all publishers

NVIDIA NeMo

@nvidia-nemo source repo

204 published skills · page 2 of 3

  1. ▌
    Nemotron Super3 · nvidia-nemo bundle
    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.
    2.3k repo stars
  2. ▌
    Nemotron Add Step · nvidia-nemo
    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.
    2.3k repo stars
  3. ▌
    Nemotron Add Model · nvidia-nemo
    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.
    2.3k repo stars
  4. ▌
    Nemotron Add Pattern · nvidia-nemo
    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.
    2.3k repo stars
  5. ▌
    Nemotron Customizer Airgap · nvidia-nemo bundle
    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.
    2.3k repo stars
  6. ▌
    Nemotron Retrieval Recipes · nvidia-nemo bundle
    Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron `embed`/`rerank` retrieval recipes.
    2.3k repo stars
  7. ▌
    Nemotron 3 Ultra Text2sql Lora · nvidia-nemo bundle
    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.
    2.3k repo stars
  8. ▌
    Nemotron 3 5 Lightning Text2sql Lora · nvidia-nemo bundle
    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 a Hugging Face checkpoint. Use when the user wants to run this cookbook, fine-tune Nemotron-3.5 Lightning with LoRA, or adapt the notebook to their own machine.
    2.3k repo stars
  9. ▌
    Nooa Agentdoc · nvidia-nemo
    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 type docs, or tuning value truncation.
    2.3k repo stars
  10. ▌
    Nooa Channels · nvidia-nemo
    Reactive input for NOOA agents — Channel/QueueManager for queued and event-mode input, race() turn dispatch, spawn() background jobs with JobHandle, and the bundled producers (monitor a shell command, cron ticks, one-shot timers, file tails). Use when an agent must react to external input mid-run — user messages, CI output, timers, job completions — or when building an interactive/long-running agent loop.
    2.3k repo stars
  11. ▌
    Context Blocks · nvidia-nemo
    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.
    2.3k repo stars
  12. ▌
    Nooa Trace Viewer · nvidia-nemo
    Run and use the NOOA trace viewer — the web UI + OTLP receiver for browsing agent traces and eval results. Use when starting the viewer, importing/exporting/deleting traces, querying the viewer's REST API, or wiring an agent run so traces show up at localhost:5001.
    2.3k repo stars
  13. ▌
    Nooa Self Extending · nvidia-nemo
    Let NOOA agents extend themselves — persistent skill libraries the agent writes and hot-reloads (SkillWriting / self.libs, LibraryManager), in-cell helper functions and standalone @strategy sub-calls (MethodWriting), and @slash_command user actions. Use when an agent should accumulate reusable code across sessions, define its own helpers or LLM-powered sub-functions at runtime, or ship user-typed /commands from a skill.
    2.3k repo stars
  14. ▌
    Nooa Trace Explorer · nvidia-nemo
    Analyze NOOA execution traces programmatically with the trace-explorer CLI and Python API. Use when debugging why an agent run failed, inspecting LLM turns and code executions, diffing two runs, aggregating errors across an eval experiment, or root-causing behavior from a trace file or viewer session.
    2.3k repo stars
  15. ▌
    Refine Agent Prompt · nvidia-nemo
    Render and refine the system prompt of a nooa agent. Use when the user wants to inspect, debug, or improve an agent's prompt, context blocks, or tool documentation.
    2.3k repo stars
  16. ▌
    Nooa Agent Authoring · nvidia-nemo
    Authoring NVIDIA-labs Object Oriented Agents (NOOA)
    2.3k repo stars
  17. ▌
    Nooa Capturing Traces · nvidia-nemo
    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.
    2.3k repo stars
  18. ▌
    Nooa Codeact Advanced · nvidia-nemo
    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 models that return prose instead of tool calls, writing a custom prefill, restricting generated code, or debugging truncation and eviction.
    2.3k repo stars
  19. ▌
    Nooa Middleware Hooks · nvidia-nemo
    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/LLMComplete/turn events), and the InstrumentationHooks protocol for observability backends. Use when adding guardrails, redacting or rewriting prompts, blocking or faking an LLM call or code execution, rate-limiting agent methods, subscribing to lifecycle events, or wiring custom telemetry.
    2.3k repo stars
  20. ▌
    Nooa Tools And Skills · nvidia-nemo
    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 reusable guidance as an agent skill.
