DOCA Pipeline Language Developer Tools
Scope boundaries
These requests are out of scope: say so, name the skill that owns
the request, and stop.
- installing DOCA and bringing up the DPL Runtime Service container:
doca-setup/SKILL.md. Name doca-setup in the answer and route the
whole install/bring-up there; do not walk the install steps from this
skill or from the DPL Installation Guide.
- DPU mode or firmware state changes:
doca-hardware-safety/SKILL.md.
- which DOCA version is installed, version compatibility:
doca-version/SKILL.md.
- authoring, compiling and deploying DPL programs (DOCA Pipeline Language Service Guide):
doca-public-knowledge-map/SKILL.md.
Examples
- "How do I inspect the DPL runtime tables on the DPU?" — this is
in scope. Use DPL Nspect; do not author or compile DPL programs here.
- "I want to visualize packet flow through my DPL program." — this
is in scope. Use DPL Debugger; ensure the program was compiled with
the debug flag
-g and loaded into dpl_rtd using the P4Runtime
controller.
- "How do I dynamically change a configuration item in dpl_rtd?" —
this is in scope. Use DPL Admin; inspect current state first.
- "Can I build a custom P4Runtime application for DPL?" — this is
in scope. Use the DPL Runtime Controller SDK.
- "My DPL program is loaded but I cannot start a debug session." —
check the debug-flag prerequisite and the P4Runtime load path before
assuming the tool is broken.
Quick facts
The authoritative source for the tool names, flags, and paths is the public
DOCA Pipeline Language Developer Tools guide for your release; confirm them
with the installed tool's help before quoting any of them. As that guide
describes it:
- The developer tools are a suite for validating and debugging DPL
applications: DPL Compiler, P4 Runtime Shell, DPL Nspect, DPL Debugger,
DPL Admin, and DPL Runtime Controller SDK.
- All tools interact with the DPL Runtime Daemon (
dpl_rtd) running on the
BlueField DPU.
- DPL Compiler converts DPL source code into a binary format that can be
loaded by
dpl_rtd.
- P4 Runtime Shell is an open-source control plane manager implementing the
P4Runtime API.
- DPL Nspect is a command-line interface for inspecting DPL runtime state,
including tables, keys, counters, and more.
- DPL Debugger is a graphical interface for visualizing and debugging packet
flow through the DPL program.
- DPL Admin is a CLI tool for dynamically modifying configuration items in
the DPL Runtime Daemon.
- DPL Runtime Controller SDK is an SDK for building custom P4Runtime
applications or integrating with DPL shared memory APIs.
- Prerequisites: the DPL Runtime Service container must be deployed and
running on the DPU, the
dpl_rtd process must be active, and the DPU must
be configured to operate in DPU mode.
- Starting a debug session requires the DPL program to be compiled for
debugging: compile with the DPL Compiler debug flag
-g enabled, then load
the compiled binary into dpl_rtd using the P4Runtime controller.
- The developer tools are included in the DPL Development Container, which is
publicly available on NGC. Installation instructions refer to the DPL
Installation Guide.
- For instructions on creating, compiling, and deploying DPL programs, refer
to the DOCA Pipeline Language Service Guide.
- Support and feedback: visit the NVIDIA DOCA Enterprise Networking Forum.
Registration with the NVIDIA Developer Program is required to post;
registration is not required to view existing discussions. For help with
registration, refer to the FAQ.
Instructions
Follow Loading order below. Open the tasks companion for
inspect / debug / modify / build / shell. Open the capabilities companion for
what the tools inspect and change. Do not open every companion file.
Where to start: This is a tool skill for invoking the DOCA Pipeline
Language Developer Tools — the suite for inspecting and debugging DPL
programs on BlueField DPUs. Open the tasks companion and start at
## inspect for DPL Nspect runtime-state inspection, ## debug for DPL
Debugger packet-flow visualization, ## modify for DPL Admin dynamic
configuration changes, ## build for DPL Runtime Controller SDK custom
P4Runtime applications, and ## shell for P4 Runtime Shell control-plane
use. Open the capabilities companion when the question is what state can
the tools inspect, what do they change, and what prerequisites gate their
use. If the user has not installed DOCA yet, route to
doca-setup/SKILL.md first. If the user is asking about DPL program
authoring, compiling, or deploying rather than inspecting or debugging a
loaded program, route to the DOCA Pipeline Language Service Guide, not this
skill. Any step that changes hardware or firmware state routes through
doca-hardware-safety/SKILL.md. Version questions route through
doca-version/SKILL.md; installs route through doca-setup/SKILL.md.
