Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/NVIDIA-NeMo/nemo-platform.Loading the repository README…
Showing 40 of 69 collected skills.
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…
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…
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…
End-to-end NeMo Platform 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…
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,…
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.
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.
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.
A security war-game for an agent through NeMo Platform: 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`…
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.
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…
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…
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…
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…
Help a user with no evals establish a required Ethos, plan evaluation cases, and set up a small working Harbor suite while explaining its parts. No prior traces or coverage reports are required. Missing Harbor blocks scaffolding and execution, not planning.
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.
Build first evals from a required Ethos or work on existing 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.…
Propose dataset improvements from Eval Author audit findings, then optionally create one Harbor task from one actionable uncovered tool. Prove the task with Harbor's Oracle, run it repeatedly with the repository's real agent when authorized, and accept it…
Use MLflow, Intake, OpenTelemetry, or ATIF trace evidence to derive a private, reproducible Harbor environment candidate.
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.
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…
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,…
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.
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.
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.
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…
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…
Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.
Evaluate models, datasets, and agents with the NeMo Evaluator plugin. Use for metric selection, SDK checks, platform jobs, and result retrieval.
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`…
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…
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…
Create, validate, attach, inspect, update, or remove NeMo Guardrails configurations through the NeMo Platform SDK.
The repository README could not be loaded. You can still explore its Skills below.