К основному содержанию
скилл CX Codex

doca-dms — скилл для Claude Code: управление DMS и установка

Скилл doca-dms для Claude Code управляет NVIDIA DOCA Management Service на BlueField, хосте или в Kubernetes. Выполняет локальные операции через dms-cli и удалённые gNMI/gNOI-операции.

Apache-2.0 138 установок ★ 4 106 обновлён 2026-10-23

Установить в Claude Code · Через Skills CLI (Vercel) Все способы и платформы ↓
npx skills add NVIDIA/skills --skill doca-dms -a claude-code
Открыть на GitHub

Что делает doca-dms

Скилл работает с NVIDIA DOCA Management Service на x86-хосте, BlueField Arm или в Kubernetes pod. Для DOCA 3.5+ он использует локальный dms-cli без сервера: помогает исследовать YANG-пути через --tree, --describe и list-xpaths, читать и менять значения, запускать действия и проверять запросы через --dry-run.

Для удалённого и fleet-управления скилл разбирает связку dmsd и dmspe, выбор аутентификации, gNMI Get/Set, поддерживаемые сценарии gNOI и ошибки frontend/backend. Перед записью нужно проверить путь: набор доступных путей зависит от устройства. На DOCA 3.5 обычному пользователю для dms-cli может понадобиться sudo или членство в dmsgroup.

Перезагрузка, установка ОС, factory reset и удаление управляемых файлов требуют подтверждения для конкретного устройства и действия. Без установленного DOCA на management endpoint сначала нужен doca-setup/SKILL.md; вопросы установки самого DOCA и сборки библиотек относятся к другим скиллам.

Какие задачи решает

  • прочитать значение по YANG-пути на BlueField
  • изменить настройку через локальный dms-cli
  • настроить удалённое управление по gRPC
  • выполнить gNMI Get или Set
  • разобрать ошибку frontend или backend

Примеры запросов агенту

  • Покажи дерево доступных путей под /nvidia через dms-cli, затем подготовь чтение нужного значения.
  • Настрой управление удалённым BlueField через dmsd и dmspe с подходящей аутентификацией.
  • Подготовь gNOI-перезагрузку устройства, но сначала проверь его identity и запроси явное подтверждение для этой цели.

Как установить doca-dms

1Через Skills CLI (Vercel)

npx skills add NVIDIA/skills --skill doca-dms -a claude-code

2Вручную: положить файлы

~/.claude/skills/doca-dms/SKILL.md

Папка скилла целиком; для одного проекта — .claude/skills/doca-dms/

По шагам, с командами для каждой платформы: Как установить скилл в Claude Code: пять способов

Вопросы о doca-dms

Как установить doca-dms в Claude Code?

Выполните npx skills add NVIDIA/skills --skill doca-dms -a claude-code, затем проверьте файл ~/.claude/skills/doca-dms/SKILL.md.

Что делает doca-dms?

Скилл помогает работать с NVIDIA DOCA Management Service: использовать dms-cli, настраивать dmsd и dmspe, выполнять gNMI/gNOI-операции и искать причины ошибок.

Где запускается NVIDIA DOCA Management Service?

Сервис работает на management endpoint: x86-хосте без DPU, BlueField Arm или в Kubernetes pod. Для проверки нужен живой DOCA install.

