Automation & Ops ✓ NVIDIA · Official

DOCA BlueField-3 Bring-Up

Guides operators through BF3 day-one bring-up, recovery, RShim/BFB provisioning, and installation validation.

56/ 100
Use with care

Useful, but reliability, evidence or controls still have material gaps.

See how it was scored ↓
Works as-is in
Codex · Claude Code
Stars
★ 3.8k
Last updated
today
License
Apache-2.0
bluefield-3docarshimbfb-install
+3tmfifomlxconfigdpu-bring-up

What does this skill do, and when should you use it?

This skill is for DOCA operators working with real, powered BlueField-3 hardware. It covers the classic host-to-DPU RShim/BFB path, including pushing a BFB with bfb-install, using the RShim console and TMFIFO management channel, and selecting DPU or separated-host/NIC mode. It also provides post-BFB recovery guidance, a six-state BlueField classifier, and version verification. It excludes BlueField-4 provisioning, application launch, container deployment, and fresh DOCA installation.

Guides checks and use of the host-side RShim daemon and /dev/rshim* device tree; pushes a BFB to BF3 with bfb-install; handles console-over-rshim, tmfifo_net0, tm-br, and the documented 192.168.100.x convention; routes mlxconfig mode changes and other mutating operations through the hardware-safety policy; classifies failures such as a missing DPU is ready marker, working ping with refused SSH, or missing host PF netdevices; and verifies the Arm-side installation with cat /etc/mlnx-release and the four-way version match.

Good fit
  • An operator performing first-time BFB provisioning on a powered BlueField-3.
  • An operator recovering a DPU after bfb-install exited 0 but the DPU never returned.
  • An operator who can ping 192.168.100.2 but cannot establish SSH.
  • A user deciding whether DOCA belongs on the host, the BlueField Arm side, or both.
  • An operator identifying the correct /dev/rshim<N> device on a multi-DPU host.

How do you install this skill?

Before you use it
  • Before any BFB reflash, mlxconfig set, firmware burn, or kernel-parameter change, ensure the safety meta-policy is actually loaded and obtain explicit confirmation, a maintenance window, out-of-band access, and an executable rollback plan.
  • This skill does not provide a complete copy-paste runbook. Check the live NVIDIA manuals and installed-tool --help for the target DOCA/BFB version; do not blindly reuse example symbols, addresses, or parameters.
  • The frontmatter license and skill-card license wording are inconsistent and should be reconciled before publication.
  • Chinese interaction and mainland-China network reachability are not verified; overseas public documentation dependencies may require mirrors, caching, or user-supplied references.
Before you start
Your agent needs
  • Shell / CLI
  • Network access
  • Local filesystem
Install first
  • physical BlueField-3 hardware
  • host-side RShim daemon and /dev/rshim* access
  • matching DOCA-Host installation
  • BlueField bundle (BFB) image
  • out-of-band console or management path

Install the individual skill with the NVIDIA skills CLI:

npx skills add nvidia/skills --skill doca-bf3-deployment --yes

The README does not document a specific manual folder-copy procedure.

Generic route: install into Claude Code manually (macOS / Linux)
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/skills/doca-bf3-deployment" ~/.claude/skills/
rm -rf "$tmp"

Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.

How do you use this skill?

Try saying

Once installed, send your agent any of these to trigger it:

  • Push a BFB to my BlueField-3
  • bfb-install exited 0 but the DPU never came back
  • ping 192.168.100.2 works but ssh fails

After installation, describe the operational problem in natural language, for example: "Push a BFB to my BlueField-3", "bfb-install exited 0 but the DPU never came back", or "ping 192.168.100.2 works but ssh fails". The operational workflows require real BlueField-3 hardware, host-side RShim access, a matching DOCA-Host installation, a BFB image, and an out-of-band console or management path for recovery. BFB reflashing, mlxconfig set, firmware burns, and kernel boot-parameter changes require explicit target-bound confirmation and the doca-hardware-safety skill.

What are this skill's strengths and limitations?

Pros
  • Covers BF3 day-one bring-up, recovery, RShim/TMFIFO management, and install validation in one lifecycle-focused skill.
  • Distinguishes host-side DOCA from BlueField Arm-side DOCA.
  • Provides a six-state BlueField-state classifier and explicit routing boundaries.
  • Adds safety routing for BFB reflashes, mode changes, firmware burns, and other mutating operations.
Limitations
  • Requires physical BlueField-3 hardware, host RShim access, DOCA-Host, and a BFB image for operational use.
  • Does not cover the BlueField-4 BMC-Redfish provisioning path.
  • Does not cover fresh DOCA installation, application execution, service containers, or library APIs.
  • SKILL.md is a thin loader; substantive procedures are referenced in CAPABILITIES.md and TASKS.md, whose full contents are not included here.

