OpenClaw AI 技能

Start or patch Dynamo router modes and run router endpoint smoke checks. Use for round-robin, KV-aware, least-loaded, or device-aware routing setup; u

Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after recipe-runner brings a d

Stage 1 of Clinical ASR Flywheel. Use when bootstrapping a cycle: NVCF+MW disclosure, NVIDIA_API_KEY check, deps install, TTS+ASR smoke test.

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 f

Stage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipa_source diagnostic). Not for ASR auth (/riva-

Stage 2 of the Clinical ASR Flywheel. Use when curating clinical terms, tagging IPA, and synthesizing a NeMo manifest. NOT for scoring (use /digital-h

Used for converting one CT DICOM series folder to a HU NIfTI volume with affine evidence. Not for multi-frame DICOM or clinical use.

Used for header-only preflight of one DICOM series folder before conversion or inference. Not for de-identification or clinical clearance.

Used for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence. Not for anonymization or clinical use.

Use this skill to bring any vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download,

NVIDIA DeepStream SDK 9.0 development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, T

Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.

DALI imperative dynamic mode (`nvidia.dali.experimental.dynamic`, ndd): use when working on ndd code or migrating pipelines; skip pipeline-only tasks.

Load a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distributed cuPyNumeric ndarray via a m

Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will sca

Install and verify cuPyNumeric for Python — requirements, commands, verification. Source builds are out of scope.

Read and write large cuPyNumeric arrays to HDF5 with Legate's parallel, distributed HDF5 I/O (legate.io.hdf5: to_file, from_file, from_file_batched).

Base rules for end users calling NVIDIA cuOpt (routing/LP/MILP/QP/install/server). Not for cuOpt internals — use cuopt-developer for those.

After solving a non-trivial problem, detect generalizable learnings and propose skill updates. Always active — applies to every interaction.

cuOpt REST server — what it does and how requests flow. Domain concepts; no deploy or client code.