Official Agent Skills
Skills published by verified organisations. Every one is reviewed before listing, and the publisher's identity is checked, not just claimed.
-
nvidia Bundle I4h Workflow Dataset ConvertConvert workflow HDF5 recordings to LeRobot datasets for training or browser inspection. Use for conversion; do not use for replay, augmentation, or raw-data repair.
2.2k - nvidia Bundle Nemo Relay Migrate From Flow
Use this skill when migrating applications, examples, integrations, documentation, manifests, or repository code from NeMo Flow to NeMo Relay across Python, Rust, Node.js, Go, C FFI, CLI, configuration, and observability surfaces.
2.2k - nvidia Bundle Paidf Curation And Retrieval
Use when operating PAIDF Curation and Retrieval or NVIDIA Cosmos Curator pipelines (split, filter, caption, embed, dedup, shard, image annotate) or PAIDF Data Mining nearest-neighbor matching on Curator embeddings. Activate for Make or CLI pipeline config, GPU run preflight, FFmpeg sidecar, SAM3 keys, or Curator-to-TAO handoff. Do not use for generic ETL, vector-database RAG, model training, orchestration, or embeddings outside Cosmos Curator and PAIDF Data Mining.
2.2k - nvidia Bundle Rtvi Cv Scaffold Vss Service
Scaffold a standalone RTVI CV microservice that plugs into VSS Search and Alerts profiles via Kafka mdx-raw. The shipped scaffold script is a YOLO26 reference implementation (ONNX, labels, custom parser required). Use when building a new perception microservice repo, validating the VSS integration contract, extending that scaffold for segmentation frame-mask payloads, or scaffolding with placeholders before customer YOLO26 assets exist. For swapping the detector in the stock vss-rt-cv container, use rtvi-cv-customize-model instead. Live DeepStream integration cannot run until the customer-supplied ONNX, labels file, and parser library exist.
2.2k - nvidia Bundle I4h Catheter Navigation Smoke
Run CPU-only fluorosim smoke tests (imports, preprocessing, CLI parsers). Use when asked to smoke-test catheter navigation in CI or without a GPU.
2.2k - nvidia Bundle I4h Workflow Dataset Annotate
Grade or filter workflow HDF5 episodes with an OpenAI-compatible vision model. Use for visual success labels; do not use for replay, policy evaluation, or recordings without frames.
2.2k - nvidia Bundle Medtech Model Evidence Export
Exports sanitized metadata, parameters, reproducibility details, quality metrics, and optional review artifacts from Medical AI inference runs or evidence packs to MLflow. Use after inference, including NV-Generate runs; not for live training tracking, model registration, or clinical use.
2.2k - nvidia Bundle Paidf Orchestration Write Dag
Use when a user describes a custom PAIDF Orchestration pipeline — a specific ordered combination of stages such as augmentation only, auto-labeling only, detection+captioning only, or image attribute augmentation without full auto-labeling — that no existing DAG in airflow/dags/workflows/ covers, and asks for a new Kubernetes DAG. Also use to check that a generated or existing DAG's model/container/prompt choices match an external spec document (e.g. a PAIDF `launchable.md`).
2.2k - nvidia Bundle Doca Structured Tools Contract
Use this skill whenever another DOCA skill says "prefer the structured tool per doca-structured-tools-contract", or when the user wants a one-shot answer that consolidates info multiple manual commands would produce — DOCA env / version / devices / capabilities / validate / host vs DPU state. Trigger even when the user does not explicitly mention "structured tool" or "doca-env --json" — typical implicit phrasings include "is there one command that tells me everything about my DOCA install", "what version is X capability available since", "every PF/VF/SF visible on this BlueField with PCIe address", "will this pipe pass validate before commit", "diff host vs DPU state", or "why does the agent give a one-line answer on host A and five commands on host B". Refuse and route elsewhere for general DOCA orientation, specific library API how-to, or install-from-scratch guidance — those belong to the per-library skill, doca-public-knowledge-map, or doca-setup.
2.2k - nvidia Bundle Nemo Relay Plugin Observability
Use this skill when choosing or configuring NeMo Relay 0.6 or 0.7 observability through the built-in plugin, subscribers, or exporters, including raw ATOF events, ATIF trajectories, OpenTelemetry, OpenInference, or custom event handling.
2.2k - nvidia Bundle Nemo Relay Plugin Adaptive Tuning
Use this skill when baseline NeMo Relay instrumentation exists and the user wants to configure or evaluate adaptive plugin behavior, including telemetry, state, adaptive_hints, tool_parallelism, ACG, hint consumption, or measured rollout.
2.2k - nvidia Bundle Physical AI Event Video Generation
Run the PAIDF Orchestration Event Video Generation DAG on Kubernetes - 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. Runs environment setup first when controller readiness is unknown. Not for person-crop clothing/attribute augmentation (that is image-attribute-augmentation-workflow) and not for video style transfer.
2.2k - nvidia Bundle Tao Generate Referring Expressions
Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region descriptions, scene captions, grounded referring expressions, and (optionally) verified expressions via VLM distillation. Use when the user wants to generate referring-expression annotations from images with KITTI labels, build region descriptions, produce grouped grounding phrases tied to bboxes, run a double-check verification pass on grounding expressions, auto-label traffic / scene images for referring datasets, or run the image_referring_expression pipeline. Triggers include 'referring expression', 'region description', 'KITTI labels', 'spatial relationship annotation', 'auto-label image referring expression', 'image_referring_expression'.
