[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69BPBMS89S03WSRCJP5XDYN":3,"skill-same:01M69BPBMS89S03WSRCJP5XDYN":99},{"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":23,"publishedAt":28,"linkOnly":29,"markdownContent":30,"markdownBody":31,"frontMatter":32,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":40,"ownerDescription":41,"updatedAt":42,"install":43,"resources":56},"01M69BPBMS89S03WSRCJP5XDYN","write-report-zeroshot",null,"Write a chest X-ray report grounded in MedImageInsight (MI2) zero-shot classifier scores. Invoke whenever drafting a CXR report when MI2 is available — get vision-grounded per-finding probabilities, then delegate the prose to `write-report-simple`.","microsoft\u002Fsiim-workshop-2026","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69BP2QSG1ZYW8ZV65FMSVJN",6,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fsiim-workshop-2026\u002Fblob\u002Fmain\u002Fchapters\u002Fchapter2-foundation-models\u002Fanswer-key\u002F.github\u002Fskills\u002Fwrite-report-zeroshot\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[24,25,26,27],"write report","report","write report zeroshot","image","2026-11-10 10:12:30",false,"---\nname: write-report-zeroshot\ndescription: Write a chest X-ray report grounded in MedImageInsight (MI2) zero-shot classifier scores. Invoke whenever drafting a CXR report when MI2 is available — get vision-grounded per-finding probabilities, then delegate the prose to `write-report-simple`.\nargument-hint: |\n  - image_path: required path to the CXR image (PNG or JPEG)\n  - extra_labels: optional list of additional MI2-format label strings to score alongside the default set\n---\n\n# write-report-zeroshot\n\nTwo-step skill: (1) call MI2 to get per-finding probabilities for the image, then (2) hand those off to the existing `write-report-simple` skill to produce the actual report. The report itself never mentions MI2 — it reads as the radiologist's direct read of the image.\n\n## Budget\n\n- Tool calls: 1 — exactly one `mcp_medimageinsig_zeroshot_classify` call per image.\n- Output: ≤ 200 words for the full report.\n- Do not re-invoke skills already used in this turn.\n- Do not retry tool calls on success.\n\n## How to use\n\n1. **Resolve the image to an absolute path.** The MCP tool runs in a different working directory than the agent. If `image_path` is not absolute, resolve it (e.g. via `realpath`) before calling the tool. If you can't resolve it, ask the user.\n\n2. **Get scores from MI2.**\n   - Read the canonical label list from [`references\u002Flabels.md`](references\u002Flabels.md) and use those strings **verbatim**.\n   - If the caller provided `extra_labels`, append them.\n   - Call `mcp_medimageinsig_zeroshot_classify` with `file_path` = the **absolute** path from step 1 and `labels` = the assembled list.\n   - Bucket the returned scores using the cutoffs below.\n\n3. **Hand off to `write-report-simple`.** Invoke the `write-report-simple` skill (already in the workspace skill drawer at `.github\u002Fskills\u002Fwrite-report-simple\u002F`). Pass:\n   - `findings`: the bucketed list (positives + possibles), using the original MI2 label names.\n   - `scores`: the raw per-finding probabilities (so the report skill can calibrate hedging).\n\n   The downstream skill derives confidence from `scores`.\n\n4. **Return what `write-report-simple` returns.** Do not re-wrap, re-format, or annotate the report. The downstream skill emits the `\u003Cconfidence>` and `\u003Creport>` blocks; pass them through unchanged.\n\n## Score buckets\n\nProbabilities sum to ~1.0 across the label set. With the default label list, use these cutoffs:\n\n- **≥ 0.20** → positive finding (pass to `write-report-simple` as a confident finding).\n- **0.08 – 0.20** → possible finding (pass through; the report skill hedges accordingly).\n- **\u003C 0.08** → absent (omit from `findings`).\n\n## Critical rule\n\n**The report must not mention MI2, zero-shot scores, or any model output.** That's the responsibility of `write-report-simple` (which has the rule baked in), but it's worth restating here: this skill exists to ground the report in vision-model evidence, not to surface that evidence in the prose. If you want to attribute or caveat the model in the chat reply *outside* the `\u003Creport>` tags, that's fine.\n","# write-report-zeroshot\n\nTwo-step skill: (1) call MI2 to get per-finding probabilities for the image, then (2) hand those off to the existing `write-report-simple` skill to produce the actual report. The report itself never mentions MI2 — it reads as the radiologist's direct read of the image.