NVIDIA
- 1.2k skills
- 0 followers
- 23k repo stars
- 561 verified
- 11 hours ago last updated
- ▌ I4h Workflow Validate · nvidia bundleRun the root-level workflow runtime policy or rule-based rollouts and verify simulator success. Use for evaluation, checkpoints, or local controllers; do not use for replay or dataset annotation.
- ▌ Jetson Video Pipeline · nvidia bundleUse when planning, executing, and independently validating Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or concise acceptance workflows.
- ▌ Doca Version · nvidia bundleDOCA version handling: detect the installed release and validate the four-way match across pkg-config doca-common, applications/VERSION, doca_caps --version, and bfver/mlnx-release on BlueField; reason about NGC tags; look up whether a capability exists on this release; diagnose build-vs-runtime drift. Use this skill alongside doca-debug when a symptom smells of version skew: "built but nothing on the wire", "undefined reference to a symbol the docs claim exists", "DOCA_ERROR_NOT_SUPPORTED at runtime", "what does latest mean for this tag", or "is my LTS still supported". Once all four sources match, the component's build / run workflow belongs to its own library, service or tool skill. Refuse install / package choice (doca-setup), per-library API questions (matching library skill), DOCA_ERROR_* taxonomy (doca-programming-guide), and the general debug ladder (doca-debug).
- ▌ I4h Workflow · nvidia bundleOrient users to the i4h workflow runtime and route them to the correct stage skill. Use for architecture, support, or where-to-start questions; do not execute a known stage.
- ▌ Doca Compress · nvidia bundleHardware compression offload with DOCA Compress on a BlueField DPU, ConnectX NIC, or host: DEFLATE compress and decompress, plus LZ4 decompress (stream and block; LZ4 encode is NOT supported), instead of CPU zlib / zstd. Trigger on "offload this gzip", "decompress incoming network data on the NIC", "compress task returns INVALID_VALUE on alloc_init", "submitted a task but no completion arrives", or "decompress LZ4 on the BlueField", even without naming DOCA Compress. Covers enabling compress-deflate, decompress-deflate, decompress-lz4-stream and decompress-lz4-block tasks on a doca_compress context, sizing source / destination doca_buf against the per-task cap query, mmap permissions, offload vs CPU decisions, a round-trip smoke, and DOCA_ERROR_* from Compress calls. Refuse and route elsewhere for zstd / Snappy / brotli, LZ4 encode (a CPU LZ4 library), pure mmap-to-mmap copies (doca-dma), or DOCA Core lifecycle internals.
- ▌ Doca Gpunetio · nvidia bundleUse this skill when the user is doing hands-on DOCA GPUNetIO programming — wiring a CUDA kernel on an NVIDIA GPU to a doca-eth queue via doca_gpu_eth_rxq / doca_gpu_eth_txq, standing up the per-CUDA-device doca_gpu context, designing the persistent CUDA kernel that drains the GPU-visible queue, running the dual capability check (DOCA cap-query plus cudaGetDeviceProperties), registering cudaMalloc pools via doca_buf_arr_create_*, or debugging DOCA_ERROR_* returns from the GPUNetIO API. Trigger even when the user does not explicitly mention "DOCA GPUNetIO" or "persistent kernel" — typical implicit phrasings include "CUDA kernel reading packets directly from the NIC", "GPU-initiated networking on BlueField", "DOCA_ERROR_DRIVER on doca_gpu_create", "nvidia_peermem not loaded", "kernel-per-packet is too slow", or "which GPU supports GPU-side packet I/O". Refuse and route elsewhere for general CUDA programming, DOCA Ethernet queue bring-up, DOCA DPA, or DOCA install — those belong to other skills.
- ▌ Doca Urom Svc · nvidia bundleOperate the DOCA UROM Service container on BlueField Arm for remote memory operations (puts, gets, atomics, collectives) enqueued by a paired host using `doca-urom`: pull the NGC image, choose the UCX component, size queues, configure Comch pairing, and align host and service versions. SECURITY: the service has no standalone access control; Comch pairing and RDMA permissions are the boundary. Pair only intended hosts, expose least-privilege memory regions, and verify both views before start. Trigger for slow UCX collectives, unexpected NOT_PERMITTED, or missing completions. Do not use for host application code, MPI/UCX integration design, or DOCA install.
- ▌ Doca Flow Tune · nvidia bundleUse this skill when the user is tuning a live or captured `doca-flow` pipeline with `doca_flow_tune` — snapshotting pipe / counter / KPI state, picking a tuning axis (rule placement, resource hints / table sizing, HW-offload mode) and a matching measurement (rule-install rate, lookup latency, hardware-counter delta), running offline or online (read-only or state-changing) modes, reading the dumper CSV / analyze JSON / visualize mermaid, or applying a recommendation back into the Flow program. Trigger even when the user does not explicitly mention "doca_flow_tune" — typical implicit phrasings include "Flow rule-install rate is low on BlueField", "table sizing looks wrong for this pipe", "tune visualize step is empty", "before/after counters don't move", or "which doca-flow knob does this recommendation hit". Refuse and route elsewhere for writing the doca-flow application, DOCA install, or streaming Flow telemetry — those belong to other skills.
- ▌ Doca Telemetry · nvidia bundleUse this skill to read DOCA hardware-counter events from a `doca_dev` through the per-domain Telemetry reader libraries: `doca_telemetry_pcc`, `_dpa`, `_diag`, `_adp_retx`, `_phy`, and `_pci`. It covers capability checks, context creation, startup, and per-domain reads or samples. Trigger for implicit requests such as "read PCC counters from my BlueField app", "sample DPA counter exports", or "expose PHY, PCI, or DIAG counters from this doca_dev". This is the counter-reader surface, not a NetFlow, IPFIX, or local-socket collector. Route publishing and export to `doca-telemetry-exporter`; route the deployed DOCA Telemetry Service to `doca-dts`, and collectors and plain stdout logging elsewhere.
- ▌ I4h Lerobot Viz · nvidia bundleServe and visually inspect a converted LeRobot dataset in the browser. Use for videos and state/action timelines; do not use for raw workflow HDF5 or incomplete conversion output.
- ▌ Doca Dpdk Bridge · nvidia bundleUse this skill when the user has an existing DPDK application and is adding DOCA capabilities in-place — most commonly DOCA Flow hardware steering — without rewriting the data-plane in DOCA-native form: binding a DPDK port id to a `doca_dev` (`doca_dpdk_port_probe` / `doca_dpdk_port_as_dev`), converting `rte_mbuf` ↔ `doca_buf`, querying `doca_dpdk_cap_is_rep_port_supported`, or debugging `DOCA_ERROR_*` from a bridge call. Trigger even without "DOCA DPDK Bridge": "how do I add DOCA Flow to my DPDK app", "make a DPDK port visible to DOCA", "the bridge loads but every operation returns errors", "pkg-config --exists doca-dpdk-bridge fails", or "DOCA_ERROR_NOT_FOUND on port registration". Route elsewhere for fresh DOCA-native packet I/O (doca-eth), flow-rule programming (doca-flow), DOCA or DPDK install (doca-setup), or RDMA data movement (doca-rdma).
