{"id":"7329438c-21d9-4b7e-97ec-e6d342be80d8","entityType":"agent","slug":"clawhub-unisound-llm-med-critical-disease-review","name":"med-critical-disease-review","canonicalUrl":"https://www.xpersona.co/agent/clawhub-unisound-llm-med-critical-disease-review","canonicalPath":"/agent/clawhub-unisound-llm-med-critical-disease-review","generatedAt":"2026-10-14T00:24:13.964Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T22:53:06.148Z","emptyReason":null},"description":"重大疾病理赔智能评估（支持 28 种病种）。输入住院病历结构化数据，调用内网评估接口，输出原始 JSON 与自然语言结论（结论 + 证据）。 Skill: med-critical-disease-review Owner: unisound-llm Summary: 重大疾病理赔智能评估（支持 28 种病种）。输入住院病历结构化数据，调用内网评估接口，输出原始 JSON 与自然语言结论（结论 + 证据）。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-07-16T06:07:59.548Z | user - 更新评估服务 API 地址与鉴权方式，现需通过 Authorization: Bearer <LLM_API_KEY> 请求头访问新接口域名 https://skills-medical.hivoice.cn - 输入字段建议规范化，移除原始接口特有参数，补充病例标识字段说明 - 明确接口响应判定与常见错误提示，完善判定流程说明 - 参数列表中新增 --appkey（必填）与 --base，调整说明顺序 -","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 981 downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s1770nyybxj4gn0vk38n6wr6k584x8ea:med-critical-disease-review","sourceUrl":"https://clawhub.ai/unisound-llm/med-critical-disease-review","homepage":"https://clawhub.ai/unisound-llm/skills/med-critical-disease-review","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/unisound-llm/med-critical-disease-review","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/unisound-llm/skills/med-critical-disease-review","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"重大疾病理赔智能评估（支持 28 种病种）。输入住院病历结构化数据，调用内网评估接口，输出原始 JSON 与自然语言结论（结论 + 证据）。 Skill: med-critical-disease-review Owner: unisound-llm Summary: 重大疾病理赔智能评估（支持 28 种病种）。输入住"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T22:53:06.148Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T22:53:06.148Z","emptyReason":null},"stars":null,"forks":null,"downloads":981,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.0.2","tractionLabel":"981 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T22:53:06.141Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T22:53:06.148Z","lastCrawledAt":"2026-10-11T22:53:06.141Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T22:53:06.141Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.2","createdAt":"2026-07-16T06:07:59.548Z","changelog":"- 更新评估服务 API 地址与鉴权方式，现需通过 `Authorization: Bearer <LLM_API_KEY>` 请求头访问新接口域名 `https://skills-medical.hivoice.cn` - 输入字段建议规范化，移除原始接口特有参数，补充病例标识字段说明 - 明确接口响应判定与常见错误提示，完善判定流程说明 - 参数列表中新增 `--appkey`（必填）与 `--base`，调整说明顺序 - 明确依赖说明，新增对 `_shared/doc-preprocess` 的软依赖说明 - 移除多余的 skill-card.md 文件","fileCount":6,"zipByteSize":13633},{"version":"1.0.1","createdAt":"2026-04-24T03:28:15.734Z","changelog":"- 新增统一入口脚本 `scripts/run.py`，支持直接处理多种主流文件格式（pdf/doc/docx/xls/xlsx/csv/txt/json）。 - SKILL.md 增加输入多格式自动归一化与统一运行入口说明。 - 更新依赖与外部工具说明，覆盖新格式支持（如 openpyxl、pypdf、LibreOffice、pdftotext、tesseract）。 - 兼容原有 `medicalRecord` JSON 入口，功能无迁移门槛。","fileCount":6,"zipByteSize":15157},{"version":"1.0.0","createdAt":"2026-04-16T08:37:15.883Z","changelog":"med-critical-disease-review 1.0.0 - Initial release. - Provides intelligent major disease claim assessment for 28 disease types based on structured inpatient medical records. - Outputs both original JSON results and natural language conclusions with supporting evidence. - Enforces strict data privacy: de-identifies all sensitive information, processes data in-memory, and avoids local persistence. - Includes minimal input validation before assessment. - Command-line interface supports disease selection, input/output file specification, and timeout