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.
5813 skills
NVIDIAOfficial
A reference guide for MoE training configurations across various hardware platforms and model families.
NVIDIAOfficial
Run ProteinMPNN inverse folding via NVIDIA NIM to design protein sequences for a target backbone. Sends user-provided PDB files and design parameters to NVIDIA's hosted API, authenticated with an environment API key, or to a user-selected local NIM. Use for sequence design, backbone redesign, fixed chains and residues, omit_AAs, sampling temperature, soluble model, local Docker, and multi-FASTA output.
NVIDIAOfficial
Execute Python training and evaluation scripts directly within a local virtual environment without containers.
NVIDIAOfficial
Orchestrate and maintain resilient NVIDIA Physical AI infrastructure on MicroK8s or Azure AKS for synthetic data generation.
NVIDIAOfficial
Expand HDF5 workflow demonstration datasets by generating synthetic variants with action jitter.
NVIDIAOfficial
Assists with configuring, building, and running the DOCA Telemetry Traceback application for local telemetry monitoring on BlueField DPUs and ConnectX NICs.
NVIDIAOfficial
Plan, execute, and validate NVIDIA Jetson video codec workflows using official SDK samples.
NVIDIAOfficial
Configure and enable Jetson Thor MGBE 25G/10G/1G Ethernet interfaces via kernel-DT overlays.
NVIDIAOfficial
Generates a fixed-format SystemVerilog top-level scaffold for HSB IP integration based on validated HOLOLINK_def.svh files.
NVIDIAOfficial
Use when running video data augmentation and auto-labeling workflows on OSMO: flow selection, preflight, submit-time interpolation, monitoring, and output retrieval. Trigger keywords: video data augmentation, data enrichment, auto labeling, VDA demo, OSMO workflow, pseudo labeling.
NVIDIAOfficial
Expert guidance for implementing hardware-accelerated AES-GCM encryption and decryption using the NVIDIA DOCA SDK.
NVIDIAOfficial
Guidelines and procedures for running Megatron-LM and Megatron Bridge training, including correlation testing and multi-GPU configurations.
NVIDIAOfficial
A systematic procedure to diagnose and reduce cold-start compilation latency in applications using Warp kernels.
NVIDIAOfficial
Train, evaluate, and run inference for Co-DETR object detection models within the NVIDIA TAO framework.
NVIDIAOfficial
Guidance for programming the DOCA Telemetry Exporter library to emit structured application telemetry.
NVIDIAOfficial
Bootstraps the Jetson BSP customization workspace, including source repositories and the cross-compilation toolchain.
NVIDIAOfficial
Export a trained Isaac Lab DisplayPort task-space checkpoint with LEAPP, run it through Isaac ROS Deploy and Isaac Sim 6.0 in separate Docker containers, verify training asset parity, and record insertion video and measured results. Use for post-training simulation deployment and testing of cable insertion policies.
NVIDIAOfficial
Run the CDF Orchestration Event Video Generation DAG on Kubernetes or OSMO - image-to-video anomaly generation, auto-labeling, and anomaly dataset generation. Select for requests about event video generation, anomaly video generation, image-to-video synthesis, Cosmos3 image2video, anomaly dataset creation, safety/surveillance SDG, or generating person-falling, person-climbing, person-running, fighting, smoking/vaping, fire/smoke, or shoplifting video clips from a seed image. Covers both event_video_generation_dag_k8s and the external-endpoints-only event_video_generation_dag_osmo. Runs environment setup first when controller readiness is unknown. Not for person-crop clothing/attribute augmentation (that is cdf-image-attribute-augmentation) and not for video style transfer.
NVIDIAOfficial
A wrapper for the NVIDIA-Medtech NV-Generate-CTMR rectified-flow pipeline to generate synthetic CT volumes and masks.
NVIDIAOfficial
Use this skill to locate authoritative NVIDIA DOCA information without the source tree: the docs.nvidia.com page for a library/service/tool, which DOCA libraries are installed and at what version, a sample on disk or GitHub, a path under /opt/mellanox/doca, or a 404'd/renamed doc URL. Activate on implicit phrasing only when the conversation already names DOCA, BlueField, ConnectX, or /opt/mellanox. Do not activate for generic 'which version is installed' or 'where is the sample' questions with none of that context. Refuse and route elsewhere for hands-on programming, env prep, API tutorials, or hardware/firmware mutation — those belong to doca-programming-guide, doca-setup, the per-library skills, and doca-hardware-safety.
NVIDIAOfficial
Use this skill for OpenFold3, NVIDIA's BioNeMo NIM microservice for biomolecular structure prediction. Invoke whenever the user mentions OpenFold3 or needs protein, protein-ligand, protein-DNA/RNA, or multi-chain complex prediction with the hosted NVIDIA API or local Docker NIM. Covers endpoint choice, auth, request payloads, output artifacts, confidence scores, and local container setup.
NVIDIAOfficial
Generate synthetic object-detection defect data using AnomalyGenNext 1.1.
Samuel Berthe· Community
Expert guidance on selecting production-ready Go libraries and leveraging the standard library.
Samuel Berthe· Community
Provides guidance and best practices for implementing GraphQL APIs in Go using gqlgen or graphql-go.