[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69BF5DFRTGPQX0E6BYQNH0E":3,"skill-same:01M69BF5DFRTGPQX0E6BYQNH0E":61},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":28,"publishedAt":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":44,"ownerDescription":45,"updatedAt":46,"install":47,"resources":60},"01M69BF5DFRTGPQX0E6BYQNH0E","write-report-with-ehr",null,"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.","microsoft\u002Fhealthcare-models-and-agents-workshop","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69BEFF0TQHSY4MP1845AB1N",5,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fhealthcare-models-and-agents-workshop\u002Fblob\u002Fmain\u002Fchapters\u002Fchapter3-knowledge-sources\u002Fanswer-key\u002F.github\u002Fskills\u002Fwrite-report-with-ehr\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[29,30,31],"write report with ehr","image","change","2026-11-10 10:12:30",false,"---\nname: write-report-with-ehr\ndescription: 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.\nargument-hint: |\n  - image_path: required path to the current brain MRI image. The patient_id comes from the filename (`{patient_id}_{study_index}.nii.gz`).\n  - patient_id: optional override if the filename does not follow that convention.\n---\n\n# write-report-with-ehr\n\nCombine the patient record with descriptor measurements, then write a comparison-aware report. This skill writes the report itself; it does not delegate to `write-report-simple`.\n\n## How to use\n\n1. **Look up the record.** Invoke `lookup-patient-history` with `image_path`. If it returns \"Not on file,\" continue without history and write `COMPARISON: None available.`\n2. **Pick the prior image.** Use the most recent study in IMAGING HISTORY, before the current study, that has a retained image. Resolve the current and prior image paths to absolute paths.\n3. **Measure.** Invoke `write-imaging-factsheet` with the current image and that prior image, or the current image alone if no prior image is retained. Keep its factsheet and each scan's `audit_dir`.\n4. **Write the report** in the format below.\n\n## Reading the change\n\n- **Check what happened between the prior image and the current exam.** If PROCEDURES or TREATMENTS fall between them, such as a resection, the factsheet's change lines compare across that event. Say so, and do not describe the change as growth of the same lesion. Compare with later summary-only studies, such as a post-operative baseline, in words.\n- **Read change against the treatment timeline.** After radiation, enhancement and edema can increase without tumor growth (pseudoprogression or radiation necrosis). When the record allows both treatment effect and tumor, say that imaging alone cannot separate them; do not call progression outright.\n- **Expected findings are expected.** Describe items from EXPECTED POST-TREATMENT FINDINGS in one sentence; do not call them new.\n- **Answer the order.** The IMPRESSION addresses the question in the current study's pending order.\n- **Medications matter.** Mention steroids when describing edema or mass effect.\n\n## Sources\n\n- Measurements and change come from the factsheet only, copied verbatim with units. Do not compute, round, or convert numbers. Report on all available measurements, both volumetric and linear.\n- Values from summary-only studies, such as midline shift on a CT, are quoted with that study's date; the tools did not measure them.\n- Location and side come from the record or your own read of the image; the descriptors assign none.\n- Do not invent priors. A finding absent from every prior report and summary is new.\n- If LAST RECORD ENTRY NOTE says the record stops before the current exam, do not assume what happened in the gap.\n- The report must not mention tools, models, masks, descriptors, or the record's JSON.\n\n## Output format\n\nReturn the two trace sections first, then the report block last.\n\n```\n## Prior information used\n\nUp to 6 one-line bullets: the record fields and prior studies you relied on, including the prior image you measured against and any procedure between it and the current exam.\n\n## Clinical details used in the report\n\nUp to 10 one-line bullets, one per substantive report phrase, each paired with its source: a record field (`diagnosis`, `procedures`, `medications`, `pending_orders`, `prior report _NNN`, `study _NNN summary`) or a factsheet descriptor ID (`[L1.bidimensional]`). Flag anything with no source.