- ▌ I4h Workflow E2e · nvidia bundleRun the maintained workflow data-to-policy pipeline from recording through checkpoint validation. Use for full end-to-end requests; do not use for one individual stage.
- ▌ Doca Pcc Counters · nvidia bundleUse this skill when the user is invoking the DOCA PCC Counters tool — the `pcc_counters.sh` bash script under the DOCA tools directory — to arm and read the fixed firmware/hardware PCC (Programmable Congestion Control) diagnostic counters (CNP, RTT, WRED-drop, etc.) on a ConnectX / BlueField device via mst + the mlx5 debugfs `diag_cnt` interface. The script takes two positional args — `set | query` and an mst device path — with no `--help` or subcommands. Trigger even without "pcc_counters.sh" or "PCC counters": "how do I read the CNP / RTT / WRED-drop counters", "PCC counter stuck at zero", "the script says Bad Device", or "is congestion control dropping packets on this port?". Route elsewhere for writing a custom PCC algorithm (doca-pcc), factory firmware PCC config, DOCA install, or fleet-wide CC tuning.
- ▌ Doca Socket Relay · nvidia bundleUse this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint, walking the bind → connect → round-trip → admit-fleet smoke, or diagnosing a stuck/silent relay. Trigger even when the user does not explicitly mention "DOCA Socket Relay" — typical implicit phrasings include "move my socket app onto the BlueField without rewriting it", "host app gets ECONNREFUSED on the relay", "relay accepts the connection but bytes never arrive on the DPU side", "first round-trip works, the rest hang", "bridge an AF_UNIX (UDS) socket to a DPU peer over Comch", or "I want a sidecar that forwards my socket to the BlueField". Refuse and route elsewhere for the comch programming API, line-rate raw packet I/O via doca-eth, and DOCA install/bring-up — those belong to other skills.
- ▌ Tao Run On Docker · nvidia bundleThe Docker execution platform for TAO jobs — a local daemon or a remote GPU box via DOCKER_HOST=ssh://user@host. Implements the four-verb consumer contract (submit/status/logs/cancel) over the docker CLI, wired to the job-record, tao-data-io staging, and the redact lint, on top of the underlying docker conventions (--gpus, mounts, NGC auth, inspection, data-root relocation, error modes). Use to run any single-node TAO container action on Docker without the SDK. Trigger keywords — docker, docker run, run on docker, DOCKER_HOST, remote docker, nvcr.io, --gpus, single-node GPU job.
- ▌ I4h Workflow Setup · nvidia bundlePreflight and set up the root-level workflow runtime. Use for installation, missing component environments, or third-party failures; do not use for rollout validation.
- ▌ Jetson Video Setup · nvidia bundleUse when installing, repairing, reusing, inspecting, or verifying readiness of the native NVIDIA Video Codec SDK or PyNvVideoCodec on Jetson, including the one-frame encode/decode smoke test with official samples, and when interpreting what those readiness results, including CPU-buffer and device-memory sample modes, do and do not establish.
- ▌ Doca Rmax · nvidia bundleDOCA Rivermax (doca_rmax) receive streams for timing-precise media over IP (SMPTE ST 2110 video / audio, market data, scientific feeds) on a target BlueField DPU (DOCA Rivermax apps run only there), once the Rivermax libraries and license are installed; getting them is doca-setup / doca-public-knowledge-map territory. Trigger on "ST 2110 receive isn't getting frames", "sub-microsecond jitter on my media receiver", "NOT_SUPPORTED from doca_rmax_init", "no recv events after stream start", or "license check failing on a media receiver", even without naming Rivermax. Covers doca_rmax_in_stream sessions, the SDK + license precondition check, doca_rmax_get_*_supported capability queries, pairing with doca-eth queues and doca-flow steering, and DOCA_ERROR_* from Rivermax calls. Refuse and route elsewhere for programming the underlying queue (doca-eth), steering rules (doca-flow), PTP / clock sync (doca-firefly), or best-effort packet I/O.
- ▌ Doca Urom · nvidia bundleHost-side DOCA UROM library (doca_urom_*): offload an HPC / UCX / MPI application's remote memory operations (puts, gets, atomics, collectives) from the host CPU onto a BlueField DPU. Trigger on "MPI all-reduce burning host CPU", "push UCX traffic onto the BlueField", "first doca_urom call returns NOT_PERMITTED", or "host library and DPU service look out of sync", even without naming DOCA UROM. An offload needs both halves: this host library and the UROM Service on the DPU (doca-urom-svc), which owns deploying that container. Covers creating UROM Service contexts (doca_urom_service_*) and Worker contexts (doca_urom_worker_*) that run plugins on the DPU, discovering plugins via doca_urom_service_get_plugins_list, progressing completions, and DOCA_ERROR_* from doca_urom_* calls. Route elsewhere for UROM Service deployment on the DPU side, MPI / UCX collective algorithm design, and RDMA / RoCE / IB substrate bring-up.
- ▌ Doca Argus · nvidia bundleUse this skill when the user is deploying or operating the DOCA Argus Service — the packaged BlueField-side runtime-security container that watches the BlueField and attached host for suspicious activity, integrity violations, and operational anomalies, and forwards findings to a SIEM (Splunk / ELK / Sentinel / syslog). Covers the four-axis config (detection policy, forwarding, sampling, host coverage), running the NGC container on BlueField Arm, and wiring the forwarder. Trigger even without "DOCA Argus" by name — typical implicit phrasings: "container green but no findings arrive", "false-positive flood in Splunk", or "runtime security on a fleet of BlueField-3s". Refuse and route elsewhere for installing DOCA, SIEM-side ingest stanzas, pre-baked detection-rule packs, and metrics observability (DOCA Telemetry). Argus is NVIDIA's currently- promoted runtime-security framework, superseding the older App Shield library; name it first for new runtime-security work.
- ▌ Doca Bench · nvidia bundleRun `doca_bench` (DOCA 2.7.0 or newer) to measure throughput, bulk latency, precision latency, or maximum bandwidth for RDMA, Compress, AES-GCM, SHA, DMA, EC, Ethernet, Comch, or GPUNetIO on a host or BlueField Arm. Use it to discover enabled benchmark libraries, capture a reproducible command/version/device/environment baseline, compare stable runs against a declared tolerance, or diagnose configuration, device-binding, workload-precondition, and measurement failures. Trigger for requests such as measuring BlueField compression speed, NIC RDMA throughput, crypto latency, or a pre-upgrade baseline. Do not use for application end-to-end timing, custom benchmark code, DOCA installation, or binary patches.
