radiology-annotation
Design/audit imaging truth, readers, ROI geometry, reproducibility and label noise; not model training.
Install / Use
npx skills add huang-sir1/radiology-skills --skill radiology-annotationInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Our assessment of radiology-annotation
radiology-annotation scores 82/100 on our quality scale, 3358th of 4,700 Development & Engineering skills we index.
Its SKILL.md is 6.7 KB long, well organised into 8 sections and no code examples: a thorough specification that gives an agent plenty to work with.
With 1,785 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated about 2 months ago, so radiology-annotation is actively maintained.
- Our last check on 2026-11-07 found the source still online.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 88/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-10-01. Automated pattern scan on 2026-10-01. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
radiology-annotation compared with similar skills
All 4 of these similar skills score higher than radiology-annotation; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| radiology-annotation (this skill)by huang-sir1 | 82 | 1.8k | 56d ago | SKILL.md |
| taste-skillby Leonxlnx | 100 | 116.8k | 8d ago | CLAUDE.md |
| ai-job-searchby ai-job-search-dev | 100 | 72.1k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 47.3k | 2d ago | CLAUDE.md |
| Claude-Code-Game-Studiosby Donchitos | 100 | 39.7k | 7d ago | CLAUDE.md |
Frequently asked questions
- How do I install radiology-annotation?
- Run
npx skills add huang-sir1/radiology-skills --skill radiology-annotation. The install tabs above show the steps for each supported agent. - Which AI agents does radiology-annotation work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is radiology-annotation safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 88/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is radiology-annotation still maintained?
- The repository was last updated about 2 months ago, so radiology-annotation is actively maintained.
Skill content
View source on GitHubname: radiology-annotation description: "Design/audit imaging truth, readers, ROI geometry, reproducibility and label noise; not model training."
ROI / VOI / Mask Annotation SOP
Use this skill to make the annotation behind a radiomics/segmentation/radiogenomics study defensible. Reviewers reject papers when the segmentation is a black box: unknown readers, no reproducibility, masks that don't align with the images, or feature instability never tested. This skill specifies the lesion-selection strategy, the reader protocol, the reproducibility plan, and the geometric checks — and writes the Methods text.
Core stance
- Segmentation is a measurement, so characterise its error. Report inter-/intra-observer reproducibility and propagate it (drop unstable features) — don't treat masks as ground truth.
- Pre-specify the lesion-selection rule. 2D vs 3D, whole-tumour vs largest-slice vs peritumoral ring vs sub-regional habitat vs multi-lesion handling — decided up front, applied uniformly, and justified by the biology and the endpoint.
- Readers are part of the method. Number, seniority, blinding to outcome, independent vs consensus, and the adjudication rule for disagreement all belong in Methods.
- Geometry must be exact. Mask and image must share spacing, origin, direction, and slice order; a one-voxel or flipped-axis mismatch silently corrupts every feature.
- Reproducibility before modelling. Filter to reproducible features (e.g. ICC threshold) before selection/modelling, on training data only — leakage hides here too.
- Integrity. Never invent ICC/Dice values, reader counts, or QC results; mark what must be measured.
When to use
- "Design an ROI/mask annotation SOP / 帮我写标注 SOP(勾画规范)。"
- "Two radiologists contoured the lesions — how do I report agreement and select stable features?"
- "Whole-tumour or largest-slice? 2D or 3D? peritumoral? habitat?"
- "My masks don't line up with the images / DICOM-SEG/RTSTRUCT conversion issues."
- "Write the segmentation + reproducibility paragraph for Methods."
When to open extra files
| File | Open when | |---|---| | references/lesion-selection.md | Choosing 2D/3D, whole-tumour/largest-slice/peritumoral/habitat/multi-lesion; what the endpoint and biology imply | | references/reader-protocol.md | Reader number/seniority, blinding, independent vs consensus, adjudication, training set | | references/reproducibility-qc.md | Repeat-annotation design, ICC/Dice/Hausdorff, feature-stability filtering, sensitivity analysis | | references/mask-geometry.md | DICOM/NIfTI/DICOM-SEG/RTSTRUCT spacing/origin/direction/slice-order checks, conversion pitfalls | | references/label-ontology-and-reference-standard.md | Defining case/lesion/exam labels, indeterminate states, composite reference standards, adjudication and provenance beyond masks | | references/noisy-weak-and-report-derived-labels.md | Using report-mined, weak, noisy or incomplete labels without silently treating them as verified truth | | references/longitudinal-lesion-and-exam-linkage.md | Linking patients, examinations and lesions over time; new/disappearing/split/merged lesions and treatment-time ambiguity |
Workflow
- Fix the target construct and reference standard. Define case/lesion/exam ontology, indeterminate/failure categories, label source, verification window, adjudication and provenance; use the noisy/weak-label and longitudinal-linkage references when applicable.
- Fix the segmentation target. What is segmented (whole tumour, core, necrosis, edema, node, organ), in which modality/sequence/phase, and why that target serves the endpoint.
- Choose the selection strategy (lesion-selection.md) — dimension, region, peritumoral extent, habitats, and the multi-lesion rule. Justify it.
- Specify the reader protocol (reader-protocol.md) — who, how many, blinded to what, independent vs consensus, adjudication, and any segmentation-training phase.
- Plan reproducibility (reproducibility-qc.md) — repeat-annotation subset, ICC/Dice/HD, the feature-stability filter and threshold, and a sensitivity analysis.
- Verify geometry (mask-geometry.md) — confirm image↔mask spacing/origin/direction/slice order; document the conversion path (DICOM-SEG/RTSTRUCT/NIfTI) and QC.
- Write Methods — the annotation paragraph: target, software+version, readers, blinding, reproducibility, stability filtering — in Radiology style.
Output contract
Annotation SOP— target, selection strategy, software/version, step-by-step procedure.Ground-truth passport— ontology, unit, source, verification window, indeterminate/failure handling, adjudication, label confidence and patient–exam–lesion linkage.Reader protocol— number/seniority/blinding/independent-or-consensus/adjudication.Reproducibility & QC plan— repeat design, metrics (ICC/Dice/HD), stability filter + threshold (frozen here from measured reproducibility, applied byradiology-radiomicsinside training), sensitivity analysis — with placeholders for values to be measured.Geometry checklist— the alignment/conversion checks and their pass/fail.Annotation provenance— mask/image IDs or irreversible hashes, version, reader, timestamp/status, adjudication/revision history, software/version, and geometry-QC artifact when a full project record is requested.Methods paragraph— submission-ready prose (+ 待确认 list for Chinese authors).
Quality bar
A good annotation spec lets an independent group reproduce the masks and the feature set, tells the reviewer exactly how segmentation error was measured and controlled, and never reports an agreement value that was not computed.
Handoffs
- Series/phase/sequence acceptance and image-formation/QC passport →
radiology-acquisition-qc; annotation owns labels, contours, reader process and image-mask geometry, not scanner conformance. - IBSI feature reproducibility / CLEAR-METRICS audit →
radiology-reporting. - Hand-crafted feature extraction pipeline →
radiology-radiomics. - ICC model choice, Dice/Bland-Altman statistics →
radiology-stats. - Habitat masks for imaging×omics →
radiology-radiogenomics. - De-identifying shared masks/images →
radiology-data/radiology-ethics. - Project manifest and downstream staleness after mask revisions →
radiology-pipeline. - This skill specifies and reports annotation; it does not perform clinical contouring.
Related Skills
taste-skill
116.8kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
ai-job-search
72.1kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
47.3kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
Claude-Code-Game-Studios
39.7kTurn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
