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-multiomics-fusiongit 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-multiomics-fusion)<a href="https://agentmods.dev/skills/huang-sir1/radiology-skills/radiology-multiomics-fusion"><img src="https://agentmods.dev/badge/skills/huang-sir1/radiology-skills/radiology-multiomics-fusion/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-multiomics-fusion"><img src="https://agentmods.dev/badge/skills/huang-sir1/radiology-skills/radiology-multiomics-fusion.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 | $0.00095 | $0.02222 |
| Opus 5 | $0.00048 | $0.01111 |
| Sonnet 5 | $0.00019 | $0.00444 |
| Haiku 4.5 | $0.00010 | $0.00222 |
Grade A, and why
radiology-multiomics-fusion 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Five-Dimensional Multi-Omics Fusion
Use this skill when all five dimensions — imaging, clinical, pathology, bulk molecular omics, and single-cell or spatial omics — are intended for joint prediction or integration. The analysable cohort is defined by patient-level linkage and modality availability, not by the largest source cohort. If fewer than five dimensions are used, label the study a reduced-dimensional variant and confirm that this module is still more appropriate than an existing focused module.
Core stance
- Availability before architecture. Build the patient-by-modality matrix and report the matched intersection before choosing a fusion method.
- Matched n limits complexity. The complete-case count, modality patterns, centers, and validation groups — plus endpoint events for supervised prediction — must support every fitted component. De-escalate when they do not.
- Earn the fusion by branch. Supervised models must beat clinical-only, single-modality, and simple regularized or late-fusion baselines. Unsupervised solutions must show stable, assignable, independently replicable structure.
- Nest the whole pipeline. Fit normalization, harmonization, embeddings, feature selection, imputation, fusion, and tuning using training data only.
- Respect the experimental unit. Cells, spots, regions, slides, and tiles are nested observations; donors or patients, not their subunits, determine the independent n.
- Missing blocks are design information. Distinguish structural, workflow, and quality-related absence; do not silently convert them into complete cases.
- Contribution is comparative, not causal. For supervised prediction, use single-block models, predictive ablation, conditional permutation, and pre-specified interactions. For unsupervised discovery, examine block-removal effects on cluster/factor alignment, stability, and assignment uncertainty. Neither establishes biological mechanism.
- Validate transportability. Preserve patient, site, batch, and time boundaries; external validation must reproduce the required modalities and processing route.
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 · 161 lines · 95 tokens per session scan A 83ff1e18af03
radiology-multiomics-fusion is a skill published in the GitHub repository huang-sir1/radiology-skills (1,687 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 2,222 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.