Engineering
98,147 rows, by stacks then stars
NVIDIA/skills/skills/doca-programming-guide Skill
4,064★ repoUse this skill when the user is writing their first DOCA app or asking a library-agnostic programming question — picking a shipped sample to copy and modify, wiring the canonical pkg-config doca-{library} + meson build (or FFI from Rust / Go / Python against the public C ABI), walking the cfg-create → init → start → use → stop → destroy lifecycle, validating a spec before commit, or decoding a DOCA_ERROR_* return with doca_error_get_descr(). Trigger even when the user does not say "DOCA programming guide" — implicit phrasings: "write my first DOCA program", "meson line for doca_rdma_*", "got DOCA_ERROR_BAD_STATE on my first call", "call DOCA from Rust without writing C", "built clean but nothing on the wire", "what order do doca_*_pipe calls go in". Refuse and route for install / hugepages / pkg-config not resolving doca-{library} (doca-setup), docs or version lookup (doca-public-knowledge-map), and library-internal API construction like Flow pipe topology or RDMA QP setup (matching library skill).
NVIDIA/skills/skills/doca-setup Skill
4,064★ repoUse this skill when the user is dealing with the DOCA environment around their workload — verifying an install is healthy, preparing the build env (pkg-config, headers, LD_LIBRARY_PATH, hugepages, devlink, representors), debugging env-class failures, deciding container-vs-bare-metal deployment shape, or reaching a DOCA install from a host that doesn't have one yet via the NGC DOCA container Stage-1 fallback. Trigger even when the user does not explicitly mention "DOCA setup" — typical implicit phrasings include "I just got a BlueField, what now", "my code is built, how do I run it", "pkg-config can't find doca-flow", "no free 2048 kB hugepages", "representor X not found", "I'm on a Mac and want to learn DOCA". Refuse and route elsewhere for library API specifics (Flow pipes, RDMA queues), the modify-a-sample first-app workflow or DOCA_ERROR_* program-side debugging, and "where is X documented" knowledge-map questions — those belong to other skills.
NVIDIA/skills/skills/doca-spcx-cc Skill
4,064★ repoUse this skill when the user is invoking `doca_spcx_cc` (the host-side CLI under /opt/mellanox/doca/tools/) to load, parameterize, start, observe, or stop a Programmable Congestion Control (SPCX) algorithm on a BlueField with a DPA processor against a live RDMA / RoCE fabric, or picking SPCX vs the established `doca-pcc` surface. Trigger even when the user does not say "DOCA SPCX" or "doca_spcx_cc" — typical implicit phrasings include "I want to write a custom RTT-based CC algorithm for my RoCE fabric", "my SPCX session loaded but throughput / latency didn't change", "doca_pcc status shows Active but factory CC seems to still be in charge", "DOCA_PCC_PS_ERROR on start", "is the programmable-CC surface available on my install", or "DPA-side algorithm image won't load". Refuse and route elsewhere for DPA-side algorithm authoring detail, factory PCC firmware configuration, read-only PCC counter inspection, raw DPA cycle profiling, RDMA library programming, or general DOCA install — those belong to other skills.
NVIDIA/skills/skills/doca-telemetry-exporter Skill
4,064★ repoUse this skill when the user is doing hands-on DOCA Telemetry Exporter programming on a host where DOCA is installed — defining a doca_telemetry_exporter_schema, creating sources, picking counter/gauge/event types, running capability queries before assuming limits, registering schemas before the first emit, or debugging DOCA_ERROR_* failures from the exporter API. Trigger even when the user does not explicitly mention "DOCA Telemetry Exporter" or "doca_telemetry_exporter_*" — typical implicit phrasings include "publishing counters from my DOCA app", "emit returns AGAIN under bulk load", "consumer sees nothing but emit reports success", "NOT_FOUND on first submit", or "should I link the exporter or the telemetry service". Refuse and route elsewhere for the receiving DOCA Telemetry Service, plain stdout logging via doca_log, non-DOCA Prometheus scrape sinks, or real-time event subscription back into the app via doca-comch — those belong to other skills.
