all publishers

NVIDIA NeMo

@nvidia-nemo source repo

204 published skills · page 1 of 3

  1. ▌
    Audio Curation · nvidia-nemo bundle
    Build and run a NeMo Curator audio curation pipeline from a natural-language goal (host-driven planner over the audio_agent tool core). Use for any audio, speech or audio-dataset task - quality filtering, transcription, WER filtering, VAD, diarization, ALM windowing, resampling, channel conversion, or inspecting an audio corpus. Route such work through this skill rather than writing ad-hoc ffprobe, librosa or soundfile scripts.
    2.3k repo stars
  2. ▌
    Checkpoint Placement · nvidia-nemo
    Select a core-proven metadata checkpoint for same-dataset parameter feedback. Use after recipe validation and semantic critique, before authoritative smoke, when the user expects to tune a declared downstream decision after seeing results.
    2.3k repo stars
  3. ▌
    Audio Stage Authoring · nvidia-nemo
    Make a new or existing NeMo Curator audio stage agent-ready so the audio agent can discover, configure and chain it. Use when adding an audio stage, writing or fixing its describe() contract or StageContract, adding *_key fields or semantic roles, writing a capability card, or when card conformance or assert_agent_ready fails. This is for authoring stage code in a Curator checkout, not for curating a dataset - use the audio-curation skill for that.
    2.3k repo stars
  4. ▌
    Nemo Agent Hardener · nvidia-nemo bundle
    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.
    2.3k repo stars
  5. ▌
    Plugin Platform Services 2 · nvidia-nemo bundle
    Calls NeMo Helix services (entity store, jobs, files, secrets, models, inference gateway, auth) from a plugin. Use when a plugin needs to submit jobs, access files, read secrets, look up models, call the inference gateway, check permissions, or route calls between services. Trigger keywords: jobs service, files service, secrets service, models service, inference gateway, auth client, typed client, NemoClient, platform client, service-to-service, inter-service call, add_job_routes, job_route_factory, NHX_BASE_URL.
    2.3k repo stars
  6. ▌
    Plugin Inference Middleware 2 · nvidia-nemo
    Implements NemoInferenceMiddleware plugins for in-process inference request/response interception in IGW. Use when building a middleware plugin, implementing process_request or process_response, handling MiddlewareCall config (inline or config_id), exposing config entity CRUD APIs, or wiring up the nemo.inference_middleware entry-point. Trigger keywords: inference middleware, NemoInferenceMiddleware, process_request, process_response, MiddlewareCall, config_id, ImmediateResponse, VirtualModel middleware, middleware plugin.
    2.3k repo stars
  7. ▌
    Nemo Agent Config 2 · nvidia-nemo bundle
    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, environment, or telemetry.
    2.3k repo stars
  8. ▌
    Nemo Model Selection 2 · nvidia-nemo bundle
    Recommends an LLM for a NeMo Helix agent
    2.3k repo stars
  9. ▌
    Nemo Skill Selection 2 · nvidia-nemo bundle
    Top-level skill selector for ambiguous tasks involving NeMo Helix (NVIDIA's agent platform). Picks the right downstream skill for setup, design, specification, agent configuration, build, deployment, testing, observability, status, teardown, evaluation, optimization, security, or model customization. Use when the user needs help deciding where a NeMo Helix task should start.
    2.3k repo stars
  10. ▌
    Supercool Guidelines 2 · nvidia-nemo
    The Supercool Coding Guidelines — mandatory naming conventions for every function you write. Use this whenever you are asked to write or edit a Python function.
    2.3k repo stars
  11. ▌
    Nemo Retrieval Recipes · nvidia-nemo bundle
    End-to-end NeMo Helix recipe for domain embedding and reranking fine-tuning: Data Designer retrieval-generate/prepare, Automodel bi_encoder/cross_encoder, Evaluator retrieve-eval on frozen eval_beir (NIM providers via Deployment Manager). Use when the user has a document corpus, wants better retrieval nDCG/recall, or asks to fine-tune Nemotron embed or rerank models on Platform.