- ▌ Doca Comch · nvidia bundleUse this skill when the user is doing hands-on DOCA Comch work on a host + BlueField pair — bringing up host ↔ DPU PCIe control-plane messaging, picking server (DPU) vs client (host) roles, choosing slow-path send-task / recv-callback vs fast-path producer / consumer, querying max-msg-size or max-clients capabilities, registering connection callbacks, or debugging DOCA_ERROR_* returns from the Comch API. Trigger even when the user does not explicitly mention "DOCA Comch" or "Comm Channel" (renamed in DOCA 2.5) — typical implicit phrasings include "send a control message from host to BlueField over PCIe", "DPU can't see the host representor", "DOCA_ERROR_NOT_PERMITTED on server_create", "DOCA_ERROR_AGAIN on task_send submit", "connect callback never fires", or "stream bulk data from a host driver to a DPU agent". Refuse and route elsewhere for installing DOCA itself, BFB / firmware bring-up, non-Comch DOCA libraries, or deploying Comch apps at scale — those belong to other skills.
- ▌ Doca Debug · nvidia bundleUse this skill when the user is debugging any DOCA symptom — a build that won't compile, a link step that can't resolve a doca_* symbol, a runtime call returning DOCA_ERROR_*, a silent service or tool, or a stack trace / valgrind / core dump — and needs the layered ladder (install → version → build → link → runtime → program → driver), verbosity controls (--sdk-log-level, DOCA_LOG_LEVEL, the doca-{lib}-trace flavor), container-debug constraints, or how to capture state for a Developer Forum post. Trigger even when the user does not say "DOCA debug" — implicit phrasings include "undefined reference to doca_*", "how do I get more logs", "packets aren't reaching the wire", "doca_caps returned nothing", or "hugepages empty in the container". Refuse and route elsewhere for library-specific debug (Flow pipe trace, RDMA QP, Comch stats), env-class pkg-config or hugepages symptoms, the DOCA_ERROR_* taxonomy and lifecycle interpretation, and performance or incident-response work — those belong to other skills.
- ▌ Doca Setup · nvidia bundleUse 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 "just got a BlueField, what now", "code is built, how to run it", "pkg-config can't find doca-flow", "no free 2048 kB hugepages", "representor X not found", "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.
- ▌ Doca Verbs · nvidia bundleRaw verbs inside DOCA Core (doca-verbs): direct control of QP, CQ, PD, SRQ and address-handle objects through doca_verbs_context and doca_verbs_qp_create / doca_verbs_qp_modify / doca_verbs_cq_create, porting libibverbs code into DOCA Core, or a QP attribute, opcode or WR flag the doca-rdma task API does not expose. Trigger on "raw QP attribute the task API does not expose", "porting libibverbs code", "IO_FAILED on WR submit", "QP state transition rejected", or "attach a congestion-control group", even without naming doca-verbs. Refuse and route elsewhere for ordinary doca-rdma / doca-eth / doca-rmax workloads, DOCA install, Core internals, and general libibverbs theory.
- ▌ Doca Common · nvidia bundleUse this skill whenever the user is doing hands-on DOCA programming on a BlueField DPU or ConnectX NIC and needs the foundation primitives every per-library context rests on — walking the doca_ctx lifecycle, discovering doca_dev / doca_devinfo and gating on doca_*_cap_* before trusting a feature, wiring doca_mmap / doca_buf_inventory / doca_buf for zero-copy I/O across libraries, driving doca_pe for completions, or DOCA Log's two-tier (--sdk-log-level vs app-side) model. Trigger even when the user does not say "DOCA Common" — typical implicit phrasings include "my tasks submit but nothing completes", "DOCA_ERROR_BAD_STATE from doca_ctx_start", "--sdk-log-level does nothing for my DOCA_LOG_DBG lines", "share a buf between doca_dma and doca_rdma", or "crashes far from the offending line". Refuse and route elsewhere for per-library questions in isolation (load doca-flow / doca-rdma / doca-eth alongside), installing DOCA (doca-setup), or doc lookup (doca-public-knowledge-map).
- ▌ Doca Devemu · nvidia bundleUse this skill when the user is doing hands-on DOCA Device Emulation on a BlueField DPU — exposing a custom emulated PCIe device the host sees as a real peripheral while DPU-side code runs the backend, picking the sub-library (PCI Generic, virtio-net, virtio-fs), wiring the per-sub-library Core context plus doorbell / DMA primitives, querying `doca_devemu_*_cap_*`, or debugging DOCA_ERROR_* from a `doca_devemu_*` call. Trigger even when the user does not say "devemu" — typical implicit phrasings include "expose a custom PCIe device from BlueField to the host", "host should see a virtio NIC backed by my DPU code", "lspci does not show my emulated device", "device enumerated but no driver binds", "DPU sees nothing when host kicks the queue", or "virtio feature negotiation failed at bind". Refuse and route elsewhere for the packaged DOCA SNAP / Virtio-net Services, host-side virtio kernel drivers, backend body design, or standard BlueField NIC behavior — those belong to other skills.
- ▌ Doca Aes Gcm · nvidia bundleUse this skill when the user is doing hands-on DOCA AES-GCM work on a BlueField DPU or ConnectX NIC — configuring `doca_aes_gcm_task_encrypt` / `_task_decrypt`, querying `doca_aes_gcm_cap_*` for per-key-type (only `DOCA_AES_GCM_KEY_128` / `_256` — AES-192 not supported) and per-task support, sizing plaintext against the max-buf cap, setting source / destination mmap permissions, validating with a NIST GCMVS or RFC 5288 vector, or debugging DOCA_ERROR_* including the security-critical tag-verification-failed outcome on decrypt. Trigger even when the user does not explicitly mention "DOCA AES-GCM" or "AEAD" — typical implicit phrasings: "decrypt completion IO_FAILED", "auth tag isn't verifying", "NOT_PERMITTED on my encrypt buffer", "is AES-192-GCM on this BlueField" (no), or "encrypted record came back tampered". Refuse and route elsewhere for non-GCM AES modes (CBC / CTR / XTS — CPU OpenSSL), key management (KMS / HSM / rotation), SHA (doca-sha), or general AEAD background.
- ▌ Doca Firefly · nvidia bundleUse this skill when the user is operating the DOCA Firefly Service container on BlueField — picking the four PTP configuration axes (role / profile / domain / interface), wiring the BlueField PHC + host follower + consumer workload pairing, deciding whether PTP-grade time is even needed (vs. chrony / NTP), or debugging a Firefly deployment where PTP isn't syncing or the host clock isn't following. Trigger even when the user does not explicitly mention "DOCA Firefly" or "PTP" — typical implicit phrasings include "container green but PTP never advances past LISTENING", "Firefly says synced but the host clock still drifts", "sync acquired but offset is tens of microseconds", "my Rivermax SMPTE workload needs PTP", or "is chrony good enough". Refuse and route elsewhere for installing DOCA, host-side chrony / ptp4l config bodies, PTP topology / boundary-clock design, building DOCA apps that read the disciplined PHC, or other DOCA services (DMS, Flow-Inspector, HBN) — those belong to other skills.
- ▌ Doca Spcx Cc · nvidia bundleUse 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 an SPC-X congestion-control 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.