NVIDIA/skills/skills/doca-telemetry-utils Skill
4,064★ repoUse this skill when the user is invoking `doca_telemetry_utils` on a host with DOCA installed — discovering the diagnostic-counter schema, translating counter names to binary Data IDs, validating per-device counter support before committing a DOCA Telemetry exporter config, or reverse-resolving a captured Data ID. Trigger even when the user does not explicitly mention "doca_telemetry_utils" or "Data ID" — typical implicit phrasings include "my exporter ships but the collector sees nothing", "this metric silently drops downstream", "which counters does this BlueField expose", "translate this 0x... back to a counter name", "what do node / pcie_index / depth mean here", or "is this counter supported on this device before I commit it". Refuse and route elsewhere for developer-side collector / exporter library programming, DTS deployment, or DOCA install / repair — those belong to doca-telemetry, doca-public-knowledge-map, and doca-setup.
NVIDIA/skills/skills/doca-telemetry Skill
4,064★ repoUse this skill when reading **DOCA hardware-counter events** from a `doca_dev` via the per-domain DOCA Telemetry reader libraries — `doca_telemetry_pcc`, `_dpa`, `_diag`, `_adp_retx`, `_phy`, `_pci`. This is the **counter-READER** surface — there is no NetFlow / IPFIX / local-socket collector framework here; the bundle previously framed it that way and that framing is wrong. Each domain ships its own `doca_telemetry_{domain}_*` API: cap-query `_cap_is_supported(devinfo)`, `_create()` on a `doca_dev`, `_start()`, then per-domain read / sample. Trigger even when the user does not say "DOCA Telemetry" — typical implicit phrasings: "read PCC counters from my BlueField app", "sample DPA counter exports", "expose PHY / PCI / DIAG counters from this `doca_dev`". Refuse and route elsewhere for the publishing / export side (`doca-telemetry-exporter`), DOCA Telemetry Service (DTS) as deployed (out of scope), NetFlow / IPFIX collectors, and plain stdout logging.
NVIDIA/skills/skills/doca-version Skill
4,064★ repoUse this skill when the user is doing DOCA version handling — detecting the installed release, validating the four-way match across pkg-config doca-common, applications/VERSION, doca_caps --version, and bfver/mlnx-release on BlueField, reasoning about NGC container tags, looking up whether a capability is on the installed release, or diagnosing build-vs-runtime drift. Trigger even when the user does not explicitly say "DOCA version" or "four-way match" — typical implicit phrasings include "program built but does nothing on the wire", "undefined reference to a symbol the docs claim exists", "DOCA_ERROR_NOT_SUPPORTED at runtime", "counter didn't increment", "what does `latest` mean for this tag", or "is my LTS still supported". Refuse and route elsewhere for installing or choosing DOCA packages (doca-setup), per-library API/capability questions (matching library skill), the cross-library DOCA_ERROR_* taxonomy (doca-programming-guide), or the general debug ladder (doca-debug) — those belong to other skills.
NVIDIA/skills/skills/dynamo-recipe-runner Skill
4,064★ repoSelect, 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.
NVIDIA/skills/skills/dynamo-router-starter Skill
4,064★ repoStart or patch Dynamo router modes and run router endpoint smoke checks. Use for round-robin, KV-aware, least-loaded, or device-aware routing setup; use recipe-runner for recipe deployment and troubleshoot for failure diagnosis.
NVIDIA/skills/skills/dynamo-troubleshoot Skill
4,064★ repoDiagnose failed or unhealthy Dynamo deployments. Use when pods, model-cache jobs, PVCs, workers, frontend/router health, endpoints, or benchmark jobs fail; use recipe-runner/router-starter before this for normal bring-up.
Earth2studio create diagnostic
NVIDIA/skills/skills/earth2studio-create-diagnostic Skill
4,064★ repoCreate Earth2Studio diagnostic model wrappers for single-step data transformations, including simple derived diagnostics, packaged AutoModel diagnostics, and generative or diffusion diagnostics. Do NOT use for prognostic time-stepping models, data sources, or installation.
NVIDIA/skills/skills/holoscan-setup Skill
4,064★ repoGuides Holoscan SDK installation: inspects the host, assesses platform compatibility, recommends an install method, and delegates to the matching install skill.
NVIDIA/skills/skills/hsb-setup Skill
4,064★ repoClone the latest NVIDIA Holoscan Sensor Bridge repo, ask which supported devkit is being used, configure the host per platform, build the correct demo container, run it, and verify HSB connectivity by pinging 192.168.0.2. Use for Holoscan Sensor Bridge setup, build, container launch, and first-connectivity bring-up.
