Official agent skill

Doca Debug

by NVIDIA in NVIDIA/skills

A skill your agent uses when the user is debugging any DOCA symptom — a build that won't compile, a link step that can't resolve a doca symbol, a runtime call returning DOCAERROR, a silent service…

OfficialApache-2.0Auto-check passedDevelopment

Install Doca Debug

skills CLI
$ npx skills add NVIDIA/skills --skill doca-debug -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install NVIDIA/skills doca-debug --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/doca-debug .claude/skills/doca-debug && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
doca-debug
GitHub stars
3.5k
Token cost
~2.5k tokens
SKILL.md length
1,064 words
Files
7
Skills in repo
380
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when the user is debugging any DOCA symptom — a build that won't compile, a link step that can't resolve a doca symbol, a runtime call returning DOCAERROR, a silent service…

  • Works in 4 steps: Read this SKILL.md first to confirm the… → For the layered debug model, the… → For the canonical layered debug ladder… → …
  • The user is debugging any DOCA symptom — a build that wont compile
  • SKILL.md covers Example questions this skill…, When to load this skill, What this skill provides and Loading order, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Doca Debug is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. Use this skill when the user is debugging any DOCA symptom — a build that won't compile, a link step that can't resolve a doca symbol, a runtime call returning DOCAERROR, a silent service or tool, or a stack trace / valgrind / core dump — and needs the layered ladder (install → version → build → link → runtime → program → driver), verbosity controls (--sdk-log-level, DOCALOGLEVEL, the doca-{lib}-trace flavor), container-debug constraints, or how to capture state for a Developer Forum post. Trigger even when the…

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files (for example `BENCHMARK.md`, `CAPABILITIES.md` and `TASKS.md`). Compatibility notes: No DOCA install required to read this skill (it is an overlay loaded against any DOCA artifact skill); the validation steps within DO require a live DOCA…

It sits in Development, covering Debugging and Incident response. The repository describes itself as: Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end. The licence is Apache-2.0.

When your agent uses it

  • The user is debugging any DOCA symptom — a build that wont compile
  • A link step that cant resolve a doca symbol
  • A runtime call returning DOCAERROR
  • A silent service

Example prompts

  • “t compile, a link step that can”
  • “DOCA debug”
  • “undefined reference to doca”
  • “/doca-debug”

Requirements

  • Compatibility (from SKILL.md): No DOCA install required to read this skill (it is an overlay loaded against any DOCA artifact skill); the validation steps within DO require a live DOCA install at /opt/mellanox/doca.

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Read this SKILL.md first to confirm the user's symptom is cross-cutting debug (not env-class only, not program-class only, not…
  2. For the layered debug model, the read-only stance, the version-availability of debug tools, and the observability surface DOCA emits, see…
  3. For the canonical layered debug ladder and the capture-and-report workflow, see TASKS.md. The build, modify, and run anchors in TASKS.md…
  4. If the user's symptom turns out to be env-class (install / build prerequisites), hand off to doca-setup ## debug. If program-class, hand…

What it can do on your machine

Read from SKILL.md and the folder at commit 0e0d506. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    No DOCA install required to read this skill (it is an overlay loaded against any DOCA artifact skill); the validation steps within DO require a live DOCA install at /opt/mellanox/doca.

    From compatibility in the SKILL.md frontmatter.

Context cost

Doca Debug loads about 2.5k tokens when it runs. Until then it costs about 257 tokens; SKILL.md has 1,064 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~257
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from NVIDIA/skills at commit 0e0d506, republished under its Apache-2.0 licence (© NVIDIA). 1,064 words, ~2,543 tokens.

Download SKILL.mdSave it as .claude/skills/doca-debug/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
doca-debug
description
Use this skill when the user is debugging any DOCA symptom — a build that won't compile, a link step that can't resolve a doca_* symbol, a runtime call returning DOCA_ERROR_*, a silent service or tool, or a stack trace / valgrind / core dump — and needs the layered ladder (install → version → build → link → runtime → program → driver), verbosity controls (--sdk-log-level, DOCA_LOG_LEVEL, the doca-{lib}-trace flavor), container-debug constraints, or how to capture state for a Developer Forum post. Trigger even when the user does not say "DOCA debug" — implicit phrasings include "undefined reference to doca_*", "how do I get more logs", "packets aren't reaching the wire", "doca_caps returned nothing", or "hugepages empty in the container". Refuse and route elsewhere for library-specific debug (Flow pipe trace, RDMA QP, Comch stats), env-class pkg-config or hugepages symptoms, the DOCA_ERROR_* taxonomy and lifecycle interpretation, and performance or incident-response work — those belong to other skills.
compatibility
No DOCA install required to read this skill (it is an overlay loaded against any DOCA artifact skill); the validation steps within DO require a live DOCA install at /opt/mellanox/doca.
license
Apache-2.0
metadata.kind
library

DOCA debug

Where to start: This skill is the canonical layered-ladder reference both doca-setup ## debug and doca-programming-guide ## debug escalate to. If the symptom does not fit cleanly in env-class or program-class, start at TASKS.md ## debug — the full layered ladder lives there.

