AI tools for “ci”

…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…

…/ `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…

…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…

…DGX Spark and related GB10 system identification, capacity, troubleshooting, known issues, updates, recovery, playbooks, examples, NVIDIA Sync, clustering, Custom Apps, Field Diagnostics, or support evidence.…

Profile 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.

LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.

Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.

…cuml.accel (zero-code-change GPU acceleration of scikit-learn, umap-learn and hdbscan), or GPU UMAP/HDBSCAN/RandomForest/KMeans/SVC, including through libraries that wrap cuML (BERTopic, rapids-singlecell).…

Use when porting circuits from another framework (e.g. Qiskit) into CUDA-Q kernels while preserving the source algorithm and validation fidelity.

…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…

…protein sequence-to-structure prediction, A3M MSAs, mmCIF templates, hosted NVIDIA API calls, or local Docker…

Use when building or debugging cuEquivariance PyTorch tensor products or equivariant GNNs, especially CPU references, layouts, indexing, and gradients.

…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…

…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,…

…SMILES or CCD ligands, pIC50/IC50 affinity scoring, mmCIF output, hosted NVIDIA API calls, or local Docker…

Official 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.

…a concrete business task directly to its available specialist without an onboarding interview. Unrelated greetings do not select this…

…Credits to Bills, Cash and Liquidity, Executive Financial Reporting, Finance Controls Review, Financial Statement Review, Invoice Collections, Journal Entry Review, Period Close Status, Variance and Flux…

Use for Customers & Sales: Advanced Pricing Price Rule Review, Customer Service Order Triage, Customer Support Assistant, Knowledge Base Quality Assistant, Lead Management Assistant, Marketing Campaign Assistant,…

…N/cache, and security directly from SAFE Guide principles. Generate quizzes from code or SAFE Guide…