configuration.","fileCount":4,"zipByteSize":7078}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s1770nyybxj4gn0vk38n6wr6k584x8ea:med-critical-disease-review","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-med-critical-disease-review/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-med-critical-disease-review/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-med-critical-disease-review/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-med-critical-disease-review/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-med-critical-disease-review/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-med-critical-disease-review/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-14T00:24:13.964Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-med-critical-disease-review/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-med-critical-disease-review/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-med-critical-disease-review/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-med-critical-disease-review/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T22:53:06.148Z","emptyReason":null},"readme":"Skill: med-critical-disease-review\n\nOwner: unisound-llm\n\nSummary: 重大疾病理赔智能评估（支持 28 种病种）。输入住院病历结构化数据，调用内网评估接口，输出原始 JSON 与自然语言结论（结论 + 证据）。\n\nTags: latest:1.0.2\n\nVersion history:\n\nv1.0.2 | 2026-07-16T06:07:59.548Z | user\n\n- 更新评估服务 API 地址与鉴权方式，现需通过 `Authorization: Bearer <LLM_API_KEY>` 请求头访问新接口域名 `https://skills-medical.hivoice.cn`\n- 输入字段建议规范化，移除原始接口特有参数，补充病例标识字段说明\n- 明确接口响应判定与常见错误提示，完善判定流程说明\n- 参数列表中新增 `--appkey`（必填）与 `--base`，调整说明顺序\n- 明确依赖说明，新增对 `_shared/doc-preprocess` 的软依赖说明\n- 移除多余的 skill-card.md 文件\n\nv1.0.1 | 2026-04-24T03:28:15.734Z | user\n\n- 新增统一入口脚本 `scripts/run.py`，支持直接处理多种主流文件格式（pdf/doc/docx/xls/xlsx/csv/txt/json）。\n- SKILL.md 增加输入多格式自动归一化与统一运行入口说明。\n- 更新依赖与外部工具说明，覆盖新格式支持（如 openpyxl、pypdf、LibreOffice、pdftotext、tesseract）。\n- 兼容原有 `medicalRecord` JSON 入口，功能无迁移门槛。\n\nv1.0.0 | 2026-04-16T08:37:15.883Z | user\n\nmed-critical-disease-review 1.0.0\n\n- Initial release.\n- Provides intelligent major disease claim assessment for 28 disease types based on structured inpatient medical records.\n- Outputs both original JSON results and natural language conclusions with supporting evidence.\n- Enforces strict data privacy: de-identifies all sensitive information, processes data in-memory, and avoids local persistence.\n- Includes minimal input validation before assessment.\n- Command-line interface supports disease selection, input/output file specification, and timeout configuration.\n\nArchive index:\n\nArchive v1.0.2: 6 files, 13633 bytes\n\nFiles: _meta.json (146b), scripts/format_assessment_nl.py (3236b), scripts/major_disease_assess.py (5497b), scripts/run.py (13104b), skill-card.md (2757b), SKILL.md (8476b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: med-critical-disease-review\ndescription: 重大疾病理赔智能评估（支持 28 种病种）。输入住院病历结构化数据，调用内网评估接口，输出原始 JSON 与自然语言结论（结论 + 证据）。\nmetadata:\n  {\n    \"openclaw\":\n      {\n        \"emoji\": \"🏥\"\n      }\n  }\n---\n\n# 重大疾病理赔评估\n\n概述\n----\n给定一份住院病历（结构化 `medicalRecord`，含诊断/文书等），本技能调用内网评估服务，对 **任意重大疾病病种** 进行判定，并返回：\n\n- **最终结论**：符合/不符合（来自 `final_result`）\n- **原因与证据**：按条件逐条给出 evidence（可带来源 source）\n- **原始结果**：接口返回的完整 JSON（便于追溯与二次加工）\n\n数据安全、隐私与伦理声明\n------------------------\n- **最小必要原则**：仅处理完成评估所必需的数据字段；不要求提供与评估无关的身份信息。\n- **严格脱敏**：在发送至任何模型/接口前，会对可识别个人身份的信息进行脱敏/去标识化处理（如姓名、证件号、手机号、详细地址、人脸/影像等）。仅传递脱敏后的必要信息用于本次 skill 调用。\n- **不做本地持久化**：不将用户输入与中间结果写入本地持久化存储（包含磁盘文件、数据库、日志）。仅在内存中短暂处理；**本次调用结束即销毁**。\n- **第三方 API 风险提示**：在功能需要时，可能会调用第三方模型/服务接口；此时仅会发送**脱敏后的必要信息**，并使用加密传输。除完成本次请求外，不用于任何其他用途（如训练、画像、营销）。\n- **医疗边界**：本技能输出为理赔条款/条件匹配与证据整理的辅助信息，不构成医疗诊断或治疗建议；如涉及临床判断请以执业医生意见为准。\n\n支持病种（28）\n--------------\n- 心脏瓣膜手术：`heart_valve_surgery`\n- 主动脉手术：`aortic_surgery`\n- 冠状动脉搭桥术：`coronary_artery_bypass`\n- 重大器官或造血干细胞移植术：`major_organ_transplant`\n- 恶性肿瘤——重度：`malignant_tumor`\n- 严重慢性肾衰竭：`severe_chronic_kidney_failure`\n- 严重慢性肝衰竭：`severe_chronic_liver_failure`\n- 急性重症肝炎或亚急性重症肝炎：`acute_severe_hepatitis`\n- 严重慢性呼吸衰竭：`severe_chronic_respiratory_failure`\n- 严重特发性肺动脉高压：`severe_idiopathic_pulmonary_hypertension`\n- 严重脑损伤：`severe_brain_injury`\n- 深度昏迷：`deep_coma`\n- 严重脑中风后遗症：`severe_stroke_sequelae`\n- 严重阿尔茨海默病：`severe_alzheimers_disease`\n- 严重原发性帕金森病：`severe_primary_parkinsons_disease`\n- 严重运动神经元病：`severe_motor_neuron_disease`\n- 严重脑炎后遗症或严重脑膜炎后遗症：`severe_brain_encephalitis_sequelae`\n- 严重非恶性颅内肿瘤：`severe_non_malignant_intracranial_tumor`\n- 瘫痪：`paralysis`\n- 双耳失聪：`bilateral_deafness`\n- 双目失明：`bilateral_blindness`\n- 语言能力丧失：`language_ability_loss`\n- 严重克罗恩病：`severe_crohn_disease`\n- 严重溃疡性结肠炎：`severe_ulcerative_colitis`\n- 重型再生障碍性贫血：`severe_aplastic_anemia`\n- 较重急性心肌梗死：`moderate_acute_myocardial_infarction`\n- 严重Ⅲ度烧伤：`severe_third_degree_burn`\n- 多个肢体缺失：`multiple_limb_loss`\n\n输入格式\n--------\n请求为 JSON（示例见 `../data/med-major-disease-assess/req_data.json`），推荐使用以下结构：\n\n- `medicalRecord`：病历结构化对象\n  - `hospitalId` / `admissionId`：可选，病例标识\n  - `mainDiagName` / `otherDiagName`：诊断信息（字符串/JSON 字符串均可）\n  - `docs`：文书列表（推荐每个 doc 含 `docName`、`nodes`、`format_page_text`）\n\n也支持通过统一入口 `scripts/run.py` 直接输入 `pdf/doc/docx/xls/xlsx/csv/txt/json`。