    2.3k repo stars
  21. ▌
    Nooa Context And State · nvidia-nemo
    Manage what a NOOA agent sees and remembers — context blocks, event history and queries, history summarization, and persistent memory/storage. Use when pinning information into the system prompt, querying past events, bounding context growth in long conversations, or persisting agent state.
    2.3k repo stars
  22. ▌
    Trace Explorer · nvidia-nemo
    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.
    2.3k repo stars
  23. ▌
    Grid Game Solver · nvidia-nemo
    Solve an interactive grid game iteratively — observe, hypothesize, experiment, record knowledge, and submit action sequences until every level is won.
    2.3k repo stars
  24. ▌
    Interactive Game Solver · nvidia-nemo
    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.
    2.3k repo stars
  25. ▌
    Nemo Teardown · nvidia-nemo bundle
    Guided shutdown of NeMo Platform. 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 Platform teardown task.
    2.3k repo stars
  26. ▌
    Skills Optimization · nvidia-nemo
    Improve agent skills via the `nemo agents` plugin (evaluate-suite / analyze / optimize-skills). Use when the user wants to improve an agent's skills using a Harbor or NAT eval suite, run a batch of agentic tests, analyze why evals fail, or kick off an automated skill-optimization loop. Trigger keywords - optimize skills, evaluate agent suite, analyze eval batch, skills optimizer, harbor evals.
    2.3k repo stars
  27. ▌
    Refresh Data Designer Skill · nvidia-nemo
    Refresh the vendored data-designer skill bundle in this plugin from the upstream NVIDIA-NeMo/DataDesigner repo at the pinned library version, adapting CLI commands and platform-specific guidance to the NeMo plugin context. Use when bumping the `data-designer` library pin in pyproject.toml, when upstream ships skill changes that need to land here, or when auditing drift. Trigger keywords - refresh data designer skill, update data designer skill, vendor data designer skill, sync data designer skill, bump data-designer version.
    2.3k repo stars
  28. ▌
    Nemo Evaluator · nvidia-nemo bundle
    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, 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 Try Agent · nvidia-nemo bundle
    Invokes an existing NeMo Platform 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
  30. ▌
    Nemo Guardrails · nvidia-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 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
  31. ▌
    Nemo Build Agent · nvidia-nemo bundle
    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, testing an existing deployment, onboarding an existing non-Deep-Agents agent, or maintaining NAT workflows.
    2.3k repo stars
  32. ▌
    Nemo Agent Config · 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
  33. ▌
    Deploy Sandbox · nvidia-nemo bundle
    Deploys an already-built NAT agent as a policy-governed OpenShell sandbox on a local NeMo Platform, so the same agent image gets Landlock filesystem isolation and a pure default-deny network policy (the sandbox reaches nothing on the network directly; its model calls are brokered by the OpenShell gateway through the inference.local route) for free. Covers the proven wire-inference.local -> package -> DeploymentConfig -> deploy (executor openshell-local) -> wait -> query -> zero-egress proof -> cleanup flow. Use when the user asks to deploy an agent as a sandbox, sandbox a deployment, run an agent under a Landlock/egress policy, or use the openshell-local executor. Trigger keywords - deploy sandbox, sandboxed agent, openshell deployment, openshell-local executor, sandbox policy, egress policy, landlock, governed deployment, network egress governance, inference.local.
    2.3k repo stars
  34. ▌
    Supercool Guidelines · 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
  35. ▌
    Guardrails Plugin · nvidia-nemo bundle
    Use when working on guardrailing chat completions through the Inference Gateway API — creating guardrail configs, validating them with the `/checks` endpoint, attaching `nemo-guardrails` middleware to a VirtualModel, or proving guarded behavior.
    2.3k repo stars
  36. ▌
    Nemo Model Selection · nvidia-nemo bundle
    Recommends an LLM for a NeMo Platform agent based on what the agent actually has to do, explained in plain English before any benchmark name appears. Use when the user is choosing a model for a new agent, assessing a model they already selected, or deciding what belongs in ETHOS.md or Platform agent.yaml. Invoked by nemo-explore at the model question; also runs standalone when the user starts mid-flow.
    2.3k repo stars
  37. ▌
    Nemo Skill Selection · nvidia-nemo bundle
    Top-level skill selector for ambiguous tasks involving NeMo Platform (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 Platform task should start.