\n\n## Budget\n\n- Tool calls: 1 — exactly one `mcp_medimageinsig_zeroshot_classify` call per image.\n- Output: ≤ 200 words for the full report.\n- Do not re-invoke skills already used in this turn.\n- Do not retry tool calls on success.\n\n## How to use\n\n1. **Resolve the image to an absolute path.** The MCP tool runs in a different working directory than the agent. If `image_path` is not absolute, resolve it (e.g. via `realpath`) before calling the tool. If you can't resolve it, ask the user.\n\n2. **Get scores from MI2.**\n   - Read the canonical label list from [`references\u002Flabels.md`](references\u002Flabels.md) and use those strings **verbatim**.\n   - If the caller provided `extra_labels`, append them.\n   - Call `mcp_medimageinsig_zeroshot_classify` with `file_path` = the **absolute** path from step 1 and `labels` = the assembled list.\n   - Bucket the returned scores using the cutoffs below.\n\n3. **Hand off to `write-report-simple`.** Invoke the `write-report-simple` skill (already in the workspace skill drawer at `.github\u002Fskills\u002Fwrite-report-simple\u002F`). Pass:\n   - `findings`: the bucketed list (positives + possibles), using the original MI2 label names.\n   - `scores`: the raw per-finding probabilities (so the report skill can calibrate hedging).\n\n   The downstream skill derives confidence from `scores`.\n\n4. **Return what `write-report-simple` returns.** Do not re-wrap, re-format, or annotate the report. The downstream skill emits the `\u003Cconfidence>` and `\u003Creport>` blocks; pass them through unchanged.\n\n## Score buckets\n\nProbabilities sum to ~1.0 across the label set. With the default label list, use these cutoffs:\n\n- **≥ 0.20** → positive finding (pass to `write-report-simple` as a confident finding).\n- **0.08 – 0.20** → possible finding (pass through; the report skill hedges accordingly).\n- **\u003C 0.08** → absent (omit from `findings`).\n\n## Critical rule\n\n**The report must not mention MI2, zero-shot scores, or any model output.** That's the responsibility of `write-report-simple` (which has the rule baked in), but it's worth restating here: this skill exists to ground the report in vision-model evidence, not to surface that evidence in the prose. If you want to attribute or caveat the model in the chat reply *outside* the `\u003Creport>` tags, that's fine.\n",{"name":5,"description":7,"argument-hint":33},"- image_path: required path to the CXR image (PNG or JPEG)\n- extra_labels: optional list of additional MI2-format label strings to score alongside the default set","main","a5e67c5253aeb4d3186860e989a54781bd3f859c","chapters\u002Fchapter2-foundation-models\u002Fanswer-key\u002F.github\u002Fskills\u002Fwrite-report-zeroshot",0,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fsiim-workshop-2026","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-09-02 06:32:37",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add microsoft\u002Fsiim-workshop-2026 --skill write-report-zeroshot",{"tool":49,"command":50},"bunx","bunx skills add microsoft\u002Fsiim-workshop-2026 --skill write-report-zeroshot",{"tool":52,"command":53},"pnpm","pnpm dlx skills add microsoft\u002Fsiim-workshop-2026 --skill write-report-zeroshot","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fsiim-workshop-2026\u002Fblob\u002Fmain\u002Fchapters\u002Fchapter2-foundation-models\u002Fanswer-key\u002F.github\u002Fskills\u002Fwrite-report-zeroshot\u002FSKILL.md",true,[57,63,67,71,75,79,83,87,91,95],{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Farchitecture-design.md","REFERENCE","参考文档",4680,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fcloud-design-patterns\u002Freferences\u002Farchitecture-design.md",{"path":64,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Fazure-service-mappings.md",606,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fcloud-design-patterns\u002Freferences\u002Fazure-service-mappings.md",{"path":68,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fbest-practices.md",1592,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fcloud-design-patterns\u002Freferences\u002Fbest-practices.md",{"path":72,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Fdeployment-operational.md",3310,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fcloud-design-patterns\u002Freferences\u002Fdeployment-operational.md",{"path":76,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fevent-driven.md",715,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fcloud-design-patterns\u002Freferences\u002Fevent-driven.md",{"path":80,