AI & LLM Engineering · NVIDIA AI Platform · For data scientists

Add a new step under src/nemotron/steps/<category/<stepid/ — manifest (step.toml), runner glue, configs, and per-step README.md.

NVIDIA-NeMo/Nemotron

Shows how to launch distributed Megatron-LM training on a SLURM cluster: sbatch skeleton, torch.distributed.run setup, CUDA_DEVICE_MAX_CONNECTIONS rules and failure diagnosis.

NVIDIA/Megatron-LM

Plans memory headroom, works through out-of-memory failures and watches temperature and power during long ML training jobs on NVIDIA DGX Spark.

wshobson/agents

YOLO 2026 — state-of-the-art real-time object detection. An agent skill from SharpAI/DeepCamera.

SharpAI/DeepCamera

A skill your agent uses when quantizing a diffusion DiT with NVIDIA ModelOpt and making the resulting FP8 or NVFP4 checkpoint loadable, verifiable, and benchmarkable in SGLang Diffusion.

sgl-project/sglang

Preflight checks and diagnosis for ten known failure modes of ML training on NVIDIA DGX Spark's GB10, spanning launch errors, memory, thermals, bandwidth and precision.

wshobson/agents

Set up the NVIDIA "Build an Agent" DevX workshop as a working JupyterLab environment from INSIDE a locked-down OpenShell/NemoClaw sandbox, and hand the user the token URL + access commands.

brevdev/workshop-build-an-agent

Reference desk for Nemotron 3 Nano / Llama-Nemotron Nano 3 — architecture, training data, recipes, evaluation, quantization, deployment.

NVIDIA-NeMo/Nemotron

Verify a CV-CUDA optimization campaign's deterministic definition-of-done and concise versioned MR summary per .agents/guidance/OPTIMIZATIONGUIDELINES.md.

CVCUDA/CV-CUDA

Reference desk for NVIDIA Nemotron 3 Super — architecture, training data, recipes (pretrain/SFT/RL/eval/quantization), and deployment notes.

NVIDIA-NeMo/Nemotron

Covers serving LLMs with SGLang, whose RadixAttention reuses cached prefixes, and constraining output to JSON, regex or grammar for agent and tool-calling workloads.

Orchestra-Research/AI-Research-SKILLs

Orchestrates defect image generation for PCBA, metal surface and glass inspection with NVIDIA Cosmos AnomalyGen on OSMO, from cold-start Day 0 to real-photo Day 1 labeling.

NVIDIA/skills

Orchestrates video data augmentation and auto-labeling workflows on OSMO, from flow selection and preflight checks to submission, monitoring and output download.

NVIDIA/skills

Run the Nemotron-3 Ultra Text2SQL LoRA fine-tuning tutorial (NeMo Megatron-Bridge) end-to-end for the user on their SLURM cluster: data prep, distributed checkpoint conversion, and packed LoRA…

NVIDIA-NeMo/Nemotron

Runs NVIDIA TAO Data Services KPI analysis on object detection results, comparing predictions to ground truth and writing per-class precision, recall and AP to a CSV.

NVIDIA/skills

Verify a new CV-CUDA operator against the deterministic final regression checklist (the /make-op done-gate).

CVCUDA/CV-CUDA

Reference desk for NVIDIA Nemotron 3 Ultra (550B-A55B) — architecture, NVFP4 pretraining, SFT, MOPD (multi-teacher on-policy distillation), MTP boosting, quantization, inference.

NVIDIA-NeMo/Nemotron

Runs TAO Data Services gap analysis that compares ground-truth and predicted boxes to find weak images by per-class recall, precision and AP50.

NVIDIA/skills

Review a CV-CUDA operator's BENCHMARK coverage — drivers, layout axis, baselines, the basic-tier floor, row counts, and coverage statistics.

CVCUDA/CV-CUDA

Sets up and runs NVIDIA Cosmos Policy evaluations on the LIBERO and RoboCasa simulators, including headless GPU rendering and inference latency profiling.

