Generated banner for Doca Bf3 Deployment
Generated logo for Doca Bf3 Deployment

Doca Bf3 Deployment

NVIDIAOfficialCreated by NVIDIA

  • Skill
  • Workflow
  • Cloud and DevOps
  • Apache-2.0
  • Medium risk

From the author

Use this skill for BlueField-3 (BF3) day-1 platform bring-up via the classic RShim/BFB path: pushing a BlueField bundle (BFB) to the DPU over RShim with bfb-install from the host, the host-to-DPU TMFIFO management channel (tmfifo_net0, the 192.168.100.x convention), RShim daemon state and console-over-rshim, DPU mode selection (DPU/embedded-function vs separated-host/NIC mode) via mlxconfig, post-BFB recovery, a six-state BlueField-state classifier, and verifying the install (cat /etc/mlnx-release plus version checks). Trigger even when the user does not say "BF3" — typical phrasings include {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}, or {is DOCA on the host or the Arm side?}. BFB reflash, mlxconfig set, mode changes, and firmware burns are destructive: require explicit target-bound confirmation and load doca-hardware-safety. App launch, container deploy, env install, and the BF4 BMC-Redfish path route elsewhere.
— the description by NVIDIA

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill provides the operational framework for BlueField-3 (BF3) day-1 platform bring-up. It guides users through the classic RShim/BFB installation path, covering the management of the host-to-DPU TMFIFO channel, DPU mode selection, and post-installation verification. It includes a six-state classifier to help diagnose and recover DPUs that fail to reach a ready state after a bundle push. The skill is designed for operators with physical access to BF3 hardware and requires integration with hardware safety policies for any destructive operations like firmware burns or mode changes.

What it does

  • Guides the BFB installation process via the host-side RShim interface.
  • Manages the host-to-DPU TMFIFO management channel configuration.
  • Provides a six-state classifier for diagnosing DPU readiness issues.
  • Verifies successful BFB installation and version compatibility.
  • Assists with DPU mode selection between DPU/embedded-function and separated-host/NIC modes.
  • Routes destructive hardware operations to the appropriate safety-governed workflows.

When to use it

  • When performing initial platform bring-up for a physical BlueField-3 DPU.
  • When a BFB installation appears to finish but the DPU fails to become ready.
  • When troubleshooting connectivity issues between the host and the DPU over TMFIFO.
  • When needing to verify the installed BFB version and overall system health.
  • When determining if a DPU should be configured for DPU or separated-host mode.

Advantages

  • Standardizes the bring-up procedure for BlueField-3 hardware.
  • Reduces downtime by providing a structured diagnostic path for failed installs.
  • Ensures safe operation by integrating with hardware safety policies for destructive tasks.
  • Clarifies the distinction between host-side and Arm-side DOCA installations.

Usage examples

“I have a BlueField-3 and a BFB image — how do I push it?”
The agent provides the step-by-step sequence for using bfb-install from the host, ensuring the RShim daemon is active and the DPU is ready.
“bfb-install exited 0 but the DPU never came back.”
The agent initiates the six-state classifier to identify the current DPU state and suggests recovery steps instead of re-attempting the burn.
“ping 192.168.100.2 works but ssh fails.”
The agent guides the user through the TMFIFO management channel verification, including checking local-loopback routing and SSH service status.
“Is DOCA on the host or the Arm side?”
The agent clarifies the installation requirements for both the host and the BlueField-Arm side, helping the user identify where the software should be deployed.

Install

  1. Download the skill as a ZIP:

    https://autogineer.com/agent-skills/nvidia/doca-bf3-deployment/download
  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip doca-bf3-deployment.zip -d .agents/skills

Documentation by NVIDIA

DOCA BlueField-3 (BF3) deployment

Examples

  • "I have a BlueField-3 and a BFB — how do I push it?" — RShim plus bfb-install from the host. Exit 0 is not success until the DPU is ready.

  • "bfb-install exited 0 but the DPU never came back." — start at the six-state classifier, not a second burn.

Instructions

Follow Loading order below. Open the tasks companion for BFB push and recover. Open the capabilities companion for the RShim/BFB contract and safety overlay. Do not open every companion file.