Исходный текст

SKILL.md · Apache-2.0
---
license: Apache-2.0
name: doca-dms
description: >
  Operate NVIDIA DOCA Management Service on a BlueField, Arm/x86 host,
  or Kubernetes pod: from DOCA 3.5 the local `dms-cli` (one command per
  YANG path, no server), and the `dmsd` + `dmspe` service: choose deployment and
  authentication, configure `-allowed_users` and `dmsgroup`, use gNMI
  Get/Set, run supported gNOI workflows, and debug
  frontend/backend failures. Trigger even without "DMS" for "manage a
  remote BlueField over gRPC", "gNOI reboot from orchestrator", or
  fleet-management requests. SAFETY: reboot, OS install, factory-reset,
  and managed-file deletion are destructive and require target-bound
  explicit confirmation; never invoke them speculatively. Route
  installation and library/API build questions elsewhere, and route
  telemetry streaming and aggregation to doca-dts (DOCA Telemetry
  Service).
metadata:
  author: NVIDIA <[email protected]>
  kind: service
  doca_version: "3.5"
  tags:
    - doca
    - dms
    - gnmi
compatibility: >
  DOCA service shipped with the DOCA install at /opt/mellanox/doca on
  the management endpoint (x86 host (non-DPU), BlueField Arm, or
  Kubernetes pod) on Linux (Ubuntu 22.04/24.04 or RHEL/SLES); `dmsd` +
  `dmspe` run there, and DMS is also pulled as an NGC container image.
  Verify the public DMS guide version matches the installed DOCA release
  before quoting flags or YANG paths. The validation steps require a
  live DOCA install.
---

# DOCA Management Service (DMS)

## Examples

- **"Read or change a BlueField setting locally."** — use
  `dms-cli` (DOCA 3.5+); explore the path with `--tree` first.
- **"Manage a remote BlueField over gRPC."** — this is in
  scope. Use `dmsd` + `dmspe` with the chosen auth; do not
  drop to ad-hoc SSH for the management plane.
- **"gNOI reboot from orchestrator."** — treat reboot / OS
  install / factory-reset as destructive: require target-bound
  explicit confirmation first.

## Instructions

Follow Loading order below. Open the tasks companion for configure /
gNMI / debug. Open the capabilities companion for auth and gNOI
scope. Do not open every companion file.

> **⚠️ Destructive operations.** The gNOI `reboot`, `OS install`,
> `factory-reset`, and managed-file deletion operations are
> **irreversible** and **service-impacting**
> — they can take a production BlueField or ConnectX offline or wipe its
> configuration. Before issuing any of them the agent MUST: (1) verify the
> target device identity, and (2) obtain explicit confirmation bound to
> that target and action. In an interactive session this is an explicit
> user reply naming/accepting both; in unattended execution it must be an
> approved-system authorization artifact bound to both. Otherwise stop
> with `confirmation_required`. Never invoke them speculatively or as
> a side effect of another task. See the public DMS guide's safety
> guidance for these operations.

**Where to start:** This skill is for *operating* DMS, not for
*linking against* a library. If the user wants to *deploy* or *run*
the daemon, open the tasks companion and start at
`## configure`. If the question is *what shape
of service is DMS and what protocols does it speak*, start at
the capabilities companion. If DOCA is not installed on the
management endpoint yet, route to
`doca-setup/SKILL.md` first.

**How to use this skill.** Read this file, then search the companion file
for the `## <name>` heading the question needs and read that whole section.
Answer completely from it, quoting only its symbols and commands. Do not
browse docs; use the entry points in `doca-public-knowledge-map`. Give
environment checks as commands for the user's DOCA host. For out-of-scope
requests, name the skill that owns them and stop.

**DOCA 3.5 and later: start with `dms-cli`.** The DMS guide now centres on
`/opt/mellanox/doca/services/dms/dms-cli`, run directly on the host or
BlueField Arm with no server or daemon. One syntax per YANG path:
`dms-cli -t pci/<BDF> /nvidia/mode/operating-mode` reads a value, the same
path plus a value sets it, and action paths run operations. Explore before
writing: `--tree /nvidia`, `--describe <path>` and `list-xpaths <path>`;
script with `--json`; validate with `--dry-run`. VFs and SFs take
`-t pci/<BDF>,pf<N>vf<M>` or `pf<N>sf<M>`. On DOCA 3.5: as a normal
user it fails with `backend fork/exec .../dmspe: permission denied` — run it
with `sudo` or add the user to `dmsgroup`; some example paths do not exist on
every device (for example congestion-control slots are under
`/nvidia/cc/algo/slot` there), so confirm every path with `--tree` /
`list-xpaths` before using it. Firmware or BFB installs
(`/nvidia/provisioning/install`), resets and mode changes are
hardware-state changes: follow `doca-hardware-safety`. The `dmsd` + `dmspe`
gRPC (gNMI / gNOI) service below remains for remote and fleet management.

