NVIDIA/skills is a catalogue of portable instruction sets that teach coding agents how to use NVIDIA software for robotics, simulation, CUDA, retrieval-augmented generation, and related workflows. Developers install these skills in agents such as Claude Code or Codex, while the catalogue mirrors skills maintained in separate NVIDIA product repositories.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/NVIDIA/skillsnpx agentmods add skills/nvidia/skills/cdf-defect-image-generationWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nvidia/skills/cdf-defect-image-generation)<a href="https://agentmods.dev/skills/nvidia/skills/cdf-defect-image-generation"><img src="https://agentmods.dev/badge/skills/nvidia/skills/cdf-defect-image-generation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nvidia/skills/cdf-defect-image-generation"><img src="https://agentmods.dev/badge/skills/nvidia/skills/cdf-defect-image-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00143 | $0.04405 |
| Opus 5.5 | $0.00057 | $0.01762 |
| Sonnet 5.5 | $0.00029 | $0.00881 |
| Haiku 4.5 | $0.00014 | $0.00441 |
Grade A, and why
cdf-defect-image-generation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CDF Orchestration — SMT Defect Image Generation
Run defect_image_generation_smt_dag_k8s: CDF Simulation renders PCB components,
CDF Augmentation turns the renders into realistic clean (golden) images, and
CDF AnomalyGen adds texture defects. Simulation can also render pose defects
(shift, tombstone, sideflip). One DAG serves every mode; pipeline_mode selects
which stages run.
Requirements
Execution needs an authorized Kubernetes connection, a reachable Airflow 3 controller with the DIG DAG loaded, and storage and model access for the chosen mode. The payload checker needs a trusted CDF Orchestration checkout and its Airflow Python environment. Explaining the workflow or drafting JSON needs neither.
Execution readiness also requires the companion script
skills/cdf-orchestration-preflight/scripts/storage_check.py in the product
checkout. If it is unavailable, report the missing dependency as a readiness
blocker; do not skip the storage mapping check.
In that checkout, the payload contract is defined by
airflow/dags/workflows/defect_image_generation_dag/callables/smt/models.py and
airflow/dags/workflows/defect_image_generation_dag/callables/smt/config_generation.py.
The component templates that payload overrides merge into are in
airflow/dags/workflows/defect_image_generation_dag/configs/smt/.
Available scripts
| Script | Purpose |
|---|---|
scripts/payload.py |
Check a payload with the DAG's own model and compiler, then print job counts, output paths and effective AnomalyGen staging. Submits nothing and accesses no storage or cluster. |
Instructions
1. Resolve the requested operation and mode
| User intent | pipeline_mode |
Required stages |
|---|---|---|
| Render PCB components only | simulation |
Simulation |
| Good (golden) component images from a board scene | sim2real |
Simulation → image-edit |
| Pose defects (shift, tombstone, sideflip) from a board scene | sim2real, with a pose operation in the simulation override |
Simulation → image-edit |
| Texture defects (bridge, excess solder, missing) from a board scene | full |
Simulation → image-edit → AnomalyGen |
| Texture defects on real or prepared clean images | defect |
AnomalyGen |
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 369 B
- BENCHMARK.md 11 KB
- evals/EVAL.md 4.6 KB
- evals/evals.json 20 KB
- evals/test_payload.py 10 KB runs code
- references/airflow-direct-api.md 6.3 KB
- references/outputs.md 3.3 KB
- references/payload-contract.md 17 KB
- references/setup-and-preflight.md 5.3 KB
- references/troubleshooting.md 4.4 KB
- scripts/payload.py 10 KB runs code
- skill-card.md 6.4 KB
- skill.oms.sig 6.6 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 318 lines · 143 tokens per session scan A 8e64338933fc
cdf-defect-image-generation is a skill published in the GitHub repository NVIDIA/skills (3,733 stars, last pushed today), licensed Apache-2.0. It adds 143 tokens to every session and 4,405 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-22.
Other skills, from other repositories
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-memory-thermal-ops
Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
deep-learning-pytorch
Use when writing or changing PyTorch code — model, Dataset/DataLoader, training and evaluation loops, determinism, mixed precision, torch.compile, checkpoints with safetensors, Hugging Face models, ONNX export, and tests that run on CPU.
experiment-tracking-and-reproducibility
Use when a change trains a model, reports a metric, or touches seeds, data or model versions, the lockfile, MLflow or DVC — what every run must log, seeding, environment pinning, data versioning and keeping tests off the shared tracking server.
ml-testing-strategy
Use when writing tests for data or ML code — what to test at each layer (transforms, schemas, properties, pipeline smoke, model-quality thresholds, determinism and parity), how to build small synthetic fixtures, and what not to test.