    2.3k repo stars
  12. ▌
    Nemo Gym Environments · nvidia-nemo bundle
    Build, convert, validate and upload a NeMo Gym reward environment for GRPO training: package your own reward code or a NeMo Gym server, convert a Prime Intellect or verifiers environment, and write the rollout-row dataset. Hand off to nemo-customizer to submit the GRPO job.
    2.3k repo stars
  13. ▌
    Nemo Experiments Upload 2 · nvidia-nemo bundle
    End-to-end guide for getting evaluation data into NeMo Helix 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 rollups in Studio. Use when a user wants to create named evaluation runs, publish evaluation results, or compare runs in NeMo Experiments.
    2.3k repo stars
  14. ▌
    Plugin Job 2 · nvidia-nemo
    Creates schedulable NemoJob surfaces for NeMo Helix plugins. Use when adding a job, declaring spec_schema / input_spec_schema / to_spec / compile, mounting job routes with add_job_routes, understanding generated job CLI shape, or running jobs in containers. Trigger keywords - job, NemoJob, spec_schema, input_spec_schema, to_spec, compile, add_job_routes, nemo_helix_plugin.jobs, generated job CLI, explain, NemoJobScheduler.
    2.3k repo stars
  15. ▌
    Plugin Authz 2 · nvidia-nemo bundle
    Declares HTTP authorization on NeMo Helix plugin routes with @path_rule, AuthzScope, PermissionSet, and CallerKind. Use when adding or securing a plugin route, minting permission ids, choosing PRINCIPAL vs SERVICE_PRINCIPAL callers, fixing a hard_fail bundle build from an unruled route, or migrating off get_authz_contribution. Trigger keywords: authz, authorization, permission, path_rule, AuthzScope, PermissionSet, perm, CallerKind, SERVICE_PRINCIPAL, scope, hard_fail, on_invalid_plugin, unruled route, bundle build, get_authz_contribution.
    2.3k repo stars
  16. ▌
    Plugin Config 2 · nvidia-nemo
    Creates plugin configuration using NemoConfig with environment variables and YAML file support. Use when adding plugin configuration fields, reading config values at runtime, setting up test config overrides, or understanding the env var naming formula. Trigger keywords: config, configuration, NemoConfig, env var, environment variable, plugin_name, NHX_CONFIG, YAML config, config override, test config.
    2.3k repo stars
  17. ▌
    Plugin Service 2 · nvidia-nemo bundle
    Builds HTTP service surfaces for NeMo Helix plugins using NemoService, RouterSpec, NemoListResponse, and NemoFilter. Use when adding REST API routes to a plugin, implementing CRUD endpoints, handling pagination and filtering, or testing FastAPI routes. Trigger keywords: HTTP routes, REST API, FastAPI, CRUD, endpoint, router, NemoService, pagination, filter, list endpoint, NemoListResponse, RouterSpec.
    2.3k repo stars
  18. ▌
    Plugin Testing 2 · nvidia-nemo
    Tests NeMo Helix plugin surfaces without a running platform. Use when writing tests for entity CRUD routes, mocking the entity client, testing NemoJob run() methods, setting up config overrides, or verifying FastAPI route error handling. Trigger keywords: test, pytest, mock entity client, TestClient, dependency_overrides, AsyncMock, test job, test config, test service, test controller.
    2.3k repo stars
  19. ▌
    Plugin Entities 2 · nvidia-nemo
    Defines NemoEntity subclasses and uses NemoEntitiesClient for CRUD in the NeMo Helix entity store. Use when defining a new entity type, storing plugin data in the entity store, handling optimistic locking conflicts, listing entities with filters, or building entity clients for controllers. Trigger keywords: entity, entity store, NemoEntity, entity_type, NemoEntitiesClient, entity client, store data, optimistic lock, EntityConflictError, EntityNotFoundError.
    2.3k repo stars
  20. ▌
    Plugin Function 2 · nvidia-nemo
    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 - function, NemoFunction, spec_schema, add_function_routes, nemo_helix_plugin.functions, streaming, NDJSON, FunctionContext.
