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-reportinggit 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-reporting)<a href="https://agentmods.dev/skills/huang-sir1/radiology-skills/radiology-reporting"><img src="https://agentmods.dev/badge/skills/huang-sir1/radiology-skills/radiology-reporting/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-reporting"><img src="https://agentmods.dev/badge/skills/huang-sir1/radiology-skills/radiology-reporting.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 | $0.00169 | $0.02787 |
| Opus 5 | $0.00084 | $0.01393 |
| Sonnet 5 | $0.00034 | $0.00557 |
| Haiku 4.5 | $0.00017 | $0.00279 |
Grade A, and why
radiology-reporting 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Radiology Reporting-Guideline Compliance
Use this skill to make an imaging study reviewer-proof on reporting. Radiology and the RSNA family require the relevant EQUATOR checklist at submission, and imaging-AI / radiomics papers are now judged against a specific, version-sensitive stack of guidelines. This skill (1) identifies the study type, (2) selects the correct guideline(s), (3) audits the manuscript item-by-item, and (4) returns a submission-ready checklist plus a prioritised fix list.
Core stance
- The checklist is the contract. A reviewer maps your paper to a guideline; do the same first, in their seat.
- Report honestly. Mark each item
PRESENT,PARTIAL, orMISSING. Never label something compliant to be agreeable. AMISSINGflag you surface is cheaper than a reviewer finding it. - Cite the location. Every
PRESENTclaim must point to a section / page / figure / supplement. If you cannot point to it, it isPARTIALat best. - Versions matter. Use the current version (CLAIM 2024 Update, TRIPOD**+AI** 2024, CLEAR 2023, METRICS 2024). Name the version you audited against.
- Reporting ≠ quality ≠ risk-of-bias. CLEAR (reporting) → METRICS / RQS (methodological quality) → PROBAST(-AI) / QUADAS-2 (risk of bias). Different tools, different jobs; pick the right one(s).
- Don't invent the science. This skill audits reporting; it never fabricates the missing experiment, metric, or dataset. It tells the author what to add.
- Venue changes the stack, not the rigor. Radiology-family submissions stop at the
guideline checklist; Nature-portfolio submissions add a Reporting Summary / Editorial
Policy Checklist on top of the same guideline stack (→
nature-reporting-summary.md) — never treat the Reporting Summary as a replacement for CLAIM/TRIPOD+AI/CLEAR.
When to use
- "Which checklist does my study need?" / "What will Radiology require at submission?"
- "Audit this manuscript against CLAIM / TRIPOD+AI / STARD / CLEAR / METRICS / RQS."
- "Is my radiomics pipeline reported reproducibly (IBSI)?"
- "Fill in the CLAIM checklist with page numbers."
- "What's my risk-of-bias exposure under PROBAST-AI / QUADAS-2?"
- Pre-submission self-audit, or triaging a reviewer comment that cites a guideline.
What ships with it
9 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.
- README.md 2.7 KB
- references/claim-2024.md 4.0 KB
- references/clear-metrics-rqs.md 4.4 KB
- references/guideline-router.md 5.9 KB
- references/ibsi-features.md 3.0 KB
- references/nature-reporting-summary.md 5.3 KB
- references/radiology-submission-map.md 2.8 KB
- references/stard-prisma-quadas.md 3.1 KB
- references/tripod-ai-probast.md 3.6 KB
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 · 157 lines · 169 tokens per session scan A 038262b6f0c8
radiology-reporting is a skill published in the GitHub repository huang-sir1/radiology-skills (1,687 stars, last pushed 1mo ago), licensed MIT. It adds 169 tokens to every session and 2,787 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…