- ▌ Doca Upgrade · nvidia bundleChanging DOCA versions safely: upgrading or downgrading the host DOCA packages, refreshing the BlueField BFB, bumping the NGC DOCA container tag, or rolling back, with the discipline detect -> report -> ASK -> only then a guided upgrade. Trigger on "is there a newer DOCA", "I want the newest DOCA features, can I just apt upgrade in place", "should I move to the next release", "the upgrade stopped midway and dpkg is in a broken state", "my component is being deprecated, what now", or "roll me back", even without the word upgrade. Detect what is installed, find the newer release, report the gap, then STOP and ask for explicit confirmation; never upgrade automatically. Do not use it for a runtime error on an unchanged install (doca-debug). Version detection alone belongs to doca-version, first-time install to doca-setup, any hardware / firmware / reboot step to doca-hardware-safety, and public-docs or sunset routing to doca-public-knowledge-map.
- ▌ Doca Dma · nvidia bundleUse this skill when the user is doing hands-on DOCA DMA programming — bringing up a doca_dma context, configuring the single doca_dma_task_memcpy task type, sizing buffers via the doca_dma_cap_task_memcpy_* queries, setting LOCAL_READ_ONLY / LOCAL_READ_WRITE permissions on source / destination doca_mmap regions (plus doca_mmap_export_* for cross-peer copies), driving the progress engine, or debugging DOCA_ERROR_* returns. Trigger even when the user does not explicitly mention "DOCA DMA" or "doca_mmap" — typical implicit phrasings include "memcpy host buffer to BlueField without using the CPU", "offload a bulk copy to the DPU", "copy returns NOT_PERMITTED on first submit", "buffer too big for one DMA task", "task submitted but no completion", or "scatter-gather copy between two memory regions". Refuse and route elsewhere for cross-network copies (DOCA RDMA), producer/consumer messaging (DOCA Comch), DOCA Core / progress-engine internals, or DOCA install — those belong to other skills.
- ▌ Doca Dms · nvidia bundleOperate NVIDIA DOCA Management Service on a BlueField, Arm/x86 host, or Kubernetes pod: from DOCA 3.5 the local `dms-cli` (one command per YANG path, no server), and the `dmsd` + `dmspe` service: choose deployment and authentication, configure `-allowed_users` and `dmsgroup`, use gNMI Get/Set, run supported gNOI workflows, and debug frontend/backend failures. Trigger even without "DMS" for "manage a remote BlueField over gRPC", "gNOI reboot from orchestrator", or fleet-management requests. SAFETY: reboot, OS install, factory-reset, and managed-file deletion are destructive and require target-bound explicit confirmation; never invoke them speculatively. Route installation and library/API build questions elsewhere, and route telemetry streaming and aggregation to doca-dts (DOCA Telemetry Service).
- ▌ Doca Dpa · nvidia bundleUse this skill when the user is doing hands-on DOCA DPA host-side work on a BlueField — creating the `doca_dpa` Core context, loading a DPACC-compiled DPA app image (`doca_dpa_app`), creating DPA threads, launching kernels via `doca_dpa_kernel_launch_update_*`, draining `doca_dpa_completion`, running `doca_dpa_cap_*` discovery, choosing between the DPA comm component (inter-DPA messaging) and the DPA verbs component (in-kernel RDMA), or debugging `DOCA_ERROR_*` from `doca_dpa_*`. Trigger even without "DOCA DPA" or "Data-Path Accelerator": "run compute on the DPA from my host", "DPA kernel hangs, no completion", "DOCA_ERROR_DRIVER on launch", "DOCA/DPACC version skew", or "does this BlueField expose a DPA". Route elsewhere for DPA-side kernel programming itself, DPACC compiler internals, host↔DPU messaging (doca-comch), host-side RDMA (doca-rdma), and GPU-initiated networking (doca-gpunetio).
- ▌ Doca Eth · nvidia bundleUse this skill for hands-on DOCA Ethernet packet-queue work on a BlueField DPU or ConnectX NIC — bringing up a `doca_eth_rxq` or `doca_eth_txq` on a port / representor / SF, picking among the four `enum doca_eth_rxq_type` values (`_REGULAR` / `_CYCLIC` / `_MANAGED_MEMPOOL` / `_SHARED_MEMPOOL`), sizing burst or scatter-gather length against the `_cap_*` queries, submitting `doca_eth_txq_task_send` / `_lso_send` (carrying packet `doca_buf`s — no `doca_eth_frame` struct exists), or debugging DOCA_ERROR_* from an Ethernet call. `doca_eth_rxq` and `doca_eth_txq` are two Core contexts; one `doca_ctx_start()` does not cover both. Trigger on implicit phrasings: "my RX queue is up but no packets arrive", "send-task returns AGAIN at line rate", "which queue type for fixed-MTU ingress", "device open fails without sudo", or "is L3 checksum offload available here". Refuse and route elsewhere for installing DOCA, flow-rule / steering programming, host↔DPU control messaging, or RDMA data movement.
- ▌ Doca Pcc · nvidia bundleUse this skill when the user is doing hands-on host-side DOCA PCC work to load a CUSTOM Programmable Congestion Control algorithm onto a BlueField DPU — creating per-port `doca_pcc` contexts, loading a `dpacc`-compiled `doca_pcc_app` onto the `doca_dev` for the RoCE-bearing port, parameterizing it, walking triple-axis capability discovery (DOCA cap-query + DPA-capable BlueField + firmware custom-PCC slot enabled), or debugging `DOCA_ERROR_*` from `doca_pcc_*`. Trigger even without explicit "DOCA PCC" phrasing — implicit forms include "loading my own congestion control onto a BF port", "DOCA_ERROR_NOT_PERMITTED on algorithm load", "DOCA_ERROR_DRIVER when I attach my custom algorithm", "my custom rate-update isn't affecting RoCE traffic", or "load succeeds but no on-wire change". Refuse and route elsewhere for DPA-side algorithm-body design, the `pcc_counters` CLI, default factory PCC in ConnectX firmware, or setting up the RDMA / RoCE traffic — those belong to other skills.
- ▌ Doca Sha · nvidia bundleUse this skill when the user needs SHA-1, SHA-256, or SHA-512 digest acceleration on BlueField-2 silicon via doca_sha (absent on BF-3) — selecting one-shot `doca_sha_task_hash` versus incremental `doca_sha_task_partial_hash` for chunked input, consulting `doca_sha_cap_*` for per-algorithm digest-size limits and input alignment, or decoding DOCA_ERROR_* statuses such as BAD_STATE on a resumed partial hash. Also load it for implied asks like "accelerate SHA-256 on the NIC", "streaming digest over chunks", "digest output size mismatch", or "is SHA-512 present on this card". Refuse and route to the proper owner for cryptographic-hash theory (collision resistance, SHA-3 selection), the AES-GCM / Compress / DMA libraries, or SDK install and BFB bring-up.
- ▌ Doca Sta · nvidia bundleUse this skill when the user builds an NVMe-over-Fabrics storage target on BlueField with DOCA STA — instantiating doca_sta, declaring doca_sta_subsystem NQNs and namespaces over local NVMe disks via doca_sta_be, validating platform support with doca_sta_cap_is_supported, sizing I/O queue depth, or decoding DOCA_ERROR_* statuses such as IO_FAILED on NVMe reads. Also load it for implied asks like "Identify Controller times out over RoCE", "offload the nvmf target", "NVMe-oF Connect never completes", or "16 I/O queues at depth 1024 — supported?". Refuse and route to the proper owner for raw RDMA movement, packet I/O, steering rules, initiator-side NVMe, or SDK install.
