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-searchgit 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-search)<a href="https://agentmods.dev/skills/huang-sir1/radiology-skills/radiology-search"><img src="https://agentmods.dev/badge/skills/huang-sir1/radiology-skills/radiology-search/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-search"><img src="https://agentmods.dev/badge/skills/huang-sir1/radiology-skills/radiology-search.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 | $0.00163 | $0.01126 |
| Opus 5 | $0.00081 | $0.00563 |
| Sonnet 5 | $0.00033 | $0.00225 |
| Haiku 4.5 | $0.00016 | $0.00113 |
Grade A, and why
radiology-search 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Source Search (imaging literature + datasets)
Find and verify imaging-research papers and datasets across the right sources, merge without double-counting, and hand clean candidates to citation/export.
Core stance
- Right source first. PubMed for biomedical recall (+ MeSH); arXiv for imaging-AI methods and preprints; Crossref for DOI/cross-disciplinary metadata. Dataset registries for data.
- Verify identifiers (DOI/PMID/arXiv) before citing; expose failed/missing metadata.
- Deduplicate by DOI → PMID → arXiv ID → normalized title; don't count duplicates as independent evidence.
- Recall vs precision — for systematic/DTA reviews use MeSH + structured strategy and log it (PRISMA-DTA reproducibility); for quick lookups, precision.
- No fabrication — never invent volume/issue/pages/DOI/dataset accession.
When to use
- "Find recent papers on [imaging-AI topic]." / "Systematic search for a DTA meta-analysis."
- "Is there a public dataset for [task/organ/modality]?"
- "Verify these DOIs/PMIDs." / "Expand my query with MeSH terms."
- "Build a literature map / gap matrix / local paper RAG plan for this manuscript."
When to open extra files
| File | Open when |
|---|---|
| references/source-tiers.md | Which source to query first; fallback order; MeSH; recall vs precision; dedup keys |
| references/dataset-sources.md | Finding imaging + omics datasets (TCIA, GEO, cBioPortal, OpenNeuro, Grand Challenge, MSD) |
| references/literature-survey-workflow.md | The user needs field mapping, Introduction support, reviewer-defense literature, dataset scouting, or a manuscript-level literature synthesis rather than a quick lookup |
Workflow
- For survey-level or local-corpus work, open
literature-survey-workflow.mdand choose the mode: Intent / Triage / Deepen / Synthesize / Expand. Use its local paper/RAG ladder before expensive synthesis when a paper database is available. - Classify the need — papers vs datasets; quick lookup vs systematic recall.
- Build the query — concepts (translate Chinese → English scientific terms); for PubMed add MeSH; record the strategy for systematic searches.
- Search the right sources (source-tiers.md), per-source limits; for data use dataset-sources.md.
- Merge & dedup across sources by identifier/title.
- Verify key identifiers; flag unresolved.
- Return a ranked, deduplicated candidate list (+ a logged strategy for systematic
searches). Hand export to
radiology-citation.
What ships with it
4 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 · 69 lines · 163 tokens per session scan A 8dc4c61f61d7
radiology-search is a skill published in the GitHub repository huang-sir1/radiology-skills (1,687 stars, last pushed 1mo ago), licensed MIT. It adds 163 tokens to every session and 1,126 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
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…