Example questions this skill answers well

The CLASSES of debug questions this skill is built to answer, each with one worked example.

  • "My DOCA build / link / runtime / program failed — which layer is it?" — worked example: "ld says undefined reference to doca_flow_init — which layer?" Answered by the canonical layered ladder in TASKS.md ## debug (layer 4 = Link).
  • "How do I turn up verbosity for any DOCA library or tool?" — worked example: "My DOCA Flow program is silent — where do I get more log output?" Answered by the trace-flavor / log-level surface in CAPABILITIES.md ## Observability
  • "How do I capture state for a forum question or bug report?" — worked example: "I'd like to file a forum question with reproducible context — what should I include?" Answered by the capture-a-reproducible-state workflow in TASKS.md ## test.
  • "What does this DOCA tool's output mean / which tool answers this?" — worked example: "doca_caps returned nothing for RDMA — does that mean unsupported?" Answered by the tool-vs-capability decision tree in CAPABILITIES.md ## Capabilities and modes
  • "I'm debugging inside the NGC container — what's observable?" — worked example: "hugepages is empty inside the container; is that a real problem or a container thing?" Answered by the container-specific debug constraints in CAPABILITIES.md ## Safety policy
  • "Where do I ask for help with this?" — worked example: "Where is the customer-facing DOCA forum and what should the post contain?" Answered by the Developer-Forum routing rule in TASKS.md ## debug plus doca-public-knowledge-map.

If the symptom is purely env-class, route to doca-setup ## debug; if purely program-class, route to doca-programming-guide ## debug. This skill is the cross-cutting layer both call into.

When to load this skill

Load this skill when the user is debugging anything DOCA-related — a build that won't compile, a link step that can't resolve a doca_* symbol, a runtime call that returns DOCA_ERROR_*, a packet that does not appear on the wire, a service that won't start, or a tool that returns no useful output. Concretely:

  • The user reports a symptom and needs to find the layer that caused it (install / version / build / link / runtime / program).
  • The user asks "how do I get more logs?" or "how do I turn up the verbosity?" for any DOCA library or tool.
  • The user wants to capture state for a forum question or an internal bug report (the bundle does not own the internal-bug-report channel; it routes to the public DOCA Developer Forum).
  • The user is reading a stack trace, a valgrind output, or a core dump from a DOCA program and wants to know where to look first.
  • The user is debugging inside the NGC DOCA container and needs to know what is and is not observable from inside it.

Do not load this skill for:

  • "What is DOCA_ERROR_BAD_STATE?", "what error codes does DOCA return?" — that is the cross-library error taxonomy, owned by doca-programming-guide CAPABILITIES.md ## Error taxonomy. This skill consumes that taxonomy; it does not redefine it.
  • "My pkg-config cannot find doca-flow", "hugepages are not mounted", "my representor isn't visible" — those are env-class symptoms, owned by doca-setup ## debug. This skill is the canonical pointer that env-class debug ladder redirects to once the symptom escalates beyond install / version / build prerequisites.
  • Library-specific debugging (Flow pipe trace, RDMA queue-pair state, Comch channel statistics) — those live in the matching library skill (e.g. doca-flow ## debug). This skill provides the cross-cutting debug ladder; library skills layer their library-specific debug surface on top of it.
Show full SKILL.md (457 more words)Show less

What this skill provides

This is a thin loader. The body keeps only the orientation needed to pick the right next file. The substantive debug material lives in two companion files:

  • CAPABILITIES.md — what kinds of debug surface DOCA exposes: the layered debug model (install / version / build / link / runtime / program), the read-only-first stance, version-availability of debug tools (e.g. doca_caps since DOCA 2.6.0), the cross-library error taxonomy (cross-link only — owned by doca-programming-guide), the observability primitives DOCA emits (stderr logs, --sdk-log-level, the doca-<lib>-trace build flavor, library counters), and the safety constraints on debug actions (read-only first, don't mutate install tree mid-investigation).
  • TASKS.md — the actual debug workflows: ## configure (set up env for high-verbosity debug), ## test (capture a reproducible state), ## debug (the canonical layered ladder, the universal entry point that every library ## debug redirects to), and the Where to ask for help routing (NVIDIA DOCA Developer Forum). Three other anchors (build, modify, run) exist for lint compliance and route to doca-programming-guide, which owns those verbs after the env / program split.