\n\n\u003Cconfidence>{confidence}\u003C\u002Fconfidence>\n\u003Creport>\nEXAM: {exam from the current pending order}\n\nINDICATION: {indication from the current pending order}\n\nCOMPARISON: {the prior image's exam, date, and study_id; then other relevant studies by date and study_id}\n\nTECHNIQUE: {series, plane, and contrast; or \"MRI of the brain; sequence details not provided.\"}\n\nFINDINGS:\n{One or two prose paragraphs: the lesion and its change first, with what happened in between; then edema and mass effect; then expected post-treatment findings in one sentence.}\n\nIMPRESSION:\n1. {Answer to the order, with the change in context.}\n2. {Next finding, if needed.}\n\u003C\u002Freport>\n```\n\n- `{confidence}`: `low`, `medium`, or `high`, from how clearly the factsheet and the record support the findings.\n- The report is plain text, at most 250 words: no markdown, bullets, or bold. Impression numbering is literal text.\n","# write-report-with-ehr\n\nCombine the patient record with descriptor measurements, then write a comparison-aware report. This skill writes the report itself; it does not delegate to `write-report-simple`.\n\n## How to use\n\n1. **Look up the record.** Invoke `lookup-patient-history` with `image_path`. If it returns \"Not on file,\" continue without history and write `COMPARISON: None available.`\n2. **Pick the prior image.** Use the most recent study in IMAGING HISTORY, before the current study, that has a retained image. Resolve the current and prior image paths to absolute paths.\n3. **Measure.** Invoke `write-imaging-factsheet` with the current image and that prior image, or the current image alone if no prior image is retained. Keep its factsheet and each scan's `audit_dir`.\n4. **Write the report** in the format below.\n\n## Reading the change\n\n- **Check what happened between the prior image and the current exam.** If PROCEDURES or TREATMENTS fall between them, such as a resection, the factsheet's change lines compare across that event. Say so, and do not describe the change as growth of the same lesion. Compare with later summary-only studies, such as a post-operative baseline, in words.\n- **Read change against the treatment timeline.** After radiation, enhancement and edema can increase without tumor growth (pseudoprogression or radiation necrosis). When the record allows both treatment effect and tumor, say that imaging alone cannot separate them; do not call progression outright.\n- **Expected findings are expected.** Describe items from EXPECTED POST-TREATMENT FINDINGS in one sentence; do not call them new.\n- **Answer the order.** The IMPRESSION addresses the question in the current study's pending order.\n- **Medications matter.** Mention steroids when describing edema or mass effect.\n\n## Sources\n\n- Measurements and change come from the factsheet only, copied verbatim with units. Do not compute, round, or convert numbers. Report on all available measurements, both volumetric and linear.\n- Values from summary-only studies, such as midline shift on a CT, are quoted with that study's date; the tools did not measure them.\n- Location and side come from the record or your own read of the image; the descriptors assign none.\n- Do not invent priors. A finding absent from every prior report and summary is new.\n- If LAST RECORD ENTRY NOTE says the record stops before the current exam, do not assume what happened in the gap.\n- The report must not mention tools, models, masks, descriptors, or the record's JSON.\n\n## Output format\n\nReturn the two trace sections first, then the report block last.\n\n```\n## Prior information used\n\nUp to 6 one-line bullets: the record fields and prior studies you relied on, including the prior image you measured against and any procedure between it and the current exam.\n\n## Clinical details used in the report\n\nUp to 10 one-line bullets, one per substantive report phrase, each paired with its source: a record field (`diagnosis`, `procedures`, `medications`, `pending_orders`, `prior report _NNN`, `study _NNN summary`) or a factsheet descriptor ID (`[L1.bidimensional]`). Flag anything with no source.\n\n\u003Cconfidence>{confidence}\u003C\u002Fconfidence>\n\u003Creport>\nEXAM: {exam from the current pending order}\n\nINDICATION: {indication from the current pending order}\n\nCOMPARISON: {the prior image's exam, date, and study_id; then other relevant studies by date and study_id}\n\nTECHNIQUE: {series, plane, and contrast; or \"MRI of the brain; sequence details not provided.\"}\n\nFINDINGS:\n{One or two prose paragraphs: the lesion and its change first, with what happened in between; then edema and mass effect; then expected post-treatment findings in one sentence.