    2.3k repo stars
  21. ▌
    Creating A Plugin 2 · 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, entry-points, plugin structure, get started, plugin discovered, entry point.
    2.3k repo stars
  22. ▌
    Plugin Controller 2 · nvidia-nemo
    Creates background reconcile-loop controllers using NemoController. Use when implementing state-machine reconciliation, running periodic background work, managing deployment lifecycle, building service-principal entity clients for background use, or understanding controller startup/shutdown sequence. Trigger keywords: controller, NemoController, reconcile, background loop, reconcile_one, list_objects, on_startup, state machine, deployment lifecycle, service principal, interval_seconds.
    2.3k repo stars
  23. ▌
    Evals · nvidia-nemo
    NeMo Helix evaluator playbook covering metrics, synchronous metric runs, and asynchronous metric jobs through the platform SDK.
    2.3k repo stars
  24. ▌
    Garak · nvidia-nemo
    NeMo Helix garak playbook for audit target and config CRUD through the platform SDK. Use when the task involves audit targets, audit configs, or probes.
    2.3k repo stars
  25. ▌
    Data Designer Skill Refresh · nvidia-nemo
    Refresh the Data Designer plugin's user-facing skill bundle (`skills/nemo-data-designer-plugin/`) from the upstream NVIDIA-NeMo/DataDesigner repo at the pinned library version, adapting CLI commands and platform-specific guidance to NeMo Helix. Use when upstream ships skill changes that need to land here, when auditing drift, or as a step of `data-designer-version-bump`. For bumping the `data-designer` version itself, use `data-designer-version-bump` instead. Trigger keywords - refresh data designer skill, update data designer skill, vendor data designer skill, sync data designer skill.
    2.3k repo stars
  26. ▌
    Garak 2 · nvidia-nemo
    NeMo garak CLI reference for audit configs, targets, and jobs. Use when the task involves audit configurations, audit targets, audit jobs, vulnerability scanning, probes, or `nemo garak` CLI commands.
    2.3k repo stars
  27. ▌
    Inference 5 · nvidia-nemo bundle
    End-to-end reference for inference on the NeMo Helix — registering LLM backends as ModelProviders, wiring them to VirtualModels with Switchyard middleware (random routing, stage routing, capability classification) and `nemo-guardrails` content-safety rails, and hitting them via the nemo CLI. Use when the task involves registering inference providers, discovering served models, creating VirtualModels, configuring switchyard middleware, layering guardrails alongside routing, making OpenAI Chat Completions calls through IGW, or debugging routing failures locally. For platform startup, Switchyard install, and DB-reset prerequisites, see the setup playbook (`SETUP.md` at the repo root).
    2.3k repo stars
  28. ▌
    Nemo Evals · nvidia-nemo bundle
    NeMo Helix Evals 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, code/custom, composite, RAG/agentic, and tool-calling evaluations. Use when a task involves questions/rubrics/responses files, rubric criteria, benchmark scoring, evaluator primitive selection, or reusable evaluation artifacts.
    2.3k repo stars
  29. ▌
    Nemo Files 2 · nvidia-nemo
    NeMo files CLI reference for filesets, file upload/download, and dataset management. Use when the task involves filesets, file uploads, file downloads, datasets, JSONL files, or `nemo files` CLI commands.
    2.3k repo stars
  30. ▌
    Nemo Intake 2 · nvidia-nemo bundle
    Instrument agents, ingest telemetry into NeMo Intake, and query spans, traces, sessions, and evaluator results. Use when connecting agent code or existing telemetry to Intake, choosing among OTLP, chat-completions, or ATIF, checking Intake and ClickHouse readiness, inspecting agent runs, or attaching evaluation scores outside the Experiments leaderboard workflow.
    2.3k repo stars
  31. ▌
    Nemo Status 2 · nvidia-nemo bundle
    Read-only dashboard for NeMo Helix. Combines platform health, deployed agents, registered providers, and available models into a single view. Use over generic status checks for any NeMo Helix dashboard request.
