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-readergit 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-reader)<a href="https://agentmods.dev/skills/huang-sir1/radiology-skills/radiology-reader"><img src="https://agentmods.dev/badge/skills/huang-sir1/radiology-skills/radiology-reader/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-reader"><img src="https://agentmods.dev/badge/skills/huang-sir1/radiology-skills/radiology-reader.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 | $0.00151 | $0.01168 |
| Opus 5 | $0.00076 | $0.00584 |
| Sonnet 5 | $0.00030 | $0.00234 |
| Haiku 4.5 | $0.00015 | $0.00117 |
Grade A, and why
radiology-reader 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Full-Paper Markdown Reader (imaging-tuned)
Turn an imaging-research paper into a complete, bilingual, source-grounded Markdown reading artifact. The default output is a paragraph-level 中英对照 companion — not a summary.
Non-negotiable defaults
When the user asks to read/translate a paper, or says 中英对照 / 原文对照 / 全文翻译 / paper reader, produce a paragraph-level bilingual reader by default. Do not replace it with
a Chinese-only summary, a highlights list, or captions without figure crops.
What to preserve (and why it matters for imaging papers)
- Full prose, paragraph structure, and section flow (incl. Materials and Methods detail — scanner/protocol, segmentation, model/feature pipeline, statistical analysis).
- Original + faithful Chinese translation at block level; keep technical terms, gene/model names, units, p-values, CIs, and citation markers intact.
- Figures and tables placed near their first substantive mention. Crop tightly:
- Imaging panels — keep windowing/arrow annotations visible; note the modality/sequence.
- Result charts (ROC, calibration, forest, Kaplan-Meier, DCA) — keep axes/legend legible.
- Tables (cohort characteristics, scanner parameters, performance) — keep near the interpreting paragraph.
- Stable anchors on every block (
S###body,C###captions,F###figures,T###tables).
When to open extra files
| File | Open when |
|---|---|
| references/structured-reading-notes.md | The user is reading for literature review, paper comparison, journal club, gap discovery, manuscript writing, or wants craft/figure/limitation patterns rather than translation only |
Workflow
- Identify source & paper type (DTA / prediction model / radiomics / radiogenomics / review) — this sets how tightly to couple text, figures, and stats.
- Build a full source map before translating (page, block type, original, translation, reading order, nearby figure/table, confidence). Process the whole document, not just the abstract.
- Translate conservatively — meaning not style; keep Methods/stats detail; mark uncertain OCR rather than guessing; never drop limitations / data-availability / ethics.
- Extract & place figures/tables at first substantive mention; tight crops; keep caption
- Chinese caption; add a one-line reading note (what to inspect — e.g. "AUC and CI in panel A; calibration in panel B").
- For literature-review or journal-club reading, open
structured-reading-notes.mdand create Pass 1/2/3 notes at the depth the task deserves. - Generate
paper.md(primary) +source_map.json+translation_notes.md+assets/. Add a terminology table for recurring imaging/AI terms. - Answer follow-ups from the source with block IDs + page numbers; don't answer from memory.
What ships with it
2 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 · 83 lines · 151 tokens per session scan A 8d5a2cb85d73
radiology-reader is a skill published in the GitHub repository huang-sir1/radiology-skills (1,687 stars, last pushed 1mo ago), licensed MIT. It adds 151 tokens to every session and 1,168 once invoked, about $0.0008 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
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.