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-grantgit 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-grant)<a href="https://agentmods.dev/skills/huang-sir1/radiology-skills/radiology-grant"><img src="https://agentmods.dev/badge/skills/huang-sir1/radiology-skills/radiology-grant/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-grant"><img src="https://agentmods.dev/badge/skills/huang-sir1/radiology-skills/radiology-grant.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 | $0.00292 | $0.02027 |
| Opus 5 | $0.00146 | $0.01014 |
| Sonnet 5 | $0.00058 | $0.00405 |
| Haiku 4.5 | $0.00029 | $0.00203 |
Grade A, and why
radiology-grant 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Grant Proposals (国自然 / 省自然 / institutional / international)
Use this skill to turn an imaging-research idea or finished study into a fundable proposal.
A grant is not a paper: reviewers fund a scientific question and a credible plan to answer
it, not a model. This skill rebuilds the logic and polishes each section to the structure
funders expect. NSFC/省自然 is the primary, most fully worked-out track; the same reframing
logic extends to international funders (NIH, ERC, Wellcome) when the team is also pursuing
cross-border funding — see references/international-grants.md.
Core stance
- Grant logic, not paper logic. Lead with the clinical need and the scientific question, then hypothesis → aims → technical route → innovation → feasibility → expected outcomes. "Construct a model / improve accuracy" is an engineering task, not a science question — reframe it into the mechanism or generalisable principle being tested.
- Eligibility before drafting, for any international target. Confirm the author/institution
can actually apply as lead PI before writing a word — NIH, ERC, and Wellcome each have real,
currently-changing eligibility constraints that are easy to miss (→
references/international-grants.md). Wasting effort on an inaccessible mechanism is worse than a hard "not this track." - The key scientific question (关键科学问题) is the spine. One sharp, answerable question that the aims serve. If the aims don't all serve it, the proposal is unfocused.
- Close the loop. The technical route (技术路线) must connect need → question → each aim → method → expected result → back to the question. Reviewers reject open-loop routes.
- Innovation must be specific and defensible. Name the increment (question / data / method / validation / mechanism). Avoid "first/领先" without grounding.
- Feasibility is shown, not asserted. Preliminary data, team capability, data access, and ethics make it credible — never fabricate preliminary results.
- Don't over-promise. Aims must be achievable in the period and budget; over-scoping reads as naïveté.
- Verify the current guidelines. Word limits, format, attachments, ethics, and 限项 rules change yearly — confirm against the current official 申报指南 (the author must check; this skill flags it, it does not have the current year's rules memorised).
What ships with it
5 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 · 113 lines · 292 tokens per session scan A 590a3eea6735
radiology-grant is a skill published in the GitHub repository huang-sir1/radiology-skills (1,687 stars, last pushed 1mo ago), licensed MIT. It adds 292 tokens to every session and 2,027 once invoked, about $0.0015 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…