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, quoting only
commands documented in the public guide or installed tool help. For
out-of-scope requests, name the skill that owns them and stop.
Example questions this skill answers well
The CLASSES of DPL developer-tools 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 tools are available for inspecting and debugging DPL programs?"
— worked example: "I have a DPL program loaded on the DPU and need to
see its tables, keys, counters, or packet flow". Answered by the tool
inventory in the capabilities companion + the tasks companion.
- "How do I inspect DPL runtime state?" — worked example: "I want to
list the tables and counters currently active in dpl_rtd". Answered by
the DPL Nspect workflow in the tasks companion.
- "How do I debug packet flow through a DPL program?" — worked example:
"packets are not matching the expected table entries; I need to visualize
the path through the DPL program". Answered by the DPL Debugger
prerequisites (debug flag
-g, P4Runtime load) in the capabilities
companion + the tasks companion.
- "How do I dynamically change configuration items in dpl_rtd?" —
worked example: "I need to update a configuration item without restarting
the DPL Runtime Daemon". Answered by the DPL Admin workflow in the tasks
companion.
- "How do I build a custom P4Runtime application or integrate with DPL
shared memory APIs?" — worked example: "I want to write my own
control-plane application for DPL instead of using the P4 Runtime Shell".
Answered by the DPL Runtime Controller SDK workflow in the tasks companion.
- "What are the prerequisites for using the developer tools?" — worked
example: "the tools cannot see dpl_rtd; is the DPL Runtime Service
container running and is the DPU in DPU mode?". Answered by the
prerequisites in the capabilities companion + the tasks companion.
When to load this skill
Load this skill when the user is — or the agent needs to — drive the DOCA
Pipeline Language Developer Tools on a real BlueField DPU with the DPL
Runtime Service running. Concretely:
- Inspecting DPL runtime state (tables, keys, counters) with DPL Nspect.
- Visualizing or debugging packet flow through a DPL program with DPL
Debugger.
- Dynamically modifying configuration items in
dpl_rtd with DPL Admin.
- Building custom P4Runtime applications or integrating with DPL shared
memory APIs using the DPL Runtime Controller SDK.
- Using the P4 Runtime Shell as a P4Runtime control plane manager.
- Preparing a debug session: ensuring the DPL program was compiled with the
debug flag
-g and loaded into dpl_rtd using the P4Runtime controller.
- Diagnosing why the developer tools cannot interact with
dpl_rtd (DPL
Runtime Service container not running, dpl_rtd not active, DPU not in
DPU mode).
Do not load this skill for general DOCA orientation, DPL program
authoring/compilation/deployment, DOCA install, or hardware/firmware state
changes. For those, route to
doca-public-knowledge-map/SKILL.md,
the DOCA Pipeline Language Service Guide,
doca-setup/SKILL.md, or
doca-hardware-safety/SKILL.md.
What this skill provides
This is a thin loader. Substantive material lives in two companion
files:
- the capabilities companion — what the developer tools inspect and change:
the tool inventory (DPL Compiler, P4 Runtime Shell, DPL Nspect, DPL
Debugger, DPL Admin, DPL Runtime Controller SDK), the read-only vs
state-changing operation split (Nspect and Debugger read-only; Admin
modifies; Compiler and SDK build), the prerequisites (DPL Runtime Service
container,
dpl_rtd active, DPU mode, debug flag -g, P4Runtime load),
availability via the DPL Development Container on NGC, support/feedback via
the NVIDIA DOCA Enterprise Networking Forum, and the high-stakes safety
policy that dynamic configuration changes through DPL Admin affect the
running DPL Runtime Daemon and must be gated on a clean inspection.
- the tasks companion — step-by-step workflows for the in-scope task verbs:
inspect (DPL Nspect runtime state), debug (DPL Debugger packet flow,
including the debug-flag prerequisite), modify (DPL Admin dynamic
configuration), build (DPL Runtime Controller SDK custom P4Runtime
applications / shared memory integration), shell (P4 Runtime Shell
control plane), plus a Deferred task verbs block and a Command appendix
that honors the bundle's
doca-structured-tools-contract/SKILL.md
preamble.
