Loading...
Loading...
Found 64 Skills
Image generation skill based on Alibaba Cloud DashScope, supporting the creation of high-quality hand-drawn or standard images from user descriptions.
Provides guidance for writing and benchmarking optimized CUDA kernels for NVIDIA GPUs (H100, A100, T4) targeting HuggingFace diffusers and transformers libraries. Supports models like LTX-Video, Stable Diffusion, LLaMA, Mistral, and Qwen. Includes integration with HuggingFace Kernels Hub (get_kernel) for loading pre-compiled kernels. Includes benchmarking scripts to compare kernel performance against baseline implementations.
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens", "efficient inference", "suppress reflection tokens", or when working with verbose CoT outputs.
CLI tools execution specification (gemini/claude/codex/qwen/opencode) with unified prompt template, mode options, and auto-invoke triggers for code analysis and implementation tasks. Supports configurable CLI endpoints for analysis, write, and review modes.
Route Alibaba Cloud Model Studio requests to the right local skill (Qwen Image, Qwen Image Edit, Wan Video, Wan R2V, Qwen TTS and advanced TTS variants). Use when the user asks for Model Studio without specifying a capability.
PixVerse CLI — generate AI videos and images from the command line. Supports PixVerse, Veo, Sora, Kling, Hailuo, Wan, and more video models; Nano Banana (Gemini), Seedream, Qwen image models; and PixVerse's rich effect template library. Start here.
Minimal realtime TTS smoke test for Model Studio Qwen TTS Realtime.
Cloud GPU processing via RunPod serverless. Use when setting up RunPod endpoints, deploying Docker images, managing GPU resources, troubleshooting endpoint issues, or understanding costs. Covers all 5 toolkit images (qwen-edit, realesrgan, propainter, sadtalker, qwen3-tts).
vLLM Ascend plugin for LLM inference serving on Huawei Ascend NPU. Use for offline batch inference, API server deployment, quantization inference (with msmodelslim quantized models), tensor/pipeline parallelism for distributed serving, and OpenAI-compatible API endpoints. Supports Qwen, DeepSeek, GLM, LLaMA models with Ascend-optimized kernels.
Chat with LLM models using ModelsLab's OpenAI-compatible Chat Completions API. Supports 60+ models including DeepSeek R1, Meta Llama, Google Gemini, Qwen, and Mistral with streaming, function calling, and structured outputs.
Orchestrate Chinese LLMs (DeepSeek, Qwen, Yi, Moonshot) through OpenRouter API with LangChain. Use when: openrouter, chinese llm, deepseek, qwen, moonshot, yi model, model routing, auto router, llm orchestration.