How does this skill compare with similar options?

Side by side with related skills; every score comes from the same FSRS standard.

Skill FS score Stars Last updated License
DOCA BlueField-3 Bring-Up this page ✓ NVIDIA · Official 56 · Use with care ★ 3.8k today Apache-2.0
DOCA Hardware Safety ✓ NVIDIA · Official 57 · Use with care ★ 3.8k today Apache-2.0
DOCA Upgrade Control ✓ NVIDIA · Official 55 · Use with care ★ 3.8k today Apache-2.0
DOCA Socket Relay ✓ NVIDIA · Official 49 · Use with care ★ 3.8k today Apache-2.0
DOCA Capabilities Inspector ✓ NVIDIA · Official 56 · Use with care ★ 3.8k today Apache-2.0

The source explicitly routes BlueField-4 BMC-Redfish provisioning to doca-bf4-deployment, healthy-BF3 binary execution to doca-bare-metal-deployment, and service-container deployment to doca-container-deployment.

How did FollowSkills review this skill?

FollowSkills review · FSRS-2.0
Use with care
56/ 100 5-point scale 2.8 / 5
The upstream repository has new commits since this review. The score still applies to the reviewed revision shown and may not cover the latest changes.
1Trust18 / 25 · 3.6/5

The document explicitly routes hardware changes to a safety meta-policy, requires an out-of-band path, records version anchors, verifies the BFB hash, and forbids invented parameters. It does not fully present user confirmation, maintenance-window, or rollback execution details in this path, and it routes high-impact hardware actions, so 7 points are deducted.

2Reliability8 / 20 · 2.0/5

The workflow order, six-state classifier, failure signals, and escalation paths are clear. However, it depends on external manuals and sibling skills, lacks statically reproducible key commands, timeout boundaries, and committed tests, and contains some inconsistent stop/report wording. 12 points are deducted; the static cap is 10.

3Adaptability12 / 15 · 4.0/5

The audience, BF3/RShim scope, exclusions for BF4 and application deployment, and trigger phrases are clearly defined. Chinese-language support and mainland-China reachability are not substantively addressed, and core public-document dependencies may be network-sensitive, so 3 points are deducted.

4Convention9 / 15 · 3.0/5

The information architecture, loading order, related-skill routing, frontmatter license, version checks, and maintenance note are useful. Missing author metadata, missing recommended Instructions/Examples sections, no changelog, benchmark schema findings, and inconsistent Apache-2.0 versus Apache 2.0 AND CC-BY-4.0 license wording justify a 6-point deduction.

5Effectiveness6 / 15 · 2.0/5

The skill provides useful BF3 bring-up routing, sequencing, state classification, and safety boundaries, so the core value is clear. However, it is a thin loader dependent on sibling files and live NVIDIA manuals, without a directly executable complete runbook or verified outputs, requiring substantial manual completion. 9 points are deducted; the static cap is 7.

6Verifiability3 / 10 · 1.5/5

The files include a pinned revision context, public primary-source pointers, a skill version, and a static evaluation report. The evaluation dataset is unavailable, and there is no committed test suite or third-party execution evidence covering key paths, so 7 points are deducted; the static cap is 5.

1 2 3 4 5 6

Open a dimension to read why it scored that way

Reviewed Jul 20, 2026 Reviewed revision 55f18499943e Review evidence[1][2][3][4][5][6][7][8][9]

Evidence confidence:Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.

See the full review method →

FAQ

Can I use this without DOCA or BlueField hardware?
You can read the skill without installing DOCA, but the bring-up and validation procedures require a real BlueField-3, host-side RShim access, matching DOCA-Host, and a BFB image. Fresh no-hardware users are routed to doca-setup's no-install path.
Does the skill authorize destructive hardware changes?
It provides BF3-specific sequencing, while BFB reflashing, mlxconfig set, firmware burns, and kernel boot-parameter changes remain governed by doca-hardware-safety and require explicit target-bound confirmation.
Can it diagnose a DPU that failed to return after a BFB push?
Yes. Its scope includes missing DPU is ready markers, TMFIFO and SSH failures, and missing host PF netdevices. If the push breaks the Arm OS, recovery still requires an out-of-band console or management path.