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Flabels.md",767,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fsiim-workshop-2026\u002Fblob\u002Fmain\u002Fchapters\u002Fchapter2-foundation-models\u002Fanswer-key\u002F.github\u002Fskills\u002Fwrite-report-zeroshot\u002Freferences\u002Flabels.md",{"path":84,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fmessaging-integration.md",4643,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fcloud-design-patterns\u002Freferences\u002Fmessaging-integration.md",{"path":88,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":89,"sourceHtmlUrl":90},"references\u002Fperformance.md",6735,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fcloud-design-patterns\u002Freferences\u002Fperformance.md",{"path":92,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":93,"sourceHtmlUrl":94},"references\u002Freliability-resilience.md",6359,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fcloud-design-patterns\u002Freferences\u002Freliability-resilience.md",{"path":96,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":97,"sourceHtmlUrl":98},"references\u002Fsecurity.md",1835,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fcloud-design-patterns\u002Freferences\u002Fsecurity.md",[100,110,118,124,133,139],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":107,"publishedAt":28},"01M69BPJH4BVCT0N87CG351ZKV","write-report-with-ehr","Write a context-aware chest X-ray report grounded in the trained MedImageInsight (MI2) adapter AND the patient's EHR record. Adds a COMPARISON section and uses the most recent prior report to call out interval change.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fsiim-workshop-2026\u002Fblob\u002Fmain\u002Fchapters\u002Fchapter3-knowledge-sources\u002Fanswer-key\u002F.github\u002Fskills\u002Fwrite-report-with-ehr\u002FSKILL.md",[106],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[25,24,108,27,109],"write report with ehr","change",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":28},"01M69BPGKNN9HZ3T9R0HYWEKAP","lookup-patient-history","Load a synthetic patient EHR record (demographics, HPI, problems, meds, devices, prior imaging studies and reports) for a given chest X-ray. Invoke as the first step of any context-aware reporting flow that needs patient history. No model calls.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fsiim-workshop-2026\u002Fblob\u002Fmain\u002Fchapters\u002Fchapter3-knowledge-sources\u002Fanswer-key\u002F.github\u002Fskills\u002Flookup-patient-history\u002FSKILL.md",[],[117,27],"lookup patient history",{"skillNo":119,"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":120,"categories":121,"keywords":123,"publishedAt":28},"01M69BPF16NS8ERJATDKHVVPNN","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fsiim-workshop-2026\u002Fblob\u002Fmain\u002Fchapters\u002Fchapter2-foundation-models\u002Fstarter\u002F.github\u002Fskills\u002Fwrite-report-zeroshot\u002FSKILL.md",[122],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[26,25,24,27],{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":131,"publishedAt":28},"01M69BPDHYW62JH7VAT6JSP9R7","write-report-adapter","Write a chest X-ray report grounded in the trained MedImageInsight (MI2) adapter. Invoke whenever drafting a CXR report when the adapter is available — get vision-grounded per-finding positive\u002Fpossible\u002Fnegative calls, then delegate the prose to `write-report-simple`.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fsiim-workshop-2026\u002Fblob\u002Fmain\u002Fchapters\u002Fchapter2-foundation-models\u002Fstarter\u002F.github\u002Fskills\u002Fwrite-report-adapter\u002FSKILL.md",[130],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[132,25,24,27],"write report adapter",{"skillNo":134,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":138,"publishedAt":28},"01M69BP9Z718J2D8SA7ARERMYS","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fsiim-workshop-2026\u002Fblob\u002Fmain\u002Fchapters\u002Fchapter2-foundation-models\u002Fanswer-key\u002F.github\u002Fskills\u002Fwrite-report-adapter\u002FSKILL.md",[137],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[132,25,24,27],{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":146,"publishedAt":28},"01M69BP8JWJ7A56MWZ29H0HBH8","write-report-simple","TODO","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fsiim-workshop-2026\u002Fblob\u002Fmain\u002Fchapters\u002Fchapter1-simple-agent\u002Fstarter\u002F.github\u002Fskills\u002Fwrite-report-simple\u002FSKILL.md",[145],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[24,25,147],"write report simple"]