    2.3k repo stars
  38. ▌
    Terminator · nvidia-nemo
    Guidance for the Terminator's qualitative stop check: judge whether the optimization has plateaued in ways the numeric scores don't capture, from the latest round's analysis text, and return stop / continue.
    2.3k repo stars
  39. ▌
    Nemo Experiments Upload · nvidia-nemo bundle
    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 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
  40. ▌
    Plugin Job · nvidia-nemo
    Creates schedulable NemoJob surfaces for NeMo Platform plugins. Use when adding a job, declaring spec_schema / input_spec_schema / to_spec / compile, mounting job routes with add_job_routes, understanding the three CLI verbs (run / submit / explain), or running jobs in containers. Trigger keywords - job, NemoJob, spec_schema, input_spec_schema, to_spec, compile, add_job_routes, nemo_platform_plugin.jobs, three verbs, run, submit, explain, NemoJobScheduler.
    2.3k repo stars
  41. ▌
    Plugin Authz · nvidia-nemo bundle
    Plugin HTTP Authorization (path_rule / AuthzScope)
    2.3k repo stars
  42. ▌
    Plugin Config · nvidia-nemo
    Plugin Configuration (NemoConfig)
    2.3k repo stars
  43. ▌
    Plugin Service · nvidia-nemo bundle
    Plugin HTTP Service (NemoService)
    2.3k repo stars
  44. ▌
    Plugin Testing · nvidia-nemo
    Testing NeMo Platform Plugins
    2.3k repo stars
  45. ▌
    Plugin Entities · nvidia-nemo
    Plugin Entities (NemoEntity + NemoEntitiesClient)
    2.3k repo stars
  46. ▌
    Plugin Function · nvidia-nemo
    Creates in-process NemoFunction surfaces for NeMo Platform plugins. Use when adding a function, declaring spec_schema, mounting function routes with add_function_routes, understanding the two CLI verbs (run / submit), or streaming NDJSON frames. Trigger keywords - function, NemoFunction, spec_schema, add_function_routes, nemo_platform_plugin.functions, two verbs, run, submit, streaming, NDJSON, FunctionContext.
    2.3k repo stars
  47. ▌
    Safe Synthesizer · nvidia-nemo bundle
    Use NeMo Safe Synthesizer from the NMP plugin through platform job creation, configuration, troubleshooting, artifacts, privacy settings, PII replacement, and evaluation reports. Use when the user asks about safe-synthesizer, NeMo Safe Synthesizer, synthetic tabular data, DP settings, generation failures, filesets, model filesets, or Safe Synthesizer jobs.
    2.3k repo stars
  48. ▌
    Creating A Plugin · nvidia-nemo
    Creating a NeMo Plugin
    2.3k repo stars
  49. ▌
    Plugin Controller · nvidia-nemo
    Plugin Controllers (NemoController)
    2.3k repo stars
  50. ▌
    Nemo Experimentalist · nvidia-nemo bundle
    Improve an existing NeMo agent's source or harness from an Insight or explicit Harbor-compatible evaluation datasets. Run the Experimentalist to propose and validate candidate code changes, then optionally publish a changed winner as a draft PR or MR.
    2.3k repo stars
  51. ▌
    Plugin Platform Services · nvidia-nemo bundle
    Platform Services for Plugins
    2.3k repo stars
  52. ▌
    Plugin Inference Middleware · nvidia-nemo
    Inference Middleware Plugin
    2.3k repo stars
  53. ▌
    Nmp CLI · nvidia-nemo
    Use when developing the NeMo Platform CLI - adding commands, modifying the generator, templates, or configuration. Covers both manual commands (use-cases, config) and auto-generated API commands. Also helps troubleshoot CLI generation failures (e.g., Typer errors after updates).
    2.3k repo stars
  54. ▌
    Studio Dev · nvidia-nemo
    Switch into Studio development mode for working on the NeMo Studio frontend in web/. Use when starting frontend work, building UI features, or working on React components.
    2.3k repo stars
  55. ▌
    E2e Test · nvidia-nemo
    End-to-end testing workflow with Playwright. Use when writing, running, or debugging E2E tests for Studio user flows.