The skill assumes a BlueField DPU where the DPL Runtime Service container is
already deployed and running, dpl_rtd is active, and the DPU is configured
to operate in DPU mode.
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:
- Verbatim subcommand names, flag inventories beyond the documented debug
flag
-g, default paths, port numbers, or output column names. The
public DOCA Pipeline Language Developer Tools guide on docs.nvidia.com
and the installed tool help on the user's version are the joint source of
truth; copying them here pins the skill to one release and silently rots
when the tools evolve. The skill routes the agent at those sources instead.
- Pre-baked example output. Output is install-, version-, and
deployment-specific. A captured example will mislead an operator on a
different platform / state.
- Wrappers, parsers, or scripts in any language that consume the tools'
output. The output format is documented; users who want to script against
it should read the live guide and write the parser against their installed
version.
- A
samples/ or reference/ subtree. This is a thin loader for a
documented DOCA artifact; substantive material lives on the public page and
in the installed tool help.
Loading order
- Read this skill first to confirm the user's question is in scope (the
user wants to inspect or debug DPL programs on a BlueField DPU, not
author, compile, or deploy DPL programs).
- For what the tools inspect and change, the tool inventory, the
read-only vs state-changing split, prerequisites, availability, support,
and safety posture, see the capabilities companion.
- For the documented invocations and the workflows —
inspect, debug,
modify, build, shell, plus the Command appendix — see the tasks
companion.
Related skills
doca-public-knowledge-map/SKILL.md
— routing to the public DOCA Pipeline Language Developer Tools guide and
the rest of the public DOCA documentation set. The canonical URL is reached
via doca-public-knowledge-map ## DOCA tools
(doca-public-knowledge-map/SKILL.md#doca-tools).
doca-version/SKILL.md — canonical DOCA
version-handling rules. Version questions route here; the capabilities
companion redirects to this skill for the body.
doca-setup/SKILL.md — env preparation,
install verification, DPL Runtime Service container deployment, and the I
have no install yet path with the public NGC DPL Development Container.
This skill assumes its preconditions are satisfied.
doca-hardware-safety/SKILL.md
— any step that changes hardware or firmware state routes here.
doca-structured-tools-contract/SKILL.md
— the bundle's detect → prefer → fall back → report contract for structured
helper tools. The Command appendix in the tasks companion honors this
contract.
doca-debug/SKILL.md — the cross-cutting
debug ladder. The DPL developer tools slot in at the runtime layer as
inspection/debug tooling whose layered error surface escalates to the
cross-cutting ladder when the cause is below DOCA.
1---2license: Apache-2.03name: doca-pipeline-language-developer-tools4description: >5 Use this skill when the operator is driving the DOCA Pipeline6 Language (DPL) Developer Tools to inspect or debug DPL programs on7 a BlueField DPU — DPL Nspect for runtime state such as tables,8 keys, and counters, DPL Debugger for packet flow, DPL Admin for9 dynamic configuration changes in the DPL Runtime Daemon, P410 Runtime Shell as a P4Runtime control plane manager, or DPL Runtime11 Controller SDK for custom P4Runtime applications and DPL shared12 memory APIs. Trigger even when the user does not explicitly mention13 "DPL Developer Tools" — implicit phrasings include "inspect the DPL14 tables on the DPU", "why can't I start a DPL debug session",15 "change a dpl_rtd configuration item without restarting", "build my16 own P4Runtime app for DPL", or "visualize packet flow through my17 DPL program". Refuse and route elsewhere: authoring, compiling and18 deploying DPL programs to the DOCA Pipeline Language Service Guide,19 DOCA install/bring-up to doca-setup,20 and hardware or firmware state changes to doca-hardware-safety.21metadata:22 source: https://skillmd.com/skills/nvidia/doca-pipeline-language-developer-tools23 author: NVIDIA <doca-feedback@nvidia.com>24 kind: tool25 doca_version: "3.5"26 tags:27 - doca28 - dpl29 - developer-tools30 - p4runtime31 - debug32 - nspect33compatibility: >34 Requires a BlueField DPU configured to operate in DPU mode with the35 DPL Runtime Service container deployed and running, the dpl_rtd36 process active, and the DPL Development Container (publicly37 available on NGC) providing the developer