Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Architecture Zoo — Medical Imaging Model Selection

An advisory skill that turns a medical-imaging research question into a paper-grounded shortlist of model architectures.

Data & AnalyticsAdvanced★ 277⑂ 65AI score 8/10Last updated: Aug 29, 2026

What it does

  • Frames your problem by task (classification / segmentation / detection / transfer), modality and dimensionality (2-D vs 3-D volumes), labelled-data scale, and constraints such as class imbalance, small structures, interpretability and deployment compute.
  • Walks a decision tree (references/index.md) into a family card: ResNet/DenseNet/EfficientNet/ViT/Swin, U-Net/3-D U-Net/nnU-Net/Swin-UNETR/Mask R-CNN, Faster R-CNN/RetinaNet/YOLO/DETR, SAM/MedSAM/TotalSegmentator/BiomedCLIP/DINO/MAE, and GCN/GraphSAGE/GAT/BrainGNN for connectomes.
  • Each card supplies the source paper, core idea, when-to-use, a medical-imaging use, a reference implementation, and the typical validation setup.
  • Produces decisions/architecture_choice.md with the pick, citation, reasoning, runner-up, and the matching /model-scaffold template.
  • Strong anti-hallucination rules: never recommend without naming the paper, never invent benchmark numbers, and it explicitly is an archetype map rather than a live SOTA leaderboard.

Who it's for

  • Medical-imaging AI researchers who need a citable justification for their Methods section.
  • Grad students and ML engineers choosing a backbone by data constraints rather than hype.
  • Clinical research teams documenting model choices for reviewers.

Examples

  • "200 labelled CT volumes, small lesions — nnU-Net vs Swin-UNETR?"
  • "Can I train a ViT from scratch on 400 chest X-rays, or should I transfer from a pretrained CNN?"
  • "Which GNN (GCN, GAT, BrainGNN) fits fMRI connectome classification, with the source papers?"

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/Aperivue/medsci-skills/HEAD/skills/architecture-zoo/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/architecture-zoo folder from the GitHub repo Aperivue/medsci-skills into my ~/.claude/skills/architecture-zoo/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/Aperivue/medsci-skills.git && mkdir -p ~/.claude/skills && cp -r medsci-skills/skills/architecture-zoo ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repository: git clone https://github.com/Aperivue/medsci-skills.git
  3. Create the skills folder if needed: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r medsci-skills/skills/architecture-zoo ~/.claude/skills/
  5. Verify the references/ folder (index.md, classification.md, segmentation.md, etc.) came along — the workflow depends on it.
  6. For the full lane, also copy model-scaffold, model-validation and related skills from the same repo.
  7. Restart Claude Code and test with a prompt like "which architecture should I use for 3-D lesion segmentation?"
View source on GitHub ↗License: MIT