\n预处理成功后，会先归一化为最小可用的 `medicalRecord.docs[]` JSON，再调用本 skill 的原始评估逻辑。\n\n最小校验（先校验，再审核）\n--------------------------\n脚本会先对入参做最小结构校验，校验通过后才会调用审核接口：\n- 请求体必须是 JSON object\n- 必须包含 `medicalRecord`（object）\n- `medicalRecord.docs` 必须是非空数组\n\n后端接口\n--------\n- Base URL：`https://skills-medical.hivoice.cn`\n- 方法：`POST`\n- 路径：`/api/v1/assessment/assess/{disease}`\n- 鉴权请求头：\n  - `Authorization: Bearer <LLM_API_KEY>`\n  - `Content-Type: application/json`\n- 成功判定：\n  - HTTP 200 且 `success=true`：请求处理成功（不代表一定理赔通过）\n  - 业务结论看 `result.final_result.satisfied`：\n    - `true`：满足条件\n    - `false`：不满足，原因见 `result.final_result.reason`\n- 常见错误：\n  - `401`：缺少或错误的 `Authorization: Bearer <api_key>`\n  - `200 + success=false`：业务处理失败，详见 `error`\n\n快速开始\n--------\n\n```bash\n# 在本目录下运行（统一入口）\npython3 scripts/run.py \\\n  --disease aortic_surgery \\\n  --appkey <LLM_API_KEY> \\\n  --input ../data/med-major-disease-assess/req_data.json\n\n# 或继续直接使用原始 medicalRecord JSON 入口\npython3 scripts/major_disease_assess.py \\\n  --disease aortic_surgery \\\n  --appkey <LLM_API_KEY> \\\n  --input ../data/med-major-disease-assess/req_data.json\n```\n\n参数说明\n--------\n- `--disease STRING`\n  - 病种类型（如：`aortic_surgery`、`heart_valve_surgery` 等）。\n- `--appkey STRING`\n  - **必填**。接口鉴权 key，请通过 `Authorization: Bearer <api_key>` 传递。\n- `--input PATH`\n  - 输入请求 JSON 路径（UTF-8）。\n- `--output-json PATH`\n  - 保存接口原始返回 JSON（默认：`../runs/med-major-disease-assess/{disease}_resp.json`）。\n- `--output-text PATH`\n  - 保存自然语言结论文本（默认：`../runs/med-major-disease-assess/{disease}_resp.txt`）。\n- `--base URL`\n  - 评估接口 base URL（默认：`https://skills-medical.hivoice.cn`）。\n- `--timeout SECONDS`\n  - HTTP 超时秒数（默认：60）。\n\n统一入口附加参数（`scripts/run.py`）\n----------------------------------\n- `--input-type auto|pdf|doc|docx|xls|xlsx|csv|txt|json`\n  - 输入类型；默认 `auto`。\n- `--sheet STRING`\n  - 读取 Excel 时指定 sheet（可选）。\n- `--encoding STRING`\n  - `txt/csv` 编码（默认：`utf-8`）。\n- `--save-prepared`\n  - 保存预处理后的 `medicalRecord` JSON，便于调试。\n\n输出约定\n--------\n- 若指定输出路径的父目录不存在，会自动创建。\n- 自然语言输出默认包含：\n  - 结论（符合/不符合）\n  - 原因（`final_result.reason`）\n  - 逐条条件的证据（`conditions[*].evidence`，并附 `source/description`）\n\n依赖\n----\n### 前置 Skill\n本 skill 的 `scripts/run.py` 依赖 **`_shared/doc-preprocess`** 提供的公共文件预处理库（`preprocess.py`）。\n请确保 `_shared/doc-preprocess/` 位于 `skills/` 根目录下。\n\n### 运行环境\n- Python 3.7+\n\n### 外部 API\n- 后端评估服务：`https://skills-medical.hivoice.cn/api/v1/assessment/assess/{disease}`\n  - 方法：POST\n  - 请求头必须包含：\n    - `Authorization: Bearer <LLM_API_KEY>`\n    - `Content-Type: application/json`\n\n### Python 第三方包（可选，按输入格式需要）\n| 包名 | 用途 | 必要条件 |\n|------|------|---------|\n| `openpyxl` | 读取 `.xlsx` 文件 | 输入为 xlsx 时必须 |\n| `pypdf` | 提取 PDF 文本 | 输入为 pdf 时必须（或用 pdftotext 替代） |\n\n安装：`pip install openpyxl pypdf`\n\n### 外部工具（可选，按输入格式需要）\n| 工具 | 用途 | 必要条件 |\n|------|------|---------|\n| LibreOffice (`soffice`) | 转换 `.doc` / `.xls` 为文本 | 输入为 doc/xls 时必须 |\n| `pdftotext`（poppler-utils） | 提取 PDF 文本 | 输入为 pdf 且未安装 pypdf 时必须 |\n| `tesseract`（含 chi_sim+eng 语言包） | 图片 OCR | 输入为 png/jpg/bmp/tif 等图片时必须 |\n\n安装（Ubuntu/Debian）：`sudo apt-get install libreoffice poppler-utils tesseract-ocr tesseract-ocr-chi-sim`\n\n> 仅使用 JSON 输入时，无需安装任何第三方包或外部工具。\n\n备注\n----\n- **发布约束**：示例输入、运行输出、自测脚本均放在 skill 包外（分别位于 `../data/`、`../runs/`、`../self_tests/`），skill 目录内仅保留可发布的核心文件（`scripts/`、`SKILL.md`、`_meta.json`）。\n\nFile v1.