tools. Debug sessions38 additionally require a DPL program compiled with the DPL Compiler39 debug flag -g enabled and loaded into dpl_rtd using the P4Runtime40 controller. The validation steps require a live DOCA install.41---4243# DOCA Pipeline Language Developer Tools4445## Scope boundaries4647These requests are out of scope: say so, name the skill that owns48the request, and stop.4950- installing DOCA and bringing up the DPL Runtime Service container:51 `doca-setup/SKILL.md`. Name `doca-setup` in the answer and route the52 whole install/bring-up there; do not walk the install steps from this53 skill or from the DPL Installation Guide.54- DPU mode or firmware state changes: `doca-hardware-safety/SKILL.md`.55- which DOCA version is installed, version compatibility: `doca-version/SKILL.md`.56- authoring, compiling and deploying DPL programs (DOCA Pipeline Language Service Guide): `doca-public-knowledge-map/SKILL.md`.5758## Examples5960- **"How do I inspect the DPL runtime tables on the DPU?"** — this is61 in scope. Use DPL Nspect; do not author or compile DPL programs here.62- **"I want to visualize packet flow through my DPL program."** — this63 is in scope. Use DPL Debugger; ensure the program was compiled with64 the debug flag `-g` and loaded into `dpl_rtd` using the P4Runtime65 controller.66- **"How do I dynamically change a configuration item in dpl_rtd?"** —67 this is in scope. Use DPL Admin; inspect current state first.68- **"Can I build a custom P4Runtime application for DPL?"** — this is69 in scope. Use the DPL Runtime Controller SDK.70- **"My DPL program is loaded but I cannot start a debug session."** —71 check the debug-flag prerequisite and the P4Runtime load path before72 assuming the tool is broken.7374## Quick facts7576The authoritative source for the tool names, flags, and paths is the public77DOCA Pipeline Language Developer Tools guide for your release; confirm them78with the installed tool's help before quoting any of them. As that guide79describes it:8081- The developer tools are a suite for validating and debugging DPL82 applications: DPL Compiler, P4 Runtime Shell, DPL Nspect, DPL Debugger,83 DPL Admin, and DPL Runtime Controller SDK.84- All tools interact with the DPL Runtime Daemon (`dpl_rtd`) running on the85 BlueField DPU.86- DPL Compiler converts DPL source code into a binary format that can be87 loaded by `dpl_rtd`.88- P4 Runtime Shell is an open-source control plane manager implementing the89 P4Runtime API.90- DPL Nspect is a command-line interface for inspecting DPL runtime state,91 including tables, keys, counters, and more.92- DPL Debugger is a graphical interface for visualizing and debugging packet93 flow through the DPL program.94- DPL Admin is a CLI tool for dynamically modifying configuration items in95 the DPL Runtime Daemon.96- DPL Runtime Controller SDK is an SDK for building custom P4Runtime97 applications or integrating with DPL shared memory APIs.98- Prerequisites: the DPL Runtime Service container must be deployed and99 running on the DPU, the `dpl_rtd` process must be active, and the DPU must100 be configured to operate in DPU mode.101- Starting a debug session requires the DPL program to be compiled for102 debugging: compile with the DPL Compiler debug flag `-g` enabled, then load103 the compiled binary into `dpl_rtd` using the P4Runtime controller.104- The developer tools are included in the DPL Development Container, which is105 publicly available on NGC. Installation instructions refer to the DPL106 Installation Guide.107- For instructions on creating, compiling, and deploying DPL programs, refer108 to the DOCA Pipeline Language Service Guide.109- Support and feedback: visit the NVIDIA DOCA Enterprise Networking Forum.110 Registration with the NVIDIA Developer Program is required to post;111 registration is not required to view existing discussions. For help with112 registration, refer to the FAQ.113114## Instructions115116Follow Loading order below. Open the tasks companion for117inspect / debug / modify / build / shell. Open the capabilities companion for118what the tools inspect and change. Do not open every companion file.119120**Where to start:** This is a tool skill for invoking the DOCA Pipeline121Language Developer Tools — the suite for inspecting and debugging DPL122programs on BlueField DPUs. Open the tasks companion and start at123`## inspect` for DPL Nspect runtime-state inspection, `## debug` for DPL124Debugger packet-flow visualization, `## modify` for DPL Admin dynamic125configuration changes, `## build` for DPL Runtime Controller SDK custom126P4Runtime