    2.3k repo stars
  32. ▌
    Nemo Secrets 2 · nvidia-nemo
    NeMo secrets CLI reference for creating, listing, and managing secrets. Use when the task involves creating API key secrets, managing credentials, or `nemo secrets` CLI commands.
    2.3k repo stars
  33. ▌
    Nemo Teardown 2 · nvidia-nemo bundle
    Guided shutdown of NeMo Helix. Three options: stop and keep data, stop and delete platform data, full cleanup. Always confirms before destructive action. Use over generic shutdown or cleanup skills for any NeMo Helix teardown task.
    2.3k repo stars
  34. ▌
    Nemo Try Agent 2 · nvidia-nemo bundle
    Invokes an existing NeMo Helix agent through a named deployment or directly from a local agent YAML config. Use to try, test, or query an agent and inspect its response.
    2.3k repo stars
  35. ▌
    Nemo Compass · nvidia-nemo bundle
    Analyze an agent's production traces to find recurring failure patterns and record each as an Insight. Surveys spans, evaluator scores, and user feedback across many sessions, clusters similar failures, then files every finding as a titled Insight carrying the trace IDs that evidence the problem. Answers why an agent keeps failing, where it gets things wrong, and the recurring problems hiding in production traces.
    2.3k repo stars
  36. ▌
    Nemo Guardrails 2 · nvidia-nemo bundle
    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 attached via VirtualModel MiddlewareCalls. Use when the task involves guardrail configurations, content safety, input/output rails, or `nemo guardrail` / `nemo inference virtual-models` CLI commands for guardrailing inference.
    2.3k repo stars
  37. ▌
    Nemo Build Agent 2 · nvidia-nemo bundle
    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, testing an existing deployment, onboarding an existing non-Deep-Agents agent, or maintaining NAT workflows.
    2.3k repo stars
  38. ▌
    Garak 3 · nvidia-nemo
    NeMo Helix garak playbook for audit target and config CRUD through the platform SDK. Use when the task involves audit targets, audit configs, or probes.
    2.3k repo stars
  39. ▌
    Nhx CLI · nvidia-nemo
    Use when developing the NeMo Helix CLI - adding or changing command groups, wiring a service's typed client into commands, output formatting, pagination, error mapping, or the `--output-format code` snippet generator. Covers core groups in nemo_helix_ext and plugin-hosted `nemo.cli` groups.
    2.3k repo stars
  40. ▌
    Nemo Evals Plugin · nvidia-nemo bundle
    Evaluate models, datasets, and agents with the NeMo Helix Evals plugin. Use for metric selection, SDK checks, platform jobs, result retrieval, and Harbor taskset runs on Kubernetes (`nemo evals runs`).
    2.3k repo stars
  41. ▌
    Screenshot · nvidia-nemo
    Capture a headless Playwright screenshot of a Studio page or a single element by data-testid. Use whenever you need an image of the web UI — attaching to a PR, verifying a visual change, comparing light/dark themes, or showing a bug.
    2.3k repo stars
  42. ▌
    Release Test Scope · nvidia-nemo bundle
    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 release planning, cross-functional feature review, QA scoping, and pre-release notes. Do not use it as a generic main-branch changelog.
    2.3k repo stars
  43. ▌
    Create Release Notes · nvidia-nemo bundle
    Draft or audit NeMo Helix release notes by comparing a release ref with a candidate ref, reconciling forward-merged release-line changes, checking published documentation coverage, and recording verified CLI or Studio entry points. Use when asked to create, update, compare, review, or check release notes for a NeMo Helix release. Not for publishing artifacts or running the release workflow.
    2.3k repo stars
  44. ▌
    Data Designer Version Bump · nvidia-nemo
    Bump the upstream NVIDIA NeMo Data Designer library (`data-designer`, `data-designer-config`, `data-designer-engine`) to a new release in nemo-helix. Covers upstream research, pin edits, relocking, dependency-conflict triage, wheel constraints, versioned doc links, generated license/OpenAPI/CLI artifacts, API-change adoption, the vendored plugin skill refresh, and verification. Use when asked to bump, upgrade, or update Data Designer or the data-designer dependency to a new version. Not for nemo-anonymizer, which releases on its own cadence.
