Loading...
Loading...
Found 402 Skills
Autonomous LLM training optimization with GPU support. Runs 5-minute training experiments, measures val_bpb, keeps improvements or reverts — repeat forever. Use this skill when the user asks to "train a model autonomously", "optimize LLM training", "run ML experiments", "autoresearch with GPU", "optimize val_bpb", "autonomous ML training", "LLM pretraining loop", "setup ML autoresearch", "GPU training experiments", "pretrain from scratch", "speed up training", "lower my loss", "GPU optimization", "CUDA training", or mentions "train.py", "prepare.py", "bits per byte", "val_bpb", "NVIDIA GPU training", "RTX training", "H100 training", "autonomous model training", "consumer GPU training", "low VRAM training". Always use this skill when the user wants to autonomously optimize any ML training metric.
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput.
Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container. Use when the user wants to fine-tune a HuggingFace model (full or LoRA), train a vision / VLM / LLM model end-to-end, generate a reproducible HF training pipeline, smoke-test a HuggingFace model locally before scale-up, push a fine-tuned model to the HF Hub with a model card, or emit a self-contained rerun skill for an existing HuggingFace finetune. Supports image classification, object detection, semantic / instance / panoptic segmentation, depth estimation, image-text-to-text VLM (SFT / LoRA), and LLM SFT / DPO / GRPO. Six-step workflow: inspect and qualify, hardware and NGC image, research, generate and smoke, train + eval + infer, push and emit rerun skill.
Run an ML training job on a completed Itô compute booking through the canonical Itô backend. Use after ito-compute has booked GPU nodes and the user wants pre-training, fine-tuning, or RL on that metal. Chains off a booking record; ECC implements no training stack of its own.
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.
This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Zarr), GPU acceleration (PyTorch, JAX), or memory-efficient strategies. Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter.
Async operations and background tasks in GPUI. Use when working with async, spawn, background tasks, or concurrent operations. Essential for handling async I/O, long-running computations, and coordinating between foreground UI updates and background work.
Converts cuTile Python GPU kernels (@ct.kernel) to cuTile.jl Julia equivalents. Handles kernel syntax translation, 0-indexed to 1-indexed conversion, broadcasting differences, memory layout (row-major to column-major), type system mapping, and launch API differences. Use when converting, porting, or translating cuTile Python kernels to Julia cuTile.jl, or debugging/optimizing existing Julia cuTile translations.
Use for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill. Trigger on NVIDIA products, hardware, software, SDKs, GPUs, Jetson/JetPack/L4T/BSP/SDK Manager/driver/flashing/setup, CUDA, NIM, NeMo, Omniverse/OpenUSD/SimReady, RAPIDS/cuDF, cuPyNumeric, cuOpt, Dynamo, Holoscan, TensorRT, DeepStream, VSS, TAO, NGC/NVCF. Do not use for generic non-NVIDIA route, optimize, deploy, AI, video, data, or infrastructure tasks.
CUDA kernel development, debugging, and performance optimization for Claude Code. Use when writing, debugging, or optimizing CUDA code, GPU kernels, or parallel algorithms. Covers non-interactive profiling with nsys/ncu, debugging with cuda-gdb/compute-sanitizer, binary inspection with cuobjdump, and performance analysis workflows. Triggers on CUDA, GPU programming, kernel optimization, nsys, ncu, cuda-gdb, compute-sanitizer, PTX, GPU profiling, parallel performance.
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.
Test CLI applications interactively using tmux sessions. Use when testing TUI apps (ratatui dashboard, interactive prompts), verifying CLI command output, testing keyboard navigation, or validating terminal rendering. Launches commands in tmux, waits on conditions (never sleeps), captures frames, sends keypresses, and asserts on output. Specifically designed for gpu-cli but works with any CLI. Use this skill when asked to test, verify, or QA any terminal-based UI or CLI command flow.