Loading order

  1. Read this SKILL.md first to confirm the user's symptom is cross-cutting debug (not env-class only, not program-class only, not library-internal only).
  2. For the layered debug model, the read-only stance, the version-availability of debug tools, and the observability surface DOCA emits, see CAPABILITIES.md.
  3. For the canonical layered debug ladder and the capture-and-report workflow, see TASKS.md. The build, modify, and run anchors in TASKS.md are stubs that route to doca-programming-guide; their substance lives there.
  4. If the user's symptom turns out to be env-class (install / build prerequisites), hand off to doca-setup ## debug. If program-class, hand off to doca-programming-guide ## debug. If library-internal, hand off to the matching library skill's ## debug (e.g. doca-flow ## debug).

The two companion files cross-link to each other and to doca-public-knowledge-map whenever the right answer is "look it up in the public docs or the installed package layout" rather than "debug-specific guidance".

  • doca-public-knowledge-map — public DOCA documentation routing and the on-disk layout of an installed DOCA package. This skill defers all "where is X documented", "where on disk is Y", and "how do I check the installed version" questions to the knowledge-map.
  • doca-setup — env-class debug (install / build prerequisites): pkg-config failures, missing hugepages, representors not visible, header-vs-runtime version mismatches. doca-setup ## debug is the env-class layered ladder; this skill is the cross-cutting debug ladder both env and program ladders escalate to.
  • doca-programming-guide — program-class debug (lifecycle order, DOCA_ERROR_* interpretation, doca_error_get_descr() use, the validate-before-commit rule). doca-programming-guide ## debug is the program-class layered ladder; this skill picks up where it leaves off when the symptom involves cross-library tooling (gdb, valgrind, container introspection, core dumps).
  • Library skills (e.g. doca-flow, doca-dms, doca-caps) — library-specific debug overlays. Each library's ## debug builds on the cross-cutting ladder defined here, then adds its own counters, traces, and inspector tools.

© NVIDIA, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files in skills/doca-debug of NVIDIA/skills.

  • SKILL.md
  • BENCHMARK.md
  • CAPABILITIES.md
  • TASKS.md
  • evals/evals.json
  • skill-card.md
  • skill.oms.sig

Open the folder on GitHubat commit 0e0d506

Compare with similar skills

Doca Debug next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Doca Debug compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Doca Debug this skillNVIDIA/skills3.5k—~2.5kAutomated safety check: PassApache-2.0
Root-Cause TroubleshootingdavidYichengWei/agentic-engineering-framework158—~646Automated safety check: PassMIT
Incident Triage Harnessmadebyaris/advance-minimax-m3-cursor-rules126—~984Automated safety check: PassMIT
Axiom SRE Investigatoropenclaw/clawhub9.5k—~7.1kAutomated safety check: PassMIT
Broken API InterviewerPrepLabsAI/InterviewMentor112—~2.6kAutomated safety check: PassMIT
Release Engineeringmagnus919/agent-skills111—~3.9kAutomated safety check: PassMIT

Similar skills

  • Root-Cause Troubleshooting

    davidYichengWei/agentic-engineering-framework

    Diagnoses compile errors, runtime exceptions, failing tests, pipeline failures and production alerts from code and logs, giving a root cause before any fix.

    158 GitHub stars~646 tokensUpdated 6 mo ago
    DevelopmentAuto-check passed
  • Incident Triage Harness

    madebyaris/advance-minimax-m3-cursor-rules

    Walks an agent through an evidence-first incident investigation across logs, metrics, code and screenshots, from first symptom to the smallest safe mitigation.

    126 GitHub stars~984 tokensUpdated 3 mo ago
    DevOps & CloudAuto-check passed
  • Axiom SRE Investigator

    openclaw/clawhub

    Investigates incidents and production problems with hypothesis-driven debugging, queries Axiom observability data when available, and keeps secrets out of commands and output.

    9.5k GitHub stars~7.1k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Broken API Interviewer

    PrepLabsAI/InterviewMentor

    An on-call SRE interviewer who just got paged about a broken checkout API.