## Example questions this skill answers well

> **Never invent the image tag.** It comes from the NGC catalog's DOCA
> org or the DMS page on `docs.nvidia.com`, not from memory — a
> plausible tag reads as authoritative and mismatches the installed
> DOCA. Cite where it came from, or send the user to look it up.

The CLASSES of DMS questions this skill is built to answer, each with
one worked example. The class is the load-bearing piece; the worked
example is one instance.

- **"Where should DMS run for my target topology?"** — worked example:
  *"I have a host without a DPU; can I still manage a remote
  ConnectX?"*. Answered by the deployment-shape decision in
  the capabilities companion
  + the tasks companion.
- **"Which authentication mode should I pick for my security
  posture?"** — worked example: *"a multi-tenant production env vs a
  single-tenant lab"*. Answered by the auth-mode trade-off table in
  the capabilities companion
  + the auth-wiring step in
  the tasks companion.
- **"How do I issue a gNMI `Get` / `Set` against a modeled path?"** —
  worked example: *"set `/interfaces/interface/config/mtu` on a remote
  interface"*. Answered by the gNMI/gNOI surface in
  the capabilities companion
  + the request-shape workflow in
  the tasks companion.
- **"How do I run a gNOI operation (reboot, OS install, file
  transfer)?"** — worked example: *"trigger a clean reboot of the
  target via gNOI"*. Answered by the gNOI catalog in
  the capabilities companion
  + the run workflow in the tasks companion.
- **"My DMS request returned an error — was it the frontend or the
  backend?"** — worked example: *"`mlxconfig` failed under DMS but
  works on the shell"*. Answered by the frontend-vs-backend split in
  the capabilities companion
  + the layered ladder in
  the tasks companion.
- **"Where do I read DMS logs and how do I rotate them?"** — worked
  example: *"persistent log directory + journald + log-rotation
  policy"*. Answered by the logging surface in
  the capabilities companion
  + the log-rotation step in
  the tasks companion.

## Audience

This skill serves **external operators and platform teams who deploy and
operate DMS** to manage NVIDIA® BlueField® networking platforms or
NVIDIA® ConnectX® SmartNICs from a centralized control plane. Concretely:
people running `dmsd`, integrating gNMI/gNOI clients against it, choosing
an authentication mode, or wiring DMS into a Kubernetes deployment.

It is **not** for NVIDIA developers contributing to DMS itself, and it
is **not** a programming guide for *building applications on top of*
DOCA libraries (that is `doca-programming-guide` plus the matching
library skill under `libs/`). DMS is a **service**, not a library: the
user invokes it as a daemon and talks to it over gRPC; they do not link
against `libdms.so` to write their own program.

**Status note.** Per the public DMS guide, DMS is currently in **beta**,
with General Availability scoped to SPC-X use cases. The skill reflects
the public guide's posture: prescribe the documented launch / auth /
deployment paths, follow the documented security best practices, and
defer roadmap and GA-scope questions to the live public guide rather
than guessing.

