Index of every page on this site: llms.txt
All skills
nvidia avatar

/doca-caps

@6b75e9e
by NVIDIA Corporationnvidia/skills4.1k stars
547
Run it yourself

Use this skill when the user wants to invoke the read-only doca_caps CLI to ask what DOCA sees on this host — listing DOCA devices and PCIe addresses, listing representor devices, asking which DOCA libraries are available on the current OS, checking per-device per-library capabilities, scoping output to a specific PCIe address, or capturing a side-effect-free capability snapshot for debug or install smoke-test. Trigger even when the user does not explicitly mention "doca_caps" or "capabilities print tool" — typical implicit phrasings include "what does DOCA actually see on this box", "is my BlueField PF visible to DOCA", "is Flow available on my RHEL host", "enumerate VF representors for pf0", "doca_caps: command not found", or "empty output for RDMA, is the tool broken". Refuse and route elsewhere for DOCA installation (doca-setup owns it; never walk the steps), library-internal capability matrices (Flow pipe creation, RDMA verbs features), streaming telemetry / DTS, or modifying the shipped binary.

Use this Skill: https://skilld.dev/gh/nvidia/skills/doca-caps

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈258 tokens for metadata: the name and description. ≈2.9k when used: this file. ≈14k more on demand in 6 files.

Description uses 12.8% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈1027 characters, or 12.8%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

DOCA Capabilities Print Tool (doca_caps)

Examples

  • "Does my BlueField-3 support Flow hardware steering, RDMA and GPUNetIO?" Answer in this order:
    1. Install baseline first (doca-setup): pkg-config --modversion doca-common and /opt/mellanox/doca present; doca_caps is only as current as that install.
    2. doca_caps --list-devs: the BlueField-3 row with its PCIe address must be there.
    3. doca_caps --pci-addr <bdf> scoped to that device, with the per-library flag doca_caps --help lists (never guess a flag name), once each for Flow, RDMA and GPUNetIO. Read each library's section for that device: it lists the capabilities the device supports (for Flow, the hardware steering entries; for RDMA, the supported tasks; for GPUNetIO, whether the library is listed at all).
    4. An absent capability means one of two things: the device does not support it, or this firmware / driver / DOCA version does not surface it yet. Tell them apart with the version check (doca-version) before concluding the hardware lacks it.
  • "What DOCA devices does this host see?" — this is in scope. Stay on doca_caps; do not start a library-internal capability matrix here.
  • "Is Flow available on my RHEL host?" — list libraries then scope per-device if needed.

Instructions

Follow Loading order below. Open the tasks companion for run / test. Open the capabilities companion for what the CLI reports. Do not open every companion file.

Where to start: This is a tool skill for invoking doca_caps, a side-effect-free CLI. Open the tasks companion and start at ## run for the documented invocations, or ## test when using doca_caps as an install smoke-test. Open the capabilities companion when the question is what kinds of capability families doca_caps reports.

Boundary: this skill never installs DOCA. doca_caps verifies an install and never performs one. A request to install DOCA — choosing packages, adding repositories, running a package manager — is out of scope here, and stays out of scope even though this skill's ## test verb uses the tool as an install smoke-test afterwards. Hand the whole request to doca-setup/SKILL.md by name. Naming the owner and then listing the steps anyway is the failure mode to avoid: do not walk the installation, not even as a summary or a caveat.

This narrows installation only. It is not a reason to answer narrowly about tooling: when the user's question reaches past doca_caps — what else can I ask this hardware, how do I measure it, how do I inspect a running pipeline — name the sibling tool that owns it (doca_bench, doca_flow_tune, pcc_counters.sh, doca_comm_channel_admin, …) and tie it to the question. Pointing at the rest of the catalog is this skill's job, not a boundary breach.