    112 GitHub stars~2.6k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Release Engineering

    magnus919/agent-skills

    Design, automate, and operate end-to-end software releases: release process models and pipelines (trunk-based development, CD stages, release trains), progressive delivery and feature flags…

    111 GitHub stars~3.9k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Debug Production Issue

    FerroxLabs/wayland

    Orchestrates systematic production debugging from alert through root cause identification and resolution, chaining four engineering skills into a structured diagnostic pipeline.

    608 GitHub stars~3.8k tokensUpdated yesterday
    DevOps & CloudAuto-check passed

More from NVIDIA/skills

All 380 skills in this repo
  • Official

    A skill your agent uses when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice.

    3.5k GitHub starsUsed in 1 repo~4.5k tokens
    Auto-check passed
  • Official

    Generates, validates, compares and explains HOLOLINK_def.svh macro files for the HSB IP, using bundled Python scripts and asking before it writes anything.

    3.5k GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Official

    Runs and validates an end-to-end Mission Control demo in a locally installed Isaac Sim, with a Nova Carter robot driven through a Python server.

    3.5k GitHub stars~4.8k tokensUpdated today
    Auto-check passed
  • Orchestrates defect image generation for PCBA, metal surface and glass inspection with NVIDIA Cosmos AnomalyGen on OSMO, from cold-start Day 0 to real-photo Day 1 labeling.

    3.5k GitHub stars~5k tokensUpdated today
    Auto-check: notes
  • Orchestrates video data augmentation and auto-labeling workflows on OSMO, from flow selection and preflight checks to submission, monitoring and output download.

    3.5k GitHub stars~4.7k tokensUpdated today
    Auto-check: notes
  • Official

    Runs NVIDIA TAO Data Services KPI analysis on object detection results, comparing predictions to ground truth and writing per-class precision, recall and AP to a CSV.

    3.5k GitHub stars~2.7k tokensUpdated today
    Auto-check: notes

Questions about Doca Debug

What does Doca Debug do?

A skill your agent uses when the user is debugging any DOCA symptom — a build that won't compile, a link step that can't resolve a doca symbol, a runtime call returning DOCAERROR, a silent service…. Doca Debug is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. Use this skill when the user is debugging any DOCA symptom — a build that won't compile, a link step that can't resolve a doca symbol, a runtime call returning DOCAERROR, a silent service or tool, or a stack trace / valgrind / core dump — and needs the layered ladder (install → version → build → link → runtime → program → driver), verbosity controls (--sdk-log-level, DOCALOGLEVEL, the doca-{lib}-trace flavor), container-debug constraints, or how to capture state for a Developer Forum post.

When should I use Doca Debug?

Doca Debug fits situations like: the user is debugging any DOCA symptom — a build that wont compile; A link step that cant resolve a doca symbol; A runtime call returning DOCAERROR; A silent service.

How do I install Doca Debug in Claude Code?

Run `npx skills add NVIDIA/skills --skill doca-debug -a claude-code`. Or copy the skill folder (skills/doca-debug in NVIDIA/skills) into .claude/skills/doca-debug in your project. Claude Code loads it when a task matches its description.

How do I install Doca Debug in Codex?

Run `npx skills add NVIDIA/skills --skill doca-debug -a codex`. Or copy the skill folder (skills/doca-debug in NVIDIA/skills) into .agents/skills/doca-debug in your project. Codex loads it when a task matches its description.

Can I use Doca Debug in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NVIDIA/skills --skill doca-debug -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/doca-debug, .gemini/skills/doca-debug, .github/skills/doca-debug and .opencode/skills/doca-debug in your project.

What does Doca Debug need to run?

SKILL.md names no scripts, command-line tools or credentials: Doca Debug is instructions for the agent only. Compatibility (from SKILL.md): No DOCA install required to read this skill (it is an overlay loaded against any DOCA artifact skill); the validation steps within DO require a live DOCA install at /opt/mellanox/doca. .

Does Doca Debug access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Doca Debug safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Doca Debug use?

Doca Debug is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Doca Debug use?

About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Doca Debug?

Skills that share tags, products or a category with Doca Debug: Root-Cause Troubleshooting (davidYichengWei/agentic-engineering-framework, 158 stars), Incident Triage Harness (madebyaris/advance-minimax-m3-cursor-rules, 126 stars), Axiom SRE Investigator (openclaw/clawhub, 9.5k stars) and Broken API Interviewer (PrepLabsAI/InterviewMentor, 112 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Doca Debug?

NVIDIA (a GitHub organization, an official publisher) maintains it in NVIDIA/skills, which has 3,534 GitHub stars. The repository holds 380 skills in this directory. The repository was last updated on October 7, 2026.

Source: NVIDIA/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.