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-designgit 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-design)<a href="https://agentmods.dev/skills/huang-sir1/radiology-skills/radiology-design"><img src="https://agentmods.dev/badge/skills/huang-sir1/radiology-skills/radiology-design/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-design"><img src="https://agentmods.dev/badge/skills/huang-sir1/radiology-skills/radiology-design.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 | $0.00200 | $0.01971 |
| Opus 5 | $0.00100 | $0.00986 |
| Sonnet 5 | $0.00040 | $0.00394 |
| Haiku 4.5 | $0.00020 | $0.00197 |
Grade A, and why
radiology-design 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Imaging Study Design & Feasibility
Use this skill at the front of the research chain: someone has imaging data (and maybe clinical/pathology/molecular labels) but no settled study. It (1) triages feasibility — can this data support a credible study at all? — and (2) converts a feasible idea into a complete, submittable design: clinical question, population, endpoint, methods (minimum viable → stronger), and the validation strategy that decides whether the work is generalisable or single-center-anecdote.
Core stance
- Clinical question first, model second. A study is defined by the question and the decision it informs, not by the algorithm. "Build a model" is not a study.
- Match data to task, honestly. The same images support very different ceilings. Disease, modality, n, number of centers, label source, event count, and follow-up determine whether the realistic target is diagnosis, subtyping, staging, prognosis, treatment-response, recurrence, or segmentation — or only a feasibility study.
- Validation is the spine. Internal cross-validation alone is weak. State the validation type explicitly and design it before modelling; external/temporal/geographic validation is what separates Radiology-tier work from a desk reject.
- Surface the binding constraint. Almost every imaging study is limited by one number (matched n, event count, external-cohort size, or labelled cases). Name it up front; the design must respect it.
- Pre-specify. Primary endpoint, primary analysis, and the split scheme are decided before looking at results. Retro-fitting the question to the result is the cardinal sin.
- Integrity. Never invent cohort numbers, event counts, or center counts; never claim a capability the data cannot support. If the honest answer is "not yet — do X first," say so.
When to use
- "I have [N] cases of [disease] [modality] — what can I actually study?" / "这批数据能不能做研究？"
- "Turn my data into a complete, submittable project." / "帮我把现有数据设计成一个完整课题。"
- "Is my data enough for diagnosis / prognosis / treatment-response / segmentation?"
- "Design a multi-center / external-validation / temporal-validation plan." / "多中心外部验证怎么设计？"
- "How do I show generalisability across scanners/hospitals?" / center, scanner, batch effects.
- Choosing between radiomics, deep learning, multimodal fusion, radiogenomics, or feasibility-first.
What ships with it
6 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 · 112 lines · 200 tokens per session scan A 49d35b7438dc
radiology-design is a skill published in the GitHub repository huang-sir1/radiology-skills (1,687 stars, last pushed 1mo ago), licensed MIT. It adds 200 tokens to every session and 1,971 once invoked, about $0.0010 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…