en un clic
medical-AI-skills
medical-AI-skills contient 11 skills collectées depuis NVIDIA-Medtech, avec une couverture métier par dépôt et des pages de détail sur le site.
Skills dans ce dépôt
Grades a skill or verifier directory for required files, valid manifest structure, side-effect declarations, validation gates, paired-verifier resolution, fixtures, and authoring hygiene. Engineering verification only.
Deterministic verifier for nv_segment_ct_finetune evidence packs. Audits the finetuned checkpoint, training trajectory, and dataset audit signals already recorded by the wrapper. Engineering verification only.
Audits nv_segment_ct evidence packs for label-map readability, anatomy plausibility (organ volume bounds, fragmentation, bilateral symmetry, liver-larger-than-spleen), and optional per-class Dice/IoU against a referenced ground-truth label map. Engineering verification only.
Deterministic paired verifier for nv_generate_ct_rflow evidence packs. Audits per-sample image/mask geometry, CT-HU plausibility, mask label-set sanity, declared output-label coverage, and lung-lobe HU plausibility. CPU-only; does not re-run synthesis.
Used to verify dicom-metadata-extract evidence packs for source gate success, header fact completeness, PHI-flag consistency, and scope disclosure. Not for de-identification.
Audits dicom_series_preflight evidence packs for pass/warn/fail preflight verdicts with explicit corruption, orientation, PHI, and consistency findings.
Used to verify dicom-series-to-volume evidence packs by comparing JSON geometry evidence with the emitted NIfTI artifact. Not for clinical validation.
Used to verify nv-generate-mr and nv-generate-mr-brain evidence packs by re-reading generated MR NIfTI images and checking geometry, finite nonconstant nonnegative intensities, runtime identity, and scope disclosure.
Used to verify nv-reason-cxr evidence packs for source-pack success, fixture/image hash binding, NV-Reason-CXR runtime identity, response shape, scope disclosure, and conservative forbidden overreach phrases.
Anti-pattern fixture that intentionally violates skill-completeness requirements so the verifier has known-bad input.
Minimal positive fixture for skill-completeness-v1 with required files and fields present.