Skip to main content
skill CX Codex

nemo-relay-plugin-observability — Claude Code skill

nemo-relay-plugin-observability — a Claude Code skill for selecting and configuring observability exporters and subscribers in NeMo Relay 0.6 and 0.7.

Apache-2.0 140 installs ★ 4,106 updated 2026-10-23

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add NVIDIA/skills --skill nemo-relay-plugin-observability -a claude-code
Open on GitHub

What nemo-relay-plugin-observability does

The skill configures monitoring through built-in plugins, subscribers, and exporters, supporting raw ATOF events, ATIF trajectories, OpenTelemetry, and OpenInference. Configuration depends on whether the application runs NeMo Relay version 0.6 with separate OpenTelemetry and OpenInference exporters or version 0.7 with a typed unified exporter.

Before binding APIs, establish the application version using the package manifest or lockfile. The skill covers language bindings for Python, Node.js, Rust, and Go. It advises starting with ATOF for local inspection and adding payload sanitization before sending data to production exporters.

Invoke this skill when configuring telemetry, selecting exporters, or debugging event streams in NeMo Relay.

What it helps with

  • configure telemetry exporters for NeMo Relay
  • select between version 0.6 and 0.7 configuration
  • set up OpenTelemetry tracing
  • capture raw ATOF events or ATIF trajectories

Example prompts for the agent

  • Configure NeMo Relay 0.7 observability with OpenTelemetry
  • Help me choose an exporter for raw ATOF events in NeMo Relay 0.6
  • Register an OpenInference subscriber for my NeMo Relay project

How to install nemo-relay-plugin-observability

1Skills CLI (Vercel)

npx skills add NVIDIA/skills --skill nemo-relay-plugin-observability -a claude-code

2Manually: put the files in place

~/.claude/skills/nemo-relay-plugin-observability/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/nemo-relay-plugin-observability/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about nemo-relay-plugin-observability

How to install nemo-relay-plugin-observability in Claude Code?

Run npx skills add NVIDIA/skills --skill nemo-relay-plugin-observability -a claude-code in your terminal, then reference ~/.claude/skills/nemo-relay-plugin-observability/SKILL.md.

What does nemo-relay-plugin-observability do?

It guides the setup of telemetry, subscribers, and exporters for NeMo Relay 0.6 and 0.7, supporting OpenTelemetry, OpenInference, and ATOF data streams.

What is required to use nemo-relay-plugin-observability?

A project using NeMo Relay version 0.6 or 0.7 in Python, Node.js, Rust, or Go.

Source text

SKILL.md · Apache-2.0
---
name: nemo-relay-plugin-observability
description: Use this skill when choosing or configuring NeMo Relay 0.6 or 0.7 observability through the built-in plugin, subscribers, or exporters, including raw ATOF events, ATIF trajectories, OpenTelemetry, OpenInference, or custom event handling.
license: Apache-2.0
metadata:
  author: NVIDIA Corporation and Affiliates
---

# Configure Observability Plugins

Start with one exporter managed by the built-in Observability plugin. This is
the default for reusable process configuration and the best first plugin for
most users because it makes Relay's captured activity visible.
Choose one proof output before layering additional telemetry destinations.

Use manual subscriber or exporter APIs only when a test, script, or application
needs direct control over registration names, collection windows, or flush
timing. Both paths consume the same canonical event stream.

## Select The Relay Version

Determine whether the application uses NeMo Relay 0.6 or 0.7 before proposing
configuration or binding APIs. Prefer the installed package version, lockfile,
or manifest. Ask the user when the version cannot be established; do not mix
the two surfaces in one example.

- **0.6** uses observability configuration version 2. OpenTelemetry and
  OpenInference are separate exporters with `OpenTelemetryConfig` /
  `OpenTelemetrySubscriber` and `OpenInferenceConfig` /
  `OpenInferenceSubscriber`.
- **0.7** uses observability configuration version 3. One typed OpenTelemetry
  exporter provides `full`, `gen_ai`, and `openinference` projections.

## Choose The Output

Select the output that best matches the user's immediate inspection target:

- **Console or custom event handling**
  Use a manual subscriber for short-lived in-process inspection.
- **Raw canonical lifecycle events**
  Use ATOF JSONL; read `references/atof.md`.
- **Portable execution trajectories**
  Use ATIF; read `references/atif.md`.
- **OTLP tracing**
  For 0.6, choose the separate OpenTelemetry or OpenInference exporter. For
  0.7, choose a typed OpenTelemetry endpoint (`full`, `gen_ai`, or
  `openinference`). Read `references/opentelemetry.md` and, for an
  OpenInference-aware backend, `references/openinference.md`.

Choose one output first and verify it before adding another. ATOF is the
default local proof because it preserves the raw event stream with the least
translation. Use synthetic, non-sensitive payloads for the first proof. Add and
verify sanitization before exporters receive production payloads, and never
display complete event records while validating an exporter.

