gnn-code-generation
GNN code generation for simulation frameworks. Use when generating PyMDP, RxInfer.jl, ActiveInference.jl, JAX, or DisCoPy simulation code from GNN model specifications.
GNN code generation for simulation frameworks. Use when generating PyMDP, RxInfer.jl, ActiveInference.jl, JAX, or DisCoPy simulation code from GNN model specifications.
Senior embedded software engineer specializing in firmware and driver development for ARM Cortex-M microcontrollers (Teensy, STM32, nRF52, SAMD). Decades of experience writing reliable, optimized, and maintainable embedded code with deep expertise in memory barriers, DMA/cache coherency, interrupt-driven I/O, and peripheral drivers.
Guides development of AILANG builtin functions. Use when user wants to add a builtin function, register new builtins, or understand the builtin system. Reduces development time from 7.5h to 2.5h (-67%).
Numerical computing patterns for C++20 including matrix operations, iterative solvers, numerical stability, data pipelines, and HPC I/O with MPI-IO and HDF5.
Terminal emulation, text rendering optimization, and SwiftTerm integration for modern Swift applications
High-performance computing patterns for C++20 including cache-friendly data structures, SIMD vectorization, memory management, thread parallelism, lock-free data structures, and NUMA-aware allocation.
Specialist in bare-metal and RTOS firmware - ESP32/ESP-IDF, PlatformIO, Arduino, ARM Cortex-M, STM32 HAL/LL, Nordic nRF5/nRF Connect SDK, FreeRTOS, Zephyr
Refactoring techniques for Object Pascal: Extract Method, Extract Class, Guard Clauses, Replace Magic Numbers, Replace Conditional with Polymorphism, Introduce Parameter Object, Remove With, Extract Interface. Always focusing on maintaining behavior and improving readability.
Refactoring techniques for Object Pascal focused on improving readability, removing code smells, and preserving behavior through practices like Extract Method, Guard Clauses, and polymorphism.
Apply bounded semantic-layer improvements for Aperture Lab F-Stop's frozen calibration corpus. Use when acting as the optimizer model inside the VPS F-Stop loop; edit only the allowed semantic/importer files, run the required gates, and return a structured JSON outcome.
对最终选中的论文进行深度精读,从 card.md 中提取结构化字段(sub_field、ID_paradigm、baselines 等)。当 paper-pipeline 编排流程执行到 Step 6(深度精读)时自动触发。
Analyze PyTorch internals across Python, C++, and CUDA layers using the TorchTalk MCP server. Use when asked about how PyTorch operators work internally, where functions are implemented, what would break if code is modified, or finding tests for PyTorch operators.
Use when user wants to burn tokens aggressively - infinite loop of analysis, summarization, or heavy math computation. Maximizes token consumption by defeating KV cache, randomizing prompts, and dispatching verbose subagents. Supports time limits, round limits, or unlimited burn until interrupted.
Adapt ShadCN primitives to design-system tokens. Use when importing or normalizing ShadCN components in a UI primitives directory and before creating product wrappers.
Implements mutation testing support for new programming languages using tree-sitter grammars and the LanguageEngine trait. Triggers on "add language support", "add [language] support", "implement [language]", "new language", or mentions of specific languages like Python, TypeScript, C++, Java.
Progressive-disclosure workflow for Egret optimization studies. Use when the user asks to run DC OPF, AC OPF, or unit commitment through PowerMCP, and when the agent should solve the simplest credible optimization before escalating to full commitment studies.
TypeScript infrastructure specialist for monorepo project references, type performance diagnostics (tsc --extendedDiagnostics), ESM/CJS interop, strict mode migration, and .d.ts authoring — use for project-level TypeScript decisions, not implementation patterns.