Model Selection
/model-selectionNEWWhat it does
Paper-grounded architecture choice for medical imaging, then a check of the actual repo or checkpoint: licence, version pin, weight provenance and benchmark overlap.
Highlights
- ✓Task → architecture decision tree, each archetype tied to its source paper
- ✓Licence, intended use, and pretrained-weight provenance on the record
- ✓Catches an evaluation arm sitting on the model's own development benchmark
- ✓Vets an artifact; never downloads, runs, or benchmarks one
Install this skill
git clone https://github.com/Aperivue/medsci-skills.git
mkdir -p ~/.claude/skills
cp -r medsci-skills/skills/model-selection ~/.claude/skills/Related skills
Generate a reproducible, runnable PyTorch training repo for a medical-imaging task — segmentation, classification, detection, synthesis, self-supervised pretraining, or fine-tuning a pretrained backbone — with a patient-level seed-locked split, train/evaluate scripts, and a Methods stub. Integrates MONAI / nnU-Net, never reimplements them.
Model Assessment/model-assessmentValidation design, task-correct held-out metrics (Dice + HD95, AUROC + AUPRC, FROC, calibration), uncertainty/OOD and explainability for trained imaging models, each with a gate.
Model Card & Datasheet/model-cardGenerate the documentation an engineer-built model must carry — a Model Card (Mitchell et al. 2019), a Datasheet for its dataset (Gebru et al. 2021), and a METRIC data-quality pass — filled only from user-supplied facts, then verify every required section is present with a completeness gate.
LLM/MLLM Evaluation/mllm-evalModel-agnostic evaluation harness for an LLM or MLLM on a clinical task — report generation, visual question answering, clinical text extraction — covering the adjudicated reference, clinical-efficacy metrics (RadGraph-F1 / CheXbert-F1), faithfulness, contamination, prompt sensitivity, and a reader study.