Where to start: This skill is the bundle's home for BlueField-3 day-1 platform bring-up — taking a BF3 from "powered card in the slot" (or a card that just came back broken from a BFB push) to "Arm OS healthy, TMFIFO up, host PFs bound, four-way version match closed, ready to run a workload". It owns the classic RShim/BFB path that BF3 uses today; the newer BMC-Redfish provisioning path is the sibling skill doca-bf4-deployment/SKILL.md (the BF4 equivalent). If the user has a BF3 and needs to push a BFB, recover a DPU that did not come back, or verify the install, open the tasks companion and start at ## configure. If the question is what shape does the BF3 platform-bring-up surface even have, start at the capabilities companion. Once the BF3 is healthy, this skill routes onward to the deployment skills — running a binary goes to doca-bare-metal-deployment/SKILL.md; deploying a service container goes to doca-container-deployment/SKILL.md.

Every mutating burn invoked from a bring-up step — the BFB reflash itself, any mlxconfig set (including a DPU/separated-host mode flip), a firmware burn, or a kernel-boot-parameter change — is governed by the change-application meta-policy in doca-hardware-safety/SKILL.md, which the agent loads ALONGSIDE this skill. This skill adds only the BF3-specific operational sequencing on top; it does NOT redefine the preflight / OOB-console / maintenance-window / rollback discipline that meta-policy owns.

Audience

This skill serves external DOCA operators bringing up a real BlueField-3 — i.e. people who already have:

  • a physical BlueField-3 in a host (or a standalone BF3 they can reach over its console / management network),

  • host-side RShim access to the DPU (the RShim userspace daemon and the /dev/rshim* character-device tree present over the PCIe or USB RShim interface), and

  • a matching DOCA-Host install on the host plus a BlueField bundle (BFB) image downloaded from the public DOCA Downloads page.

It is not for:

  • BlueField-4 bring-up (the BMC-Redfish provisioning path) — route to doca-bf4-deployment/SKILL.md, the BF4 equivalent of this skill,

  • kernel-driver or BlueField-OS developers contributing to mlx5_* or the BFB image itself (outside the scope of field deployment),

  • operators who already have a healthy BF3 and just want to run a binary (route to doca-bare-metal-deployment/SKILL.md) or deploy a service container (route to doca-container-deployment/SKILL.md),

  • fresh-no-hardware users with no DOCA install — route to doca-setup ## no-install.

The skill teaches the agent the BF3 bring-up procedure and the rules for quoting documented commands from the public BlueField Platform Software Manual, the public DOCA Installation Guide, and the MFT manual via doca-public-knowledge-map/SKILL.md; it does not invent bfb-install flag sets, BFB image filenames, RShim character-device paths, bf.cfg schema keys, mlxconfig parameter names, or TMFIFO subnets from memory. Where a fact is already vetted in doca-bare-metal-deployment ## bluefield-lifecycle, this skill reuses that exact fact rather than restating a new one.

When to load this skill

Load this skill when the user is doing hands-on BlueField-3 platform bring-up over the RShim/BFB path, or asking a cross-cutting BF3 lifecycle question that is not specific to one library's API. Concretely:

  • Pushing a BFB image to a BF3 for the first time (or re-pushing after a failed install), from the host over the RShim interface with bfb-install.

  • Bringing up or recovering the host-to-DPU TMFIFO management channel (tmfifo_net0, the documented 192.168.100.x convention) and the RShim console.

  • Confirming RShim driver/daemon state on the host (the userspace rshim daemon and the /dev/rshim* tree) before any push or console capture.

  • Deciding (and routing) a DPU-mode change — DPU / embedded-function mode vs separated-host / NIC mode — knowing the actual mlxconfig set burn leaves this skill for doca-hardware-safety/SKILL.md.

  • Recovering a BF3 that did not come back after a BFB push: bfb-install exited 0 but the DPU never reached the documented DPU is ready marker; ping 192.168.100.2 works but SSH refuses; host PFs are present in lspci -d 15b3: but their netdevs are gone.

  • Verifying a BF3 install — cat /etc/mlnx-release on the Arm side, the four-way version match per doca-version/SKILL.md — and distinguishing the host-side DOCA install from the BlueField-Arm-side DOCA install.

  • Cross-cutting questions: "is DOCA on the host or on the Arm side, and which one do I install?", "my BF3 was fine last week and after a BFB push it never came back — where do I start?", "how do I tell which /dev/rshim<N> is which BlueField on a multi-DPU host?".

