菜单
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/possible/negative calls, then delegate the prose to `write-report-simple`.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/microsoft/siim-workshop-2026 --skill write-report-adapter命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Write a structured chest X-ray report (Indication, Technique, Findings, Impression) using canonical radiologist phrasings. Invoke whenever drafting or revising a CXR report.
TODO
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`.
基于 SOC 职业分类
正在显示 SKILL.md
| name | write-report-adapter |
| description | 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/possible/negative calls, then delegate the prose to `write-report-simple`. |
| argument-hint | - image_path: required path to the CXR image (PNG or JPEG) - head: optional adapter head — "mlp" (default) or "svm" |
Two-step skill: (1) call the trained MI2 adapter to get per-finding positive/possible/negative calls 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, the adapter, or any classifier — it reads as the radiologist's direct read of the image.
mcp_medimageinsig_adapter_classify call per image.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.
Get calls from the adapter.
mcp_medimageinsig_adapter_classify with file_path = the absolute path from step 1, and head = the caller's head if provided (otherwise omit; defaults to mlp).{label: "positive" | "possible" | "negative"} — already bucketed using per-class operating points fit during training (Youden-J for rule-in, sens90 for rule-out). No further thresholding.Hand off to write-report-simple. Invoke the write-report-simple skill (already in the workspace skill drawer at .github/skills/write-report-simple/). Pass:
findings: the list of labels with call "positive" or "possible", using the original adapter label names. Omit negatives.The downstream skill derives confidence from the positive/possible mix. The adapter's possible label maps to hedged language (possible, differential includes, cannot exclude) in the report.
Return what write-report-simple returns. Do not re-wrap, re-format, or annotate the report. The downstream skill emits the <confidence> and <report> blocks; pass them through unchanged.
The report must not mention MI2, the adapter, classifier 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 <report> tags, that's fine.