- ▌ Doca Argp · nvidia bundleUse this skill for hands-on DOCA Arg Parser CLI work on a shipped sample or new DOCA-using app — adding / removing / renaming flags; wiring `doca_argp_init` → register params → `doca_argp_start` → `doca_argp_destroy` in order; picking a parameter type from the full public enum (`DOCA_ARGP_TYPE_STRING`, `_INT`, `_BOOLEAN`, `_DEVICE`, `_DEVICE_REP`, `_DOUBLE` — six values, not three); preserving the built-in DOCA flags (`-h` `-v` `-l` `--sdk-log-level` `--log-filter` `-j`/`--json`, NOT `--json-config`); `--device` is per-program; or debugging `DOCA_ERROR_BAD_STATE` / `INVALID_VALUE` / `NOT_SUPPORTED` / `IO_FAILED` from `doca_argp_*`. Trigger on implicit phrasings: "add a custom flag to a DOCA sample", "should I use getopt here", "BAD_STATE registering a new param", "my JSON config key is rejected", or "my sample's --json is ignored". Refuse and route elsewhere for variadic-flag / subcommand / shell-completion features, DOCA Core context, or DOCA Log internals.
- ▌ Doca Caps · nvidia bundleUse this skill when the user wants to invoke the read-only doca_caps CLI to ask what DOCA sees on this host — listing DOCA devices and PCIe addresses, listing representor devices, asking which DOCA libraries are available on the current OS, checking per-device per-library capabilities, scoping output to a specific PCIe address, or capturing a side-effect-free capability snapshot for debug or install smoke-test. Trigger even when the user does not explicitly mention "doca_caps" or "capabilities print tool" — typical implicit phrasings include "what does DOCA actually see on this box", "is my BlueField PF visible to DOCA", "is Flow available on my RHEL host", "enumerate VF representors for pf0", "doca_caps: command not found", or "empty output for RDMA, is the tool broken". Refuse and route elsewhere for DOCA installation (doca-setup owns it; never walk the steps), library-internal capability matrices (Flow pipe creation, RDMA verbs features), streaming telemetry / DTS, or modifying the shipped binary.
- ▌ Doca Flow · nvidia bundleDOCA Flow packet steering on NVIDIA NICs/DPUs, linked into a C application: match/action pipes, ports, representors, forwarding, hairpin, counters. Trigger on packet steering, classifier, rule-matching, representor, hairpin or 5-tuple-to-queue questions even when "DOCA Flow" is not named. Also covers pipe validation before hardware programming, Flow/DOCA version match, and Flow API errors. First app: follow the local bundle (doca-setup, doca-programming-guide, doca-flow, doca-public-knowledge-map). Stage 1 pull nvcr.io/nvidia/doca/doca (NGC catalog tag, never invent); Stage 2 needs a real NIC. Then ls samples inside the container; never emit main.c, a Dockerfile, or hand-typed -l flags. Route software-only host pipelines, plain DPDK `rte_flow`, kernel TC, OVS, BFB bring-up, and DPU OS installation elsewhere. DPU OS installation is destructive and always requires explicit confirmation.
- ▌ Doca Mgmt · nvidia bundleUse this skill when the user is doing hands-on DOCA Management programming against BlueField / ConnectX devices — standing up a management or representor context (doca_mgmt_dev_ctx / doca_mgmt_dev_rep_ctx), querying device caps (data-direct, caps-general), toggling congestion-control global status, modifying diagnostics-data, setting ICM quotas, or issuing a raw firmware command via doca_mgmt_raw_cmd with the right scope (CONFIGURATION / DEBUG_READ_ONLY / DEBUG_WRITE / DEBUG_WRITE_FULL). Trigger even when the user does not say "DOCA Management" — typical implicit phrasings include "fleet tool that walks every BlueField and reads device state", "toggle data-direct on a VF", "set an ICM quota per representor", "send a raw firmware command from C", "DOCA_ERROR_IO_FAILED from raw_cmd", or "fwctl ioctl is failing". Refuse and route elsewhere for mlxconfig direct operation, BFB / firmware reflash, streaming telemetry, doca_caps CLI snapshots, or DOCA install itself — those belong to other skills.
- ▌ Doca Rdma · nvidia bundleRDMA data movement on NVIDIA BlueField/ConnectX NICs (RoCE/InfiniBand) with DOCA RDMA, instead of hand-written libibverbs/rdma_cm. Use when the user moves data between processes or hosts over the NIC, or hits "one-sided read returns permission denied", "completions never arrive after submit", "connection callback never fires", atomic compare-and-swap over RoCE, or DOCA_ERROR_FULL on the send queue under burst, even without naming DOCA RDMA. Covers bringing up an RDMA context on a doca_dev, connection methods (RDMA CM, bridge/OOB, or gRPC exchange of doca_rdma_export()), the eleven task types (Send/Receive/Send-Imm, Read/Write/Write-Imm, Atomic CmpSwap/FetchAdd, Get/Set/Add Remote Sync Event), matching mmap + RDMA permissions, queue and connection sizing, doca_rdma_cap_* queries, and DOCA_ERROR_* from RDMA calls. Raw QP/verbs control belongs to doca-verbs. Refuse and route elsewhere for general RDMA / ibverbs theory (queue pairs, MRs, RoCE vs IB), installing DOCA itself, or non-RDMA DOCA libraries.
- ▌ Cuopt Numerical Optimization API · nvidia bundleLP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.
- ▌ Doca Pipeline Language Developer Tools · nvidia bundleUse this skill when the operator is driving the DOCA Pipeline Language (DPL) Developer Tools to inspect or debug DPL programs on a BlueField DPU — DPL Nspect for runtime state such as tables, keys, and counters, DPL Debugger for packet flow, DPL Admin for dynamic configuration changes in the DPL Runtime Daemon, P4 Runtime Shell as a P4Runtime control plane manager, or DPL Runtime Controller SDK for custom P4Runtime applications and DPL shared memory APIs. Trigger even when the user does not explicitly mention "DPL Developer Tools" — implicit phrasings include "inspect the DPL tables on the DPU", "why can't I start a DPL debug session", "change a dpl_rtd configuration item without restarting", "build my own P4Runtime app for DPL", or "visualize packet flow through my DPL program". Refuse and route elsewhere: authoring, compiling and deploying DPL programs to the DOCA Pipeline Language Service Guide, DOCA install/bring-up to doca-setup, and hardware or firmware state changes to doca-hardware-safety.
- ▌ Isaac Cable Insertion Policy Deployment · nvidia bundleExport 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.
- ▌ Cdf Autonomous Vehicle Dataset Generation · nvidia bundlePrepare payloads, run and monitor the Autonomous Vehicle Dataset Generation Airflow workflow, and inspect results for driving-clip retrieval and Cosmos3-Nano variants. Existing clips with no retrieval use cdf-video-data-augmentation; seed-image event or anomaly generation uses cdf-event-video-generation.
