Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e", "deepseek"). For...

This skill should be used when users want to route LLM requests to different AI providers (OpenAI, Grok/xAI, Groq, DeepSeek, OpenRouter) using SwiftOpenAI-CLI. Use this skill when users ask to...

Use this skill when developing browser/Web applications (React/Vue/Angular, static websites, SPAs) that need AI capabilities. Features text generation (generateText) and streaming (streamText) via...

Use this skill when developing Node.js backend services or CloudBase cloud functions (Express/Koa/NestJS, serverless, backend APIs) that need AI capabilities. Features text generation...

Use this skill when developing WeChat Mini Programs (小程序, 企业微信小程序, wx.cloud-based apps) that need AI capabilities. Features text generation (generateText) and streaming (streamText) with callback...

Heavy3 Code Audit - Multi-model code review for coding agents (Lite: DeepSeek, Pro: GPT+Gemini+Grok)

Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e", "deepseek")

Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e", "deepseek")

Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e", "deepseek")

Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e", "deepseek")

Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e", "deepseek")

Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e", "deepseek")

Estimate GPU memory usage for Megatron-based MoE (Mixture of Experts) and dense models. Use when users need to (1) estimate memory from HuggingFace model configs (DeepSeek-V3, Qwen, etc.), (2)...

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse...

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse...

Write, optimize, and debug high-performance AI compute kernels using TileLang (a Python DSL for GPU programming). Use when the user requests: (1) Writing custom GPU kernels for AI workloads (GEMM,...

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+...

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on...

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on...

当用户需要学习某种风格、提取写作配方、建立风格库或模仿特定作者时调用。深度解构文本的15个维度，包括作者画像、思维内核、创作路径、互动设计等，建模为可精准复制的风格文件。触发词：风格建模、提取风格、学习风格、模仿写作、解构文章、写作配方、风格库。