    2.3k repo stars
  45. ▌
    Anonymizer 2 · nvidia-nemo bundle
    Use when the user wants to detect and replace, hash, redact, annotate, or rewrite PII (names, emails, phone numbers, locations, ...) in a CSV or Parquet dataset using the NeMo Anonymizer plugin.
    2.3k repo stars
  46. ▌
    Safe Synthesizer 2 · nvidia-nemo bundle
    Use NeMo Safe Synthesizer through task-specific routing: running the CLI or SDK, configuring parameters, troubleshooting runtime failures, inspecting artifacts, and interpreting evaluation outputs. Use when the user asks about safe-synthesizer, NeMo Safe Synthesizer, synthetic data pipeline runs, DP settings, generation failures, artifacts, logs, offline/GPU setup, config overrides, or evaluation metrics.
    2.3k repo stars
  47. ▌
    Simplicity First 2 · nvidia-nemo
    Simplicity gate for ALL code written, fixed, or reviewed in this repo. Invoke BEFORE writing any code change and when reviewing any diff. Treats over-complex or oversized code as a correctness bug, not a style issue.
    2.3k repo stars
  48. ▌
    Gh Stack 2 · nvidia-nemo
    Manage stacked branches and pull requests with the gh-stack GitHub CLI extension. Use when the user wants to create, push, rebase, sync, navigate, or view stacks of dependent PRs. Triggers on tasks involving stacked diffs, dependent pull requests, branch chains, or incremental code review workflows.
    2.3k repo stars
  49. ▌
    Nemo Gym Debugging 2 · nvidia-nemo bundle
    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 problems, and throughput bottlenecks.
    2.3k repo stars
  50. ▌
    Nemo Gym Blade Analysis 2 · nvidia-nemo bundle
    Use when analyzing NeMo Gym benchmark rollouts for BLADE-style reports, writing benchmark methodology notes, checking whether a benchmark is BLADE-ready, comparing model runs, or explaining why a benchmark report passed, failed, or changed. Covers aggregate metrics, rollout evidence, report structure, root-cause taxonomy, judge expectations, and improvement recommendations. For generic reward profiling commands, prefer nemo-gym-reward-profiling; for failed infrastructure jobs, prefer nemo-gym-debugging.
    2.3k repo stars
  51. ▌
    Nemo Gym Reward Profiling 2 · nvidia-nemo bundle
    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 profiling, and rollout_infos. For failed jobs, prefer nemo-gym-debugging.
    2.3k repo stars
  52. ▌
    Guardrails 2 · nvidia-nemo
    Create, validate, attach, inspect, update, or remove NeMo Guardrails configurations through the NeMo Platform SDK.
    2.3k repo stars
  53. ▌
    Benchmark Execution 3 · nvidia-nemo
    Benchmark task execution contract: complete every numbered requirement, execute tool calls directly (never plan-only), and verify final state with a direct retrieve/list before responding. Use for every agentic-use benchmark task.
    2.3k repo stars
  54. ▌
    Files 3 · nvidia-nemo
    platform fileset and file CRUD playbook with the exact `nemo_api(resource='files'|'files.filesets', ...)` sequence used by harbor benchmarks. Use when the task involves filesets, file uploads/downloads, `verify.txt`, `harbor-test-fileset`, or `harbor-final-fileset`.
    2.3k repo stars
  55. ▌
    Evaluator 3 · nvidia-nemo
    NeMo Platform evaluator playbook covering metrics, synchronous metric runs, and asynchronous metric jobs through the platform SDK.
    2.3k repo stars
  56. ▌
    Workspace 3 · nvidia-nemo
    NeMo Platform workspace CRUD playbook through `nemo_api(resource='workspaces')`. Use for workspace creation, listing, retrieval, or deletion.
    2.3k repo stars
  57. ▌
    Verify 2 · nvidia-nemo
    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.