- ▌ Ambient Healthcare Agent With Nemotron Voice Agent · nvidia bundleCustomize NVIDIA Nemotron Voice Agent's Generic Pipecat example for healthcare appointment, five-field patient intake, or custom tool-calling workflows without a separate backend.
- ▌ Cdf Image Attribute Augmentation · nvidia bundleRun the CDF 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.
- ▌ Nvshmem Collect Performance Data · nvidia bundleCollect and package NVSHMEM put/get bandwidth, latency, and other perftest results with system and topology evidence for performance sanity checks.
- ▌ Nvshmem Configure Nic Pe Mapping · nvidia bundleRecommend NVSHMEM NIC-to-PE mappings and environment exports. Use for HCA selection, multi-NIC configuration, or topology-based mapping diagnostics.
- ▌ Runai Get Cluster Health Summary · nvidia bundlePoint-in-time Run:ai cluster and node-health check: a HEALTHY, DEGRADED, or STUCK verdict per node pool with the dominant blocker — NotReady nodes, offline or failing GPU capacity, GPU counts, allocation vs utilization, the pending backlog, and a stuck scheduler vs a full pool. Use for "is the cluster healthy?", "is the scheduler stuck?", "any nodes down?", "are GPUs failing?", "how many GPUs are free?", "is the cluster saturated?", or "why isn't node pool X scheduling?". Not for quota fairness, team GPU waste, one workload, failed-workload node correlation, XID errors on one node, or writes.
- ▌ Runai Get Workload Health Summary · nvidia bundleSummarizes scoped Run:ai workload health or one workload. Not for root cause, quota, cluster health, fleet utilization, history, or mutations.
- ▌ Compute Sanitizer Diagnose Cuda Bugs · nvidia bundleDetect and diagnose CUDA correctness bugs with NVIDIA Compute Sanitizer. Routes GPU memory errors, shared-memory data races, uninitialized-memory reads, and synchronization/barrier bugs to the right sub-tool (memcheck, racecheck, initcheck, synccheck) and explains how to build, run, and read the report. Use when debugging illegal memory access, out-of-bounds, misaligned access, leaks, WAW/WAR/RAW races, __shared__ hazards, uninitialized reads, garbage results, hangs, divergent __syncthreads/__syncwarp, or cuda::barrier / wgmma issues. Do NOT use for host/CPU-side bugs (use valgrind or AddressSanitizer) or global-memory data races (out of scope). Trigger keywords - compute-sanitizer, memcheck, racecheck, initcheck, synccheck, CUDA memory error, OOB, race condition, uninitialized memory, __syncthreads, barrier, deadlock.
- ▌ Doca Telemetry Traceback Application · nvidia bundleUse this skill when the operator is driving the DOCA Telemetry Traceback application to monitor telemetry data locally on a BlueField DPU or ConnectX NIC, detect long-term trends and threshold breaches with user-defined rules, and capture pre-event history plus active-event data to a log file. Trigger even when the user does not explicitly mention "DOCA Telemetry Traceback" — typical implicit phrasings include "monitor telemetry trends on the DPU without streaming all raw data", "log the samples before and after a threshold breach", "set up a rule that triggers when rx bytes/s exceeds 1M", "differential greater than rule on a data ID", "circular buffer of telemetry samples", or "traceback event log". Refuse and route elsewhere: the DOCA Telemetry Diag programming API and raw counter reads to doca-telemetry, DOCA install/bring-up to doca-setup, and version questions to doca-version.
- ▌ Nvshmem Troubleshoot And Report Bugs · nvidia bundleDiagnose NVSHMEM runtime failures and prepare bug reports for launch, crashes, hangs, correctness, transport, or topology issues.
- ▌ Isaac Cable Insertion Policy Training · nvidia bundleSet up the standalone IsaacLabTraining package from NVIDIA-ISAAC-ROS/isaac_ros_manipulation, then launch, monitor, resume, evaluate, and tune DisplayPort insertion policies without a separate Isaac Lab source installation. Use for setup and campaign planning, dependency repair, curriculum or PhysX troubleshooting, video evidence, and long GPU runs.
- ▌ Complexa Evaluate Pdbs · nvidia bundleAgent runbook for evaluating an existing PDB directory through the separately installed first-party Proteina-Complexa CLI. Use to refold or score designs, compute interface pAE, i_pLDDT, scRMSD, motif RMSD, or designability, run complexa analysis, or assess third-party BindCraft, AlphaProteo, or RFdiffusion outputs. SKILL.md selects and invokes the evaluation configuration; bundled executables only inspect local readiness and write a run manifest.
- ▌ Kermt Pretrain Scratch · nvidia bundlePretrain a fresh KERMT model from scratch on a user-provided corpus. Builds a new vocabulary from the corpus, instantiates the model architecture from defaults, and launches pretrain_ddp.py inside the kermt container (detached for long runs). Unlike kermt-continue-pretrain, no starting checkpoint is loaded — the model is randomly initialized.
- ▌ Isaac Mission Control Showcase · nvidia bundleRun and validate an end-to-end Mission Control showcase with a locally installed Isaac Sim launched in its GUI window, driven through the isaac-sim-remote Python server, with Nova Carter SIL. Use for demos, showcase replays, Mission Control driving a simulated robot, or diagnosing the integrated small-warehouse scenario. Detect existing Isaac Sim installations without modifying them, automatically select a usable runtime without prompting whenever compatibility can be confirmed, and delegate requested installation or version changes to isaac-sim-installation. Defaults to a canonical Isaac 6.1 warehouse and deterministic circular route when the user does not specify another scenario.
- ▌ Runai Diagnose Failed Workload · nvidia bundleUse to diagnose failed, crashed, stopped, OOMKilled, CrashLoopBackOff, ImagePullBackOff, init, mount, node, or policy-terminated Run:ai workloads. Investigate one workload's failure; use other skills for workload health summaries, cluster health, scheduling-only Pending, or inference latency without a confirmed failure.
- ▌ Runai Get Utilization Overview · nvidia bundleGPU efficiency check for a Run:ai cluster: are the GPUs that projects, departments, and node pools hold actually computing? Classifies holders as WELL_UTILIZED, UNDER_UTILIZED, or IDLE from average and p95 GPU utilization over one window of any length (default 7 days), quantifies idle GPUs and GPU-hours, and names idle workloads. Use for "which projects hold GPUs but aren't using them?", "GPU utilization by project or department", "where are we wasting GPU cycles?", "is llm-serving actually busy? its GPU memory is full", "is project X actually using its GPUs?", "which workloads in project X are idle?", "which node pool wastes the most GPUs?", or "idle GPU-hours per project last quarter". For "find the idle GPUs and stop them" it answers the read part only. Not for quota fairness, cluster health or free capacity, one workload's status, comparing windows, forecasts, or prices.