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn7ft98qwhxyrgcy7b7rzdhrrd8366k6\",\n  \"slug\": \"med-critical-disease-review\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1784182079548\n}\n\nFile v1.0.2:skill-card.md\n\n## Description:\n\nAssesses structured inpatient medical records against 28 critical-disease insurance claim categories, calls a medical assessment API, and returns raw JSON plus a natural-language conclusion with evidence.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[unisound-llm](https://clawhub.ai/user/unisound-llm)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nClaims operations teams and developers use this skill to submit inpatient medical record data for critical-disease insurance review and produce a conclusion, reasons, and evidence for downstream review. The skill is an insurance-criteria assessment aid and is not a medical diagnosis or treatment tool.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The security review says the skill handles sensitive medical records and has misleading privacy and persistence claims.\n\nMitigation: Install only where operators are authorized to send records to the documented assessment service, and clarify de-identification, retention, endpoint allowlisting, credential handling, and output-file protections before using real patient data.\n\nRisk: The skill stores raw API responses and natural-language assessment results as local files by default.\n\nMitigation: Use controlled output paths, restrict access to generated files, and avoid storing real patient data unless local storage controls are approved.\n\nRisk: The assessment service requires an API credential for `Authorization: Bearer <LLM_API_KEY>`.\n\nMitigation: Provide credentials through an approved secret-handling process, avoid hard-coding keys, and limit access to authorized operators.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/unisound-llm/skills/med-critical-disease-review)\n- [Publisher profile](https://clawhub.ai/user/unisound-llm)\n- [Assessment service base URL](https://skills-medical.hivoice.cn)\n- [Assessment API endpoint](https://skills-medical.hivoice.cn/api/v1/assessment/assess/{disease})\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with shell commands; runtime outputs are raw JSON and natural-language text files.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires a disease identifier, an input medical-record artifact or JSON payload, and an API key for the assessment service.]\n\n## Skill Version(s):\n\n1.0.2 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.0.1: 6 files, 15157 bytes\n\nFiles: _meta.json (146b), scripts/format_assessment_nl.py (3236b), scripts/major_disease_assess.py (5403b), scripts/run.py (19953b), skill-card.md (2739b), SKILL.md (7574b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: med-critical-disease-review\ndescription: 重大疾病理赔智能评估（支持 28 种病种）。输入住院病历结构化数据，调用内网评估接口，输出原始 JSON 与自然语言结论（结论 + 证据）。\nmetadata:\n  {\n    \"openclaw\":\n      {\n        \"emoji\": \"🏥\"\n      }\n  }\n---\n\n# 重大疾病理赔评估\n\n概述\n----\n给定一份住院病历（结构化 `medicalRecord`，含诊断/文书等），本技能调用内网评估服务，对 **任意重大疾病病种** 进行判定，并返回：\n\n- **最终结论**：符合/不符合（来自 `final_result`）\n- **原因与证据**：按条件逐条给出 evidence（可带来源 source）\n- **原始结果**：接口返回的完整 JSON（便于追溯与二次加工）\n\n数据安全、隐私与伦理声明\n------------------------\n- **最小必要原则**：仅处理完成评估所必需的数据字段；不要求提供与评估无关的身份信息。\n- **严格脱敏**：在发送至任何模型/接口前，会对可识别个人身份的信息进行脱敏/去标识化处理（如姓名、证件号、手机号、详细地址、人脸/影像等）。仅传递脱敏后的必要信息用于本次 skill 调用。\n- **不做本地持久化**：不将用户输入与中间结果写入本地持久化存储（包含磁盘文件、数据库、日志）。仅在内存中短暂处理；**本次调用结束即销毁**。\n- **第三方 API 风险提示**：在功能需要时，可能会调用第三方模型/服务接口；此时仅会发送**脱敏后的必要信息**，并使用加密传输。除完成本次请求外，不用于任何其他用途（如训练、画像、营销）。\n- **医疗边界**：本技能输出为理赔条款/条件匹配与证据整理的辅助信息，不构成医疗诊断或治疗建议；如涉及临床判断请以执业医生意见为准。