Do not load this skill for: BlueField-4 bring-up (route to doca-bf4-deployment/SKILL.md, the BF4 equivalent); running a DOCA-linked binary on a healthy BF3 (route to doca-bare-metal-deployment/SKILL.md); deploying a DOCA service container (route to doca-container-deployment/SKILL.md); env-preparation including hugepages, IOMMU, pkg-config, and devlink mode flips (use doca-setup/SKILL.md); the body of the version-match rule (use doca-version/SKILL.md); or any hardware-state-changing burn itself — the change-application discipline is meta-policy owned by doca-hardware-safety/SKILL.md, loaded ALONGSIDE this skill.

What this skill provides

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

  • the capabilities companion — the BF3 platform-bring-up contract: the RShim/BFB transport surface (the userspace RShim daemon, the /dev/rshim* tree, console-over-rshim, the BFB image as the unit of input), the TMFIFO management-channel surface (tmfifo_net0 / tm-br, the documented 192.168.100.x convention, the ip route get-before-ping loopback gotcha), the DPU-mode surface (DPU / embedded-function vs separated-host / NIC mode, set via mlxconfig at BFB-install time — a MUTATING burn routed to doca-hardware-safety/SKILL.md), the host-side-vs-Arm-side DOCA install distinction, the BF3-version overlay on the four-way match owned by doca-version/SKILL.md, the cross-cutting error taxonomy, the observability surface, and the safety policy (overlay on doca-hardware-safety/SKILL.md).

  • the tasks companion — step-by-step workflows for the in-scope BF3 lifecycle verbs: configure, build (routing stub), modify, run (the BFB-install + RShim/TMFIFO bring-up sequence), test (the post-BFB readiness smoke), debug (the six-state bluefield-state-classifier), and the Deferred task verbs block routing app-launch / container / install / library-API / hardware-state-change / BF4 questions out to their owning skills.

The skill assumes a target where:

  • a BlueField-3 is physically present and powered, reachable from a host that has the RShim daemon and /dev/rshim* tree available,

  • the operator has a BFB image downloaded from the public DOCA Downloads page (route via doca-public-knowledge-map/SKILL.md), and

  • the operator has an out-of-band path (BMC console, serial-over-LAN, or physical UART) to reach the BF3 if a push breaks the Arm OS.

It does not cover installing DOCA on a host from scratch (that goes through doca-setup/SKILL.md), and it does not cover BlueField-4 (that goes through doca-bf4-deployment/SKILL.md).

Loading order

  1. Read this skill first to confirm the user's question is in scope (BF3 platform bring-up over the RShim/BFB path; NOT BF4, NOT app-launch, NOT a library-API question).

  2. For the bring-up contract (RShim/BFB transport, TMFIFO channel, DPU-mode surface, host-vs-Arm install distinction, BF3-version overlay, error taxonomy, observability surface, BF3 safety overlay), see the capabilities companion.

  3. For step-by-step workflows — configure, build (routing stub), modify, run (BFB install + RShim/TMFIFO bring-up), test (post-BFB readiness smoke), debug (the six-state bluefield-state-classifier), plus the Deferred task verbs block — see the tasks companion.

Example questions this skill answers well

What this skill deliberately does not ship

Files

BENCHMARK.md

Skill Benchmark: doca-bf3-deployment

✅ Overall verdict: PASS — Recommended for publication

Publication Recommendation

Recommended for publication based on the completed evaluation evidence in this report.

Evaluation Metadata

  • Skill: doca-bf3-deployment

  • Validation status: passed

  • Evaluation date: 2026-10-28

  • Evaluator version: 1.6.2

  • Agents: Claude Code (aws/anthropic/bedrock-claude-opus-5-5), Codex (openai/openai/gpt-6.1-sol)

  • Tasks: 3 evaluation tasks (2 positive, 1 negative)

  • Dataset digest: sha256:c3d6c876b2c75b4892b8cad068e3cffbe5d78b34b73f1ee3a8be5c76fc675e88 (skill-evaluator-dataset-snapshot/1)

  • Attempts per task: 1

  • Environment: k8s-sandbox

  • Tier 2 evidence: required for publication

  • Tier 3 evidence: required for publication

Each task attempt ran in its own isolated sandbox pod.

Tier 1 LLM Provenance

SkillSpector provider, model, analyzer revision, and determinism evidence retained for this scan.