## When to load this skill

Load this skill when the user is doing **hands-on DMS operation work**
against a BlueField or ConnectX target where DOCA is already installed
on the management endpoint (host, DPU, or pod). Concretely:

- Deciding *where* DMS should run (host non-DPU / BlueField Arm /
  Kubernetes pod) for a given target topology.
- Bringing up the `dmsd` daemon — choosing SystemD vs manual launch,
  selecting an authentication mode, wiring `-allowed_users` (the gRPC
  client authorization boundary) and, if needed, `dmsgroup` (the
  `dmspe` backend-helper Unix group).
- Issuing `gNMI` `Get` / `Set` requests against modeled paths
  (e.g. `/interfaces/interface/config/mtu`).
- Issuing `gNOI` operations: OS install, reboot, file transfer,
  factory-reset, `mlxconfig`, containerz.
- Choosing an authentication mode (localhost / PAM / credentials / mTLS)
  and understanding the security trade-offs the public guide calls out.
- Reading or rotating DMS logs, configuring config persistency, or
  recovering from a crashed daemon.
- Debugging a DMS request that returned an error — separating
  "frontend rejected before reaching backend" from "backend executed and
  the underlying tool (e.g. `mlxconfig`) failed".

Do **not** load this skill for general DOCA orientation, install of
DOCA itself, or library-API questions. For those, route via
`doca-public-knowledge-map/SKILL.md`,
`doca-setup/SKILL.md`, or the matching
`libs/<library>` skill.

## What this skill provides

This is a **thin loader**. Substantive material lives in two companion
files:

- the capabilities companion — DMS architecture (frontend `dmsd` / privileged
  backend `dmspe`), management protocols (gNMI, gNOI), the YANG-based
  unified configuration dictionary, deployment shapes, authentication
  modes with their security trade-offs, the configuration-persistency
  model, the logging surface, and DMS's documented security posture.
- the tasks companion — step-by-step workflows for the in-scope DMS verbs:
  `configure`, `build`, `modify`, `run`, `test`, `debug`, plus a
  `Deferred task verbs` block routing out-of-scope questions.

The skill assumes a host where DOCA is already installed and the
operator has root / `sudo` access where the public guide says it is
required. It does not cover installing DOCA — that path goes through
`doca-setup/SKILL.md`.

## What this skill deliberately does not ship

This skill is **agent guidance**, not a templates or sample-config
bundle. To keep the boundary clean, it deliberately does not contain —
and pull requests should not add:

- **Pre-baked DMS configuration files** (YANG instance documents,
  full-stack example configs, ready-to-run `dmsd` flag bundles)
  intended to be copy-pasted into production. Configs are deployment-
  specific and the safe answer for an external operator is to derive
  them from the public guide against their own target. The agent's
  job is to prescribe the *procedure* and quote the documented flags
  and paths, not to ship a config the user might run unmodified.
- **Pre-written gNMI / gNOI client programs in any language.** The
  client surface is standard gNMI / gNOI (publicly documented); the
  skill describes which paths and operations DMS supports, not how to
  build a gRPC client in language X.
- **TLS material, credentials, or PAM stanzas.** These are
  user-environment artifacts; the skill points at the documented
  configuration knobs and the documented security best practices and
  stops there.
- **A `samples/`, `templates/`, or `reference/` subtree** of any
  kind. A mock or incomplete artifact in this skill's tree, even one
  labeled "reference", is misleading: operators will read it as
  production-ready.

## Loading order

1. Read this skill first to confirm the user's question is in scope.
2. **For the DMS architecture, deployment shapes, auth modes,
   protocol/path inventory, persistency, logging, and security
   posture, see the capabilities companion.**
3. **For step-by-step workflows — configure, build, modify, run, test,
   debug — see the tasks companion.**
4. **Apply the destructive-operation gate in every phase.** Before any
   gNOI OS install, reboot, factory reset, or managed-file deletion —
   including a test or debug action — verify the exact target and obtain explicit
   confirmation for that specific operation using the interactive or
   approved-system mechanism defined in the warning above. No earlier
   confirmation or workflow phase carries authorization forward.

