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-prereviewgit 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-prereview)<a href="https://agentmods.dev/skills/huang-sir1/radiology-skills/radiology-prereview"><img src="https://agentmods.dev/badge/skills/huang-sir1/radiology-skills/radiology-prereview/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-prereview"><img src="https://agentmods.dev/badge/skills/huang-sir1/radiology-skills/radiology-prereview.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 | $0.00172 | $0.01626 |
| Opus 5 | $0.00086 | $0.00813 |
| Sonnet 5 | $0.00034 | $0.00325 |
| Haiku 4.5 | $0.00017 | $0.00163 |
Grade A, and why
radiology-prereview 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-submission Mock Review
Use this skill to be the harshest fair reviewer before the real one is. It reads the manuscript the way a methods-literate Radiology/Lancet-DH/Nature-Medicine reviewer would, finds the dealbreakers, and returns a reviewer-style report you can act on — so issues are fixed on your terms, not surfaced in a rejection.
Core stance
- Adversarial but on the author's side. Hunt for the weakness a reviewer will weaponise, then hand back the fix — not just the criticism.
- Dealbreakers first. No patient-level split, data leakage, no external validation, undefined labels, unclear segmentation, incomplete statistics, overclaiming — these decide the outcome. Triage them before cosmetics.
- Map to the guideline. Tie each issue to the specific CLAIM/CLEAR/TRIPOD+AI/STARD/IBSI item or methodological risk a reviewer would cite (→ radiology-reporting).
- Check the claims against the evidence. Does the abstract/Discussion overstate AUC, correlation, or retrospective results? Flag every claim the data don't support.
- Honest readiness verdict. Give an editor-style recommendation (ready / minor / major / not yet) with the reasons — don't reassure.
- Integrity. Never invent compliance, never wave through a real weakness to be encouraging.
When to use
- "Mock-review my paper before I submit." / "投稿前帮我模拟审稿、做预审。"
- "Find the holes a reviewer will find."
- "Is this ready for [target journal], or what must I fix first?"
- After drafting, before
radiology-journalselection and submission.
When to open extra files
| File | Open when |
|---|---|
| references/review-dimensions.md | The full set of dimensions to review (design, data, labels, leakage, stats, reporting, figures, claims, sharing) |
| references/dealbreakers.md | The hard issues that trigger desk-reject / major revision, with how to detect and fix each |
| references/review-report-format.md | The reviewer-report + editor-recommendation output structure |
| references/pre-submission-hard-gates.md | Final submission readiness audit, rejected-paper rescue, contribution map, reviewer objection register, or when deciding whether a paper is truly ready |
| references/ai-radiogenomics-pitfall-audit.md | Imaging-AI, foundation-model, VLM, radiomics, deep radiomics, or radiogenomics manuscripts need a targeted audit for leakage, external validation, site/scanner confounding, superficial XAI, weak clinical utility, or mechanism overclaim |
| references/claim-verification-gate.md | Submission-facing abstract, Key Results, figure legend, table, graphical abstract, novelty, comparison, and numerical claims need two-pass extraction and verification |
What ships with it
7 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 · 100 lines · 172 tokens per session scan A 9059d2b6b7ae
radiology-prereview is a skill published in the GitHub repository huang-sir1/radiology-skills (1,687 stars, last pushed 1mo ago), licensed MIT. It adds 172 tokens to every session and 1,626 once invoked, about $0.0009 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…