    2.3k repo stars
  56. ▌
    Nemo Evaluator Plugin · nvidia-nemo bundle
    Evaluate models, datasets, and agents with the NeMo Evaluator plugin. Use for metric selection, SDK checks, platform jobs, and result retrieval.
    2.3k repo stars
  57. ▌
    UI Design · nvidia-nemo bundle
    Reference hub for implementing UI changes in Studio. Use whenever building or modifying Studio frontend UI — pages, components, tables, panels, empty states, and other shared patterns. Routes to the standardized references below.
    2.3k repo stars
  58. ▌
    Unit Test · nvidia-nemo
    Unit testing workflow with Vitest and React Testing Library. Use when writing, running, or debugging unit tests for Studio components and utilities.
    2.3k repo stars
  59. ▌
    Visual Dev · nvidia-nemo
    Screenshot-driven visual development workflow using Playwright MCP. Use when implementing designs from mockups or Figma, building new UI components, or fixing visual bugs.
    2.3k repo stars
  60. ▌
    Nemo Data Designer Plugin · nvidia-nemo bundle
    Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.
    2.3k repo stars
  61. ▌
    Feature Flags · nvidia-nemo
    Inspect and manage Studio feature flags. Use when working with feature flags, adding new flags, checking flag state across environments, or debugging why a feature is enabled/disabled.
    2.3k repo stars
  62. ▌
    UX Guidelines · nvidia-nemo
    UX design guidelines and standards for NeMo Studio. Use when implementing new UI features, reviewing designs, or making UX decisions.
    2.3k repo stars
  63. ▌
    Studio Worktree · nvidia-nemo bundle
    Prepare the current git worktree for Studio web/ development — copies missing .env.*.local files and runs pnpm install. Use when the user is inside a newly-created linked worktree and wants to bring it to a runnable state. Does NOT create/remove worktrees — use your tool's built-in worktree features for that (Claude Code --worktree, Cursor, git worktree add, etc.).
    2.3k repo stars
  64. ▌
    Contributor Create Pr · nvidia-nemo
    Create, publish, or advance a GitHub pull request for NVIDIA-NeMo/nemo-platform with repository-aware branch checks, targeted validation, DCO sign-off enforcement, trusted PR-template completion and post-push description refresh, conventional titles, safe pushes, draft or ready-for-review creation, CI and CodeRabbit follow-up, and merge-conflict handling. Use when the user asks to commit and push work, create or open a PR, submit changes for review, mark a draft ready, monitor a PR, address automated review or CI feedback, or update a conflicted PR in nemo-platform.
    2.3k repo stars
  65. ▌
    Add Studio Feature Flag · nvidia-nemo
    Adds a NeMo Studio (Vite) feature flag end-to-end: typed definition, runtime injection mapping, FastAPI build env markers, and optional Helm config. Use when the user asks for a new feature flag, VITE_FF_ variable, studio.feature_flags setting, toggling UI behind a flag, or preview/boolean flags for Studio.
    2.3k repo stars
  66. ▌
    Files · 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
  67. ▌
    Auditor · 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
  68. ▌
    Secrets · nvidia-nemo
    NeMo Platform secret CRUD lifecycle through the platform SDK.
    2.3k repo stars
  69. ▌
    Eval Author · nvidia-nemo
    Work on evaluation suites in a user's repository, derive an environment from trace evidence, or understand an agent run from NeMo Intake. Owns the evidence standard that every Eval Author sub-flow follows. Use when the user asks "help me with my evals", "what's the state of the eval suite here?", "what happened in this trace?", or when you need to pick between the Eval Author sub-flows. Routes to a sub-flow and changes none of the user's source. The selected sub-flow uses the provider's supported tools and saves its findings under `.eval-author/`.
    2.3k repo stars
  70. ▌
    Entities · 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. ▌
    Test Coverage Improvement · nvidia-nemo
    Autonomous Vitest coverage workflow for a chosen package under web/packages: baseline report, agent-curated shortlist of ~10 files, then per-file context from reading source, inferred behaviors, implemented tests, and verification (vitest + typecheck) before the next file; after the loop, **eslint only the files you created or edited** and fix issues. Human review happens outside this skill (e.g. MR, local diff). Use when improving unit coverage in the web monorepo. Trigger keywords — package coverage, vitest coverage, pnpm workspace tests, coverage baseline, raise coverage.