2.2k - nvidia Bundle Tao Route Visual Changenet Samples
Routes the weakest VCN samples (output of `tao-analyze-gaps-visual-changenet`) into per-augmentation-module subsets based on each module's label eligibility. Use when the user asks to "route VCN gap samples", "split AOI gaps for k-NN mining and AnomalyGen", or prepare the immediate next step after DEFT gap analysis in a VCN AOI SDA iteration.
2.2k - nvidia Bundle Tilegym Converting Cutile To Julia
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.
2.2k - nvidia Bundle Tilegym Improve Cutile Kernel Perf
Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints, persistent scheduling, num_ctas, flush_to_zero, and IR-level debugging. Use when asked to "optimize cutile kernel", "improve kernel perf", "tune cutile performance", "make kernel faster", or iteratively benchmark and refine a cuTile GPU kernel in the TileGym project.
2.2k - nvidia Bundle Earth2studio Deterministic Forecast
Build deterministic forecast scripts with Earth2Studio (model, data source, IO, inference). Do NOT use for ensemble, diagnostics, data-only fetch, or install.
2.2k - nvidia Bundle Nemo Automodel Distributed Training
Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.
2.2k - nvidia Bundle Physical AI Defect Image Generation
Use when the user wants to orchestrate defect image generation with NVIDIA Cosmos AnomalyGen (Cosmos-Predict2-derived) on OSMO for PCBA, metal surface, and glass inspection. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint, cosmos defect generation, cosmos-predict2 defect, cosmos-anomalygen, cosmos predict2 finetune.
2.2k - nvidia Bundle Physical AI Video Data Augmentation
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.
2.2k - nvidia Bundle Tilegym Converting Cutile To Triton
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.
2.2k - nvidia Bundle Digital Health Clinical Asr Finetune
Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT for generic word boosting (use /finetune-asr).
2.2k - nvidia Bundle Nemo Mbridge Perf Tp Dp Comm Overlap
Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.
2.2k - nvidia Bundle Nemo Relay Debug Runtime Integration
Use this skill when NeMo Relay is installed or imported but application-side runtime behavior is missing or incorrect, including load failures, inactive scopes, missing events, and plugin or adaptive wiring problems.
2.2k - nvidia Bundle Nemo Relay Instrument Typed Wrappers
Use this skill when adding NeMo Relay typed wrappers, domain types, or provider codecs while preserving JSON middleware semantics and caller-visible behavior.
2.2k - nvidia Bundle Tao Train Metric Learning Recognition
Metric-learning recognition (ml-recog) for fine-grained visual recognition. Learns embeddings for retrieval-based matching (e.g., retail product recognition) using triplet / contrastive losses. Use when training, evaluating, exporting, or running inference for a TAO metric-learning recognition model. Trigger phrases include "train metric learning", "ml-recog", "retrieval embeddings", "triplet loss recognition", "fine-grained matching".
2.2k - nvidia Bundle Nemo Mbridge Perf Activation Recompute
Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute. Use for activation memory OOMs or regressions involving recompute_granularity, recompute_num_layers, recompute_modules, recompute_method, selective recompute, full recompute, or activation checkpointing.
2.2k - nvidia Bundle Nemo Mbridge Perf Moe Hardware Configs
Representative, point-in-time MoE training playbooks by hardware and model family. Use them as candidate seeds, then revalidate the exact runtime, semantics, topology, and steady-state throughput.
2.2k - nvidia Bundle Nemo Relay Instrument Context Isolation
Use this skill when concurrent requests, async tasks, threads, workers, goroutines, or agents need independent NeMo Relay scope stacks and correct ancestry propagation.
2.2k - nvidia Bundle Cuopt Numerical Optimization Formulation
LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.
2.2k - nvidia Bundle Nemo Mbridge Perf Parallelism Strategies
Operational guide for choosing and combining parallelism strategies in Megatron Bridge, including sizing rules, hardware topology mapping, and combined parallelism configuration.
2.2k - nvidia Bundle Physical AI Image Attribute Augmentation
Run the PAIDF Orchestration Image Attribute Augmentation DAG on Kubernetes - person-crop clothing augmentation, attribute search, and augmented dataset generation. Select for requests about image attribute augmentation, person attribute search, person re-identification data, clothing augmentation, attribute captions, augmentation payloads, run status, or result retrieval. Runs environment setup first when controller readiness is unknown. Not for video or defect-image generation.
2.2k - nvidia Bundle Tao Generate Video Reasoning Annotations
Multi-step video annotation pipeline that turns raw videos into Chain-of-Thought training data — multi-level captions, structured descriptions, and QA pairs (MCQ, binary, open-ended) with reasoning traces, via VLM/LLM distillation. Use when the user wants to "create video training data", "generate video QA datasets", "build CoT reasoning traces from videos", "auto-label videos", or run the video_reasoning_annotation pipeline. Triggers include "video annotation", "video CoT", "video QA", "chain-of-thought", "video captioning pipeline", "video distillation".
2.2k - nvidia Bundle Nemo Mbridge Perf Expert Parallel Overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlap_moe_expert_parallel_comm, delay_wgrad_compute, and flex dispatcher backends such as DeepEP and HybridEP.
2.2k - nvidia Bundle Nemo Mbridge Perf Moe Dispatcher Selection
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.
2.2k - nvidia Bundle Nemo Mbridge Perf Moe Optimization Workflow
Evidence-gated workflow for MoE performance optimization in Megatron Bridge. Covers measurement contracts, the Three Walls framework, parallel folding, profiling, matched A/B tuning, and final validation.
2.2k