    2.3k repo stars
  58. ▌
    Fix Issue 2 · nvidia-nemo
    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.
    2.3k repo stars
  59. ▌
    Debug Training Logs 2 · nvidia-nemo
    Debug distributed training failures (NeMo, Megatron, PyTorch) from worker stderr logs and optional AIStore daemon logs. Finds root cause across NCCL timeouts, data loading errors, and storage failures.
    2.3k repo stars
  60. ▌
    Nemo Speech Asr Finetune 2 · nvidia-nemo bundle
    Guide NeMo Speech users through ASR fine-tuning with container setup and Lhotse training.
    2.3k repo stars
  61. ▌
    Migrate To Resumable Dataloader 2 · nvidia-nemo bundle
    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 AIStore GetBatch", or "convert this YAML to the resumable path". Walks a NeMo training YAML and optional launcher, data blend, and runtime context through the indexed + resumable Lhotse migration; lints interacting fields; auto-patches safe YAML changes; emits a migration report, pre-flight checklist, and index-build command. Static analysis only; never launches training.
    2.3k repo stars
  62. ▌
    Gh Stack · nvidia-nemo
    Manage stacked branches and pull requests with the gh-stack GitHub CLI extension. Use when the user wants to create, push, rebase, sync, navigate, or view stacks of dependent PRs. Triggers on tasks involving stacked diffs, dependent pull requests, branch chains, or incremental code review workflows.
    2.3k repo stars
  63. ▌
    Nemo Gym Debugging · nvidia-nemo bundle
    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 problems, and throughput bottlenecks.
    2.3k repo stars
  64. ▌
    Nemo Gym Blade Analysis · nvidia-nemo bundle
    Use when analyzing NeMo Gym benchmark rollouts for BLADE-style reports, writing benchmark methodology notes, checking whether a benchmark is BLADE-ready, comparing model runs, or explaining why a benchmark report passed, failed, or changed. Covers aggregate metrics, rollout evidence, report structure, root-cause taxonomy, judge expectations, and improvement recommendations. For generic reward profiling commands, prefer nemo-gym-reward-profiling; for failed infrastructure jobs, prefer nemo-gym-debugging.
    2.3k repo stars
  65. ▌
    Nemo Gym Reward Profiling · nvidia-nemo bundle
    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 profiling, and rollout_infos. For failed jobs, prefer nemo-gym-debugging.
    2.3k repo stars
  66. ▌
    Simplicity First · nvidia-nemo
    Simplicity gate for ALL code written, fixed, or reviewed in this repo. Invoke BEFORE writing any code change and when reviewing any diff. Treats over-complex or oversized code as a correctness bug, not a style issue.
    2.3k repo stars
  67. ▌
    Files 2 · nvidia-nemo
    platform fileset and file CRUD playbook with the exact `nemo_api(resource='files'|'files.filesets', ...)` sequence used by harbor benchmarks. Use when the task involves filesets, file uploads/downloads, `verify.txt`, `harbor-test-fileset`, or `harbor-final-fileset`.
    2.3k repo stars
  68. ▌
    Auditor 2 · nvidia-nemo
    NeMo Platform auditor playbook for audit target and config CRUD through the platform SDK. Use when the task involves audit targets, audit configs, or probes.
    2.3k repo stars
  69. ▌
    Secrets 2 · nvidia-nemo
    NeMo Platform secret CRUD lifecycle through the platform SDK.
    2.3k repo stars
  70. ▌
    Entities 2 · nvidia-nemo
    NeMo Platform model and dataset CRUD lifecycle through the platform SDK, with strict field matching on final verification entities.
    2.3k repo stars
  71. ▌
    Evaluator 2 · nvidia-nemo
    NeMo Platform evaluator playbook covering metrics, synchronous metric runs, and asynchronous metric jobs through the platform SDK.
    2.3k repo stars
  72. ▌
    Inference 2 · nvidia-nemo
    NeMo Platform inference provider registration lifecycle through the platform SDK (secret -> create temp provider -> verify -> delete -> create final provider).
