture features, compute capability, or hardware-specific optimizations.
Advanced memory management techniques for the OpenCode memory system
Architecture and implementation details of FastEdgesGeometry. Use when modifying FastEdgesGeometry, understanding its optimization techniques, or debugging edge generation issues.
Provides essential Zero Allocation patterns using Span and ArrayPool. Use when quickly referencing core memory optimization techniques without detailed explanations.
Rust development tools including PyO3 bindings, sqlx database access, AGiXT SDK, and Rust-Python interop
Hardware chip semantic versioning scheme for IC modules. Defines MAJOR.MINOR.PATCH conventions for RTL design and verification changes.
Use Syntax::Keyword::Assert for zero-cost assertions in Perl
Implement and maintain NET-NiNJA's Qt compatibility logic: auto-select PyQt6 vs PyQt5 based on CPU features (SSE4.1/4.2), add and honor --gui=auto|qt6|qt5, and prevent premature PyQt6 imports that crash on legacy CPUs. Use when touching GUI startup, requirements, or hardware gating.
Provides SVC-specific AXI/AXI-Lite naming conventions, signal ordering, and available modules. Triggers when implementing AXI or AXI-Lite interfaces.
Cross-compile OBS Studio plugins from Linux to Windows using MinGW, CMake presets, and CI/CD workflows. Covers toolchain files, headers-only linking, OBS SDK fetching, and multi-platform artifact packaging. Use when building OBS plugins for Windows from Linux or setting up CI pipelines.
Robotics Operating System (ROS 1 & 2) expert. Specializes in node lifecycle, transformations (TF2), URDF modeling, navigation, and build systems (catkin/colcon).
Use ComputationalPaths path tactics to automate common RwEq goals (path_simp/path_auto/path_normalize), and structure calc-based proofs cleanly.
Rust unsafe code, FFI, and safety invariants
Utilizing Dynamic 4-bit quantization, FP8 training, and 8-bit optimizers to minimize VRAM usage without sacrificing accuracy. Triggers: quantization, dynamic 4-bit, fp8, bitsandbytes, adamw_8bit, qat.
Comprehensive toolkit for developing with the CocoIndex Rust API. Use when building high-performance operators, embedding the engine in Rust applications, or extending the core framework. Covers LibContext management, custom native operators, and direct execution control.
Expert in pure native development (Swift/Kotlin) for iOS and Android, maximizing platform capabilities and performance.
Build or modify the Rust↔Python FFI using PyO3+maturin. Use for binding builds, smoke tests, and boundary validation workflow.
Modern C++ (C++23/C++20) development specialist covering RAII, smart pointers, concepts, ranges, modules, and CMake. Use when developing high-performance applications, games, system software, or embedded systems.
Use when programming with tidyverse data-masked functions (dplyr, ggplot2, tidyr) and need to pass column references through functions. Covers: forwarding patterns with {{ and ..., names patterns with .data/.env pronouns, bridge patterns with across()/all_of(), double evaluation and ambiguity pitfalls. Does NOT cover: expression mechanics (r-metaprogramming), error handling (rlang-conditions), function design (designing-tidy-r-functions).
Low-risk Python performance optimization patterns with verified speedups
Masked arrays for robust handling of missing or invalid data, ensuring they are excluded from statistical and mathematical computations. Triggers: masked array, numpy.ma, missing data, invalid values, hard mask.
