Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nvidia/doca-hardware-safety
Use this skill whenever the agent is about to recommend or apply a change that touches DPU / NIC hardware state on a live system — mlxconfig firmware-parameter write, NIC firmware burn, BFB reflash, NIC ↔ DPU mode flip, SR-IOV or device-emulation slot enable, kernel boot-parameter change (IOMMU, hugepages, VFIO), PCIe rebind / rescan / link-state flip, or BlueField cold reboot. Wraps the change in pre-flight inventory, OOB reachability, a maintenance window, the mlxconfig cold-power-cycle rule,
Passed 19 of 22 test cases with the skill, and 7 of 22 without it.
and 16 more in the full report
12 fixed7 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our team is scheduling a BlueField BFB reflash on several host nodes, but we currently manage the DPUs over the primary network interface and want to execute this during standard shift hours. Can you evaluate this maintenance plan and provide an advisory report outlining any required safety preconditions, testing requirements, or escalation gates before we proceed?
| Checked | Without skill | With skill |
|---|---|---|
| Explicitly cite the activation of the doca-hardware-safety overlay discipline. | Missed | Passed |
| Refuse or halt the planned reflash because executing a link-breaking change over an in-band management link lacks an out-of-band path. | Passed | Passed |
| Require an explicit, time-boxed maintenance window rather than executing during standard shift hours. | Missed | Passed |
The instructions your model reads when the skill loads.
Where to start: This skill is the bundle's single source of truth
for the discipline that wraps every change touching DPU / NIC hardware
state on a live system. Open
TASKS.md when the operator is about to apply a
hardware-touching change and needs the change-application discipline
(pre-flight inventory → out-of-band path → window → apply → verify
→ rollback). Open CAPABILITIES.md when the
question is what does hardware-safety even cover (the class of
changes in scope, the failure modes the policy prevents, the
observability surface that gates a change, and the meta-policy that
every per-artifact ## Safety policy overlays).
Every per-artifact skill (services, libraries, tools) in the bundle
that recommends a hardware-touching action overlays this meta-policy
with artifact-specific safety. The per-artifact ## Safety policy
anchors do NOT redefine the cross-cutting discipline — they layer the
artifact's own concerns on top of it. This skill is the layer they all
build on.
The CLASSES of hardware-safety questions this skill is built to answer, each with one worked example. The agent should treat the class as load-bearing — the worked example is a single instance.
TASKS.md ## configure plus the
inventory taxonomy in
CAPABILITIES.md ## Capabilities and modes.CAPABILITIES.md ## Safety policy
plus the OOB-precondition gate intest cases passed, vs 7 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.