NVIDIA-NeMo

Creates a new NeMo plugin from scratch. Use when starting plugin development, setting up a plugin package, registering surfaces via entry points, or asking how plugins are discovered by the platform. Trigger keywords: create plugin, new plugin, plugin setup,…

Creates NemoFunction HTTP surfaces for NeMo Helix plugins. Use when adding a function, declaring spec_schema, mounting function routes with add_function_routes, understanding the generated flat CLI command, or streaming NDJSON frames. Trigger keywords -…

Optimizes and accelerates a deployed NeMo agent by suggesting switchyard routing splits, prompt/hyperparameter tuning, and evaluations against newly available models. Persists snapshots and structured suggestions to the NeMo files service for diffing and UI…

A security war-game for an agent through NeMo Helix: register or upload the agent, resolve a war-game manifest, synthesize a benign suite, attack/defend/validate, adopt the hardened image. Covers red-teaming, hardening, and every `nemo agent-hardener` command.

Use when a customer asks NeMo Helix to build, implement, package, register, or deploy a new agent from confirmed requirements. Builds the supported LangChain Deep Agents shape through Fabric. Do not use for design-only work, focused agent.yaml editing,…

Package and deploy an existing Fabric agent through the OpenShell deployment mode, then verify invocation and network policy. Use for sandboxed agent deployments on an already configured gateway; not for building a new agent, installing the platform, or…

Build one pre-cut NeMo Helix release test-scope artifact with feature descriptions, QA validation, stakeholder review fields, and draft release notes from the previous-release-to-release-branch range while verifying release-derived work on main. Use for…

Evaluate models, datasets, and agents with the NeMo Helix Evals plugin. Use for metric selection, SDK checks, platform jobs, and result retrieval.

End-to-end reference for inference on the NeMo platform — registering LLM backends as ModelProviders, wiring them to VirtualModels with Switchyard middleware (random routing, translate) and `nemo-guardrails` content-safety rails, and hitting them via the nemo…

Author and validate Platform-managed NeMo Agents agent.yaml files using the nemo-agents-spec-v1 format. Use when the user wants to create, edit, validate, or adapt an agent.yaml file, choose a supported harness, add instructions, skills, MCP servers, tools,…

Use when a customer asks NeMo Platform to build, implement, package, register, or deploy a new agent from an idea or approved Ethos. Builds the supported LangChain Deep Agents shape through Fabric. Do not use for design-only work, focused agent.yaml editing,…

Captures a NeMo Platform agent Ethos as a durable artifact at agents/<name>-ethos/ETHOS.md. Validates the front matter and required markdown sections, writes the file, and uploads it to a NeMo Filesets fileset (the canonical copy). The Ethos location is fully…

NeMo Evaluator SDK-first rubric-to-eval guide for BYOB (Bring Your Own Benchmark): parse domain expert rubrics, choose composable evaluation primitives, generate human-reviewable eval configs/artifacts, and run reproducible exact, numeric, LLM-as-judge,…

End-to-end guide for getting evaluation data into NeMo Platform Intake so it shows up in the Experiments leaderboard. Create an Experiment, create an Evaluation, then log traces and evaluator results via ATIF (Harbor), chat-completions, or OTLP and view the…

Captures what a NeMo Platform agent should do before any code or YAML. Explores the user's codebase and docs first, then asks one intent question at a time for what source cannot supply. Output feeds nemo-ethos. Use over generic brainstorming for any NeMo…

NeMo guardrails CLI reference for creating guardrail configs and applying them to chat completions through an IGW VirtualModel. Covers config CRUD, the standalone `/checks` endpoint for verifying a config, and the `nemo-guardrails` inference middleware plugin…

Create or update concise, agent-readable Megatron Bridge model verification cards. Use when adding a model support card, auditing cross-model convergence comparability or verification coverage, recording conversion, deterministic inference, training,…

Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute. Use for activation memory OOMs or regressions involving recompute_granularity, recompute_num_layers, recompute_modules,…

Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and other multimodal experiments.

Recommend and customize Megatron Bridge library and benchmark recipes for a user's model, GPU count, hardware, sequence length, and pretrain/SFT/PEFT goal. Use when selecting a starting recipe, comparing library and benchmark configs, resizing parallelism for…

Guide for adding support for new LLM or VLM models in Megatron-Bridge. Covers bridge, builder-backed model config, recipe, tests, docs, and examples.