\n\n支持病种（28）\n--------------\n- 心脏瓣膜手术：`heart_valve_surgery`\n- 主动脉手术：`aortic_surgery`\n- 冠状动脉搭桥术：`coronary_artery_bypass`\n- 重大器官或造血干细胞移植术：`major_organ_transplant`\n- 恶性肿瘤——重度：`malignant_tumor`\n- 严重慢性肾衰竭：`severe_chronic_kidney_failure`\n- 严重慢性肝衰竭：`severe_chronic_liver_failure`\n- 急性重症肝炎或亚急性重症肝炎：`acute_severe_hepatitis`\n- 严重慢性呼吸衰竭：`severe_chronic_respiratory_failure`\n- 严重特发性肺动脉高压：`severe_idiopathic_pulmonary_hypertension`\n- 严重脑损伤：`severe_brain_injury`\n- 深度昏迷：`deep_coma`\n- 严重脑中风后遗症：`severe_stroke_sequelae`\n- 严重阿尔茨海默病：`severe_alzheimers_disease`\n- 严重原发性帕金森病：`severe_primary_parkinsons_disease`\n- 严重运动神经元病：`severe_motor_neuron_disease`\n- 严重脑炎后遗症或严重脑膜炎后遗症：`severe_brain_encephalitis_sequelae`\n- 严重非恶性颅内肿瘤：`severe_non_malignant_intracranial_tumor`\n- 瘫痪：`paralysis`\n- 双耳失聪：`bilateral_deafness`\n- 双目失明：`bilateral_blindness`\n- 语言能力丧失：`language_ability_loss`\n- 严重克罗恩病：`severe_crohn_disease`\n- 严重溃疡性结肠炎：`severe_ulcerative_colitis`\n- 重型再生障碍性贫血：`severe_aplastic_anemia`\n- 较重急性心肌梗死：`moderate_acute_myocardial_infarction`\n- 严重Ⅲ度烧伤：`severe_third_degree_burn`\n- 多个肢体缺失：`multiple_limb_loss`\n\n输入格式\n--------\n请求为 JSON（示例见 `../data/med-major-disease-assess/req_data.json`），最少需要包含：\n\n- `medicalRecord`：病历结构化对象\n  - `mainDiagName` / `otherDiagName`：诊断信息（字符串/JSON 字符串均可）\n  - `docs`：文书列表（每个 doc 至少包含 `docType` 与文本字段，如 `format_page_text`）\n\n也支持通过统一入口 `scripts/run.py` 直接输入 `pdf/doc/docx/xls/xlsx/csv/txt/json`。\n预处理成功后，会先归一化为最小可用的 `medicalRecord.docs[]` JSON，再调用本 skill 的原始评估逻辑。\n\n最小校验（先校验，再审核）\n--------------------------\n脚本会先对入参做最小结构校验，校验通过后才会调用审核接口：\n- 请求体必须是 JSON object\n- 必须包含 `medicalRecord`（object）\n- `medicalRecord.docs` 必须是非空数组\n- `docs` 中至少一项包含 `docType`\n\n后端接口\n--------\n- HTTP API：`http://10.10.20.15:9010/api/v1/assessment/assess/{disease}?model_type=qwq`\n- Content-Type：`application/json`\n\n快速开始\n--------\n\n```bash\n# 在本目录下运行（统一入口）\npython3 scripts/run.py \\\n  --disease aortic_surgery \\\n  --input ../data/med-major-disease-assess/req_data.json\n\n# 或继续直接使用原始 medicalRecord JSON 入口\npython3 scripts/major_disease_assess.py \\\n  --disease aortic_surgery \\\n  --input ../data/med-major-disease-assess/req_data.json\n```\n\n参数说明\n--------\n- `--disease STRING`\n  - 病种类型（如：`aortic_surgery`、`heart_valve_surgery` 等）。\n- `--input PATH`\n  - 输入请求 JSON 路径（UTF-8）。\n- `--output-json PATH`\n  - 保存接口原始返回 JSON（默认：`../runs/med-major-disease-assess/{disease}_resp.json`）。\n- `--output-text PATH`\n  - 保存自然语言结论文本（默认：`../runs/med-major-disease-assess/{disease}_resp.txt`）。\n- `--model-type STRING`\n  - 查询参数 `model_type`（默认：`qwq`）。\n- `--timeout SECONDS`\n  - HTTP 超时秒数（默认：60）。\n\n统一入口附加参数（`scripts/run.py`）\n----------------------------------\n- `--input-type auto|pdf|doc|docx|xls|xlsx|csv|txt|json`\n  - 输入类型；默认 `auto`。\n- `--sheet STRING`\n  - 读取 Excel 时指定 sheet（可选）。\n- `--encoding STRING`\n  - `txt/csv` 编码（默认：`utf-8`）。\n- `--save-prepared`\n  - 保存预处理后的 `medicalRecord` JSON，便于调试。\n\n输出约定\n--------\n- 若指定输出路径的父目录不存在，会自动创建。\n- 自然语言输出默认包含：\n  - 结论（符合/不符合）\n  - 原因（`final_result.reason`）\n  - 逐条条件的证据（`conditions[*].evidence`，并附 `source/description`）\n\n依赖\n----\n### 运行环境\n- Python 3.7+\n\n### 外部 API\n- 后端评估服务：`https://shangbao.yunzhisheng.cn/skills/critical-disease/api/v1/assessment/assess/{disease}`\n  - 方法：POST，Content-Type: application/json\n  - 需要网络访问 `shangbao.yunzhisheng.cn`\n\n### Python 第三方包（可选，按输入格式需要）\n| 包名 | 用途 | 必要条件 |\n|------|------|---------|\n| `openpyxl` | 读取 `.xlsx` 文件 | 输入为 xlsx 时必须 |\n| `pypdf` | 提取 PDF 文本 | 输入为 pdf 时必须（或用 pdftotext 替代） |\n\n安装：`pip install openpyxl pypdf`\n\n### 外部工具（可选，按输入格式需要）\n| 工具 | 用途 | 必要条件 |\n|------|------|---------|\n| LibreOffice (`soffice`) | 转换 `.doc` / `.xls` 为文本 | 输入为 doc/xls 时必须 |\n| `pdftotext`（poppler-utils） | 提取 PDF 文本 | 输入为 pdf 且未安装 pypdf 时必须 |\n| `tesseract`（含 chi_sim+eng 语言包） | 图片 OCR | 输入为 png/jpg/bmp/tif 等图片时必须 |\n\n安装（Ubuntu/Debian）：`sudo apt-get install libreoffice poppler-utils tesseract-ocr tesseract-ocr-chi-sim`\n\n> 仅使用 JSON 输入时，无需安装任何第三方包或外部工具。\n\n备注\n----\n- **发布约束**：示例输入、运行输出、自测脚本均放在 skill 包外（分别位于 `../data/`、`../runs/`、`../self_tests/`），skill 目录内仅保留可发布的核心文件（`scripts/`、`SKILL.md`、`_meta.json`）。\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn7ft98qwhxyrgcy7b7rzdhrrd8366k6\",\n  \"slug\": \"med-critical-disease-review\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1777001295734\n}\n\nFile v1.0.1:skill-card.md\n\n## Description: <br>\nAssesses structured inpatient medical records against 28 critical-disease insurance claim categories by calling a remote assessment service and producing raw JSON plus a natural-language conclusion with evidence. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[unisound-llm](https://clawhub.ai/user/unisound-llm) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nClaims reviewers and insurance operations teams use this skill to prepare evidence-backed critical-disease claim assessments from inpatient medical records. Developers can run the bundled scripts to normalize common record formats before submitting a supported disease review. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Medical-record contents may be sent to a remote assessment service, and the security evidence says the skill's privacy promises do not match the code behavior. <br>\nMitigation: Use only records you are authorized to process, confirm the remote service's privacy and retention terms, and de-identify sensitive information before running the skill. <br>\nRisk: The scripts can write raw assessment JSON, text summaries, and optional prepared medical-record payloads to local output paths. <br>\nMitigation: Choose controlled output locations, restrict access to generated files, and delete outputs that are no longer needed. <br>\nRisk: The assessment output supports insurance claim review and could be mistaken for clinical advice. <br>\nMitigation: Use the output as claim-evidence assistance only; route medical diagnosis or treatment questions to qualified clinicians. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/unisound-llm/med-critical-disease-review) <br>\n- [Critical-disease assessment API endpoint](https://shangbao.yunzhisheng.cn/skills/critical-disease/api/v1/assessment/assess/{disease}) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Analysis, Text, JSON, Files] <br>\n**Output Format:** [Raw JSON response and natural-language text summary, written to files or printed as a preview.] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Requires a supported disease code and medical-record input; optional preprocessing supports JSON, PDF, Office documents, spreadsheets, CSV, text, and image inputs.] <br>\n\n## Skill Version(s): <br>\n1.0.1 (source: server release metadata) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.0: 4 files, 7078 bytes\n\nFiles: _meta.json (146b), scripts/format_assessment_nl.py (3236b), scripts/major_disease_assess.py (5403b), SKILL.md (5567b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: med-critical-disease-review\ndescription: 重大疾病理赔智能评估（支持 28 种病种）。输入住院病历结构化数据，调用内网评估接口，输出原始 JSON 与自然语言结论（结论 + 证据）。\nmetadata:\n  {\n    \"openclaw\":\n      {\n        \"emoji\": \"🏥\"\n      }\n  }\n---\n\n# 重大疾病理赔评估\n\n概述\n----\n给定一份住院病历（结构化 `medicalRecord`，含诊断/文书等），本技能调用内网评估服务，对 **任意重大疾病病种** 进行判定，并返回：\n\n- **最终结论**：符合/不符合（来自 `final_result`）\n- **原因与证据**：按条件逐条给出 evidence（可带来源 source）\n- **原始结果**：接口返回的完整 JSON（便于追溯与二次加工）\n\n数据安全、隐私与伦理声明\n------------------------\n- **最小必要原则**：仅处理完成评估所必需的数据字段；不要求提供与评估无关的身份信息。\n- **严格脱敏**：在发送至任何模型/接口前，会对可识别个人身份的信息进行脱敏/去标识化处理（如姓名、证件号、手机号、详细地址、人脸/影像等）。仅传递脱敏后的必要信息用于本次 skill 调用。\n- **不做本地持久化**：不将用户输入与中间结果写入本地持久化存储（包含磁盘文件、数据库、日志）。仅在内存中短暂处理；**本次调用结束即销毁**。\n- **第三方 API 风险提示**：在功能需要时，可能会调用第三方模型/服务接口；此时仅会发送**脱敏后的必要信息**，并使用加密传输。除完成本次请求外，不用于任何其他用途（如训练、画像、营销）。\n- **医疗边界**：本技能输出为理赔条款/条件匹配与证据整理的辅助信息，不构成医疗诊断或治疗建议；如涉及临床判断请以执业医生意见为准。\n\n支持病种（28）\n--------------\n- 心脏瓣膜手术：`heart_valve_surgery`\n- 主动脉手术：`aortic_surgery`\n- 冠状动脉搭桥术：`coronary_artery_bypass`\n- 重大器官或造血干细胞移植术：`major_organ_transplant`\n- 恶性肿瘤——重度：`malignant_tumor`\n- 严重慢性肾衰竭：`severe_chronic_kidney_failure`\n- 严重慢性肝衰竭：`severe_chronic_liver_failure`\n- 急性重症肝炎或亚急性重症肝炎：`acute_severe_hepatitis`\n- 严重慢性呼吸衰竭：`severe_chronic_respiratory_failure`\n- 严重特发性肺动脉高压：`severe_idiopathic_pulmonary_hypertension`\n- 严重脑损伤：`severe_brain_injury`\n- 深度昏迷：`deep_coma`\n- 严重脑中风后遗症：`severe_stroke_sequelae`\n- 严重阿尔茨海默病：`severe_alzheimers_disease`\n- 严重原发性帕金森病：`severe_primary_parkinsons_disease`\n- 严重运动神经元病：`severe_motor_neuron_disease`\n- 严重脑炎后遗症或严重脑膜炎后遗症：`severe_brain_encephalitis_sequelae`\n- 严重非恶性颅内肿瘤：`severe_non_malignant_intracranial_tumor`\n- 瘫痪：`paralysis`\n- 双耳失聪：`bilateral_deafness`\n- 双目失明：`bilateral_blindness`\n- 语言能力丧失：`language_ability_loss`\n- 严重克罗恩病：`severe_crohn_disease`\n- 严重溃疡性结肠炎：`severe_ulcerative_colitis`\n- 重型再生障碍性贫血：`severe_aplastic_anemia`\n- 