- ▌ Kermt Add Cmim Pretrain · nvidia bundleConvert a grover_base checkpoint (encoder-only or encoder + vocab heads) into a hybrid checkpoint by adding a randomly-initialized cMIM decoder + latent_dist, then continue pretraining on the user's corpus as hybrid (vocab + contrast). Effectively kermt-continue-pretrain with a one-time ckpt-conversion step prepended.
- ▌ Kermt Continue Pretrain · nvidia bundleContinue KERMT pretraining on a custom SMILES corpus with a grover_base, cmim, or hybrid checkpoint. Use a local checkpoint or optionally download a pinned Hugging Face model bundle using HF_TOKEN if configured. Run containerized training and write model bundles, prepared data, logs, and checkpoints to user-selected host directories.
- ▌ Nvshmem Select Remote Transport · nvidia bundleSelect an NVSHMEM remote transport from target system and kernel evidence. Use for inter-node selection, compatibility checks, or configuration.
- ▌ Holoscan App Debug Build Run · nvidia bundleUse when a concrete holoscan command in holoscan-applications or a standalone Module fails, hangs, regresses, or returns wrong output.
- ▌ Isaac Humanoid Cloud Control · nvidia bundleRun streamed Unitree G1 cloud-navigation demos in Isaac Sim with guarded gantry release. Use for demo, destination, Mission Control, or cleanup requests.
- ▌ Nemotron Voice Agent Builder · nvidia bundleCreate, refine, or fix NVIDIA voice agents (Cascaded or Omni) with Pipecat or LiveKit. Use when building, scaffolding, or iterating on a real-time voice-agent pipeline, including speech (ASR/TTS) customization and cloud or local deployment. Not for offline/batch speech-to-text, text-only chat or RAG, or generic Docker or CUDA work unrelated to a voice agent.
- ▌ Physical AI Physics Selection · nvidia bundleChoose a physics engine and integration for robot learning, manipulation, assembly, differentiable optimization, or other Physical AI simulation. Compare Newton, PhysX, MuJoCo/MJX, Bullet/PyBullet, VSim Robotics, Genesis, and Drake. Evaluate Newton first for suitable new workflows, select ovnewton when supported shared-stage integration adds value, then verify setup. Use for simulator comparisons, migration decisions, and Newton/ovnewton first-run issues; preserve an explicitly chosen engine.
- ▌ Tao Generate Image Embeddings · nvidia bundleRun TAO Data Services image embedding to turn a parquet of image filepaths into an embedding parquet using CLIP, SigLIP, or a TAO checkpoint. Use when a workflow needs embeddings before nearest-neighbor or unique-neighbor mining, or when the user asks to "embed images", "compute image embeddings", or "generate SigLIP embeddings".
- ▌ Tao Token Efficient Execution · nvidia bundleToken-efficient execution kit for repeated TAO agentic workflows. Compiles a skill into stage cards once (with a strong model), then executes them forever in fresh, small headless sessions coordinated by a bash driver — measured 67-91% token reduction and 3-5x lower peak context vs one long conversation. Use when a TAO workflow will be run repeatedly, when token cost matters, when the target model has a small context window, or on trigger phrases like "token efficient", "reduce token cost", "card pack", "stage cards", "run this workflow on a small model", "compile this skill into cards".
- ▌ Cdf Defect Image Generation · nvidia bundleGenerate synthetic PCB inspection images on Kubernetes with the SMT Defect Image Generation (DIG) DAG in CDF Orchestration. The DAG renders components in simulation, turns the renders into realistic golden images (sim2real), and uses AnomalyGen to add texture defects such as solder bridges, excess solder or missing components. Simulation can also render shift, tombstone and sideflip pose defects. Use it to build DIG payloads, pick a pipeline mode (full, simulation, sim2real or defect-only), check GPU readiness, follow a run, and match each defect image to its golden and simulated source. Not for running Simulation, Augmentation or AnomalyGen on their own.
- ▌ Cdf Orchestration Preflight · nvidia bundleSet up missing Linux prerequisites and audit whether a Cosmos Data Factory (CDF) Orchestration checkout and its Kubernetes or OSMO environment are ready to install the controller and run every packaged DAG. Use for prerequisite, pre-setup, Kubernetes, GPU, RWX/NFS, credential, controller-readiness, and quick-start checks. Not for deploying the controller (use cdf-orchestration-setup, which calls this audit first), authoring payloads, or running workflows.
- ▌ Cdf Orchestration Write Dag · nvidia bundleUse when a user describes a custom CDF 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 CDF `launchable.md`). Not for requests that an existing DAG already covers, including payload-only changes such as different inputs, endpoints, models, or variant counts — route those to the matching workflow skill, unless the user still wants a separate DAG after being pointed to it.
- ▌ Cdf Video Data Augmentation · nvidia bundleRun the CDF Video Data Augmentation Airflow workflow on Kubernetes or OSMO to create Cosmos video-to-video variants and auto-label both source and generated videos. Use for VDA payload authoring, preflight, execution, monitoring, output verification, or result retrieval. OSMO requires external endpoints. Standalone augmentation or auto-labeling configuration belongs to the respective component skill. Not for retrieval-driven CDF pipelines or image-to-video event generation.
- ▌ Cdf Curation And Retrieval · nvidia bundleNVIDIA CDF curation and retrieval. Cosmos Curator video and image pipelines (split, dedup, shard, annotate) with filtering, captioning, and embedding. Cosmos Dataset Search ingest, search, and capability qualification. TAO data mining embeddings and neighbor matching. Ships domain event catalogs, including workplace employee conduct monitoring, which requires legal review before use. Use when a request names Cosmos Curator, Cosmos Dataset Search, CDF, or their Make and CLI surfaces. Not for model training, orchestration, or unrelated dataset questions.
- ▌ Cdf Event Video Generation · nvidia bundleRun 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.
- ▌ Nvidia Ontology Management · nvidia bundleModel and publish semantic definitions in Auto Ontology. Use for terms, relationships, measures, imports, and governed results—not deployment or querying.
- ▌ Omniverse Content Services · nvidia bundleOmniverse Content Services, also discoverable as Omniverse Content Workspace or USD Content Workspace. Use for USD content collaboration as well as content access. Guide USD workflows on existing infrastructure, USD content versioning, 3D creation pipelines, and data access across distributed and scale-out compute. Use for manufacturing, automotive, factory and digital-twin workflows, architecture and construction, media and 3D content, robotics, fleet simulation, and physical AI content delivery. Discover requirements and route to ovstorage, ovpackage, ovlive, usd-content-workspace, and usd-caches experts.
- ▌ Runai Audit Assigned Quota · nvidia bundleAudit GPU quota fairness across a Run:ai cluster — find which projects are starved and which are borrowing over their deserved quota in each node pool, and where GPUs can be reclaimed. Use when an admin asks "who is over quota in node-pool X", "which projects are starved", "is the cluster shared fairly", "where can I reclaim GPUs", "show deserved vs allocated by project or department", or when a team reports it can't get GPUs and you suspect unfair borrowing. This is the quota / fairness axis (deserved vs allocated). For idle-but-held GPUs use runai-get-utilization-overview; for a health/scheduling verdict use runai-get-cluster-health-summary.