    2.3k repo stars
  73. ▌
    Workspace 2 · nvidia-nemo
    NeMo Platform workspace CRUD playbook through `nemo_api(resource='workspaces')`. Use for workspace creation, listing, retrieval, or deletion.
    2.3k repo stars
  74. ▌
    Auditor 3 · nvidia-nemo
    NeMo auditor CLI reference for audit configs, targets, and jobs. Use when the task involves audit configurations, audit targets, audit jobs, vulnerability scanning, probes, or `nemo auditor` CLI commands.
    2.3k repo stars
  75. ▌
    Inference 3 · nvidia-nemo
    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 CLI. Use when the task involves registering inference providers, discovering served models, creating VirtualModels, configuring switchyard middleware, layering guardrails alongside translate (correct middleware ordering for OpenAI/Anthropic cross-format setups), making inference calls through IGW, or debugging routing and translation failures locally. For platform startup, Switchyard install, and DB-reset prerequisites, see the setup playbook (`SETUP.md` at the repo root).
    2.3k repo stars
  76. ▌
    Auditor 4 · nvidia-nemo
    NeMo Platform auditor playbook for audit target and config CRUD through the platform SDK. Use when the task involves audit targets, audit configs, or probes.
    2.3k repo stars
  77. ▌
    Secrets 3 · nvidia-nemo
    NeMo Platform secret CRUD lifecycle through the platform SDK.
    2.3k repo stars
  78. ▌
    Entities 3 · nvidia-nemo
    NeMo Platform model and dataset CRUD lifecycle through the platform SDK, with strict field matching on final verification entities.
    2.3k repo stars
  79. ▌
    Inference 4 · nvidia-nemo
    NeMo Platform inference provider registration lifecycle through the platform SDK (secret -> create temp provider -> verify -> delete -> create final provider).
    2.3k repo stars
  80. ▌
    Benchmark Execution 2 · nvidia-nemo
    Benchmark task execution contract: complete every numbered requirement, execute tool calls directly (never plan-only), and verify final state with a direct retrieve/list before responding. Use for every agentic-use benchmark task.
    2.3k repo stars
  81. ▌
    Guardrails Developer Guide · nvidia-nemo
    Routes NVIDIA NeMo Guardrails library product-usage questions to the canonical documentation. Use when users ask how to install, configure, integrate, evaluate, observe, deploy, troubleshoot, or use the NVIDIA NeMo Guardrails library. Trigger keywords - install guardrails, configure rails, guardrail catalog, Colang, Python API, LangChain, LangGraph, server, evaluate guardrails, tracing, metrics, Docker, troubleshooting.
    2.3k repo stars
  82. ▌
    Guardrails Developer Create Guardrails · nvidia-nemo
    Helps developers create a NeMo Guardrails configuration for an LLM application. Use when users want to build, scaffold, configure, test, or iterate on input, output, retrieval, dialog, execution, Colang, or catalog-based guardrails. Trigger keywords - create guardrails, build guardrails, scaffold config, write rails, create config.yml, add input rails, add output rails, Colang flow, guardrails config, test guardrails.
    2.3k repo stars
  83. ▌
    Add Benchmark · nvidia-nemo bundle
    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 library. Covers the full workflow: data preparation, resources server implementation, agent wiring, YAML config, testing, and reward profiling (baselining). Triggered by: "add benchmark", "new resources server", "integrate benchmark", "wrap benchmark", "add training environment", "add eval".
    2.3k repo stars
  84. ▌
    Nemo Gym Docs · nvidia-nemo
    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 docs", any request that touches `fern/`.
    2.3k repo stars
  85. ▌
    Nemo Gym Pivot Datasets · nvidia-nemo bundle
    Use when creating, validating, or documenting Nemo Gym pivot datasets from rollout, trajectory, chat-completion, Responses API, or tool-call artifacts. Covers Gym Responses-style row conversion, reconstructing model calls from flattened rollout output, parallel tool-call (function_call_batch) labels, reasoning placement and label leakage, pivot selection, single-step tool-use configs, agent_ref alignment, verifier knobs, expected-action row contracts, and train/eval usage.