Answer contract for "does my device support X?" This applies only to capability questions on a machine that has (or will verify) a DOCA install. A request to install DOCA is not one: do not walk doca_caps for it; say installation is out of this skill's scope and route to doca-setup. For capability questions, every answer contains these, in this order:

  1. Install baseline first, per doca-setup. Quote the command itself, pkg-config --modversion doca-common, plus ls /opt/mellanox/doca, and name doca-setup as the skill that owns the baseline. doca_caps is only as current as that install.
  2. doca_caps --list-devs: the target device's row (PCIe address).
  3. Scoped run and what to read: doca_caps --pci-addr <bdf> with the per-library flag doca_caps --help lists, and name the line to read per capability (Flow: the hardware-steering entries in its section; RDMA: the supported tasks; GPUNetIO: whether the library is listed for the device at all).
  4. Absent is not unsupported: a missing entry means the device lacks it or this firmware / driver / DOCA version does not surface it yet; run the version check (doca-version, firmware and driver via doca-setup) before telling the user the hardware cannot do it.
  5. The next question's tool: when the user also asks what else to ask the hardware, name the sibling tool that answers it (PCC counters: pcc_counters.sh; performance: doca_bench; Flow pipeline inspection: doca_flow_tune) and tie it to that question.

Example questions this skill answers well

The CLASSES of doca_caps 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.

  • "What DOCA devices does this host see?" — worked example: "is my BlueField PF visible to DOCA". Answered by the device enumeration in the capabilities companion
    • the --list-devs invocation in the tasks companion.
  • "Which DOCA libraries are available on this OS?" — worked example: "is Flow available on my RHEL host". Answered by the library-availability surface in the capabilities companion
    • the library-listing invocation in the tasks companion.
  • "Does this device support library X capability Y?" — worked example: "does this device support Flow hairpin?". Answered by the per-device per-library capability matrix in the capabilities companion
    • the --pci-addr-scoped invocation in the tasks companion.
  • "What representors are visible to DOCA?" — worked example: "enumerate VF representors for pf0". Answered by the representor enumeration in the capabilities companion
    • the --list-rep-devs invocation in the tasks companion.
  • "I want a snapshot of state to attach to my debug session." — worked example: "save device + library + capability output to a file". Answered by the snapshot workflow in the tasks companion and consumed by doca-debug/SKILL.md step 3 (read-only triple) and doca-programming-guide/SKILL.md.
  • "doca_caps returned nothing for capability Y — what does that mean?" — worked example: "empty output for RDMA". Answered by the empty-output interpretation rules in the tasks companion + the capabilities companion.

Audience

This skill serves external operators, developers, and AI agents who need a side-effect-free way to ask "what does DOCA see on this host?" before doing anything that changes state. Concretely:

  • An external developer who installed DOCA (or is using the public NGC DOCA container per doca-setup/SKILL.md) and wants to confirm the install can see hardware before writing code.
  • A platform operator deploying a DOCA service who wants a documented, read-only snapshot of which DOCA libraries this host actually supports and which capabilities each DOCA device offers.
  • An AI agent producing a capability snapshot artifact during the documented setup or programming-guide debug procedures (it's listed as the canonical first step in doca-setup/SKILL.md and doca-programming-guide/SKILL.md).

It is not for users debugging doca_caps itself, and not a substitute for the live public Capabilities Print Tool guide.

doca_caps is shipped as a tool (a single CLI binary), not a library you link against. The skill uses the same kind: tool three-file shape as the rest of the bundle so the agent's task-verb contract (configure / build / modify / run / test / debug) is uniform across libraries, services, and tools — even when individual verbs collapse to a routing stub for a shipped read-only binary.

When to load this skill

Load this skill when the user is — or the agent needs to — invoke doca_caps on a real host with DOCA installed (or inside the public NGC DOCA container). Concretely:

  • Running doca_caps --list-devs to enumerate DOCA devices.
  • Running doca_caps --list-rep-devs to enumerate representor devices.
  • Scoping output to a specific PCIe address with --pci-addr.
  • Listing the DOCA libraries the install reports as available on the current OS.
  • Listing the available DOCA logger names.
  • Capturing a documented, side-effect-free capability snapshot as prerequisite evidence for later ## debug workflows.