较重急性心肌梗死：`moderate_acute_myocardial_infarction`\n- 严重Ⅲ度烧伤：`severe_third_degree_burn`\n- 多个肢体缺失：`multiple_limb_loss`\n\n输入格式\n--------\n请求为 JSON（示例见 `../data/med-major-disease-assess/req_data.json`），最少需要包含：\n\n- `medicalRecord`：病历结构化对象\n  - `mainDiagName` / `otherDiagName`：诊断信息（字符串/JSON 字符串均可）\n  - `docs`：文书列表（每个 doc 至少包含 `docType` 与文本字段，如 `format_page_text`）\n\n最小校验（先校验，再审核）\n--------------------------\n脚本会先对入参做最小结构校验，校验通过后才会调用审核接口：\n- 请求体必须是 JSON object\n- 必须包含 `medicalRecord`（object）\n- `medicalRecord.docs` 必须是非空数组\n- `docs` 中至少一项包含 `docType`\n\n后端接口\n--------\n- HTTP API：`http://10.10.20.15:9010/api/v1/assessment/assess/{disease}?model_type=qwq`\n- Content-Type：`application/json`\n\n快速开始\n--------\n\n```bash\n# 在本目录下运行\npython3 scripts/major_disease_assess.py \\\n  --disease aortic_surgery \\\n  --input ../data/med-major-disease-assess/req_data.json\n```\n\n参数说明\n--------\n- `--disease STRING`\n  - 病种类型（如：`aortic_surgery`、`heart_valve_surgery` 等）。\n- `--input PATH`\n  - 输入请求 JSON 路径（UTF-8）。\n- `--output-json PATH`\n  - 保存接口原始返回 JSON（默认：`../runs/med-major-disease-assess/{disease}_resp.json`）。\n- `--output-text PATH`\n  - 保存自然语言结论文本（默认：`../runs/med-major-disease-assess/{disease}_resp.txt`）。\n- `--model-type STRING`\n  - 查询参数 `model_type`（默认：`qwq`）。\n- `--timeout SECONDS`\n  - HTTP 超时秒数（默认：60）。\n\n输出约定\n--------\n- 若指定输出路径的父目录不存在，会自动创建。\n- 自然语言输出默认包含：\n  - 结论（符合/不符合）\n  - 原因（`final_result.reason`）\n  - 逐条条件的证据（`conditions[*].evidence`，并附 `source/description`）\n\n备注\n----\n- **发布约束**：示例输入、运行输出、自测脚本均放在 skill 包外（分别位于 `../data/`、`../runs/`、`../self_tests/`），skill 目录内仅保留可发布的核心文件（`scripts/`、`SKILL.md`、`_meta.json`）。\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn7ft98qwhxyrgcy7b7rzdhrrd8366k6\",\n  \"slug\": \"med-critical-disease-review\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1776328635883\n}","readmeExcerpt":"Skill: med-critical-disease-review Owner: unisound-llm Summary: 重大疾病理赔智能评估（支持 28 种病种）。输入住院病历结构化数据，调用内网评估接口，输出原始 JSON 与自然语言结论（结论 + 证据）。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-07-16T06:07:59.548Z | user - 更新评估服务 API 地址与鉴权方式，现需通过 Authorization: Bearer <LLM_API_KEY> 请求头访问新接口域名 https://skills-medical.hivoice.cn - 输入字段建议规范化，移除原始接口特有参数，补充病例标识字段说明 - 明确接口响应判定与常见错误提示，完善判定流程说明 - 参数列表中新增 --appkey（必填）与 --base，调整说明顺序 - ","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"# 在本目录下运行（统一入口）\npython3 scripts/run.py \\\n  --disease aortic_surgery \\\n  --appkey <LLM_API_KEY> \\\n  --input ../data/med-major-disease-assess/req_data.json\n\n# 或继续直接使用原始 medicalRecord JSON 入口\npython3 scripts/major_disease_assess.py \\\n  --disease aortic_surgery \\\n  --appkey <LLM_API_KEY> \\\n  --input ../data/med-major-disease-assess/req_data.json"},{"language":"bash","snippet":"# 在本目录下运行（统一入口）\npython3 scripts/run.py \\\n  --disease aortic_surgery \\\n  --input ../data/med-major-disease-assess/req_data.json\n\n# 或继续直接使用原始 medicalRecord JSON 入口\npython3 scripts/major_disease_assess.py \\\n  --disease aortic_surgery \\\n  --input ../data/med-major-disease-assess/req_data.json"},{"language":"bash","snippet":"# 在本目录下运行\npython3 scripts/major_disease_assess.py \\\n  --disease aortic_surgery \\\n  --input ../data/med-major-disease-assess/req_data.json"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: med-critical-disease-review\ndescription: 重大疾病理赔智能评估（支持 28 种病种）。输入住院病历结构化数据，调用内网评估接口，输出原始 JSON 与自然语言结论（结论 + 证据）。\nmetadata:\n  {\n    \"openclaw\":\n      {\n        \"emoji\": \"🏥\"\n      }\n  }\n---\n\n# 重大疾病理赔评估\n\n概述\n----\n给定一份住院病历（结构化 `medicalRecord`，含诊断/文书等），本技能调用内网评估服务，对 **任意重大疾病病种** 进行判定，并返回：\n\n- **最终结论**：符合/不符合（来自 `final_result`）\n- **原因与证据**：按条件逐条给出 evidence（可带来源 source）\n- **原始结果**：接口返回的完整 JSON（便于追溯与二次加工）\n\n数据安全、隐私与伦理声明\n------------------------\n- **最小必要原则**：仅处理完成评估所必需的数据字段；不要求提供与评估无关的身份信息。\n- **严格脱敏**：在发送至任何模型/接口前，会对可识别个人身份的信息进行脱敏/去标识化处理（如姓名、证件号、手机号、详细地址、人脸/影像等）。仅传递脱敏后的必要信息用于本次 skill 调用。\n- **不做本地持久化**：不将用户输入与中间结果写入本地持久化存储（包含磁盘文件、数据库、日志）。仅在内存中短暂处理；**本次调用结束即销毁**。\n- **第三方 API 风险提示**：在功能需要时，可能会调用第三方模型/服务接口；此时仅会发送**脱敏后的必要信息**，并使用加密传输。除完成本次请求外，不用于任何其他用途（如训练、画像、营销）。\n- **医疗边界**：本技能输出为理赔条款/条件匹配与证据整理的辅助信息，不构成医疗诊断或治疗建议；如涉及临床判断请以执业医生意见为准。