## Embedded Event And Subscriber Model

Use this model when explaining how capture and export relate:

- NeMo Relay emits one canonical event stream from scopes, marks, managed tool
  calls, managed LLM calls, middleware, and manual lifecycle APIs.
- Subscribers consume events without defining the event model. Multiple
  subscribers can observe the same stream for logging, export, analytics, or
  diagnostics.
- Global subscribers remain active process-wide until removed.
- Scope-local subscribers are owned by one active scope and disappear when that
  scope closes.
- Plugin-installed subscribers are reusable, configuration-driven runtime
  components.
- Exporter-oriented subscribers preserve raw ATOF or translate the event stream
  into ATIF or the version-appropriate OpenTelemetry/OpenInference form.
- Event payloads reflect sanitized post-guardrail input and output when calls
  use managed helpers or manual lifecycle params provide those fields.
- LLM annotations follow the freshness rules:
  - Each owning agent scope starts fresh, and a `compaction` mark refreshes it.
  - The first subsequent LLM start retains complete annotation history. Later
    starts retain system instructions, the latest user message, and every
    following assistant or tool message.
  - When a request codec supplies an annotation, Relay applies the same
    event-only projection to provider-shaped event input without changing
    provider execution.
- Event fields include semantic input/output through the ATOF `data` field,
  typed profile data such as `model_name` and `tool_call_id`, and codec-provided
  annotated LLM request/response data for in-process subscribers and exporters.
- First-class skill tools and the requests to read a complete `SKILL.md`
  automatically emit `skill.load` marks under the tool span. The payload
  contains only `skill_name`; metadata records the load source and tool name.
  Partial reads do not count, and ambiguous slash-command expansions use the
  separate `skill.load.inferred` name. The eager mark remains present if tool
  execution later fails.

## Shared Lifecycle

1. Create the exporter or subscriber.
2. Register it with a unique name before the relevant scoped work.
3. Run NeMo Relay-instrumented work inside scopes.
4. Flush and deregister in the exporter-specific reference's documented order.
5. Shut it down when the process or subsystem is done.

## Binding Names

Use the names exported by the selected language binding and Relay version:

- Python 0.6: `nemo_relay.subscribers.register(...)`, `AtofExporter`,
  `AtifExporter`, `OpenTelemetrySubscriber`, and `OpenInferenceSubscriber`
- Python 0.7: the same registration and file exporters, plus
  `OpenTelemetrySubscriber` for all three typed projections
- Node.js follows the same 0.6/0.7 split through its root exports
- Rust: `nemo_relay::api::subscriber` and `nemo_relay::observability::*`
- Go: source-first wrappers expose equivalent register, exporter, and subscriber
  lifecycle methods

## Load A Reference When

Load only the reference required by the selected output:

- Load `references/atof.md` for raw JSONL events used in local debugging or
  offline inspection.
- Load `references/atif.md` for ATIF trajectories.
- Load `references/opentelemetry.md` for OTLP/OpenTelemetry traces.
- Load `references/openinference.md` for the standalone 0.6 OpenInference
  exporter or the 0.7 `openinference` OpenTelemetry projection.

## Use Another Skill When

Choose another skill when the task belongs to an adjacent workflow:

- Use `nemo-relay-plugin-build` to package subscriber-based export behavior as
  a reusable plugin.
- Use `nemo-relay-get-started` or `nemo-relay-instrument-calls` when no scope,
  tool call, or LLM call has been instrumented.
- Use `nemo-relay-debug-runtime-integration` to diagnose missing telemetry.

## Related Skills

Use these skills for adjacent workflows:

- Instrument application calls with `nemo-relay-instrument-calls`.
- Add typed wrappers with `nemo-relay-instrument-typed-wrappers`.
- Package reusable behavior with `nemo-relay-plugin-build`.
- Diagnose missing events with `nemo-relay-debug-runtime-integration`.

© NVIDIA Corporation and Affiliates · Apache-2.0 · NVIDIA/skills

Similar skills

All skills for AI and ML →

From the same set312

The whole set →
doca-container-deployment The doca-container-deployment skill deploys DOCA services as containers on BlueField using kubelet standalone. Use it when running Argus, DMS, Firefly, or UROM from pod specs and troubleshooting startup or service readiness issues. CX Codex +1 145installs doca-gpunetio This skill covers hands-on DOCA GPUNetIO work: connecting CUDA kernels to network queues and checking whether a GPU can run the path. CX Codex +1 144installs doca-dma Get help configuring and debugging memory copies with DOCA DMA. The skill covers memcpy tasks between host and DPU memory. CX Codex +1 143installs doca-comch doca-comch is a Claude Code skill for setting up DOCA Comch messaging between a host and BlueField. It handles role selection, transfer modes, capability checks, and API errors. CX Codex +1 142installs doca-compress doca-compress is a Claude Code skill for moving DEFLATE compression and DEFLATE or LZ4 decompression to DOCA Compress. It activates for task setup, buffer checks, and accelerator errors. CX Codex +1 140installs doca-dms doca-dms is a Claude Code skill for managing NVIDIA DOCA Management Service on BlueField, hosts, and Kubernetes, with local dms-cli and remote gNMI/gNOI operations. CX Codex +1 138installs doca-eth Guides DOCA Ethernet packet queue setup on BlueField DPUs and ConnectX NICs, covering RX queue selection, buffer sizing, and error diagnosis. CX Codex +1 137installs doca-sha The doca-sha skill guides SHA acceleration through DOCA on BlueField-2. Use it to choose a hashing mode, inspect capabilities, and diagnose API errors. CX Codex +1 131installs

Project sponsors

Companies that keep this analytics open