Instructions file
Instructions for NVIDIA-NeMo/DataDesigner, a project described as: 🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
2.2k 2d ago A 13 tokens
original Apache-2.0
Skill Claude CodeCodex
Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.
2.2k 2d ago A 25 tokens
copy · 100% Apache-2.0
Plugin Claude Code
Plugin marketplace listing 1 plugin: nemotron-customize.
2.0k 10d ago A
tokens not measured
original Apache-2.0
Skill Claude CodeCodex
Prepare, validate, build, and use Nemotron Customizer airgap image bundles for offline clusters. Use when planning airgapped deployments, editing deploy/nemotron-customizer/airgap/airgap.yaml, selecting workflow targets, grouping step execution images, baking repo overlays or wheel additions, resuming airgap runner…
2.0k 10d ago A 89 tokens
original Apache-2.0
Skill Claude CodeCodex
Onboard a new model family (Nemotron or third-party) into skills/ — paper chunks, recipe summaries, context packs, and model card. Use when a contributor wants downstream skills like /nemotron-customize to be able to route to a new model.
2.0k 10d ago A 58 tokens
original Apache-2.0
Skill Claude CodeCodex
Add a cross-cutting decision pattern under src/nemotron/steps/patterns/. Use when a recurring ML decision (tokenizer lock, eval bookends, LoRA-on-small-data, etc.) must be encoded so other skills can fire it during planning.
2.0k 10d ago A 58 tokens
original Apache-2.0
Skill Claude CodeCodex
Add a new step under src/nemotron/steps/ / / — manifest (step.toml), runner glue, configs, and per-step README.md. Use when extending the catalog so /nemotron-customize can route to it.
2.0k 10d ago A 56 tokens
original Apache-2.0
Plugin Claude Code
Plan and configure repo-native Nemotron customization workflows from existing steps: curate/nemocurator JSONL cleaning, translate/nemocurator corpus translation, sft/automodel, peft/automodel, sft/megatronbridge, peft/megatronbridge, pretrain/CPT, rl/nemorl alignment, byob/mcq benchmarks, convert/megatrontohf an.
2.0k 10d ago A
tokens not measured
original Apache-2.0
Skill Claude CodeCodex
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 alignment (DPO/RLVR/GRPO/RLHF), BYOB/MCQ benchmarks, checkpoint conversion, ModelOpt optimization, env profiles, and…
2.0k 10d ago A 159 tokens
original Apache-2.0
Skill Claude CodeCodex
Reference desk for Nemotron 3 Nano / Llama-Nemotron Nano 3 — architecture, training data, recipes, evaluation, quantization, deployment. Use when the user asks facts about the model rather than building a pipeline.
2.0k 10d ago A 53 tokens
original Apache-2.0
Skill Claude CodeCodex
Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal Nemotron-3-Content-Safety. Produces a Markdown policy, JSON taxonomy, and drop-in inference prompts. Maps rough words or an existing policy to V2 categories, adding custom…
2.0k 10d ago A 85 tokens
original Apache-2.0
Skill Claude CodeCodex
Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron embed/rerank retrieval recipes.
2.0k 10d ago A 36 tokens
original Apache-2.0
Skill Claude CodeCodex
Reference desk for NVIDIA Nemotron 3 Super — architecture, training data, recipes (pretrain/SFT/RL/eval/quantization), and deployment notes. Use when the user asks facts about Super3 rather than building a pipeline.
2.0k 10d ago A 53 tokens
original Apache-2.0
Skill Claude CodeCodex
Reference desk for NVIDIA Nemotron 3 Ultra (550B-A55B) — architecture, NVFP4 pretraining, SFT, MOPD (multi-teacher on-policy distillation), MTP boosting, quantization, inference. Use when the user asks facts about Ultra rather than building a pipeline.
2.0k 10d ago A 68 tokens
original Apache-2.0
Skill Claude CodeCodex
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 fine-tuning of the 550B hybrid Mamba-Transformer MoE, ending at a saved adapter. Use when the user wants to run this cookbook…
2.0k 10d ago A 113 tokens
original Apache-2.0
Instructions file CodexOpenCode
AGENTS.md instructions for NVIDIA-NeMo/labs-OO-Agents, covering nvidia oo agents framework, core concept, quick rules, method design and visibility.
1.9k 3d ago A 2,418 tokens
Skill Claude CodeCodex
Solve an interactive grid game iteratively — observe, hypothesize, experiment, record knowledge, and submit action sequences until every level is won.
1.9k 3d ago A 33 tokens
Skill Claude CodeCodex
Solve an interactive grid game by learning a compressed world model (encode state to a latent z, learn a predict function), planning action sequences by search over it, and recording hypotheses, plans and knowledge to memory.
1.9k 3d ago A 47 tokens
Skill Claude CodeCodex
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
1.9k 3d ago A 77 tokens
wiki
44MCP server Claude CodeCodexCursor +2
MCP server "wiki" as configured in NVIDIA-NeMo/labs-OO-Agents. Runs examples/assets/wiki_mcp_server.py with python.
1.9k 3d ago A
tokens not measured
Skill Claude CodeCodex
How to manage context blocks (system prompt sections) in NOOA. Use when configuring what appears in an agent's LLM prompt — adding, overriding, suppressing, or positioning blocks. Covers the unified Context API, well-known framework keys, and the declarative/runtime interface.
1.9k 3d ago A 60 tokens
Skill Claude CodeCodex
Author agents with NVIDIA-labs Object Oriented Agents (NOOA). Use when writing or modifying an Agent subclass, agentic methods (ellipsis bodies), docstring prompts, structured output contracts, strategy selection (CodeAct/Predict), visibility control, orchestrators, or subagent composition.
1.9k 3d ago A 0 tokens
Skill Claude CodeCodex
Make NOOA agent types render useful documentation for the LLM — doc(), spec(), hidden, Annotated field descriptions, and pformat/pprint tuning. Use when designing Pydantic models/dataclasses the LLM will see, controlling what appears in doc(self), hiding internals, adding field descriptions, fixing noisy or missing…
1.9k 3d ago A 79 tokens
Skill Claude CodeCodex
Capture execution traces from NOOA. Use when instrumenting an agent run, writing traces to JSONL files, sending traces to the viewer or an OTLP/Langfuse/Phoenix backend, controlling which methods are traced, or when traces are mysteriously missing.
1.9k 3d ago A 62 tokens