Loading...
Loading...
Found 102 Skills
[QianWen] Recommend the best Qwen model and parameters. TRIGGER when: choosing between Qwen models, comparing Qwen model pricing, understanding Qwen model capabilities, checking usage or billing, viewing cost history, when an execution skill needs model selection advice, or user explicitly invokes this skill by name (e.g. use qianwen-model-selector). DO NOT TRIGGER when: non-Qwen model discussions (OpenAI, Gemini, etc.), general AI questions unrelated to Qwen.
Converts Opus-quality skills into deterministic Haiku-executable workflows via trace-driven distillation and cross-model validation. Triggers on: "distill this skill", "make this skill work on Haiku", "cross-model optimization", "optimize skill for cost". NOT for code simplification, use code-refiner.
Guide for adding support for new LLM or VLM models in Megatron-Bridge. Covers bridge, provider, recipe, tests, docs, and examples.
ONLY for OpenAI Triton (@triton.jit) kernel development. NEVER use for CUDA C++ kernels, TileIR, or profiling tools (ncu, nsys). The user's request must involve Triton explicitly. Covers Triton-specific patterns: fused elementwise, reductions (softmax, LayerNorm, RMSNorm), tiled GEMM with triton.autotune, and flash attention. Workflow: design, write, verify (with fast-path for explicit requests).
Use when importing a new model architecture into MAX from a Hugging Face model ID. Triggers on: "import a model into MAX", "add model to MAX", "bring up <HF model> in MAX". Workflow: inspect Hugging Face config and modeling code, scaffold from a similar MAX architecture, implement each graph layer to match HF, serve, then debug against the Hugging Face reference until outputs match.
Model Selection and Recommendation for Alibaba Cloud Tongyi Wanli. Activated when users need to "select, recommend, compare" models, or describe an AI scenario/functional requirement (implying the need to decide which model to use). The core intention is to help users make decisions, not just provide information. Trigger words: recommend model, which one to choose, which is suitable, compare, build a XX, implement XX function, which model is good to use, XX scenario solution. When users involve both model query and model selection at the same time, prioritize using this skill (this skill will read model data internally to complete the recommendation).
Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter for router-only mode work and troubleshoot for broken deployments.
Help users integrate Runway image generation APIs (text-to-image with reference images)
Representative MoE training playbooks by hardware platform and model family. Summarizes rounded throughput bands, parallelism patterns, and common tuning stacks.
MosaicML integration. Manage data, records, and automate workflows. Use when the user wants to interact with MosaicML data.
Minimal text generation smoke test for Model Studio Qwen text models.
Generate images directly using the Runway API via runnable scripts. Supports text-to-image with optional reference images.