Structured framework for exact HF↔MCore weight verification, forward-pass logit correlation, and optional strict numerical diagnostics. Use when debugging weight mismatches, verifying HF↔MCore checkpoint round-trips, choosing verification tools, or…

Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data. Covers correlation testing, available recipes, and multi-GPU examples.

Operational guide for choosing and combining parallelism strategies in Megatron Bridge, including sizing rules, hardware topology mapping, and combined parallelism configuration.

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,…

Advanced tuning of NOOA strategies — CodeAct prefill, loop guards, text-only recovery callbacks, truncation, code restrictions, execution internals, and PredictStrategy tuning. Use when configuring CodeActConfig or PredictConfig beyond defaults, handling…

Attach images, audio, video, and PDFs to NOOA agents. Use typed parameters or CodeAct show(), configure media_inputs, and troubleshoot text-only notices, URLs, MIME types, and size limits.

Configure and troubleshoot NOOA model registry entries with Connect or the library, including endpoints, credentials, reply budgets, reasoning levels, cache reuse and reasoning replay. Use for model onboarding, editing aliases, or Connect diagnostic handoffs,…

Give a NOOA agent capabilities — methods as tools, built-in tools (ShellTools, TodoManager), MCP servers, agent skills (Skill/TextSkill/SkillRegistry), and multimodal media. Use when adding tools or external integrations to an agent, wiring MCP, or packaging…

Solve an interactive grid game iteratively — observe, hypothesize, experiment, record knowledge, and submit action sequences until every level is won.

Explore and debug agent execution traces. Use when the user asks to analyze a trace, debug an agent run, investigate errors in a trace, or when they paste a trace-explorer prompt from the viewer UI.

Intercept and observe NOOA execution — middleware via event_manager.intercept() (guardrails, input/output transforms, blocking), event observers via event_manager.on() (react to Task/Error/LLMResponse/turn events), and the InstrumentationHooks protocol for…

Build and dependency management for NeMo-RL. Covers Docker image building and running, uv usage, venv setup, and adding dependencies.

CI/CD reference for NeMo-RL. Covers GitHub Actions pipeline structure, CI triggering via /ok to test, and CI failure investigation.

Configuration conventions for NeMo-RL. YAML is the single source of truth for defaults. Covers BaseModel/TypedDict usage, dataclass for internal classes, exemplar YAML updates, and forbidden default patterns.

Contribution conventions for NeMo-RL. Covers PR title format, commit sign-off, and CI triggering.

NVIDIA copyright header requirements for NeMo-RL. Covers which files need headers and the exact header text.

Manually cherry-pick a merged NVIDIA-NeMo/RL PR from a release branch (r0.X.0) back onto main when the auto cherry-pick bot failed. Stops at conflicts for the user to resolve, then verifies, pushes, opens a cp PR, copies CI labels and posts /ok to test.

Manually cherry-pick a merged NVIDIA-NeMo/RL PR onto the current release branch (r0.X.0) and open a cp PR with matching CI labels and /ok to test.

Error handling guidelines for NeMo-RL. Covers exception specificity, minimal try bodies, and else blocks.

Review Nemotron pull requests for code correctness, instructions that match the implementation, first-user setup, and reproducible notebooks and cookbooks.

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…

Configure and chain repo-native Nemotron steps for curation, tokenizer extension, SDG/BYOB, training, conversion, optimization, and evaluation.

Use for Nemotron embed/rerank recipes, including Nemotron 3.5 multimodal SDG, tuning, evaluation, and deployment. Not for generic retrieval.

Reference desk for NVIDIA Nemotron 3.5 Lightning (30B-A3B), a hybrid Mamba-Transformer MoE with MTP built from Nano 3 Base by distillation from Super 3 Base, single-stage text SFT, RLVR, MTP boosting, and W4A16 NVFP4 quantization. Use when the user asks facts…

Reference desk for NVIDIA Nemotron 3.5 Super (120B-A12B), covering vision-language architecture, MTP, distillation pretraining from Ultra 3 Base, Indic CPT, SFT, RLVR, specialist teachers, two-phase MOPD, MTP boosting, NVFP4 quantization, and inference. Use…

Run the Nemotron-3.5 Super VL finance LoRA cookbook (NeMo Megatron-Bridge) end-to-end for the user, on one 8-GPU node or a Slurm cluster: data prep, checkpoint conversion, text+vision LoRA fine-tuning of the 120B-A12B model, merge to a Hugging Face…

