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 i4h-workflow-dataset-mimicgit 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/i4h-workflow-dataset-mimic)<a href="https://agentmods.dev/skills/nvidia/skills/i4h-workflow-dataset-mimic"><img src="https://agentmods.dev/badge/skills/nvidia/skills/i4h-workflow-dataset-mimic/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/i4h-workflow-dataset-mimic"><img src="https://agentmods.dev/badge/skills/nvidia/skills/i4h-workflow-dataset-mimic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.01047 |
| Opus 5.5 | $0.00019 | $0.00419 |
| Sonnet 5.5 | $0.00010 | $0.00209 |
| Haiku 4.5 | $0.00005 | $0.00105 |
Grade A, and why
i4h-workflow-dataset-mimic scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 26d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mimic Workflow Demonstrations
Purpose
Clone successful source episodes and perturb recorded actions.
Instructions
- Run the checkout resolver and select the source HDF5.
- Inspect successful episodes and segments.
- Run mimic to generate the requested additional action-jitter variants.
- Compare exact counts and preserved contracts.
Resolve and inspect
export I4H_WORKFLOWS_REPO_URL="${I4H_WORKFLOWS_REPO_URL:-https://github.com/isaac-for-healthcare/i4h-workflows}"
I4H_REPO_DIR_NAME="${I4H_WORKFLOWS_REPO_URL%/}"
I4H_REPO_DIR_NAME="${I4H_REPO_DIR_NAME##*/}"
I4H_REPO_DIR_NAME="${I4H_REPO_DIR_NAME##*:}"
I4H_REPO_DIR_NAME="${I4H_REPO_DIR_NAME%.git}"
[ -n "$I4H_REPO_DIR_NAME" ] || { echo "Cannot derive a checkout name from I4H_WORKFLOWS_REPO_URL" >&2; exit 2; }
ROOT="${I4H_WORKFLOWS:-$(git rev-parse --show-toplevel 2>/dev/null)}"
if [ ! -d "$ROOT/workflows/i4h_workflows" ]; then
ROOT="${I4H_WORKFLOWS:-$HOME/$I4H_REPO_DIR_NAME}"
[ -d "$ROOT/workflows/i4h_workflows" ] || git clone "$I4H_WORKFLOWS_REPO_URL" "$ROOT"
fi
export I4H_WORKFLOWS="$ROOT"
cd "$ROOT"
HDF5_PATH=/absolute/path/to/source.hdf5
uv run --project tools/dataset i4h-dataset inspect "$HDF5_PATH" --segments
Treat the resolver above as part of the skill contract: a hosted copy may run outside the base repository, so never assume the current checkout contains workflows/i4h_workflows. I4H_WORKFLOWS_REPO_URL selects the clone source. When I4H_WORKFLOWS is unset, derive the fallback directory from that URL; set I4H_WORKFLOWS only to reuse or choose a specific destination. Never replace an existing checkout.
Use the explicit/current-chain recording. Require at least one successful source episode. If the user asks for node-scoped jitter, require that node in segment metadata.
Expand
RUN_DIR="$(pwd)/runs/<workflow>/$(date +%Y%m%d_%H%M%S)"
mkdir -p "$RUN_DIR"
uv run --project tools/mimic i4h-mimic \
"$HDF5_PATH" "$RUN_DIR/expanded.hdf5" \
--episodes <additional-count> \
--noise 0.01 \
--seed <seed> \
--include-source \
--successful-only
What ships with it
4 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.
- 26d ago Changed · +1 lines ac1bceb56b55
- 1mo ago Changed · -40 lines · -10 tokens per session 319f4bb780bc
- 1mo ago First seen · 138 lines · 58 tokens per session scan A 0f26038e3e3d
i4h-workflow-dataset-mimic is a skill published in the GitHub repository NVIDIA/skills (3,748 stars, last pushed today), licensed Apache-2.0. It adds 48 tokens to every session and 1,047 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
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.
nlp
Use when choosing how to tokenize text or which transformer type fits an NLP task, when a tokenizer over-fragments non-English text or inflates token cost, when picking a language metric, or when classification, NER or summarization output looks wrong and it is unclear whether the tokenizer, the architecture or the…
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.
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.
model-serving-and-monitoring
Use when a model is served online (FastAPI, BentoML) or scored in batch, when changing how a model artifact is loaded or versioned, or when adding drift, quality or prediction monitoring and a rollout plan for a new model.
data-pipeline-orchestration
Use when adding or changing a scheduled data or ML pipeline — Dagster assets, Prefect flows, Airflow DAGs or a cron'd entrypoint — idempotent partitioned stages, retries, backfills, quality gates, and testing the pipeline without the scheduler.