    2.3k repo stars
  86. ▌
    Lens Review · nvidia-nemo
    Reviews pending changes in the NeMo Lens repo against the library's load-bearing invariants — SDK-import isolation, hot-path gating, fallback signature parity, span-group and preset placement, semconv naming, value classification, test state isolation, and doc sync.
    2.3k repo stars
  87. ▌
    Lens Create Issue · nvidia-nemo
    Investigate a failing GitHub Actions run or job in the NeMo Lens repo and file a well-structured GitHub issue for the failure. Covers log extraction for each of this repo's CI jobs, duplicate detection, triggering-PR resolution, and assignee lookup.
    2.3k repo stars
  88. ▌
    Lens Pre Pr Check · nvidia-nemo
    Runs the full local gate before opening or updating a pull request in the NeMo Lens repo — tests, lint, pre-commit, copyright headers, docs registration, commit sign-off, and PR title conventions. Catches the failures this repo's CI is known to reject.
    2.3k repo stars
  89. ▌
    Lens Respond To Issue · nvidia-nemo
    Research and draft a maintainer response to a GitHub issue or community question on the NeMo Lens repo. Grounds the answer in the actual code and docs, verifies every citation, and hands the draft back for approval rather than posting it.
    2.3k repo stars
  90. ▌
    Uv Build · nvidia-nemo
    uv package management, dependency groups, PyTorch index handling, hatch build system, and versioning for this repo. Triggers on: uv, uv sync, uv lock, uv add, uv build, dependency, pyproject.toml, extras, cpu, cu129, hatch, wheel, version, publish.
    2.3k repo stars
  91. ▌
    Github CLI · nvidia-nemo bundle
    Interact with the Safe-Synthesizer GitHub repository using the gh CLI. Activate when users want to list or create pull requests, check out PRs, work on someone else's PR, check CI status, investigate workflow failures, view job logs, create or triage issues, check review and approval status, manage releases, or inspect repo metadata. Trigger keywords - pull request, PR, issue, workflow, CI, actions, failed job, job log, release, review, approve, CODEOWNERS, labels, milestone, checkout, gh, GitHub.
    2.3k repo stars
  92. ▌
    Git Worktrees · nvidia-nemo bundle
    Create, clean up, or prune isolated Safe-Synthesizer git worktrees for feature development, PR review, and parallel branches across Cursor, Claude Code, Codex, and plain shells.
    2.3k repo stars
  93. ▌
    Switchyard Docs · nvidia-nemo
    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.
    2.3k repo stars
  94. ▌
    Switchyard Testing CI · nvidia-nemo
    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.
    2.3k repo stars
  95. ▌
    Publish Python Release · nvidia-nemo
    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.
    2.3k repo stars
  96. ▌
    Switchyard Rust Review · nvidia-nemo
    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.
    2.3k repo stars
  97. ▌
    Harbor F2p P2p Deep Dive · nvidia-nemo bundle
    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 when the user asks to analyze, debug, investigate, or deep dive on a Harbor run, trial, or job directory; when the user says "harbor deep dive", "f2p deep dive", or "p2p deep dive"; when a trial scores lower than expected; or when the user wants to assess task fairness, instruction quality, verifier correctness, or whether an F2P or P2P test is reasonable for the instruction given. Works with any Harbor task whose verifier reports F2P/P2P-style results, and with any supported agent (claude-code, opencode, codex). Produces a per-failure root-cause verdict (capability gap / verifier issue / instruction issue) by triangulating verifier output, the agent's implementation, the reference tests, and the instruction.
    2.3k repo stars
  98. ▌
    Gold Review · nvidia-nemo bundle
    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 results. Produces actionable recommendations (keep/remove/demote/promote/edit) with evidence.
    2.3k repo stars
  99. ▌
    Nemotron Nano3 · nvidia-nemo bundle
    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.
    2.3k repo stars
  100. ▌
    Nemotron Ultra · nvidia-nemo bundle
    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.
    2.3k repo stars