Trusted skills for AI agents from official vendors and established maintainers. Every skill is attributed to its author, scanned, and comes with install steps for your AI tool.
1928 skills
NVIDIAOfficial
Prepare and validate object-detection false-negative data for AnomalyGenNext generation workflows.
NVIDIAOfficial
Plan, install, and validate NVSHMEM and NVSHMEM4Py across various environments.
NVIDIAOfficial
Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training, evaluating, exporting, or running inference for PCB defect detection or visual inspection, comparing image pairs for PASS/NO_PASS classification, or producing change-segmentation masks. Trigger phrases include "train Visual ChangeNet", "ChangeNet classify", "ChangeNet segment", "AOI defect detection", "PCB inspection model".
NVIDIAOfficial
Hardware-accelerated DEFLATE and LZ4 compression offload for NVIDIA BlueField DPU and ConnectX NICs using the DOCA Compress library.
NVIDIAOfficial
A workflow for building and verifying the Holoscan SDK 5.x from source using the repository run wrapper.
NVIDIAOfficial
Define and validate NVIDIA PVA operator specifications, test matrices, and evidence for OpGen handoff.
NVIDIAOfficial
Configure and validate sequence packing for efficient LLM and VLM training in Megatron-Bridge.
NVIDIAOfficial
Install and verify NVIDIA cuOpt for Python, C, or REST server environments.
NVIDIAOfficial
Manage HOLOLINK_def.svh configuration files for HSB IP through generation, validation, and comparison workflows.
NVIDIAOfficial
NVIDIA DeepStream SDK development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration.
NVIDIAOfficial
Inventory host-DPU DOCA Comm Channel servers and connections using the doca_comm_channel_admin CLI tool.
NVIDIAOfficial
Manage the end-to-end lifecycle of TAO Sparse4D 3D detection and tracking models.
NVIDIAOfficial
A workflow for installing and verifying the correct NeMo Relay package, CLI, or integration for your specific development environment.
NVIDIAOfficial
Run the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models: baseline evaluate, RCA, Cosmos AnomalyGen / AMP synthetic defects, k-NN mining, retraining, and deployment gating against a customer-defined primary metric and optional constraints. Use only when the request identifies an AOI / automated-optical-inspection, PCB-defect, VisualChangeNet, or ChangeNet workflow. Supports air-gapped/offline runs with pre-staged assets. Never infer AOI from generic iterative-improvement language. Do not use for CLIP / SigLIP image retrieval, attribute-labelled image data, standalone TAO training, one-off inference, generic anomaly generation, or RCA-only analysis.
NVIDIAOfficial
Diagnose NVFLARE job failures by analyzing logs and metrics in simulation or production environments.
NVIDIAOfficial
Expert guidance for integrating NVIDIA DOCA GPUNetIO with CUDA kernels for GPU-accelerated networking.
NVIDIAOfficial
Implement typed wrappers and codecs for NeMo Relay to bridge domain models with JSON-based middleware.
NVIDIAOfficial
Monitor the progress and status of detached KERMT training or fine-tuning runs.
NVIDIAOfficial
A structured, evidence-gated workflow for optimizing Mixture-of-Experts (MoE) model throughput in Megatron Bridge.
NVIDIAOfficial
Automated generation and repair of vectorized NVIDIA PVA operators based on validated specifications.
NVIDIAOfficial
Configure and validate CPU offloading mechanisms in Megatron Bridge to optimize GPU memory usage during model training.
NVIDIAOfficial
A guide for selecting and tuning MoE token dispatchers (alltoall, DeepEP, HybridEP) based on hardware, EP degree, and workload.
NVIDIAOfficial
Official guidance for integrating PhysicsNeMo ShardTensor domain parallelism into PyTorch training and inference workflows.
NVIDIAOfficial
Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch, numerical mismatch), and mapping cuTile idioms (ct.load/ct.store, ct.Constant, ct.launch) to Triton equivalents. Covers dual-kernel layout flags (e.g. transpose=True/False + autotune grid via META) per translations/advanced-patterns.md. Use when converting, porting, or translating cuTile kernels to Triton, or debugging existing Triton translations.