Agent skills by nvidia

Ongoing research training transformer models at scale

Ongoing research training transformer models at scale

Ongoing research training transformer models at scale

Ongoing research training transformer models at scale

Ongoing research training transformer models at scale

Domain knowledge for the nightly main-to-dev sync workflow. Covers merge strategy, CI architecture, failure investigation, and known issues.

Ongoing research training transformer models at scale

Research and draft a response to a GitHub issue or question from an external contributor.

Ongoing research training transformer models at scale

Ongoing research training transformer models at scale

Ongoing research training transformer models at scale

Refresh golden values from a GitHub Actions workflow run (failing-only or all jobs), calculate signed per-model percentage changes, and produce a PR-ready summary. Use when the user asks to update goldens for a CI run,…

Install cuOpt for Python, C, or server via pip, conda, or Docker; verify the install. For building cuOpt from source, see cuopt-developer.

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

Use for CUDA-Q setup, simulation targets, QPU access, and @cudaq.kernel authoring guidance.

Launch 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…

Calibrates 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`.

Run 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…

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.

Summarize short user notes into clear action items.

Review AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review. Use when asked whether a skill or downloaded skill folder is safe, trustworthy, installable, over-permissioned, or…

Review AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review. Use when asked whether a skill or downloaded skill folder is safe, trustworthy, installable, over-permissioned, or…