NVIDIA/skills/skills/hsb-test Skill
4,064★ repoExecute QA test plans on Holoscan Sensor Bridge hardware. Reads a user-provided test document, filters tests by the user's setup, determines which tests can run automatically, executes them with pass/fail evaluation, and produces a structured test results report.
NVIDIA/skills/skills/i4h-catheter-navigation-e2e Skill
4,064★ repoEnd-to-end smoke for catheter navigation covering setup, digital twin, DRR, and unit tests. Use when asked to run the full catheter workflow smoke or demo the v0.7 pipeline.
NVIDIA/skills/skills/i4h-catheter-navigation-setup Skill
4,064★ repoVerify host/GPU requirements and PYTHONPATH for the catheter navigation workflow. Use when asked to set up, install, or bootstrap catheter_navigation, or when hitting import/GPU/slangpy errors.
NVIDIA/skills/skills/i4h-catheter-navigation-smoke Skill
4,064★ repoRun CPU-only fluorosim smoke tests (imports, preprocessing, CLI parsers). Use when asked to smoke-test catheter navigation in CI or without a GPU.
NVIDIA/skills/skills/i4h-workflow-create Skill
4,064★ repoCreate a new agentic env by forking an existing env. Use for new env/task scaffolding, not scene edits or baking.
NVIDIA/skills/skills/i4h-workflow-dataset-annotate Skill
4,064★ repoUse a VLM to verify whether each episode satisfies the env's task description. Use when the user asks to annotate, label episodes, filter demos, or gate finetuning on a success classifier.
NVIDIA/skills/skills/i4h-workflow-dataset-convert Skill
4,064★ repoConvert an agentic HDF5 recording into a LeRobot dataset (parquet, meta, videos). Use when asked to convert HDF5, prepare for training, or export to LeRobot; not for viewing — use [[i4h-lerobot-viz]].
NVIDIA/skills/skills/i4h-workflow-dataset-mimic Skill
4,064★ repoExpand an HDF5 recording by cloning trajectories with action/state noise. Use when asked to mimic, expand, or augment a dataset; not for recording new demos (use [[i4h-workflow-dataset-teleop]]).
NVIDIA/skills/skills/i4h-workflow-dataset-replay Skill
4,064★ repoReplay a recorded HDF5 episode inside Isaac Sim for visual verification. Use when the user asks to replay, play back, or step through an HDF5 recording.
NVIDIA/skills/skills/i4h-workflow-dataset-teleop Skill
4,064★ repoRecord episodes for an agentic env via teleoperation (keyboard, SO-ARM leader, or VR) into HDF5. Use when the user wants to teleop or record human demos.
NVIDIA/skills/skills/i4h-workflow-e2e Skill
4,064★ repoRun the full end-to-end agentic pipeline (record → mimic → annotate → replay → convert → visualize → finetune → validate). Use when asked to run the whole pipeline or do an e2e, smoke, or demo run.
NVIDIA/skills/skills/i4h-workflow-finetune Skill
4,064★ repoFine-tune a GR00T or openpi PI0 policy on a LeRobot dataset. Use when asked to finetune, train, or post-train a policy on demos; not for evaluating a checkpoint (use [[i4h-workflow-validate]]).
NVIDIA/skills/skills/i4h-workflow-scene-edit Skill
4,064★ repoEdit an env's scene in place — objects, cameras, task, success bounds, randomization. Use when asked to edit a scene or launch/run/open an env in edit mode (`--bridge`), incl. a just-created env.
NVIDIA/skills/skills/i4h-workflow-setup Skill
4,064★ repoVerify host requirements and run `workflows/agentic/setup.sh`. Use when asked to set up, install, or bootstrap the agentic workflow, or hits missing `.venv`, third-party checkout, or engine errors.
NVIDIA/skills/skills/i4h-workflow-validate Skill
4,064★ repoValidate, evaluate, or run i4h envs. Use for policy/checkpoint rollouts and scripted state-machine smoke runs.
NVIDIA/skills/skills/i4h-workflow Skill
4,064★ repoOverview of `workflows/agentic/` (IsaacLab-Arena + GR00T/openpi). Use when the user asks what i4h workflow is, what's supported, or where to start.