More skills from this repository

All from NVIDIA/skills

Dev & Engineering ✓ NVIDIA · Official

DOCA AES-GCM Acceleration

Configure, validate, and debug DOCA AES-GCM offload on BlueField DPUs and ConnectX NICs.

★ 3.8k FS 57 Use with care today
Automation & Ops ✓ NVIDIA · Official

DOCA Hardware Safety

A rollback-oriented operating discipline for live DPU and NIC hardware changes.

★ 3.8k FS 57 Use with care today
Dev & Engineering ✓ NVIDIA · Official

DOCA Environment Setup

Verify, prepare, and troubleshoot the DOCA environment while routing workloads to the right deployment path.

★ 3.8k FS 57 Use with care today
Dev & Engineering ✓ NVIDIA · Official

DOCA Arg Parser CLI

Guides developers in building and debugging standard CLIs for DOCA applications.

★ 3.8k FS 55 Use with care today
Automation & Ops ✓ NVIDIA · Official

DOCA Upgrade Control

Safely gate DOCA upgrades and rollbacks with explicit confirmation.

★ 3.8k FS 55 Use with care today
Dev & Engineering ✓ NVIDIA · Official

DOCA Erasure Coding Development Skill

Guides hands-on DOCA Reed-Solomon resilience development and debugging on NVIDIA hardware.

★ 3.8k FS 49 Use with care today
Automation & Ops ✓ NVIDIA · Official

DOCA Socket Relay

Bridge an existing socket application to a BlueField DPU without rewriting it

★ 3.8k FS 49 Use with care today
Dev & Engineering ✓ NVIDIA · Official

DOCA Device Emulation Development

Guides developers in building custom PCIe devices on BlueField whose backend runs on the DPU and is visible to the host.

★ 3.8k FS 48 Use with care today
Dev & Engineering ✓ NVIDIA · Official

DOCA PCC ZTR RTTCC Congestion Control

Deploy, tune, and validate NVIDIA’s RoCE RTT congestion-control reference algorithm on BlueField-3.

★ 3.8k FS 48 Use with care today
Automation & Ops ✓ NVIDIA · Official

DOCA Capabilities Inspector

Inspect what DOCA can see on a host through a read-only device and capability CLI.

★ 3.8k FS 56 Use with care today
Automation & Ops ✓ NVIDIA · Official

DOCA PCC Diagnostic Counters

Read fixed firmware and hardware PCC congestion diagnostics on ConnectX and BlueField devices.

★ 3.8k FS 56 Use with care today
Automation & Ops ✓ NVIDIA · Official

DOCA Structured Tools Contract

A governed fallback contract for consolidating DOCA environment, device, capability, validation, and host-DPU state data.

★ 3.8k FS 55 Use with care today
Dev & Engineering ✓ NVIDIA · Official

DOCA Telemetry Exporter Development

Guides DOCA applications in defining, emitting, and debugging structured telemetry for external consumers.

★ 3.8k FS 55 Use with care today
Automation & Ops ✓ NVIDIA · Official

DOCA CollectX Telemetry Deployment

Deploy, operate, and debug CollectX telemetry collectors so counters reach downstream exporters.

★ 3.8k FS 54 Use with care today
Dev & Engineering ✓ NVIDIA · Official

DOCA Programming Guide

Guides developers through building, testing, and debugging library-agnostic DOCA applications from shipped samples.

★ 3.8k FS 54 Use with care today
Automation & Ops ✓ NVIDIA · Official

DOCA BlueField Bare-Metal Deployment

Run, supervise, and troubleshoot DOCA binaries directly on BlueField hardware.

★ 3.8k FS 53 Use with care today
Dev & Engineering ✓ NVIDIA · Official

DOCA Version Consistency Assistant

Verifies DOCA version sources and host–BlueField consistency while diagnosing build-versus-runtime drift.

★ 3.8k FS 53 Use with care today
Automation & Ops ✓ NVIDIA · Official

DOCA Container Deployment

Deploy, validate, and troubleshoot DOCA service containers on NVIDIA BlueField.

★ 3.8k FS 52 Use with care today
Dev & Engineering ✓ NVIDIA · Official

DOCA DPA High-Level Tracer

Capture and decode BlueField DPA programming events to diagnose kernel behavior, communication latency, and trace failures.

★ 3.8k FS 50 Use with care today
Dev & Engineering ✓ NVIDIA · Official

DOCA GPUNetIO WRITE Bandwidth Benchmark

Build, run, and interpret sustained RDMA WRITE bandwidth measurements driven by CUDA kernels through the DOCA GPUNetIO surface.

★ 3.8k FS 50 Use with care today

Related skills