Do not load this skill for general DOCA orientation, library API work, or installation. For those, use doca-public-knowledge-map/SKILL.md, the matching libs/<library> skill, or doca-setup/SKILL.md.

What this skill provides

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

  • the capabilities companion — what doca_caps reports (the five documented capability families: devices, representors, libraries, library capabilities, loggers), version availability and execution environment, the tool's narrow error surface, its observability role inside other skills' workflows, and its read-only safety posture.
  • the tasks companion — step-by-step workflows for the in-scope task verbs: configure (route to install), build (route to install), modify (refuse), run (the documented invocations), test (capability snapshot as install smoke-test), debug (what to do when the tool reports nothing or fails), plus a Deferred task verbs block routing out-of-scope questions.

The skill assumes a host where DOCA is already installed (or the public NGC DOCA container is running) and the operator has whatever permissions the public guide requires for doca_caps to enumerate devices on their platform.

What this skill deliberately does not ship

This skill is agent guidance, not a samples or scripts bundle. To keep the boundary clean, it deliberately does not contain — and pull requests should not add:

  • Pre-baked example output. Output is install- and hardware-specific. A captured example pinned to one platform and one DOCA version misleads operators on a different platform / version.
  • Wrappers, parsers, or scripts in any language that consume doca_caps output. The output format is documented; if a user wants to script against it, the right answer is "read the live guide, write the parser against your installed version".
  • A samples/ or reference/ subtree. This is a thin loader for a documented CLI; substantive material lives on the public page and in --help.

Loading order

  1. Read this skill first to confirm the user's question is in scope (the user actually wants to invoke doca_caps, not learn about DOCA in general).
  2. For what doca_caps reports, version availability, error surface, and safety posture, see the capabilities companion.
  3. For the documented invocations and the capability-snapshot workflow — configure, build, modify, run, test, debug — see the tasks companion.

Related skills

  • doca-public-knowledge-map/SKILL.md — routing to the public Capabilities Print Tool guide and the rest of the public DOCA documentation set.
  • doca-setup/SKILL.md — env preparation, install verification (doca_caps is the canonical first step there), and the I have no install yet path with the public NGC DOCA container.
  • doca-programming-guide/SKILL.md — cross-library programming patterns, including the ## debug procedure where the saved doca_caps snapshot is consumed.
  • The matching libs/<library> skill — for fine-grained, library-specific capability questions that go beyond what doca_caps exposes.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts15d3 checks · Risk SAFE
  • Gen Agent Trust Hub20d

    The skill is a legitimate guidance tool for the NVIDIA DOCA Capabilities Print Tool (doca_caps). It follows security best practices by referencing absolute system paths and emphasizing a read-only posture for hardware discovery. No malicious code, obfuscation, or unauthorized data access were detected.

  • Socket15d

    No alerts

  • Snyk20d

    Risk: LOW · No issues

Signed by skilld at 6b75e9e. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 3 days ago
Other metadata
metadata
{
  "author": "NVIDIA <doca-feedback@nvidia.com>",
  "kind": "tool",
  "doca_version": "3.6",
  "tags": [
    "doca",
    "caps",
    "tools"
  ]
}
compatibility
Requires DOCA SDK ≥ 2.6.0 installed at /opt/mellanox/doca on Linux (Ubuntu 22.04/24.04 or RHEL/SLES) with a BlueField DPU or ConnectX NIC; runs identically on the host or on the BlueField Arm side. Invokes /opt/mellanox/doca/tools/doca_caps and reads `pkg-config doca-common` to confirm the install. The validation steps require a live DOCA install.

README badge

README badge for nvidia/skills/doca-caps