Agent skill · software engineering · nvidia
nv-reason-cxr
Used for command-shape or live NV-Reason-CXR chest X-ray reasoning smoke tests. Not for diagnosis or clinical reporting.
Why this skill is useful
Adds specific command-line scripts and detailed usage patterns for running NV-Reason-CXR smoke tests that the AI wouldn't reliably generate on its own.
What it needs
Requires cuda, python installed locally. Requires huggingface account access. About 8k tokens when loaded. Last updated 2026-08-07. 2,816 stars on the source repository.
What this skill does
NV-Reason-CXR Purpose Used for command-shape or live NV-Reason-CXR chest X-ray reasoning smoke tests. Not for diagnosis or clinical reporting. Use the wrapper exactly as documented; do not replace the upstream entrypoint with a handwritten implementation. Manifest I/O: inputs are chestxrayimageorfixture; outputs are resultjson. Instructions Read skillmanifest.yaml before changing arguments, side effects, or validation gates. Run scripts/runnvreasoncxr.py through the documented command below; pass --out-dir only for generated fixtures or harness-managed artifact directories. If a host agent exposes runscript, use runscript("scripts/runnvreasoncxr.py", args=[...]); otherwise run the Bash/Python command shown below. Check the emitted JSON and paired verifier guidance before treating the run as evidence. When reporting a completed run, return the full wrapper JSON or at minimum the complete output.responsetext exactly as emitted, including any model-generated <think>...</think> and <answer>...</answer> sections. Do not collapse the result to labels unless the user explicitly asks for a summary. Available Scripts Script Purpose Arguments --- --- --- scripts/runnvreasoncxr.py Primary entrypoint declared by skillmanifest.yaml. PATHTOCXRORFIXTURE [--out-dir OUTDIR] [--backend local\ hf-space-api] [--mock] [--check-setup] Prerequisites Local backend requirements: GPU/CUDA when declared by the manifest; Python packages listed in runtime.sideeffects.pippackages. API backend requirements: public network access to the Hugging Face Space; no local PyTorch, Transformers, CUDA, model cache, or Hugging Face token. Side effects: emits result JSON on stdout; may write generated fixture artifacts under the caller's --out-dir; may cache model assets under ~/.cache/huggingface/ for local inference; and may contact https://huggingface.co, https://github.com, or https://.hf.space outside --mock mode. Run commands from the repository root unless an existing section below says otherwise. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills nvidia/nv-reason-cxr