Loading...
Loading...
Found 104 Skills
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.
Write, review, and improve prompts for any LLM — Claude, GPT, Gemini, Llama, DeepSeek, Mistral, Cohere, Qwen, Grok, Nova, and more. Use when the user asks to "write a system prompt", "improve this prompt", "review my prompt", "make a prompt for", "optimize my prompt", "fix my prompt", "why isn't my prompt working", or wants help writing better prompts for any AI model. Also use when building agents, chatbots, or AI assistants that need system-level instructions, or when the user has a bad prompt they want rewritten. Covers system prompts, task prompts, tool descriptions, and general prompt improvement across all major model families.
Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and other multimodal experiments.
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.
Integrate Modellix's unified API for AI image and video generation into applications. Use this skill whenever the user wants to generate images from text, create videos from text or images, edit images, do virtual try-on, or call any Modellix model API. Also trigger when the user mentions Modellix, model-as-a-service for media generation, or needs to work with providers like Qwen, Wan, Seedream, Seedance, Kling, Hailuo, or MiniMax through a unified API.
Universal AI image generation supporting OpenAI DALL·E / gpt-image, Google Gemini Image / Imagen, Replicate (Flux / SDXL / any model), Stability AI, FAL, Ark (Seedream 4.5), Bailian (qwen-image / wanx), and SiliconFlow. Use this skill whenever the user asks to generate, create, draw, illustrate, render, or synthesize images from text prompts or reference images. Typical phrases include "draw a ...", "generate an image of ...", "画一张 ...", "给我来张图", "make a poster of ...", "create an illustration ...", or any mention of image-generation model families like DALL·E, gpt-image, Flux, SDXL, Seedream, Imagen, Gemini image, Kolors, or Wanx. Always use this skill even if the user does not name a specific model — pick a provider based on their EXTEND.md defaults or available API keys in the environment. Do NOT use this skill when the user explicitly mentions 即梦 / Dreamina / Jimeng — those go to happy-dreamina instead.
Use major AI models (Claude, ChatGPT, Gemini, DeepSeek, Qwen, etc.) without API tokens by leveraging browser authentication instead of paid API keys
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.
[QianWen] Check for qianwen-ai updates and notify the user when a new version is available. TRIGGER when: user asks to check for updates, check version, asks 'is there a new version', 'latest version', 'update skills', 'check update', or any other qwen skill delegates to this skill, or user explicitly invokes this skill by name (e.g. use qianwen-update-check). DO NOT TRIGGER when: non-update-related tasks, general version questions about other software.
Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Summarizes patterns from DSV3, Qwen3, Qwen3-Next, and VLM bring-up work.
Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and other multimodal experiments.
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.