radiology-skills is a collection of Codex skills for medical-imaging research, covering radiomics, deep learning, imaging genomics, multimodal studies, statistics, validation, and scientific publishing. It is intended for researchers who design, analyze, write, and submit medical-imaging AI studies. The catalogue entries are its modular research workflows and specialist advisory skills.
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 huang-sir1/radiology-skills --skill radiology-foundation-modelsgit clone --depth 1 https://github.com/huang-sir1/radiology-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/huang-sir1/radiology-skills/radiology-foundation-models)<a href="https://agentmods.dev/skills/huang-sir1/radiology-skills/radiology-foundation-models"><img src="https://agentmods.dev/badge/skills/huang-sir1/radiology-skills/radiology-foundation-models/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/huang-sir1/radiology-skills/radiology-foundation-models"><img src="https://agentmods.dev/badge/skills/huang-sir1/radiology-skills/radiology-foundation-models.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 | $0.00107 | $0.01875 |
| Opus 5 | $0.00053 | $0.00937 |
| Sonnet 5 | $0.00021 | $0.00375 |
| Haiku 4.5 | $0.00011 | $0.00187 |
Grade A, and why
radiology-foundation-models 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 13d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Foundation-Model Adaptation for Medical Imaging
Use this skill when a model with broad pretraining intended for adaptability across tasks is central to selection, adaptation, benchmarking, or audit. Treat it as a checkpoint with a specific pretraining history, input contract, and license—not as automatic evidence of robustness or clinical validity.
Core stance
- Audit the model card, checkpoint, license, pretraining sources, deduplication, and possible evaluation overlap before adaptation.
- Match modality, anatomy, dimensionality, channels/sequences, text interface, spatial resolution, task, and prediction-time inputs before considering model size.
- Climb a prespecified adaptation ladder from the least trainable valid route. Include continued self-supervised or domain-adaptive pretraining only when authorized in-domain unlabeled data and a direct fine-tuning baseline make its added value testable.
- Separate every patient and all of that patient's repeated examinations, lesions, slices, patches, or frames across development and evaluation. Choose site-held-out or temporal separation when the transportability estimand requires it; a same-site internal test is valid when clearly labeled.
- Compare against strong task-specific and conventional transfer-learning baselines using identical eligible cohorts, split assignments, prediction-time information, and fair tuning rules.
- Report calibration, uncertainty or abstention, clinically relevant subgroups, external validation, compute, reproducibility, checkpoint identity, and license.
- Bound claims to the tested task, population, comparator, adaptation route, and validation domain.
Required intake
Collect the intended use, endpoint, unit of analysis, reference standard, target population, modality and input geometry, prediction-time inputs, paired text or prompts, cohort/site/time structure, repeated measures, candidate model cards/checkpoints/licenses, pretraining sources, labels/events, compute constraints, baselines, and validation material. Mark unknown pretraining overlap, prompt provenance, incompatible licenses, and unavailable frozen tests as unresolved risks.
What ships with it
3 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.
- 13d ago First seen · 153 lines · 107 tokens per session scan A 941da5f9147b
radiology-foundation-models is a skill published in the GitHub repository huang-sir1/radiology-skills (1,687 stars, last pushed 1mo ago), licensed MIT. It adds 107 tokens to every session and 1,875 once invoked, about $0.0005 per session on Opus 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 2026-08-30.
Other skills, from other repositories
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…
pyhealth
Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer…
torchdrug
Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
deepspot-m
Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.
pick-a-pii-model
Select an on-device OpenMed PII model from the committed registry by language, runtime format, and size budget, then require recall validation before deployment. Use when an agent must choose a local PII detector for CPU, Apple Silicon, or a mobile export without relying on live model discovery.