}\n\nIMPRESSION:\n1. {Answer to the order, with the change in context.}\n2. {Next finding, if needed.}\n\u003C\u002Freport>\n```\n\n- `{confidence}`: `low`, `medium`, or `high`, from how clearly the factsheet and the record support the findings.\n- The report is plain text, at most 250 words: no markdown, bullets, or bold. Impression numbering is literal text.\n",{"name":5,"description":7,"argument-hint":37},"- image_path: required path to the current brain MRI image. The patient_id comes from the filename (`{patient_id}_{study_index}.nii.gz`).\n- patient_id: optional override if the filename does not follow that convention.","main","61aa7607e74cda657fcd824aa8261c91b0eba446","chapters\u002Fchapter3-knowledge-sources\u002Fanswer-key\u002F.github\u002Fskills\u002Fwrite-report-with-ehr",2,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fhealthcare-models-and-agents-workshop","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-03 00:53:01",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add microsoft\u002Fhealthcare-models-and-agents-workshop --skill write-report-with-ehr",{"tool":53,"command":54},"bunx","bunx skills add microsoft\u002Fhealthcare-models-and-agents-workshop --skill write-report-with-ehr",{"tool":56,"command":57},"pnpm","pnpm dlx skills add microsoft\u002Fhealthcare-models-and-agents-workshop --skill write-report-with-ehr","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fhealthcare-models-and-agents-workshop\u002Fblob\u002Fmain\u002Fchapters\u002Fchapter3-knowledge-sources\u002Fanswer-key\u002F.github\u002Fskills\u002Fwrite-report-with-ehr\u002FSKILL.md",true,[],[62,71,79,89,95,104],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":69,"publishedAt":32},"01M69BF3Z4EYEC327GH4D2E48A","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.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fhealthcare-models-and-agents-workshop\u002Fblob\u002Fmain\u002Fchapters\u002Fchapter3-knowledge-sources\u002Fanswer-key\u002F.github\u002Fskills\u002Flookup-patient-history\u002FSKILL.md",[68],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[70,30],"lookup patient history",{"skillNo":72,"name":5,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":77,"publishedAt":32},"01M69BF22K2HHE17TTJWEXRXVA","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).","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fhealthcare-models-and-agents-workshop\u002Fblob\u002Fmain\u002Fchapters\u002Fchapter3-knowledge-sources\u002Fanswer-key-improved-compliance\u002F.github\u002Fskills\u002Fwrite-report-with-ehr\u002FSKILL.md",[76],{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[29,30,78],"assistant",{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":32},"01M69BF052F87M2X96G7NBR4YH","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.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fhealthcare-models-and-agents-workshop\u002Fblob\u002Fmain\u002Fchapters\u002Fchapter3-knowledge-sources\u002Fanswer-key-improved-compliance\u002F.github\u002Fskills\u002Fwrite-imaging-factsheet-ehr\u002FSKILL.md",[],[86,87,30,88],"write imaging factsheet","write imaging factsheet ehr","cleanup",{"skillNo":90,"name":64,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":32},"01M69BEYPBQANFHDN71X44GF98","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.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fhealthcare-models-and-agents-workshop\u002Fblob\u002Fmain\u002Fchapters\u002Fchapter3-knowledge-sources\u002Fanswer-key-improved-compliance\u002F.github\u002Fskills\u002Flookup-patient-history\u002FSKILL.md",[],[70,30],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":102,"publishedAt":32},"01M69BEXDBN6Y3VXNMBWZRFA5K","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.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fhealthcare-models-and-agents-workshop\u002Fblob\u002Fmain\u002Fchapters\u002Fchapter2-foundation-models\u002Fstarter\u002F.github\u002Fskills\u002Fwrite-report-segmentation\u002FSKILL.md",[101],{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[103,30],"write report segmentation",{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":112,"publishedAt":32},"01M69BEVT3N1AXH8BNV7K31W31","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.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fhealthcare-models-and-agents-workshop\u002Fblob\u002Fmain\u002Fchapters\u002Fchapter2-foundation-models\u002Fstarter\u002F.github\u002Fskills\u002Fwrite-report-measured\u002FSKILL.md",[110,111],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},[113,30,31],"write report measured"]