- ▌ Tao Mine Nearest Neighbors · nvidia bundleRun TAO Data Services TMM nearest-neighbor mining from embedding parquet files. Use when a workflow needs to mine source samples closest to target samples.
- ▌ Tao Run Deft Cr Its Mining · nvidia bundleRun the mining-based DEFT improvement workflow for ITS Cosmos-Reason binary video questions, focused on the non-reasoning classification/evaluation path. Use when the user asks for a DEFT CR ITS mining workflow, traffic-camera Cosmos Reason improvement loop, collision-identification workflow with data mining, or iterative Cosmos-RL refinement driven by gap analysis.
- ▌ Foundationpose Pipeline · nvidia bundleAdapt BOP datasets, run the FoundationPose perception pipeline with TAO depth, and evaluate or re-score pose results. Use for dataset runs and result comparisons; environment installation belongs to foundationpose-setup.
- ▌ Tao Analyze Gaps Od Map · nvidia bundleRun TAO Data Services object-detection gap analysis from ground-truth and inference annotations. Use when an object detection workflow needs to identify weak images by comparing model predictions against ground truth using per-class recall, precision, and AP50 thresholds. Use when the user asks to "analyze OD gaps", "find weak OD images", or "run mAP gap analysis".
- ▌ Tao Finetune Video Clip · nvidia bundleInternVideo2-CLIP L14 (TAO video_clip) for video-text retrieval, zero-shot classification, embedding extraction, LoRA fine-tuning, ONNX export, and TensorRT deployment. Use when the user asks to "fine-tune IV2CLIP", "run video_clip train/evaluate/inference/export", "build a Video-CLIP TensorRT engine", "InternVideo2-CLIP on KPI chunks", or "TAO video_clip on vadr1_chunks JSON".
- ▌ Codonfm Finetune · nvidia bundleFine-tune public CodonFM Encodon checkpoints on labeled coding-sequence or coding-variant data using LoRA, head-only, or full fine-tuning. Use when a user explicitly asks to fine-tune CodonFM or Encodon for regression or classification. Support generic public-v1 Encodon workflows only; reject Decodon, MissenseDataset, missense_synom_agg, and generation workflows.
- ▌ Nvshmem Tune Performance · nvidia bundleRoute NVSHMEM tuning to data collection, remote transport, NIC-to-PE mapping, or TMA. Do not use for unrelated CUDA, NCCL, or application tuning.
- ▌ Rfd4 Proteina Nim · nvidia bundleRun RFD4-Proteina NIM for joint protein structure and sequence design, conditioned generation, and reward-guided search using the NVIDIA hosted API or a self-hosted NIM. Not for the older RFdiffusion contigs API.
- ▌ Cudf Query Engine Builder · nvidia bundleBuild the first native, single-GPU cuDF path in a query engine, or complete its initial adapter. Use for libcudf C++ or cuDF Java implementation, buffer ownership, worker readiness and CPU/reference comparison, including identifying missing POC inputs. Excludes standalone dataframe analysis, cuDF mainline changes, production integration and distributed or multi-GPU execution. Bundled maintainer evaluations use CPU simulations and source review; they do not run CUDA.
- ▌ Holoscan Module Lifecycle · nvidia bundleDevelop external Holoscan Modules with the Holoscan CLI and use them in Holoscan applications: scaffold, test, Python bindings, DEB/WHEEL packaging, and clean-consumer proof.
- ▌ Tao Analyze Detection Kpi · nvidia bundleRun TAO Data Services KPI analysis for object detection, comparing inference annotations against ground truth to compute per-class TP/FP/FN/TN, precision, recall, accuracy, and AP at a fixed IoU. Use when an object detection workflow needs per-class mAP reported after inference, or when the user asks to "run KPI analyze", "compute detection mAP", or "score my OD predictions against ground truth".
- ▌ Msa Search Nim · nvidia bundleGenerate multiple sequence alignments (MSAs) for protein sequences using the ColabFold MSA-Search NIM. Use for homolog search, UniRef30/ColabFold env searches, A3M or FASTA alignments, paired MSA search for complexes, PDB70 structural templates, hosted NVIDIA API calls, or local Docker deployment. For local deployment, download the databases in parallel with aria2c and launch via NIM_MODEL_NAME (the recommended default fast path, ~14 min vs over 80 min for the built-in downloader); a plain docker run uses the slow built-in downloader.
- ▌ Nvmolkit Usage · nvidia bundleUse when writing or debugging nvMolKit Python code for GPU-accelerated RDKit fingerprints, similarity, conformers, clustering, and molecular searches.
- ▌ Tao Generate Anomalies · nvidia bundleFull PAIDF AnomalyGen pipeline — fine-tune on a new anomaly dataset, generate synthetic anomaly images (SDG), evaluate quality (nn_score), and search per-sample (guidance, crop_ratio) parameters. Three modes: full (Phase 0→7: finetune then generate), finetune_only (Phase 0→1: train only), inference_only (Phase 0, 2→7: generate from an existing checkpoint). Use when the user asks to "fine-tune AnomalyGen", "generate anomaly images", "run PAIDF SDG", "evaluate SDG output quality", "run per-sample search", or run any part of the AnomalyGen pipeline, even if they only mention one phase.
- ▌ Complexa Target · nvidia bundleAdd, edit, inspect, or validate Proteina-Complexa target definitions for protein binders, ligand binders, and AME motif scaffolding. Use for target registries, chain/residue selectors, hotspots, ligand fields, and incomplete motif inputs. Covers direct YAML edits and complexa target/validate target commands; running a campaign with an already registered target belongs to complexa-design.
- ▌ Proteinmpnn Nim · nvidia bundleRun 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.
- ▌ Rfdiffusion Nim · nvidia bundleRun RFDiffusion protein backbone design via NVIDIA NIM. Use for de novo protein backbones, motif scaffolding, binder design, hotspot residues, contigs syntax, diffusion steps, hosted NVIDIA API calls, local Docker deployment, and PDB backbone outputs for ProteinMPNN sequence design.
- ▌ Cdf Orchestration Setup · nvidia bundleUse when the user asks to deploy, install, reinstall, redeploy, upgrade, or connect to the CDF Orchestration Airflow controller. Owns the end-to-end deploy sequence and runs the cdf-orchestration-preflight audit first. Covers make setup, controller image builds, Helm installation, controller connection, port-forwarding, and post-install verification. Not for standalone prerequisite audits or remediation, K3s environments, authoring DAGs, or running workflow payloads.
- ▌ Codonfm Embed · nvidia bundleValidate coding-sequence CSVs, extract public CodonFM/Encodon embeddings, and choose checkpoints for downstream property modeling.
- ▌ Codonfm Score · nvidia bundleValidate, prepare, or run public CodonFM Encodon masked-codon variant scoring and review compatibility of its scoring workflows. Use only when the user explicitly requests CodonFM or Encodon, or that context is already established in the conversation. Do not select this skill for a generic variant-scoring request without that context; ask for the variant and intended analysis first.