compute-sanitizer-diagnose-cuda-bugs SKILL.md skillA

compute-sanitizer-diagnose-cuda-bugs from nvidia/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add nvidia/skills/compute-sanitizer-diagnose-cuda-bugs@git:20261019.8a74306

Pins git:20261019.8a74306 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
nvidia/skills
Path
skills/compute-sanitizer-diagnose-cuda-bugs/SKILL.md
Versions recorded
1
Latest version
git:20261019.8a74306, committed Oct 19, 2026
Size
14,183 bytes
Repository stars
3,871
License
Apache-2.0

Detect and diagnose CUDA correctness bugs with NVIDIA Compute Sanitizer. Routes GPU memory errors, shared-memory data races, uninitialized-memory reads, and synchronization/barrier bugs to the right sub-tool (memcheck, racecheck, initcheck, synccheck) and explains how to build, run, and read the report. Use when debugging illegal memory access, out-of-bounds, misaligned access, leaks, WAW/WAR/RAW races, __shared__ hazards, uninitialized reads, garbage results, hangs, divergent…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Compute Sanitizer

## Purpose

NVIDIA Compute Sanitizer is a suite of four correctness tools for CUDA
(memcheck, racecheck, initcheck, synccheck). This skill is a **router**: pick
the right tool from the symptom below, then read the matching reference file for
its flags, output format, and caveats **before you run it**. Do not guess
flags — the details live in the reference.

**When to use:** finding and diagnosing GPU-side correctness bugs — illegal or
out-of-bounds memory access, misaligned access, leaks, shared-memory races,
uninitialized reads, and synchronization/barrier errors.

**When NOT to use:** host/CPU-side bugs (use valgrind or AddressSanitizer),
pure functional/logic bugs unrelated to memory or races, or **global-memory**
data races (out of scope — use iGUARD or SuperCollider).

## Prerequisites

- A CUDA Toolkit installation that provides both `nvcc` and
  `compute-sanitizer` on `PATH`.
- A CUDA-capable GPU visible to the process.
- Build with `nvcc -lineinfo` for source attribution (add `-Xcompiler
  -rdynamic` for host backtraces).

## Inputs

| Input | Required? | Where it comes from |
|---|---|---|
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add nvidia/skills/compute-sanitizer-diagnose-cuda-bugs@sha256:0253adc748efd115

The line at the top of this page pins the label git:20261019.8a74306, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_hicn5nnconpefyok.svg)](https://markdownregistry.com/a/art_hicn5nnconpefyok)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 19, 2026.

versioncommittedcommitsizeaudit
git:20261019.8a74306 latest2026-10-19 8a74306 14,183 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (14183 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

nvidia/skills · 3,871 stars · license Apache-2.0 · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_hicn5nnconpefyok
GET https://markdownregistry.com/api/v1/resolve?ref=nvidia/skills/compute-sanitizer-diagnose-cuda-bugs
GET https://markdownregistry.com/api/v1/blob/0253adc748efd1154a2337f87f44a4b236426dfed5b777ac5cea3f1a4bcba491

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from nvidia/skills

nvidia-skill-finder SKILL.md skill
nvidia/skills · plugins/nvidia-skills/skills/nvidia-skill-finder/SKILL.md · Use for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill. Trigger on…
git:20261001.4aa3fd2 · audit A · 3,871 stars
accelerated-computing-cudf SKILL.md skill
nvidia/skills · skills/accelerated-computing-cudf/SKILL.md · Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby…
git:20261015.7efb297 · audit A · 3,871 stars
aiq-deploy SKILL.md skill
nvidia/skills · skills/aiq-deploy/SKILL.md · Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.
v2.1.0 · audit A · 3,871 stars
aiq-research SKILL.md skill
nvidia/skills · skills/aiq-research/SKILL.md · Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.
v2.1.0 · audit A · 3,871 stars
ambient-healthcare-agent-with-nemotron-voice-agent SKILL.md skill
nvidia/skills · skills/ambient-healthcare-agent-with-nemotron-voice-agent/SKILL.md · Customize NVIDIA Nemotron Voice Agent's Generic Pipecat example for healthcare appointment, five-field patient intake…
v1.0.0 · audit B · 3,871 stars
amc-run-rtsp-calibration SKILL.md skill
nvidia/skills · skills/amc-run-rtsp-calibration/SKILL.md · Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP…
v1.0.0 · audit B · 3,871 stars
amc-run-sample-calibration SKILL.md skill
nvidia/skills · skills/amc-run-sample-calibration/SKILL.md · Run end-to-end calibration on the shipped sample dataset (sdg_08_2_sample_data_010926.zip) against a running AMC…
v1.0.0 · audit A · 3,871 stars
amc-run-video-calibration SKILL.md skill
nvidia/skills · skills/amc-run-video-calibration/SKILL.md · Calibrates pre-recorded `cam_*.mp4` datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s…
v1.0.0 · audit A · 3,871 stars
amc-setup-calibration-stack SKILL.md skill
nvidia/skills · skills/amc-setup-calibration-stack/SKILL.md · Launch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy…
v1.0.0 · audit A · 3,871 stars
boltz2-nim SKILL.md skill
nvidia/skills · skills/bionemo-boltz2-nim/SKILL.md · Use Boltz2 NIM for biomolecular structure prediction and binding affinity. Invoke for Boltz2, protein structures…
git:20261002.85ad857 · audit A · 3,871 stars
codonfm-embed SKILL.md skill
nvidia/skills · skills/bionemo-codonfm-embed/SKILL.md · Validate coding-sequence CSVs, extract public CodonFM/Encodon embeddings, and choose checkpoints for downstream…
git:20261009.329cfc6 · audit A · 3,871 stars
codonfm-finetune SKILL.md skill
nvidia/skills · skills/bionemo-codonfm-finetune/SKILL.md · Fine-tune public CodonFM Encodon checkpoints on labeled coding-sequence or coding-variant data using LoRA, head-only…
git:20261009.329cfc6 · audit A · 3,871 stars

Every file in nvidia/skills

Browse by kind, by grade A, or by owner.