applications, and `## shell` for P4 Runtime Shell control-plane127use. Open the capabilities companion when the question is *what state can128the tools inspect, what do they change, and what prerequisites gate their129use*. If the user has not installed DOCA yet, route to130`doca-setup/SKILL.md` first. If the user is asking about DPL program131authoring, compiling, or deploying rather than inspecting or debugging a132loaded program, route to the DOCA Pipeline Language Service Guide, not this133skill. Any step that changes hardware or firmware state routes through134`doca-hardware-safety/SKILL.md`. Version questions route through135`doca-version/SKILL.md`; installs route through `doca-setup/SKILL.md`.136137**How to use this skill.** Read this file, then search the companion file138for the `## <name>` heading the question needs and read that whole section.139Answer completely from it, quoting only its symbols and commands. Do not140browse docs; use the entry points in `doca-public-knowledge-map`. Give141environment checks as commands for the user's DOCA host, quoting only142commands documented in the public guide or installed tool help. For143out-of-scope requests, name the skill that owns them and stop.144145## Example questions this skill answers well146147The CLASSES of DPL developer-tools questions this skill is built to answer,148each with one worked example. The class is the load-bearing piece; the149worked example is one instance.150151- **"What tools are available for inspecting and debugging DPL programs?"**152 — worked example: *"I have a DPL program loaded on the DPU and need to153 see its tables, keys, counters, or packet flow"*. Answered by the tool154 inventory in the capabilities companion + the tasks companion.155- **"How do I inspect DPL runtime state?"** — worked example: *"I want to156 list the tables and counters currently active in dpl_rtd"*. Answered by157 the DPL Nspect workflow in the tasks companion.158- **"How do I debug packet flow through a DPL program?"** — worked example:159 *"packets are not matching the expected table entries; I need to visualize160 the path through the DPL program"*. Answered by the DPL Debugger161 prerequisites (debug flag `-g`, P4Runtime load) in the capabilities162 companion + the tasks companion.163- **"How do I dynamically change configuration items in dpl_rtd?"** —164 worked example: *"I need to update a configuration item without restarting165 the DPL Runtime Daemon"*. Answered by the DPL Admin workflow in the tasks166 companion.167- **"How do I build a custom P4Runtime application or integrate with DPL168 shared memory APIs?"** — worked example: *"I want to write my own169 control-plane application for DPL instead of using the P4 Runtime Shell"*.170 Answered by the DPL Runtime Controller SDK workflow in the tasks companion.171- **"What are the prerequisites for using the developer tools?"** — worked172 example: *"the tools cannot see dpl_rtd; is the DPL Runtime Service173 container running and is the DPU in DPU mode?"*. Answered by the174 prerequisites in the capabilities companion + the tasks companion.175176## When to load this skill177178Load this skill when the user is — or the agent needs to — drive the DOCA179Pipeline Language Developer Tools on a real BlueField DPU with the DPL180Runtime Service running. Concretely:181182- Inspecting DPL runtime state (tables, keys, counters) with DPL Nspect.183- Visualizing or debugging packet flow through a DPL program with DPL184 Debugger.185- Dynamically modifying configuration items in `dpl_rtd` with DPL Admin.186- Building custom P4Runtime applications or integrating with DPL shared187 memory APIs using the DPL Runtime Controller SDK.188- Using the P4 Runtime Shell as a P4Runtime control plane manager.189- Preparing a debug session: ensuring the DPL program was compiled with the190 debug flag `-g` and loaded into `dpl_rtd` using the P4Runtime controller.191- Diagnosing why the developer tools cannot interact with `dpl_rtd` (DPL192 Runtime Service container not running, `dpl_rtd` not active, DPU not in193 DPU mode).194195Do **not** load this skill for general DOCA orientation, DPL program196authoring/compilation/deployment, DOCA install, or hardware/firmware state197changes. For those, route to198`doca-public-knowledge-map/SKILL.md`,199the DOCA Pipeline Language Service Guide,200`doca-setup/SKILL.md`, or201`doca-hardware-safety/SKILL.md`.202203## What this skill provides204205This is a **thin loader**. Substantive material lives in two companion206files:207208- the capabilities companion — what the developer