SkillProviderAdapterAnalyzerModelRevisionDeterminism
doca-bf3-deploymentnv_inferenceopenaimcp_tool_poisoningaws/anthropic/bedrock-claude-opus-5-52.13.1nondeterministic / provider_defaults
doca-bf3-deploymentnv_inferenceopenaisemantic_developer_intentaws/anthropic/bedrock-claude-opus-5-52.13.1nondeterministic / provider_defaults
doca-bf3-deploymentnv_inferenceopenaisemantic_quality_policyaws/anthropic/bedrock-claude-opus-5-52.13.1nondeterministic / provider_defaults
doca-bf3-deploymentnv_inferenceopenaisemantic_security_discoveryaws/anthropic/bedrock-claude-opus-5-52.13.1nondeterministic / provider_defaults
doca-bf3-deploymentnv_inferenceopenaimeta_analyzeraws/anthropic/bedrock-claude-opus-5-52.13.1nondeterministic / provider_defaults
  • Controls for doca-bf3-deployment: temperature=not set (source=provider_default, forwarded=no); seed=not set (source=unset, forwarded=no); reasoning_effort=not set (source=provider_default, forwarded=no)

What This Report Answers

The three-tier evaluation checks whether the skill:

  • is safe to use;

  • produces correct answers;

  • is discovered and activated when needed;

  • helps the agent complete the user's goal and expected workflow; and

  • avoids wasted skill and tool usage.

Results at a Glance

MeasureClaude Code (Baseline → Skill Uplift)Codex (Baseline → Skill Uplift)
Overall96.8% — baseline ran, but no comparable score was available; uplift unavailable91.4% — baseline ran, but no comparable score was available; uplift unavailable
Security100.0% → 100.0% (±0.0 points)83.3% → 100.0% (+16.7 points)
Correctness66.7% → 100.0% (+33.3 points)93.3% → 100.0% (+6.7 points)
Discoverability100.0% — baseline ran, but no comparable score was available; uplift unavailable85.0% — baseline ran, but no comparable score was available; uplift unavailable
Effectiveness72.2% → 100.0% (+27.8 points)100.0% → 100.0% (±0.0 points)
Efficiency84.0% — baseline ran, but no comparable score was available; uplift unavailable71.8% — baseline ran, but no comparable score was available; uplift unavailable

How to read this table: baseline is the same task attempted without the target skill. Scores are rounded to one decimal; threshold-adjacent values use additional precision so their displayed band matches the verdict. Uplift is derived from those displayed scores and shown in percentage points.

Example: 47.0% → 92.0% (+45.0 points) means the skill-assisted run scored 92.0%, 45.0 percentage points above its 47.0% no-skill baseline.

A partial dimension was calculated from only the available configured signals; review the detailed report before relying on it.

Comparison details

Shared-source comparisons use the same signals and weights on both conditions. They do not replace the full dimension scores above or change the publication verdict.

AgentDimensionBasisBaseline → With skill (uplift)Explanation
claude-codeDiscoverabilityDimension comparisonN/ADiscoverability is not applicable to the no-skill baseline; there is no installed skill to discover.
claude-codeEfficiencyToken-only comparison96.9% → 93.0% (-3.9 points)Only Token Efficiency is comparable; the full dimension scores use different evaluator sources.
codexDiscoverabilityDimension comparisonN/ADiscoverability is not applicable to the no-skill baseline; there is no installed skill to discover.
codexEfficiencyToken-only comparison77.4% → 80.3% (+2.9 points)Only Token Efficiency is comparable; the full dimension scores use different evaluator sources.

Token Usage

Actual Tier 3 execution usage is reported for every observed agent/case pair and both conditions.

AgentDataset caseWith skillWithout skillDeltaChangeCoverage
claude-codeAll cases842,051408,714+433,337+106.02%skill 3/3; base 3/3
claude-codedoca-bf3-deployment.explicit-positive.v1345,682109,867+235,815+214.64%skill 1/1; base 1/1
claude-codedoca-bf3-deployment.implicit-positive.v1346,608190,847+155,761+81.62%skill 1/1; base 1/1
claude-codedoca-bf3-deployment.negative.v1149,761108,000+41,761+38.67%skill 1/1; base 1/1
codexAll cases361,740433,453-71,713-16.54%skill 3/3; base 3/3
codexdoca-bf3-deployment.explicit-positive.v1170,950262,004-91,054-34.75%skill 1/1; base 1/1
codexdoca-bf3-deployment.implicit-positive.v1106,25490,751+15,503+17.08%skill 1/1; base 1/1
codexdoca-bf3-deployment.negative.v184,53680,698+3,838+4.76%skill 1/1; base 1/1
ALL AGENTSDataset aggregate1,203,791842,167+361,624+42.94%skill 6/6; base 6/6

Prompt tokens include cached reads, so total tokens are prompt + completion (cached is not added twice). The Efficiency score uses (prompt - cached) + completion. Change is 100 * (with - without) / without; negative means fewer tokens. N/A comparisons include their reason in the coverage column; coverage is never estimated.