Run the Nemotron-3.5 Lightning Text2SQL LoRA fine-tuning tutorial (NeMo Megatron-Bridge) end-to-end for the user on a single node: data prep, checkpoint conversion, LoRA fine-tuning of the 30B-A3B hybrid Mamba-Transformer MoE, and merging the adapter back to…

Guide for adding a new benchmark or training environment to NeMo-Gym. Use when the user asks to add, create, or integrate a benchmark, evaluation, training environment, or resources server into NeMo-Gym. Also use when wrapping an existing 3rd-party benchmark…

Inspect and prepare NVIDIA-NeMo/Gym pull requests by reviewing relevant file history, selecting repository-specific local and CI checks, diagnosing missing or failed checks, and choosing current type, area, and state labels. Use for PR readiness, check…

Publish a NeMo Gym release by running the "Build, validate, and release NeMo-Gym" workflow (release.yaml) as a dry run, checking that the wheel installs, then publishing to PyPI and GitHub and verifying the result. Use when asked to release, publish, cut, or…

Use when debugging a Nemo Gym run or reward profiling job. Covers rollout collection failures, empty or partial JSONL outputs, stale materialized inputs, verifier/schema errors, Ray or Slurm issues, vLLM readiness, judge failures, tool/sandbox failures, cache…

Inert repository rubric for the formal /review service.

Write and review user-focused NeMo Gym release notes and README news entries. Use when drafting, editing, prioritizing, or validating a release summary, release-note section, changelog highlights, or release announcement.

Maintain the NeMo Gym Fern docs site — add, update, move, or remove pages under fern/. Use for any documentation change. Triggered by: "edit docs", "add doc page", "update docs", "rename page", "fix broken link", "add redirect", "preview docs", "publish…

Use to help users get started with Nemo Gym reward profiling. Covers the basic gym env start, gym eval run, and gym eval profile workflow, repeated rollouts, materialized inputs, rollout JSONL artifacts, task and rollout identity, output inspection, partial…

Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings. Use when adding or modifying distributed training strategies (FSDP2, HSDP, DDP), debugging multi-GPU or…

Dev environment setup for NeMo AutoModel — container-based development, uv package management, installation options, environment variables, and common build pitfalls. Use when setting up a dev environment, adding or removing dependencies, switching container…

CI/CD reference for NeMo AutoModel — pipeline structure, commit and PR workflow, CI failure investigation, and common failure patterns. Use when investigating a CI failure, understanding the pipeline structure, writing a commit or PR, triggering CI, 'CI is…

Maintain the NeMo AutoModel Fern docs site under docs/ (MDX content) + docs/fern/ (infra) — add, update, move, or remove pages; manage redirects, slugs, navigation, and version aliases; run validation and previews. Use when editing or adding documentation…

Code style and quality rules for NeMo AutoModel — ruff configuration, naming conventions, type hints, docstrings, copyright headers, and the code review checklist. Use when writing or reviewing code for style compliance, fixing ruff errors, understanding type…

Verify numerical parity between NeMo AutoModel implementations and reference HuggingFace models, including state dict and forward-pass checks. Use when verifying numerical correctness of a new or modified model against its HuggingFace reference, debugging…

Testing reference for NeMo AutoModel — unit and functional test layout, tier semantics (L0/L1/L2), running tests locally, adding or disabling tests, and pytest conventions. Use when adding, running, or disabling tests; debugging a test failure; choosing the…

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution. Use when configuring Slurm or SkyPilot job submission, setting up multi-node launch scripts, debugging job submission failures, or switching between…

Entry point for an AI agent's ethos.md: a durable snapshot of what the agent is for, what it must not do, and what success looks like. Routes a request to explore and capture intent (ethos-explore), or write or edit the file (ethos-write), including renaming…

Record whether a repository's Harbor and NeMo Gym evaluations are ready to run, proven in four phases rather than guessed. Probe finds the installed runtimes, Explore finds job configs, datasets, task directories, and Gym manifests, Judge has Harbor and Gym…

Guide broad eval-help requests into onboarding to build or expand evals. Build first evals from a required Ethos, work on existing evaluation suites in a user's repository, derive an environment from trace evidence (experimental), or understand an agent run…

Guide coverage audits with milestone check-ins and user-confirmed eval and trace sources. Generate, validate, measure, and report on an audit-spec coverage denominator for Eval Author. Use when the user wants a hand-editable audit.md file derived from Ethos,…

Required by Eval Author's first-eval and task-create flows before they write a Harbor or Gym task's tests, and available to trace-environment: builds the environment the task runs in, meaning the agent's databases, files, services, and tools, seeded realistic…

