nemo-relay-get-started — Claude Code skill: setup
The nemo-relay-get-started skill routes first-time NeMo Relay users to the right quick-start, then checks whether the initial integration actually works.
Apache-2.0 163 installs ★ 4,106 updated 2026-10-23
npx skills add NVIDIA/skills --skill nemo-relay-get-started -a claude-codeWhat nemo-relay-get-started does
The skill selects a quick-start around the environment already in use: a local coding agent or CLI, an agent runtime, a maintained framework integration, Switchyard, or application-owned language calls. It keeps the target established during the conversation or installation and asks a concise question when the boundary is unclear.
It then follows one guide revision for prerequisites, sample files, commands, shutdown, and verification. Application output by itself does not prove that Relay captured the work, so the skill reports the evidence required by that guide. After the first successful check, it can route the next plugin suggestion through the installed Relay release. If the guide or its sample files cannot be read, it must not invent the recipe.
Missing dependencies go to nemo-relay-install; broader call instrumentation, unsupported framework work, and extra export go to the related skills named in the instructions. Production rollout and several new behaviors are outside this first-trial flow.
What it helps with
- choose a NeMo Relay quick-start for the current environment
- walk through the first Relay integration
- verify that Relay captured the test work
- keep commands and sample files on one guide revision
- route follow-up work to the right NeMo Relay skill
Example prompts for the agent
- Choose the right NeMo Relay quick-start for my existing runtime and guide me through it.
- Run the first integration check for NeMo Relay and explain what evidence proves that Relay captured the work.
- The dependency step failed. Tell me what to pass to
nemo-relay-installand where this skill should stop.
How to install nemo-relay-get-started
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill nemo-relay-get-started -a claude-code2Manually: put the files in place
~/.claude/skills/nemo-relay-get-started/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/nemo-relay-get-started/
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill nemo-relay-get-started -a codex2Manually: put the files in place
.agents/skills/nemo-relay-get-started/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill nemo-relay-get-started -a cursor2Manually: put the files in place
.cursor/skills/nemo-relay-get-started/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install NVIDIA/skills skills/nemo-relay-get-started2Manually: put the files in place
.github/skills/nemo-relay-get-started/SKILL.md1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill nemo-relay-get-started -a gemini-cli2Platform CLI
gemini skills install https://github.com/NVIDIA/skills --path skills/nemo-relay-get-startedManually: put the files in place
.devin/skills/nemo-relay-get-started/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill nemo-relay-get-started -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about nemo-relay-get-started
How do I install nemo-relay-get-started in Claude Code?
Run npx skills add NVIDIA/skills --skill nemo-relay-get-started -a claude-code, then check ~/.claude/skills/nemo-relay-get-started/SKILL.md.
What does nemo-relay-get-started do?
It chooses a suitable NeMo Relay quick-start, helps follow that guide, and verifies the first working integration against the guide’s own checks.
Which integration boundaries does it support?
It routes between a local coding agent or CLI, an agent runtime or managed plugin, a framework integration, Switchyard, and application-owned language calls.
Source text
SKILL.md · Apache-2.0
--- name: nemo-relay-get-started description: Use this skill when first-time NeMo Relay users want help selecting and following an appropriate quick-start guide or verifying their first working integration. Do not use it for production rollout or broad integration development. license: Apache-2.0 metadata: author: NVIDIA Corporation and Affiliates --- # Get Started With NeMo Relay Help the user choose and follow the maintained quick-start guide that fits their existing runtime, framework, plugin, or application. The guide owns the implementation; this skill owns selection, continuity, and evidence. ## Select The Guide Read the current [quick-start index](https://docs.nvidia.com/nemo/relay/getting-started/quick-start). Use the user's stated goal and existing environment to find the smallest applicable path. Preserve a target established in conversation or installation. When the boundary is unclear, ask one concise question before choosing. Do not infer that every generic "try Relay" request means a coding-agent demo, or introduce a framework just to demonstrate Relay. Use these references only for target-specific routing and cautions: | Established boundary | Reference | |---|---| | Local coding agent or CLI | [CLI Trial](references/cli-try-now.md) | | Native agent runtime or managed plugin | [Agent Runtime Trial](references/agent-runtimes-try-now.md) | | Maintained framework integration | [Framework Trial](references/built-in-integrations-try-now.md) | | Switchyard routing | [Switchyard Trial](references/switchyard-try-now.md) | | Application-owned language calls | [Language Trial](references/manual-language-try-now.md) | ## Follow The Current Guide Read the selected guide before proposing commands or configuration, including its prerequisites, sample files, run instructions, verification, and limitations. Use documentation compatible with the installed stable release. The current published guide is the normal source; use an explicitly requested pending PR or other supplied revision as such, without treating it as published support. Resolve the documentation version instead of assuming an unversioned URL is current. When rendered documentation is inaccessible or omits the selected path, use the official source at the matching release tag, or the development checkout for an explicitly requested development preview. A failed HTTP request alone does not prove that a guide was removed; check its index and source. Keep commands and referenced sample files from the same guide revision. If working from source, resolve its referenced files in that checkout. Do not reconstruct the recipe from this skill, an older session, or a benchmark. If the guide cannot be read or its sample files are unavailable, state the gap rather than inventing instructions. For missing dependencies, use `nemo-relay-install` with the already-selected target. Its default is the latest published stable release, subject to explicit user or project constraints. Preserve a successful install and continue at the next appropriate guide step; do not repeat target selection. A guide's example pin is not an instruction to downgrade or use an unpublished release. If the guide and installed release are incompatible, resolve that mismatch using current release documentation before proceeding. ## Execute And Verify Use [Guide-Based First-Value Checks](references/first-value.md) while adapting only what the user's existing environment requires. Explain the guide's attachment boundary and proposed changes. Preserve the project's manager, unrelated settings, and existing artifacts. Proceed within existing authorization, honoring requests to preview or stop before a live run. Follow the selected guide's configuration, execution, shutdown, and verification steps. Derive file locations, schemas, commands, prompts, lifecycle expectations, and output formats from that guide rather than imposing a shared recipe. Run only the chosen path and report the evidence it actually establishes. Successful application output alone is not proof that Relay captured the work. Use fresh evidence and the guide's own success criteria. Do not demand model credentials, a tool call, ATIF, or another exporter when that guide does not. ## After The First Proof Stop the initial trial when the guide's success checks pass. Explain the observed value and Relay's progression: attach once, then extend supported behavior through plugin configuration. Resolve plugin and integration documentation for the installed Relay release, including any explicit version constraint, before suggesting one next plugin for the user's goal. Use the [stable plugin overview](https://docs.nvidia.com/nemo/relay/latest/configure-plugins/about) only after confirming compatibility with that release; otherwise use the release-matched documentation or official source. Do not repeat Observability setup if the guide already established it, or offer capabilities unsupported by the selected integration. Hand broader instrumentation to `nemo-relay-instrument-calls`, unsupported framework work to `nemo-relay-integrate-upstream`, and additional export to `nemo-relay-plugin-observability`. Persistent host setup belongs to `nemo-relay-install`, including its applicable Codex Desktop continuity gate. Production deployment and multiple new behaviors belong to follow-up work.
© NVIDIA Corporation and Affiliates · Apache-2.0 · NVIDIA/skills