    2.3k repo stars
  72. ▌
    Evaluator · nvidia-nemo
    NeMo Platform evaluator playbook covering metrics, synchronous metric runs, and asynchronous metric jobs through the platform SDK.
    2.3k repo stars
  73. ▌
    Inference · 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
  74. ▌
    Workspace · nvidia-nemo
    NeMo Platform workspace CRUD playbook through `nemo_api(resource='workspaces')`. Use for workspace creation, listing, retrieval, or deletion.
    2.3k repo stars
  75. ▌
    Guardrails · nvidia-nemo
    Create, validate, attach, inspect, update, or remove NeMo Guardrails configurations through the NeMo Platform SDK.
    2.3k repo stars
  76. ▌
    Mlflow To Atif · nvidia-nemo bundle
    Convert bounded live MLflow traces or exported Trace.to_dict() JSON into one canonical ATIF trajectory per trace for Harbor or Eval Author audit coverage. Use for MLflow-to-ATIF conversion, not Intake ingestion.
    2.3k repo stars
  77. ▌
    Eval Author Audit · nvidia-nemo bundle
    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, needs schema enforcement for declared tools, capabilities, failure cases, evidence, and references, wants to measure which audit items one ATIF trace covers, or wants to aggregate coverage across measured traces. Changes none of the user's source, and saves audit artifacts under `.eval-author/`.
    2.3k repo stars
  78. ▌
    Nooa · nvidia-nemo
    Build, modify, debug, or optimize agents using NVIDIA-labs OO Agents (NOOA). Use for nooa.Agent subclasses, ellipsis generation methods, CodeAct or Predict strategies, ShellTools, Skill/TextSkill, context and persistence, MCP, tracing, middleware, channels, or trace analysis.
    2.3k repo stars
  79. ▌
    Eval Author Discover · nvidia-nemo bundle
    Record whether a repository's Harbor evaluations are ready to run, and prove it with Harbor's own validators instead of guessing. Finds every repository-owned job config, dataset, and task directory, then makes Harbor judge each config: schema, job resolution, agent, environment backend, per-task validity, tasks Harbor silently dropped, and required host variables. Use when the user wants to run an eval suite they did not write, hand a suite to a cheaper model, or asks "can I run these evals?", "why won't my Harbor config resolve?", "which env vars does this suite need?", "where are the evals in this repo?", or "why did Harbor skip my task?". Changes none of your source, and leaves behind `.eval-author/discovery.md` so your team and the next model read the verdict without Harbor and without discovering again.
    2.3k repo stars
  80. ▌
    Benchmark Execution · 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. ▌
    Eval Author Task Create · nvidia-nemo bundle
    Create one Harbor task from one actionable uncovered tool in an Eval Author audit coverage report, prove the task with Harbor's Oracle, run it repeatedly with the repository's real agent when authorized, and accept it only when measured ATIF closes the selected gap every time. Use when the user asks to fill an eval gap, turn audit uncovered_items into a Harbor task, or add missing tool coverage. Writes drafts and measurements only under `.eval-author/`.
    2.3k repo stars
  82. ▌
    Eval Author Inspect Trace · nvidia-nemo
    Use when eval-author has routed to this sub-flow for one Intake trace. Do not use for instrumenting agents, ingesting telemetry, importing a trace store, verifying ingest, or querying Intake outside Eval Author; those belong to nemo-intake.
    2.3k repo stars
  83. ▌
    Eval Author Trace Environment · nvidia-nemo bundle
    Turn one MLflow, Intake, OpenTelemetry, or existing ATIF trace into a private, text-only candidate for a reproducible Harbor task environment. Use when a coding agent should derive an evaluation environment from recorded behavior and retain a candidate or no_candidate summary by task.
    2.3k repo stars
  84. ▌
    Agents Secure · nvidia-nemo bundle
    Audits a deployed NeMo agent for safety and security risks: missing content-safety guardrails on the model endpoint, PII exposure, and leaked API keys / secrets in recent telemetry. Persists snapshots and structured suggestions to the NeMo files service for diffing and UI rendering. Use when the user asks to secure, harden, audit, or review the safety of an agent, when the user mentions guardrails, content safety, jailbreaks, PII, leaked secrets, leaked API keys, sensitive data leaks, telemetry redaction, Safe Synthesizer, Anonymizer, GLiNER, or NemoGuard. Trigger keywords - secure agent, harden agent, agent safety, agent security, guardrails, content safety, PII, data safety, secrets scan, leaked api key, leaked token, telemetry scan, redact telemetry, Safe Synthesizer, Anonymizer, gliner, nemoguard.