Establish a required Ethos, plan evaluation cases, and build first evals or expand a starter Gym or Harbor suite while explaining its parts. No prior traces or coverage reports are required. Missing selected runtime blocks scaffolding and execution, not…

Propose dataset improvements from Eval Author audit findings, then optionally create one Gym or Harbor task from one actionable uncovered tool. Prove it with Gym controls and native execution or Harbor's Oracle, then run it repeatedly with the repository's…

Experimental workflow. Use Gym, MLflow, Intake, OpenTelemetry, or ATIF trace evidence to derive a private, reproducible Harbor or native NeMo Gym task candidate.

Train or adapt a DFlash or DFlash2 speculative draft against a frozen SALM speech-LLM target with NeMo speechlm2. Use for online argmax or offline model-generated labels, pretrained draft adaptation, projection-only ablations, checkpoint resume/export, and…

Fine-tune a SALM speech-LLM checkpoint (speech encoder + projection + LLM decoder) with NeMo speechlm2 on a new domain or task, and evaluate it with vLLM. Use to adapt a speech-to-text LLM to new audio, improve WER on a domain corpus, train speech…

Quantize a SALM speech-LLM checkpoint with a NemotronH decoder to FP8 or NVFP4 for vLLM serving with the NeMo SpeechLM plugin, including the audio encoder and the MTP draft head, and verify the result. Use to produce a quantized checkpoint, check one before…

Repository review rubric for the formal /review command.

Verify a NeMo Speech change or pull request before commit, push, or review by checking the complete diff, formatting, tests, documentation, and DCO sign-offs. Use when asked to verify changes, prepare a commit or PR, or review a PR's validation and coverage.

Fix a GitHub issue in NeMo Speech (NVIDIA-NeMo/Speech). Read the issue, reproduce the bug with a failing test, implement the fix, and verify tests pass. Only opens a PR if the user explicitly asks for it.

This skill should be used when the user asks to "migrate to the resumable dataloader", "switch to indexed Lhotse", "adopt the indexed + resumable pipeline", "make my training resumable", "set up StatefulDataLoader for NeMo/Lhotse", "use index packs", "use…

Guide NeMo Speech users through ASR fine-tuning with container setup and Lhotse training.

Triage or resume Switchyard's repository-wide community-maintenance queue, prepare a gardening handoff, or report a gardener's activity and impact. Do not use for one isolated issue or pull request, implementation work, or an ordinary development-status…

Deep dive on Harbor trial results for tasks that use SWE-Bench-style F2P (FAIL_TO_PASS) and P2P (PASS_TO_PASS) reference tests. Diagnoses why an agent failed and audits whether a failing task is genuinely hard or unfair (instruction-vs-verifier mismatch). Use…

Review CRAFT Search gold answer quality for a specific task. Use when the user asks to review, check, investigate, or look closely at a craft-* task ID. Evaluates gold files, functions, assertions, and explanation against actual source code and agent tier…

Review Switchyard Rust changes for correctness and maintainability. Use for pull requests or diffs touching crates, PyO3 bindings, async runtime behavior, streaming, protocol types, translation, algorithms, or LLM clients.

Build or publish nemo-switchyard Python distributions through the repository's GitHub Actions workflow. Use when asked to build a development wheel, cut a Python release, publish to PyPI, create a release tag, or debug .github/workflows/publish.yml.

Edit or debug the published Switchyard MkDocs site. Use for docs pages, mkdocs.yml navigation, mkdocs_hooks.py source links, strict build failures, local previews, or .github/workflows/docs.yml.

Select or debug Switchyard validation and GitHub CI. Use when asked which tests to run, whether a change is ready, why a CI job failed, how to reproduce CI, or whether live provider tests are appropriate.

Perform a thorough code review of the current branch or a GitHub PR by number.

Maintain the NeMo Data Designer Fern docs site under fern/. Use for any documentation change. Triggered by: "edit docs", "add doc page", "update docs", "rename page", "fix broken link", "add redirect", "preview docs", "publish docs", "regenerate notebooks",…

Search local Fern documentation for content related to a topic

Create a GitHub PR with a well-formatted description matching the repository PR template (flat Changes by default; optional Added/Changed/Removed/Fixed grouping)

Commit current changes with a clear, descriptive message

Search GitHub issues, discussions, and PRs for content related to a topic

Update an existing GitHub PR description to reflect current changes after incorporating feedback