## Related skills

- `doca-public-knowledge-map/SKILL.md`
  — the routing table to the public DMS guide and the rest of the
  public DOCA documentation set.
- `doca-setup/SKILL.md` — env preparation and
  install verification on the host where `dmsd` will run, including
  the *I have no install yet* path via the public NGC DOCA container.
  This skill assumes its preconditions are satisfied at the management
  endpoint.
- `doca-programming-guide/SKILL.md` —
  general DOCA patterns. DMS is service-shaped not library-shaped, so
  the build / modify / first-app pattern there does not apply directly,
  but the cross-library `DOCA_ERROR_*` taxonomy and the
  layered-debug order remain useful when DMS reports errors that
  originated in a DOCA library it called.

© NVIDIA · Apache-2.0 · NVIDIA/skills

Похожие скиллы

Все скиллы по теме «DevOps и инфраструктура» →
dms-schema-conversion aws Управляет миграцией схем между разными СУБД через AWS DMS Schema Conversion. Запускается при создании проекта миграции, оценке совместимости или конвертации схемы и SQL. CX Codex +1 5 500установок infisical-self-host Infisical Скилл infisical-self-host помогает развернуть и настроить серверную платформу Infisical в Docker Compose или Kubernetes. Пригодится при настройке базы данных PostgreSQL, очередей Redis и параметров безопасности. CX Codex +1 834установок docker-containerization curiositech Скилл docker-containerization настраивает многоэтапные Dockerfile, ускоряет сборку через кэш слоёв и готовит конфиги docker-compose для локальной разработки. CX Codex +1 143установок github-actions-templates Seth Hobson Скилл github-actions-templates для Claude Code создаёт GitHub Actions для тестирования, сборки и деплоя. Настраивает CI/CD и reusable workflows. CX Codex +1 17 420установок kubernetes-specialist https://github.com/Jeffallan Скилл kubernetes-specialist для Claude Code создаёт и проверяет Kubernetes-манифесты, настраивает безопасность и разбирает сбои подов. Помогает деплоить и сопровождать кластерные нагрузки. CX Codex +1 14 900установок k8s-security-policies Seth Hobson Скилл k8s-security-policies помогает задавать политики безопасности Kubernetes: сетевую изоляцию, RBAC и стандарты безопасности подов. Нужен при защите кластера. CX Codex +1 14 692установок

Из того же набора312

Весь набор →
doca-dma Скилл помогает писать и отлаживать код для копирования данных через DOCA DMA. Он пригодится при настройке memcpy между памятью хоста и DPU. CX Codex +1 143установок doca-comch Скилл doca-comch для Claude Code помогает настраивать обмен сообщениями между хостом и BlueField через DOCA Comch. Он подключается при работе с ролями клиента и сервера, режимами передачи и ошибками API. CX Codex +1 142установок nemo-relay-plugin-observability Скилл nemo-relay-plugin-observability для Claude Code помогает выбрать и настроить экспортеры и подписчики для телеметрии NeMo Relay версий 0.6 и 0.7. CX Codex +1 140установок doca-compress Скилл doca-compress для Claude Code помогает переносить сжатие DEFLATE и распаковку DEFLATE или LZ4 на DOCA Compress. Он подключается при настройке задач сжатия и разборе ошибок аппаратного ускорителя. CX Codex +1 140установок doca-eth Помогает настроить очереди пакетов DOCA Ethernet на сетевых картах ConnectX и DPU BlueField, выбрать тип RX-очереди и разобрать ошибки передачи. CX Codex +1 137установок doca-sha Скилл doca-sha для Claude Code помогает работать с аппаратным ускорением SHA на BlueField-2 через DOCA. Выбирает режим хеширования и разбирает ошибки. CX Codex +1 131установок doca-version Скилл doca-version для Claude Code сверяет четыре источника версии DOCA и выявляет расхождения между сборкой и рантаймом. CX Codex +1 130установок doca-mgmt Скилл doca-mgmt для программирования управления устройствами NVIDIA BlueField DPU и ConnectX NIC прямо из кода. CX Codex +1 128установок

Спонсоры проекта

Компании, которые помогают держать аналитику открытой