后端与 API
后端服务、API、Webhook 和服务端工具
Skills 列表
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).
nvidiadigital-health-clinical-asr-eval
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-asr).
nvidianemo-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.
nvidianemo-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.
nvidiavss-generate-video-calibration
Use to run AutoMagicCalib on local MP4s, RTSP, or the bundled sample dataset, and to deploy vss-auto-calibration when needed. Do not use for non-AMC calibration or runtime analytics.
nvidianemo-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.
nvidianemo-mbridge-resiliency
Resiliency features in Megatron Bridge including fault tolerance, straggler detection, in-process restart, preemption, and re-run state machine.
nvidiavss-manage-video-io-storage
Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add/delete sensors and streams). Not for VLM inference or search.
nvidiavss-deploy-detection-tracking-2d
Use this skill when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice. Trigger when the user says things like 'deploy rtvi-cv', 'start warehouse 2d', 'add a stream', 'check rtvi-cv health', or 'stop the perception container'. Not for VLM, embedding, or analytics — use the matching vss-* skill.
nvidiavss-manage-alerts
Use for VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries, camera onboarding. Not for non-alert analytics.
nvidiamcore-linting-and-formatting
Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.
nvidiadynamo-troubleshoot
Diagnose 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.
nvidiadigital-health-clinical-asr-setup
Stage 1 of Clinical ASR Flywheel. Use when bootstrapping a cycle: NVCF+MW disclosure, NVIDIA_API_KEY check, deps install, TTS+ASR smoke test.
nvidiavss-search-archive
Use this skill to run top-level VSS fusion search on archived video, or to ingest video files / RTSP streams for search. Do NOT use for ad-hoc visual Q&A (use vss-ask-video), live captioning (use vss-deploy-dense-captioning), or video summarization and reports (use vss-summarize-video).
nvidiacupynumeric-migration-readiness
Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
nvidiaphysical-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.
nvidianemo-automodel-distributed-training
Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.
nvidiacupynumeric-hdf5
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). Use when a developer needs to save a cuPyNumeric array to an .h5/.hdf5 file, load an HDF5 dataset into a distributed cuPyNumeric array, read a large HDF5 dataset in chunks, hand arrays to an HPC pipeline as a single file, or accelerate HDF5 disk I/O with GPUDirect Storage (GDS). Do not use it for Parquet/cuDF/raw-binary or other sharded/custom layouts (see the cupynumeric-parallel-data-load skill), Zarr or object-store/S3 output, .npz or pickled archives, plain h5py without cuPyNumeric, or pure array compute such as FFT, matmul, or reductions.
nvidiadali-dynamic-mode
DALI imperative dynamic mode (`nvidia.dali.experimental.dynamic`, ndd): use when working on ndd code or migrating pipelines; skip pipeline-only tasks.
nvidia
wecomcli-message
查询当前可以发送消息的聊天会话范围，并向会话列表中的单聊或群聊发送文本、Markdown、图片、文件、语音、视频消息。用户要求“给某人发消息”“在某个群里通知”“给最近会话发消息”或“把图片/文件/语音/视频发到企业微信”时使用。
wecomteamwecomcli-media
企业微信媒体文件上传/下载技能。承接基于 media_id 下载媒体文件到本地，以及上传本地文件获取 media_id 两类操作。当其他技能（微盘、邮件等）返回了 media_id 需要落地为本地文件，或已有本地文件需要转换为 media_id 供其他技能使用时，必须先读取本技能获取完整指引，不得凭记忆处理。本技能不解析/识别文件内容，仅负责文件本身的搬运。
wecomteamwecomcli-calendar
企业微信日程管理。当用户需要预约日程、预订会议室、查看/更新/取消日程或查忙闲时触发。本技能负责『日程』——即不含在线会议链接的安排（也涵盖纯线下面对面碰头）；若用户要的是『在线会议』（含会议号/入会链接、可远程或视频参会），改用 wecomcli-meeting 技能。用户仅说'开会/约个会/某会'等、未明确要创建的是日程还是在线会议时，必须先读取本技能并按其中的消歧流程向用户追问确认后再处理，不可臆断直接创建。
wecomteamcuopt-routing-api-python
Vehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.
nvidiadeepstream-dev
使用 Python pyservicemaker API 进行 NVIDIA DeepStream SDK 开发。适用于构建视频分析流水线、基于 GStreamer 的视频处理、集成 TensorRT 推理、目标检测与追踪，以及集成 Kafka 或消息代理（Message Broker）等场景。
nvidia