Guidelines for modern C++ development with C++17/20 standards, memory safety, and performance optimization
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization...
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization...
Write idiomatic C++ code with modern features, RAII, smart
Write idiomatic C++ code with modern features, RAII, smart
Write idiomatic C++ code with modern features, RAII, smart
Write idiomatic C++ code with modern features, RAII, smart
Use when building C++ applications requiring modern C++20/23 features, template metaprogramming, or high-performance systems. Invoke for concepts, ranges, coroutines, SIMD optimization, memory management.
Use when building C++ applications requiring modern C++20/23 features, template metaprogramming, or high-performance systems. Invoke for concepts, ranges, coroutines, SIMD optimization, memory management.
C++20 specialist with expertise in modern C++ features, performance optimization, and system programming
>
Implements JavaScript classes in C++ using JavaScriptCore. Use when creating new JS classes with C++ bindings, prototypes, or constructors.
Expert guide for Unreal Engine 5.x C++ development, covering UObject hygiene, performance patterns, and best practices.
Expert guide for Unreal Engine 5.x C++ development, covering UObject hygiene, performance patterns, and best practices.
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without...
Expert skill for integrating local Large Language Models using llama.cpp and Ollama. Covers secure model loading, inference optimization, prompt handling, and protection against LLM-specific...
|
嵌入式 C 代码风格助手, 基于 51 单片机教学项目的代码规范。默认使用蛇形命名 (snake_case), 可选驼峰命名。用于创建符合嵌入式开发规范的项目结构, 优化代码风格, 提供硬件驱动模板。适用于 51 单片机、STM32 等嵌入式 C 项目开发。
基于 PPT 模板生成新内容。PDF 自动转图片 → 分析模板风格 → 拆分文章内容 → 生成提示词 → AI 生图 → 打包 PPTX。
将文章内容拆解为小红书风格的系列配图。支持从 URL、文件或文本生成封面图、内容图和结尾图，自动创建提示词并调用图片生成工具。