Explore skills
Showing 6091–6120 of 77104 skills
Query Auto Ontology and validate generated SQL, rows, and answers. Use for MCP or REST access, readiness, authentication, conversations, and grounded questions.
NVIDIA/skills
Stars: 4kClaude CodeCodexUse when writing the objective_function= passed to Search(). Covers the two legal signatures (compiler-only str vs mixed list), the baseline-knockout branch, per-eval cache busting, framework-specific --apply-controls injection (raw PTXAS, NVCC, Triton, Helion, cuTeDSL/FA4, FlashInfer), correctness-before-timing, INVALID_SCORE handling, and the Debug-pack O0/O3 ACF-injection canary that must pass before launching a search. Triggers on "objective function", "apply-controls", "INVALID_SCORE", "save_compiler_config", "baseline knockout", "BASELINE_CONFIG", "every config returns the same score", "TypeError fromhex".
NVIDIA/skills
Stars: 4kClaude CodeCodexUse when starting a fresh CompileIQ project, hitting a hang on the first evaluation, or before running any other compileiq-* skill. Verifies CUDA 13.3+, ptxas, GPU access, that `from compileiq.ciq import Search` and friends resolve, and that `PtxasSearchSpace().retrieve()` returns a real path. Documents the env vars that control timeouts, caching, and search-space mirroring. Triggers on "set up compileiq", "compileiq doesn't work", "first eval hangs", "where do search spaces come from", "air-gapped compileiq".
NVIDIA/skills
Stars: 4kClaude CodeCodexUse when something is wrong: Search() hangs, all evaluations return INVALID_SCORE, scores aren't improving, every config returns the same number, ptxas errors fill the log, CV% is too high, or a winning ACF candidate needs NCU profiling to explain. Symptom-indexed table on top. Triggers on "compileiq hang", "socket timeout", "INVALID_SCORE", "not converging", "every score is the same", "TypeError fromhex", "ncu profile", "register spill", "ptxas error", "not in expected format", "high cv".
NVIDIA/skills
Stars: 4kClaude CodeCodexUse when composing the Search(...) call and calling .start(). Covers the four worker classes (MultiProcessWorker / IsoMultiProcessWorker / RayWorker / AsyncWorker) and when to pick each, SearchConfiguration sizing rules, dump_results checkpointing, tracker_config choice (Disabled / Loguru / MLflow), num_workers/task_timeout semantics, and GPU clock locking for stable measurements. Triggers on "Search()", "tuner.start()", "pool_size", "num_workers", "task_timeout", "IsoMultiProcessWorker", "RayWorker", "dump_results", "MLflow", "GPU clocks".
NVIDIA/skills
Stars: 4kClaude CodeCodexUse when picking the search_space= argument for Search(). Covers the three provider classes (PtxasSearchSpace, NvccSearchSpace, LocalSearchSpaceBin), how to pin a version/variant/tag, the attention-focused 'att' variant for attention kernels (FlashAttention, GQA, MHA, MLA, FlashInfer Batch Decode), air-gapped mirroring via CIQ_SEARCH_SPACES_DIR, and custom user-defined search spaces built from compileiq.search_spaces.base primitives. Triggers on "search space", "PtxasSearchSpace", "NvccSearchSpace", "air-gapped compileiq", "offline compileiq", "CIQ_SEARCH_SPACES_DIR", "attention variant", "ptxas att".
NVIDIA/skills
Stars: 4kClaude CodeCodexUse AFTER a Search has completed and BEFORE claiming any speedup or shipping an ACF. Loads the dump_results CSV, extracts top-K candidates (single-objective) or the Pareto front (multi-objective), re-measures each against the no-ACF baseline with 100+ trials on fresh caches, runs Welch's t-test plus Cohen's d, rejects three classic false-positive patterns (lucky-min / higher-variance / multiple-comparisons-of-N), and saves the validated winner as best.acf. Triggers on "validate result", "extract best config", "Welch's t-test", "is my speedup real", "save best ACF", "pareto front", "claim speedup", "ship config".
NVIDIA/skills
Stars: 4kClaude CodeCodexUse this skill when answering a question about previously analyzed or freshly scoped VSS video, or when reading a stored VSS memory job or record by id, or whenever a question should be answered by running the `vss memory introspect` command. Route through hot context, agent Markdown notes, `vss memory get` or `vss memory query`, `vss memory introspect`, or an exact-window `vss vlm run`. Not for video retrieval or metadata-answerable questions.
NVIDIA/skills
Stars: 4kClaude CodeCodexUse this skill when producing a VSS analysis report — Mode A per-clip VLM, Mode B incident-range via video-analytics, Mode C SOP compliance via the SOP tools. Not for standalone video summarization, real-time alerts or ad-hoc Q&A.
NVIDIA/skills
Stars: 4kClaude CodeCodexGenerates VSS video summary reports with LVS HITL and optional Enterprise RAG document grounding. Trigger when the user asks for a frag/RAG-assisted video report, knowledge-enhanced analysis, or Enterprise RAG context in a video summary.