NVIDIA/skills/skills/jetson-derive-carrier Skill
4,064★ repoBootstrap a custom carrier board by forking carrier files and scaffolding a DT overlay from the reference devkit. Use after jetson-init-source; not for module-level or kernel-DTB changes.
NVIDIA/skills/skills/jetson-diagnostic Skill
4,064★ repoRead-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
NVIDIA/skills/skills/jetson-init-image Skill
4,064★ repoExtract Jetson Linux + sample-rootfs tarballs and run apply_binaries.sh for the active target, then record bsp_image in the profile. Use after jetson-init-target; not for source-tree setup.
NVIDIA/skills/skills/jetson-init-source Skill
4,064★ repoSet up the BSP source workspace: Linux_for_Tegra overlay tracker, bsp_sources, Crosstool-NG toolchain. Use after jetson-init-image; not for fetching inputs.
NVIDIA/skills/skills/jetson-init-target Skill
4,064★ repoAuthor a new Jetson target-platform profile (reference_devkit + optional custom_carrier) and update the active pointer. Use to create a target; not for switching existing profiles.
NVIDIA/skills/skills/jetson-llm-benchmark Skill
4,064★ repoBenchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.
NVIDIA/skills/skills/jetson-llm-serve Skill
4,064★ repoStand up vLLM or SGLang serving on Jetson, using upstream vLLM on Thor and Orin JetPack 7.2+, and NVIDIA-AI-IOT vLLM on older Orin.
NVIDIA/skills/skills/jetson-memory-audit Skill
4,064★ repoMeasure Jetson DRAM/NvMap usage and verify before/after memory reclamation with live audit data.
NVIDIA/skills/skills/jetson-optimize-memory Skill
4,064★ repoReclaim DRAM by disabling unused subsystems across MB1 BCT, MB2 BCT, kernel reserved-memory, and SWIOTLB. Use for headless or no-camera Jetson deployments; not for CPU/GPU frequency tuning.
NVIDIA/skills/skills/launch-nemo-rl Skill
4,064★ repoPlaybook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI. Covers ephemeral vs long-lived RayCluster modes, iterating on runs, and debugging hung or failed training jobs.
NVIDIA/skills/skills/mcore-testing Skill
4,064★ repoTest system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.
Nemo automodel launcher config
NVIDIA/skills/skills/nemo-automodel-launcher-config Skill
4,064★ repoConfigure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
Nemo automodel model onboarding
NVIDIA/skills/skills/nemo-automodel-model-onboarding Skill
4,064★ repoGuide for onboarding new model architectures into NeMo AutoModel, including architecture discovery, implementation patterns, registration, and validation.
Nemo mbridge perf memory tuning
NVIDIA/skills/skills/nemo-mbridge-perf-memory-tuning Skill
4,064★ repoTechniques for reducing peak GPU memory in Megatron Bridge — expandable segments, PEFT + SP input re-gather, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM fixes.
Nemo mbridge perf moe optimization workflow
NVIDIA/skills/skills/nemo-mbridge-perf-moe-optimization-workflow Skill
4,064★ repoSystematic workflow for MoE training optimization in Megatron Bridge, based on the Megatron-Core MoE paper. Covers the Three Walls framework, parallel folding, recompute strategy, dispatcher choice, and CUDA-graph bring-up.
Nemo relay debug runtime integration
NVIDIA/skills/skills/nemo-relay-debug-runtime-integration Skill
4,064★ repoUse 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.
NVIDIA/skills/skills/nemo-relay-install Skill
4,064★ repoUse this skill when choosing or running NeMo Relay installation for the CLI, Python, Node.js, Rust, OpenClaw, Hermes, or maintained framework integrations before runtime configuration or quick-start setup.
Nemo relay plugin observability
NVIDIA/skills/skills/nemo-relay-plugin-observability Skill
4,064★ repoUse this skill when choosing or configuring NeMo Relay observability through the built-in plugin, subscribers, or exporters, including raw ATOF events, ATIF trajectories, OpenTelemetry traces, OpenInference export, or custom event handling.
NVIDIA/skills/skills/nemo-rl-session-memory Skill
4,064★ repoManage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work, handoffs, or any session where important state should be written periodically under the repo's session directory. Do NOT use for: simple questions, short tasks, one-off commands, linting, or code review.
