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-polishinggit 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-polishing)<a href="https://agentmods.dev/skills/huang-sir1/radiology-skills/radiology-polishing"><img src="https://agentmods.dev/badge/skills/huang-sir1/radiology-skills/radiology-polishing/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-polishing"><img src="https://agentmods.dev/badge/skills/huang-sir1/radiology-skills/radiology-polishing.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 | $0.00139 | $0.01095 |
| Opus 5 | $0.00069 | $0.00548 |
| Sonnet 5 | $0.00028 | $0.00219 |
| Haiku 4.5 | $0.00014 | $0.00110 |
Grade A, and why
radiology-polishing 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Radiology-Style Prose Polishing
Use this skill to take existing imaging-research prose and make it read the way
Radiology publishes — precise, concise, correctly formatted, and free of overclaiming. For
building new content, use radiology-writing.
Core stance
- Preserve meaning and numbers exactly. Never change a reported value, CI, p-value, n, or citation. Flag suspected errors; don't silently "fix" data.
- Clarity over flourish. Short, direct sentences; one idea each. Remove filler ("it is worth noting that," "very," "novel").
- Precise stats reporting — estimate + 95% CI; exact p (
P = .03); correct number/unit format; named test. (stat-reporting.md) - American English (color, tumor, analyze, catheterization) — Radiology house style.
- Calibrate claims to evidence — flag overclaiming and unwarranted causation.
- Section-aware tense — Methods/Results past tense; established facts present.
When to use
- "Tighten / copyedit / polish this paragraph for Radiology."
- "Fix the statistical reporting and number formatting."
- "Convert to American English and journal style."
- "Is this overclaiming?"
When to open extra files
| File | Open when |
|---|---|
| references/radiology-house-style.md | Voice, tense, abbreviations, American spelling, terminology, units |
| references/stat-reporting.md | Formatting p-values, CIs, decimals, percentages, n, ranges, and test names |
| references/style-guardrails.md | Overclaim/causation detection, hedging calibration, forbidden phrasings |
| references/venue-voice-and-house-style.md | Target venue is known, or the user supplied author-guide PDFs/classic papers and wants European Radiology / Nature Partner / npj / other venue voice rather than generic Radiology polish |
Workflow
- Confirm the target venue (Radiology-family default, or Nature-family — see the deltas
table at the end of
radiology-house-style.md) — the leading-zero and reference-style rules flip between the two; polishing to the wrong one is itself an error. - For venue-specific voice, open
venue-voice-and-house-style.mdand apply the target family's wording, abbreviation, p-value, data-availability, and pending-guide checks. - Identify the section (sets tense and expectations).
- Pass 1 — clarity: split long sentences, cut filler, fix vague verbs, ensure each sentence has one idea and the subject is clear.
- Pass 2 — statistics & numbers: enforce estimate + CI, exact p, decimal/unit format, named tests (stat-reporting.md). Do not change values.
- Pass 3 — house style: American English, abbreviation rules (define at first use; not in Key Results), terminology, units.
- Pass 4 — guardrails: flag overclaiming, causal language unsupported by design, "first/novel," scope creep; propose calibrated wording (style-guardrails.md).
- Return clean prose + a concise change log; list any flags the author must resolve.
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 · 77 lines · 139 tokens per session scan A 3fa1270ad255
radiology-polishing is a skill published in the GitHub repository huang-sir1/radiology-skills (1,687 stars, last pushed 1mo ago), licensed MIT. It adds 139 tokens to every session and 1,095 once invoked, about $0.0007 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…