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
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add NVIDIA/skills --skill cdf-simulationgit clone --depth 1 https://github.com/NVIDIA/skillsWrote 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-simulation)<a href="https://agentmods.dev/skills/nvidia/skills/cdf-simulation"><img src="https://agentmods.dev/badge/skills/nvidia/skills/cdf-simulation/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-simulation"><img src="https://agentmods.dev/badge/skills/nvidia/skills/cdf-simulation.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 | $0.00117 | $0.09075 |
| Opus 5.5 | $0.00047 | $0.03630 |
| Sonnet 5.5 | $0.00023 | $0.01815 |
| Haiku 4.5 | $0.00012 | $0.00907 |
Grade A, and why
cdf-simulation 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 3d 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 — 584 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cdf-simulation
Turns DIG Flow Catalog prompt templates and equivalent direct requests into
cdf jobs through the declarative Python API. This skill is the
component-owned guidance for cdf-simulation: a caller supplies a board
USD and output root, this skill builds and compiles the job, and the caller
can pass the payload to its own executor. Airflow may inject those required
inputs, or the caller may provide them directly. If either is missing and
interaction is possible, ask once. All optional ambiguity is resolved with
fixed, documented defaults. If a request truly cannot be served (an
unsupported defect type, a non-USD input), say so rather than guessing at a
fake capability or silently doing nothing.
This skill does not execute. It produces a validated CDFJob build and
its compiled JobOrder payload, then stops. An Airflow DAG or another executor
chosen by the caller performs rendering.
Catalog coverage
This skill implements five DIG Flow Catalog rows, all taking a board USD as input:
| # | Row | Status |
|---|---|---|
| 1 | Golden board (THT) | Implemented |
| 2 | Variation type (THT pin geometry) | Implemented |
| 3 | Good images (SMT) | Implemented |
| 4 | Structural defects (SMT) | Implemented |
| 5 | Texture defects (SMT solder) | Implemented, except bridge (unsupported — see below) |
Reference flows
Beside the catalog rows, the skill serves the five reference flows in
references/reference-flows.md: complete
inspection jobs, each phrased as one prompt whose compiled plan must equal
the equivalent YAML config. A prompt carrying a flow marker -- a scan grid
and "stitched", a defect on a named refdes ("shift on C33",
"insufficient solder on J17", "missing-component defect on LS1"),
"component-focus" or "pin-focus" crops -- is a flow, not a catalog row, and
takes its fixed values from that file (they differ from the catalog
defaults: shift is translate_range=0.5, rotate_z_range=5.0 with no
variant_index, crops are ROI captures rather than postprocess.crop).
What ships with it
8 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.
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.
- 3d ago First seen · 584 lines · 117 tokens per session scan A 59f38fee52cc
cdf-simulation is a skill published in the GitHub repository NVIDIA/skills (3,722 stars, last pushed yesterday), licensed Apache-2.0. It adds 117 tokens to every session and 9,075 once invoked, about $0.0005 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
desktop-and-local-ipc-security
Use when the diff adds or changes a loopback HTTP or WebSocket server, a bind address, a Unix socket, named pipe, XPC or D-Bus service, an Electron or Tauri main-process handler, a custom URL scheme or file association, a privileged helper or updater, or code that spawns tools inside directories a user or download…
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.
qmclaw-workbench
A local simulator for superconducting quantum-bit experiments, including measurements used to study and tune a qubit. It produces bounded synthetic results without connecting to laboratory hardware or quantum cloud services.
accelerator-physicist
Think and work like an expert Accelerator Physicist. Use when a task calls for Accelerator Physicist judgment. Reasons from beam optics, RF cavities, emittance budgets, and loss maps while treating halo and impedance-driven instabilities as first-class failure modes.
acoustical-engineer
Think and work like an expert Acoustical Engineer. Use when a task calls for Acoustical Engineer judgment. Reasons from source-path-receiver control, logarithmic decibel levels, and mass-law transmission loss through IEC 61672 Class 1 metering, ISO 9613-2 propagation, SEA/FEM/BEM simulation, and ISO 9612 occupational…
acoustics-physicist
Think and work like an expert Acoustics Physicist. Use when a task calls for Acoustics Physicist judgment. Reasons from impedance Z=p/u, Helmholtz number kL regime, and the sonar equation SL-TL-NL+DI+PG through impedance tubes (ISO 10534), anechoic and reverberation rooms, laser vibrometry, and k-Wave/COMSOL…