tools inspect and change:209 the tool inventory (DPL Compiler, P4 Runtime Shell, DPL Nspect, DPL210 Debugger, DPL Admin, DPL Runtime Controller SDK), the read-only vs211 state-changing operation split (Nspect and Debugger read-only; Admin212 modifies; Compiler and SDK build), the prerequisites (DPL Runtime Service213 container, `dpl_rtd` active, DPU mode, debug flag `-g`, P4Runtime load),214 availability via the DPL Development Container on NGC, support/feedback via215 the NVIDIA DOCA Enterprise Networking Forum, and the high-stakes safety216 policy that dynamic configuration changes through DPL Admin affect the217 running DPL Runtime Daemon and must be gated on a clean inspection.218- the tasks companion — step-by-step workflows for the in-scope task verbs:219 `inspect` (DPL Nspect runtime state), `debug` (DPL Debugger packet flow,220 including the debug-flag prerequisite), `modify` (DPL Admin dynamic221 configuration), `build` (DPL Runtime Controller SDK custom P4Runtime222 applications / shared memory integration), `shell` (P4 Runtime Shell223 control plane), plus a `Deferred task verbs` block and a `Command appendix`224 that honors the bundle's225 `doca-structured-tools-contract/SKILL.md`226 preamble.227228The skill assumes a BlueField DPU where the DPL Runtime Service container is229already deployed and running, `dpl_rtd` is active, and the DPU is configured230to operate in DPU mode.231232## What this skill deliberately does not ship233234This skill is **agent guidance**, not a samples or scripts bundle. To keep235the boundary clean, it deliberately does not contain — and pull requests236should not add:237238- **Verbatim subcommand names, flag inventories beyond the documented debug239 flag `-g`, default paths, port numbers, or output column names.** The240 public DOCA Pipeline Language Developer Tools guide on `docs.nvidia.com`241 and the installed tool help on the user's version are the joint source of242 truth; copying them here pins the skill to one release and silently rots243 when the tools evolve. The skill routes the agent at those sources instead.244- **Pre-baked example output.** Output is install-, version-, and245 deployment-specific. A captured example will mislead an operator on a246 different platform / state.247- **Wrappers, parsers, or scripts** in any language that consume the tools'248 output. The output format is documented; users who want to script against249 it should read the live guide and write the parser against their installed250 version.251- **A `samples/` or `reference/` subtree.** This is a thin loader for a252 documented DOCA artifact; substantive material lives on the public page and253 in the installed tool help.254255## Loading order2562571. Read this skill first to confirm the user's question is in scope (the258 user wants to inspect or debug DPL programs on a BlueField DPU, not259 author, compile, or deploy DPL programs).2602. **For what the tools inspect and change, the tool inventory, the261 read-only vs state-changing split, prerequisites, availability, support,262 and safety posture, see the capabilities companion.**2633. **For the documented invocations and the workflows — `inspect`, `debug`,264 `modify`, `build`, `shell`, plus the `Command appendix` — see the tasks265 companion.**266267## Related skills268269- `doca-public-knowledge-map/SKILL.md`270 — routing to the public DOCA Pipeline Language Developer Tools guide and271 the rest of the public DOCA documentation set. The canonical URL is reached272 via `doca-public-knowledge-map ## DOCA tools`273 (`doca-public-knowledge-map/SKILL.md#doca-tools`).274- `doca-version/SKILL.md` — canonical DOCA275 version-handling rules. Version questions route here; the capabilities276 companion redirects to this skill for the body.277- `doca-setup/SKILL.md` — env preparation,278 install verification, DPL Runtime Service container deployment, and the *I279 have no install yet* path with the public NGC DPL Development Container.280 This skill assumes its preconditions are satisfied.281- `doca-hardware-safety/SKILL.md`282 — any step that changes hardware or firmware state routes here.283- `doca-structured-tools-contract/SKILL.md`284 — the bundle's detect → prefer → fall back → report contract for structured285 helper tools. The Command appendix in the tasks companion honors this286 contract.287- `doca-debug/SKILL.md` — the cross-cutting288 debug ladder. The DPL developer tools slot in at the *runtime* layer as289 inspection/debug tooling whose layered error surface escalates to the290 cross-cutting ladder when the cause is below DOCA.