The same file is in 1 other repository
NVIDIA/skills/skills/nemoclaw-user-guide Skill
4,064★ repoGuides human users' AI agents to the NemoClaw docs MCP server and canonical Fern documentation in Markdown form. Use when users ask how to install, configure, operate, troubleshoot, secure, or learn NemoClaw with an AI coding assistant. Trigger keywords - nemoclaw docs, use nemoclaw with ai agent, nemoclaw mcp docs, nemoclaw install help, nemoclaw quickstart, nemoclaw markdown docs, llms.txt, agent skills.
NVIDIA/skills/skills/nemotron-customize Skill
4,064★ repoPlan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or Megatron-Bridge), pretraining/CPT, RL alignment (DPO/RLVR/GRPO/RLHF), BYOB/MCQ benchmarks, checkpoint conversion, ModelOpt optimization, env profiles, and evaluation of trained checkpoints or existing/hosted endpoints. Use when a request names a Nemotron step or workflow, or asks to clean, translate, train, fine-tune, align, convert, optimize, evaluate, or compose these into a pipeline. Do NOT use for frontend/dashboard/visualization work, generic ML advice, billing/access, or non-Nemotron coding tasks.
Omniverse usd performance tuning
NVIDIA/skills/skills/omniverse-usd-performance-tuning Skill
4,064★ repoTop-level workflow skill for USD performance diagnosis and optimization. Use for slow loading, high memory, low FPS, or 'optimize my scene' requests; delegates auth/runtime setup to Phase 0 owners.
Physical ai defect image generation
NVIDIA/skills/skills/physical-ai-defect-image-generation Skill
4,064★ repoUse 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.
Physical ai infrastructure setup and resilient scaling
NVIDIA/skills/skills/physical-ai-infrastructure-setup-and-resilient-scaling Skill
4,064★ repoUse when the user wants to set up, scale, validate, or harden NVIDIA physical AI infrastructure for synthetic data generation workflows across local MicroK8s or Azure AKS, including Kubernetes clusters, inference endpoint deployment, OSMO deployment, workload submission readiness, and infrastructure failure recovery. Trigger keywords: physical ai infrastructure, resilient scaling, SDG infrastructure, microk8s, azure aks, NVCF deployment, NIM Operator, OSMO deploy, workflow scaling. Don't trigger for: OSMO log summarization or workload-only operations unless infrastructure setup, scaling, validation, or recovery is requested.
NVIDIA/skills/skills/physicsnemo-discover Skill
4,064★ repoOfficial NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment setup, training-loop or other code authoring/scaffolding, contributor/CI/packaging questions, repo-specific questions in physicsnemo-sym/-cfd/-curator, or general (non-physics) ML/PyTorch.
NVIDIA/skills/skills/rag-blueprint Skill
4,064★ repoNVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure, troubleshoot, debug, fix, shutdown, stop, or tear down any RAG feature or service (Agentic RAG, VLM, guardrails, query rewriting, models, search, ingestion, observability, summarization, reasoning, and more).
NVIDIA/skills/skills/rag-eval Skill
4,064★ repoFilesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this repo layout.
NVIDIA/skills/skills/rag-perf Skill
4,064★ repoPerformance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / RAGAS scoring (use rag-eval) or for deploying / repairing services (use rag-blueprint).
NVIDIA/skills/skills/tao-analyze-changenet-rca Skill
4,064★ repoPerforms deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with image-evidence-driven investigation. Use when analyzing ChangeNet model failures, investigating poor recall / FAR / PASS-NO_PASS metrics, auditing visual inspection pipeline quality, or running an RCA report for an AOI defect-detection model. Trigger phrases include "RCA on my ChangeNet model", "why is my AOI model failing", "audit ChangeNet predictions", "investigate FAR regressions", "root cause analysis on visual-changenet".
Tao finetune huggingface model
NVIDIA/skills/skills/tao-finetune-huggingface-model Skill
4,064★ repoFine-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.
NVIDIA/skills/skills/tao-launch-workflow Skill
4,064★ repoShared launch intake for any TAO workflow or action. Use when the user wants to run TAO AutoML, train, evaluate, infer, export, generate TensorRT engines, or launch DEFT/workflow jobs on an execution platform.