    2.3k repo stars
  85. ▌
    Agents Optimize · nvidia-nemo
    Optimizes and accelerates a deployed NeMo agent by suggesting switchyard routing splits, skill optimization, prompt/hyperparameter tuning, and evaluations against newly available models. Persists snapshots and structured suggestions to the NeMo files service for diffing and UI rendering. Use when the user asks to optimize, accelerate, tune, route, or reduce the cost of an agent or its underlying model. Trigger keywords - agent optimization, optimize agent, accelerate agent, smaller model, switchyard router, routing split, agents optimize-skills, agents optimize, agents evaluate, new model scan, nemotron, frontier model.
    2.3k repo stars
  86. ▌
    Langchain Framework · nvidia-nemo bundle
    Guidance for building LLM-powered agents with LangChain, LangGraph, or Deep Agents. Use when building agents with any of these frameworks, implementing tool-calling agents, stateful graph workflows, or multi-step orchestration. Read this skill before writing any LangChain/LangGraph agent code.
    2.3k repo stars
  87. ▌
    Nemo Ethos · nvidia-nemo bundle
    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 derivable from the agent's workspace and name — this skill does not return or persist a ref. Use over generic planning skills for any NeMo Platform agent Ethos.
    2.3k repo stars
  88. ▌
    Nemo Files · 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
  89. ▌
    Nemo Customizer · nvidia-nemo bundle
    Fine-tune models on NeMo Platform with `automodel`, `unsloth`, or `rl` (all `submit`-only): HF dataset conversion, filesets, model entities, and job JSON (hyperparameters, batch, schedule, optimizer) + job polling. `automodel`/`unsloth` run SFT/LoRA as Docker GPU jobs; `rl` runs DPO (preference) or GRPO (NeMo Gym environment + reward) on a Ray cluster (Kubernetes). Covers building and converting NeMo Gym environment packages (native-v1, wheels-v1, adapter-wheels-v1) and Gym rollout-row datasets. Use for train, fine-tune, customize, SFT, LoRA, DPO, GRPO, RLHF, reinforcement learning, reward environment, NeMo Gym, verifiers, Prime Intellect, preference optimization, learning rate, epochs, or nemo customization.
    2.3k repo stars
  90. ▌
    Nemo Analyst · 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. Produces the Insight that the Experimentalist later acts on.
    2.3k repo stars
  91. ▌
    Nemo Intake · 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
  92. ▌
    Nemo Status · nvidia-nemo bundle
    Read-only dashboard for NeMo Platform. Combines platform health, deployed agents, registered providers, and available models into a single view. Use over generic status checks for any NeMo Platform dashboard request.
    2.3k repo stars
  93. ▌
    Example Debug · nvidia-nemo bundle
    Demonstrates plugin skill companion file installation from the example plugin.
    2.3k repo stars
  94. ▌
    Example Hello · nvidia-nemo
    Demonstrates a minimal plugin-provided skill from the example plugin.
    2.3k repo stars
  95. ▌
    Nemo Explore · nvidia-nemo bundle
    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 Platform agent design conversation.
    2.3k repo stars
  96. ▌
    Nemo Secrets · 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
  97. ▌
    Iron Swarm · nvidia-nemo
    NeMo Iron Swarm CLI reference for red-teaming and hardening NAT agents. Use when the task involves attacking, red-teaming, hardening, or running a security war-game against an agent, or any `nemo iron-swarm` CLI command.
    2.3k repo stars
  98. ▌
    Anonymizer · nvidia-nemo bundle
    Use when the user wants to anonymize a text dataset, redact PII, de-identify free-text data, or rewrite text to remove sensitive or inferable identifying information. Produces a runnable Python script that calls the NeMo Anonymizer pipeline (detection → replace or rewrite).
    2.3k repo stars
  99. ▌
    L0 Test · nvidia-nemo
    Reproduce all L0 PR CI checks locally for the Emerging-Optimizers repo — pre-commit lint on host, then all CPU and GPU tests inside the NGC pytorch container. Use before opening or updating a PR to catch CI failures locally.
    2.3k repo stars
  100. ▌
    Verify · 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