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, fine-tune Nemotron-3 Ultra with LoRA, or adapt the notebook to their own cluster.

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.

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.

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.

Add a new step under src/nemotron/steps/<category>/<step_id>/ — manifest (step.toml), runner glue, configs, and per-step README.md. Use when extending the catalog so /nemotron-customize can route to it.

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.

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.

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 builds, or submitting `nemotron steps run` jobs inside an airgapped environment.

Import and use Kubb's generated code (types, clients, hooks, schemas, mocks). Use when writing app or test code that consumes a Kubb build.

How to author a kubb.config.ts and pick the right @kubb/plugin-* packages when generating TypeScript from an OpenAPI/Swagger spec. Use whenever setting up Kubb, adding a generator, or debugging codegen output.

Rules and checklist for preparing PRs, creating changesets, and releasing packages in the monorepo.

Full JSDoc format guide for TypeScript, covering @example formats (short, multi-line, multi-variant), tag usage (@default, @deprecated, what to avoid), documentation patterns for properties/enums/functions, and tag order.

Remove AI writing patterns to make documentation sound natural, specific, and human. Covers content patterns, language patterns, style patterns, and communication patterns.

Use when writing blog posts or documentation markdown files - provides writing style guide (active voice, present tense), content structure patterns, and SEO optimization. Overrides brevity rules for proper grammar.

Remove AI-generated code slop from a branch or diff. Use after writing or generating code to strip unnecessary comments, defensive checks, `any` casts, and style that does not match the surrounding file. For prose and markdown, use the humanizer skill instead.

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

Deep-dive interview to flesh out a spec or design document

Implement a spec from the plans directory

Research how a feature works in reference libraries

Review developer experience and API ergonomics