write-report-measured
Write a brain MRI report with tool-computed lesion measurements and, when a prior image is supplied, change from that prior. Use for brain MRI reports when the medimageparse `segment`, `clean_segmentation`, and `describe_lesions` tools are available; preferred over write-report-segmentation.
- License 许可
- MIT
- 最近更新
- 2026-11-03
- Stars
- ★ 5
- Forks
- 2
01 前言 Front Matter
- name
- write-report-measured
- description
- Write a brain MRI report with tool-computed lesion measurements and, when a prior image is supplied, change from that prior. Use for brain MRI reports when the medimageparse `segment`, `clean_segmentation`, and `describe_lesions` tools are available; preferred over write-report-segmentation.
- argument-hint
- image_path [prior_image_path]
03 SKILL.md 正文
Write Measured Report
Build a descriptor factsheet, then let write-report-simple write the report from it.
- Invoke
write-imaging-factsheetwith the image and any prior image. Keep its factsheet and each scan'saudit_dir. - Invoke
write-report-simplewith:findings: each tumor componentpresentwhen its total volume in the factsheet is above 0, otherwiseabsent.measurements, copied verbatim with units from the factsheet: lesion count; each lesion's diameters and tumor-core volume; total edema volume; and, with a prior, each change line (prior, current, percent change).- With a prior, the prior exam as the comparison, using its date if the path shows one.
- Return the
write-report-simpleoutput unchanged, then end with the factsheet path and each scan'saudit_dir.
Rules
- Numbers come from the factsheet only. Do not compute, round, or convert them.
- Lesion IDs are ranked separately for each scan. Do not match lesions across scans or attribute change to one lesion; change lines compare totals.
- The descriptors assign no side or anatomy. Use your own read of the image, such as the overlay film grids (patient right on screen left), only for location wording.
04 同仓库更多 Skills
write-report-with-ehr
Write a context-aware brain MRI follow-up report from the patient's record, tool-computed lesion measurements, and change from the most recent prior image. Use when asked for a report that uses the patient's history, chart, or EHR.
lookup-patient-history
Load a synthetic patient EHR record (demographics, diagnosis, treatments, medications, expected post-treatment findings, prior imaging studies and reports, pending orders) for a given brain MRI image. Invoke as the first step of any context-aware reporting flow that needs patient history. No model calls.
write-report-with-ehr
Write a context-aware brain MRI report using the patient chart and mandatory tool-computed linear and volumetric measurements. Use for EHR reporting with Radiology Assistant (EHR).
write-imaging-factsheet-ehr
Produce an EHR imaging factsheet with mandatory segmentation, cleanup, linear dimensions, and volumes. Use when write-report-with-ehr requests imaging evidence or when explicitly asked for this factsheet.
lookup-patient-history
Load the synthetic patient chart and verbatim prior reports for EHR reporting. Use before measuring the selected current and prior images; this lookup does not perform segmentation or measurements.
write-report-segmentation
Write a brain MRI report grounded in MedImageParse 3D tumor segmentation. Use for brain MRI reports when the medimageparse `segment` tool is available but `clean_segmentation` or `describe_lesions` is not.