Tier Status

TierPurposeStatusEvidence
Tier 1Static validationPASSED WITH OBSERVATIONS11 validator(s); 12 finding(s)
Tier 2Semantic deduplicationPASSED WITH OBSERVATIONS2 validator(s); 2 finding(s)
Tier 3Live agent evaluationPASS2 agent(s); 3 task(s)

Findings and Observations

<details> <summary>Show detailed findings and successful checks</summary>

  • CRITICAL CONTENT_DEDUP/llm_error: LLM analysis failed for a content cluster (skills/doca-bf3-deployment)

  • HIGH DUPLICATE/duplicate: Duplicate content found across CAPABILITIES.md and TASKS.md: "## Error taxonomy" in CAPABILITIES.md (lines 184-224) vs "## debug" in TASKS.md (lines 296-328) (CAPABILITIES.md:184)

  • MEDIUM QUALITY/quality_discoverability: Description uses first/second person (skills/doca-bf3-deployment/SKILL.md)

  • MEDIUM QUALITY/quality_efficiency: Deeply nested references in details.md (skills/doca-bf3-deployment/SKILL.md)

  • MEDIUM SCHEMA/metadata_key_style: Metadata key 'doca_version' is not kebab-case (skills/doca-bf3-deployment/SKILL.md)

  • 9 additional finding(s) are available in the full evaluation artifacts.

</details>

Scoring Methodology

<details> <summary>Show dimension definitions, source signals, and thresholds</summary>

DimensionQuestionScored signals
SecurityIs it safe to use?security (100%)
CorrectnessIs the answer correct?accuracy (100%)
DiscoverabilityWas the right skill loaded when needed?skill_execution (100%)
EffectivenessDid the skill help complete the task?goal_accuracy (50%) + behavior_check (50%)
EfficiencyDid it avoid wasted tool calls and token usage?skill_efficiency (50%) + token_efficiency (50%)
  • Dimension bands: PASS at 50% or above; NEUTRAL from 40% to below 50%; FAIL below 40%.

  • Overall Tier 3 lift: PASS at +5 points or more; FAIL at -10 points or less; values between those bands are NEUTRAL.

  • Overall verdict: PASS only when every configured dimension passes for at least one supported agent. Lift is reported as diagnostic evidence and does not override this gate.

  • The 50% attempt pass threshold is a separate per-task gate; it is not the dimension pass threshold.

  • Effectiveness is the equal-weight mean of goal completion (goal_accuracy) and expected workflow adherence (behavior_check).

  • Efficiency is 50% tool-call productivity (the backward-compatible skill_efficiency wire id) and 50% token_efficiency. Positive-case skill routing is scored under Discoverability, not Efficiency; a negative case without a routing target is N/A. N/A sources are omitted, remaining weights are renormalized, and the dimension is marked partial.

Signals present in this run:

  • security (Security): unsafe operations, secret leakage, and unauthorized access.

  • skill_execution (Skill Execution): whether the expected skill was selected, decoys were avoided, and the workflow executed.

  • skill_efficiency (Tool Productivity): tool-call productivity (legacy wire id; routing is scored under Discoverability).

  • accuracy (Accuracy): final-answer correctness against the reference answer.

  • goal_accuracy (Goal Accuracy): whether the user's goal was achieved.

  • behavior_check (Behavior Check): whether the expected workflow behavior was followed.

  • token_efficiency (Token Efficiency): actual uncached prompt plus completion usage (50% of Efficiency).

</details>

Freshness

Regenerate this benchmark when the skill, evaluation dataset, target agent/model, evaluator version, environment, or scoring policy changes.

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

The author says: No DOCA install required to read this skill (it is a platform-lifecycle overlay loaded against BF3 hardware); the bring-up and validation steps within DO require a real BlueField-3, host-side RShim access (PCIe or USB), the matching DOCA-Host install, and a BlueField bundle (BFB) image downloaded from the public DOCA Downloads page. The validation steps require a live DOCA install.

Security

What our scanner noticed· Medium risk

  • Large base64-encoded blobs

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by
NVIDIA
Publisher
NVIDIA (Official)
Source
NVIDIA/skills · skills/doca-bf3-deployment · commit fce3cca
Licence
Apache License 2.0 (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE-APACHE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by NVIDIA or NVIDIA.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download doca-bf3-deployment.zip