NVIDIA/skills
Stars: 4kClaude CodeCodexQuery read-only video analytics with `vss analytics` for incidents, occupancy metrics, average speed, places, and analytics sensors. Load this skill for video-analytics questions about these records and metrics, including requests asking which skill to use for analytics. Not for live VLM, incident-range narrative reports, deployment, or alert-rule management.
NVIDIA/skills
Stars: 4kClaude CodeCodexUse this skill to search archived VSS video or indexed live RTSP camera streams already registered in a configured deployment — by natural-language, similarity, attribute, object-ID, or lexical tag query — and for follow-up questions about displayed search results or their verification. For fresh clip Q&A use vss-ask-video; for full-recording summaries use vss-summarize-video; for source ingestion/deletion use vss-manage-video-io-storage; for deployment use vss-build-vision-ai. Route those requests to the named workflow without loading this skill, including when media, the CLI, or the deployment is unavailable. Not for live captioning.
NVIDIA/skills
Stars: 4kClaude CodeCodexOfficial NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.
NVIDIA/skills
Stars: 4kClaude CodeCodexCustomize NVIDIA Nemotron Voice Agent's Generic Pipecat example for healthcare appointment, five-field patient intake, or custom tool-calling workflows without a separate backend.
NVIDIA/skills
Stars: 4kClaude CodeCodexCalibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.
NVIDIA/skills
Stars: 4kClaude CodeCodexRun end-to-end calibration on the shipped sample dataset (sdg_08_2_sample_data_010926.zip) against a running AMC microservice. Use when user says 'test sample dataset', 'run sample calibration', 'verify AMC install', or 'launch and test'.
NVIDIA/skills
Stars: 4kClaude CodeCodexCalibrates pre-recorded `cam_*.mp4` datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s; route live RTSP streams to `amc-run-rtsp-calibration`.
NVIDIA/skills
Stars: 4kClaude CodeCodexLaunch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy auto calibration', 'launch auto calibration', 'launch AMC', 'start MS+UI', or 'set up auto-magic-calib'. Requires NGC API key.
NVIDIA/skills
Stars: 4kClaude CodeCodexUse when running the CDF AnomalyGen pipeline over a defect dataset — mask placement, fine-tuning, synthetic defect-image generation (SDG), evaluation, quality refinement, and pseudo-labeling — even when the user names only one stage.
NVIDIA/skills
Stars: 4kClaude CodeCodexUse when authoring or validating Cosmos Data Factory (CDF) augmentation YAML configs, or running remote Cosmos Transfer (including Cosmos3 WSM controls), Cosmos Predict, image-edit, or image-to-video inference.
NVIDIA/skills
Stars: 4kClaude CodeCodexNVIDIA 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.
NVIDIA/skills
Stars: 4kClaude CodeCodexUse 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.
NVIDIA/skills
Stars: 4kClaude CodeCodexComponent-owned guidance for CDF Simulation requests submitted directly or through Airflow-triggered DIG Flow Catalog prompts — golden THT board, THT pin-geometry variation, good/clean SMT images, structural pose defects, and solder texture defects, from a board USD. Turns one matched prompt into one validated `cdf.CDFJob` build and its compiled JobOrder payload; it never executes a render itself. Requires a caller-supplied board USD and output root, asks for either when missing from an interactive request, and resolves optional details with fixed, documented defaults.
NVIDIA/skills
Stars: 4kClaude CodeCodexInstall cuOpt for Python, C, or server via pip, conda, or Docker; verify the install. For building cuOpt from source, see cuopt-developer.
NVIDIA/skills
Stars: 4kClaude CodeCodexTrace, complete, and interpret the Pareto frontier across competing objectives using repeated single-objective cuOpt solves (weighted-sum and ε-constraint).
NVIDIA/skills
Stars: 4kClaude CodeCodexLP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.
NVIDIA/skills
Stars: 4kClaude CodeCodexUse when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline. The argument is the description of the dataset to generate.
NVIDIA/skills
Stars: 4kClaude CodeCodexNVIDIA DeepStream SDK development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration.
NVIDIA/skills
Stars: 4kClaude CodeCodexBuild DeepStream GStreamer pipelines interactively. Use when the user asks about pipelines for video/image inference, detection, tracking, or streaming — including natural phrases like 'pipeline to infer on image', 'run inference on video', 'detect objects in stream', 'save inference output', 'deepstream pipeline', 'gst-launch pipeline', 'process video with detection', 'build a pipeline', or any request involving GStreamer/DeepStream elements (nvinfer, nvstreammux, nvtracker, etc.).
NVIDIA/skills
Stars: 4kClaude CodeCodexProfile a DeepStream pipeline with Nsight Systems and derive its configs from the measurement. Use when the user asks for an efficient, performant, or profiled pipeline — or to benchmark, tune, or measure FPS.
NVIDIA/skills
Stars: 4kClaude CodeCodex