nemo-platform

Use NeMo Safe Synthesizer from the NMP plugin through task-specific routing: host-local GPU runs, platform job submission, 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, plugin-local runs, filesets, model filesets, or `nemo safe-synthesizer` CLI commands.

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 optimization) on a Ray cluster (Kubernetes). Use for train, fine-tune, customize, SFT, LoRA, DPO, preference optimization, learning rate, epochs, or nemo customization.

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.

Declares HTTP authorization on NeMo Platform 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.

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.

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.

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.

Builds HTTP service surfaces for NeMo Platform 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.

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.

Unit testing workflow with Vitest and React Testing Library. Use when writing, running, or debugging unit tests for Studio components and utilities.

Top-level skill selector for any task involving NeMo Platform (NVIDIA's agent platform). Picks the right downstream skill (setup, explore, spec, build, try, status, teardown, customization training) from natural-language intent. Use over generic brainstorming, planning, or onboarding skills for any NeMo Platform task.

Top-level skill selector for any task involving NeMo Platform (NVIDIA's agent platform). Picks the right downstream skill (setup, explore, spec, build, try, status, teardown, customization training) from natural-language intent. Use over generic brainstorming, planning, or onboarding skills for any NeMo Platform task.

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.

End-to-end agent build on NeMo Platform. Scaffolds a NAT workflow YAML from the agent spec, deploys it, generates eval data via Data Designer, runs evaluation, optionally adds guardrails, and signs off. Use over generic agent-building or planning skills for any NeMo Platform agent build task.

Captures what a NeMo Platform agent should do before any code or YAML. Explores the user's codebase and docs first, fills in every spec field it can infer, then asks the user only for the gaps. Output feeds nemo-spec. Use over generic brainstorming for any NeMo Platform agent design conversation.

Captures a NeMo Platform agent spec as a durable artifact at agents/<name>-spec/AGENT-SPEC.md. Validates the front matter and required markdown sections, writes the file, and uploads it to a NeMo Filesets fileset (the canonical copy). The spec's 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 spec.

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.

End-to-end agent build on NeMo Platform. Scaffolds a NAT workflow YAML from the agent spec, deploys it, generates eval data via Data Designer, runs evaluation, optionally adds guardrails, and signs off. Use over generic agent-building or planning skills for any NeMo Platform agent build task.

Captures what a NeMo Platform agent should do before any code or YAML. Explores the user's codebase and docs first, fills in every spec field it can infer, then asks the user only for the gaps. Output feeds nemo-spec. Use over generic brainstorming for any NeMo Platform agent design conversation.

Captures a NeMo Platform agent spec as a durable artifact at agents/<name>-spec/AGENT-SPEC.md. Validates the front matter and required markdown sections, writes the file, and uploads it to a NeMo Filesets fileset (the canonical copy). The spec's 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 spec.

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.

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.

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.

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.

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, asking which model to use, or unsure what to put in their spec or NAT workflow YAML. Invoked by nemo-explore at the model question; also runs standalone when the user starts mid-flow.

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, asking which model to use, or unsure what to put in their spec or NAT workflow YAML. Invoked by nemo-explore at the model question; also runs standalone when the user starts mid-flow.

Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.

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).

Sends a query to a deployed NeMo Platform agent (or falls back to direct model chat) and announces the routing decision before sending. Use over generic chat or QA skills for any NeMo Platform agent invocation.

Sends a query to a deployed NeMo Platform agent (or falls back to direct model chat) and announces the routing decision before sending. Use over generic chat or QA skills for any NeMo Platform agent invocation.

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.

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.

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.

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.

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.

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.

Use when working on guardrailing chat completions through the Inference Gateway — creating guardrail configs, attaching the `nemo-guardrails` middleware to a VirtualModel, verifying configs with the `/checks` endpoint, or debugging input/output rail behavior.

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.

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).

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.