Orchestra-Research/AI-Research-SKILLs

Fine-tunes and evaluates OpenVLA-OFT and OFT+ robot policies with LoRA and continuous action heads on LIBERO simulation and ALOHA real-robot setups.

Orchestra-Research/AI-Research-SKILLs

Compares a vision-language model's yes/no predictions with ground truth and writes the false-positive and false-negative cases to a JSONL file with a summary report.

NVIDIA/skills

Run TLX kernel performance benchmarks on Hopper, Blackwell, and AMD (gfx950/CDNA4, gfx1250) GPUs.

facebookexperimental/triton

Analyze official Megatron-LM commits, PRs, and branch change sets to identify feature evolution, candidate breaking changes, and migration-relevant events.

ascend-ai-coding/awesome-ascend-skills

Optimize dense matrix multiplication (GEMM) kernels in Triton for NVIDIA and AMD GPUs.

ZJLi2013/awesome-kernel-skills

GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster.

K-Dense-AI/scientific-agent-skills

Turns a parquet of image file paths into a parquet of embeddings with CLIP, SigLIP or a TAO checkpoint, using the TAO Data Services container, ahead of neighbor mining.

NVIDIA/skills

Track and normalize change requests against the official Megatron-LM repository by branch, PR, commit, commit range, or time window.

ascend-ai-coding/awesome-ascend-skills

Map migration-relevant Megatron changes onto the official MindSpeed repository by resolving branch alignment, locating affected subsystems, and identifying concrete adaptation points.

ascend-ai-coding/awesome-ascend-skills

Fine-tune public CodonFM Encodon checkpoints on labeled coding-sequence or coding-variant data using LoRA, head-only, or full fine-tuning.

NVIDIA/skills

Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink.

NVIDIA/skills

Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.

NVIDIA/skills

Plan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or Megatron-Bridge), pretraining/CPT, RL…

NVIDIA/skills

Validate coding-sequence CSVs, extract public CodonFM/Encodon embeddings, and choose checkpoints for downstream property modeling.

NVIDIA/skills

A skill your agent uses when you need to print Jetson device info (module model, L4T version, kernel, OS version, current power mode) from a running Jetson target.

NVIDIA/skills

Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal Nemotron-3-Content-Safety.

NVIDIA/skills

Profile a DeepStream pipeline with Nsight Systems and derive its configs from the measurement.

NVIDIA/skills

Per-pin SFIO / direction / initial-state configurator for a Jetson Orin or Thor custom carrier from the pinmux XLSM.

NVIDIA/skills

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both.

NVIDIA/skills

A skill your agent uses when measuring Jetson Video Codec SDK or PyNvVideoCodec encode/decode throughput, comparing presets or surfaces, testing codec-worker capacity with authenticated samples and…

NVIDIA/skills

A skill your agent uses when Jetson codec, profile, chroma, bit-depth, dimension, engine-count, or operational support must be reconciled from live APIs, authenticated NVIDIA samples, and NVIDIA…

NVIDIA/skills

A skill your agent uses when planning, executing, and independently validating Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or concise…

NVIDIA/skills

A skill your agent uses when turning a Jetson encoder use case into one surface-neutral recipe with native Video Codec SDK and PyNvVideoCodec projections.

NVIDIA/skills

Automatically fetch InferenceX benchmark data and generate daily performance reports for LLM inference on various hardware (NVIDIA, AMD, etc.).

ascend-ai-coding/awesome-ascend-skills

Customize 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

Stage 2 of the Clinical ASR Flywheel. An agent skill from NVIDIA/skills.

NVIDIA/skills

Stage 1 of Clinical ASR Flywheel. An agent skill from NVIDIA/skills.

NVIDIA/skills

A skill your agent uses when you need to rebuild the BSP overlay — DT, OOT modules, or kernel — from changes under bspsources/.

NVIDIA/skills