\n\n支持病种（28）\n--------------\n- 心脏瓣膜手术：`heart_valve_surgery`\n- 主动脉手术：`aortic_surgery`\n- 冠状动脉搭桥术：`coronary_artery_bypass`\n- 重大器官或造血干细胞移植术：`major_organ_transplant`\n- 恶性肿瘤——重度：`malignant_tumor`\n- 严重慢性肾衰竭：`severe_chronic_kidney_failure`\n- 严重慢性肝衰竭：`severe_chronic_liver_failure`\n- 急性重症肝炎或亚急性重症肝炎：`acute_severe_hepatitis`\n- 严重慢性呼吸衰竭：`severe_chronic_respiratory_failure`\n- 严重特发性肺动脉高压：`severe_idiopathic_pulmonary_hypertension`\n- 严重脑损伤：`severe_brain_injury`\n- 深度昏迷：`deep_coma`\n- 严重脑中风后遗症：`severe_stroke_sequelae`\n- 严重阿尔茨海默病：`severe_alzheimers_disease`\n- 严重原发性帕金森病：`severe_primary_parkinsons_disease`\n- 严重运动神经元病：`severe_motor_neuron_disease`\n- 严重脑炎后遗症或严重脑膜炎后遗症：`severe_brain_encephalitis_sequelae`\n- 严重非恶性颅内肿瘤：`severe_non_malignant_intracranial_tumor`\n- 瘫痪：`paralysis`\n- 双耳失聪：`bilateral_deafness`\n- 双目失明：`bilateral_blindness`\n- 语言能力丧失：`language_ability_loss`\n- 严重克罗恩病：`severe_crohn_disease`\n- 严重溃疡性结肠炎：`severe_ulcerative_colitis`\n- 重型再生障碍性贫血：`severe_aplastic_anemia`\n- 较重急性心肌梗死：`moderate_acute_myocardial_infarction`\n- 严重Ⅲ度烧伤：`severe_third_degree_burn`\n- 多个肢体缺失：`multiple_limb_loss`\n\n输入格式\n--------\n请求为 JSON（示例见 `../data/med-major-disease-assess/req_data.json`），推荐使用以下结构：\n\n- `medicalRecord`：病历结构化对象\n  - `hospitalId` / `admissionId`：可选，病例标识\n  - `mainDiagName` / `otherDiagName`：诊断信息（字符串/JSON 字符串均可）\n  - `docs`：文书列表（推荐每个 doc 含 `docName`、`nodes`、`format_page_text`）\n\n也支持通过统一入口 `scripts/run.py` 直接输入 `pdf/doc/docx/xls/xlsx/csv/txt/json`。\n预处理成功后，会先归一化为最小可用的 `medicalRecord.docs[]` JSON，再调用本 skill 的原始评估逻辑。\n\n最小校验（先校验，再审核）\n--------------------------\n脚本会先对入参做最小结构校验，校验通过后才会调用审核接口：\n- 请求体必须是 JSON object\n- 必须包含 `medicalRecord`（object）\n- `medicalRecord.docs` 必须是非空数组\n\n后端接口\n--------\n- Base URL：`https://skills-medical.hivoice.cn`\n- 方法：`POST`\n- 路径：`/api/v1/assessment/assess/{disease}`\n- 鉴权请求头：\n  - `Authorization: Bearer <LLM_API_KEY>`\n  - `Content-Type: application/json`\n- 成功判定：\n  - HTTP 200 且 `success=true`：请求处理成功（不代表一定理赔通过）\n  - 业务结论看 `result.final_result.satisfied`：\n    - `true`：满足条件\n    - `false`：不满足，原因见 `result.final_result.reason`\n- 常见错误：\n  - `401`：缺少或错误的 `Authorization: Bearer <api_key>`\n  - `200 + success=false`：业务处理失败，详见 `error`\n\n快速开始\n--------\n\n```bash\n# 在本目录下运行（统一入口）\npython"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7ft98qwhxyrgcy7b7rzdhrrd8366k6\",\n  \"slug\": \"med-critical-disease-review\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1784182079548\n}"},{"path":"skill-card.md","content":"## Description:\n\nAssesses structured inpatient medical records against 28 critical-disease insurance claim categories, calls a medical assessment API, and returns raw JSON plus a natural-language conclusion with evidence.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[unisound-llm](https://clawhub.ai/user/unisound-llm)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nClaims operations teams and developers use this skill to submit inpatient medical record data for critical-disease insurance review and produce a conclusion, reasons, and evidence for downstream review. The skill is an insurance-criteria assessment aid and is not a medical diagnosis or treatment tool.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The security review says the skill handles sensitive medical records and has misleading privacy and persistence claims.\n\nMitigation: Install only where operators are authorized to send records to the documented assessment service, and clarify de-identification, retention, endpoint allowlisting, credential handling, and output-file protections before using real patient data.\n\nRisk: The skill stores raw API responses and natural-language assessment results as local files by default.\n\nMitigation: Use controlled output paths, restrict access to generated files, and avoid storing real patient data unless local storage controls are approved.\n\nRisk: The assessment service requires an API credential for `Authorization: Bearer <LLM_API_KEY>`.\n\nMitigation: Provide credentials through an approved secret-handling process, avoid hard-coding keys, and limit access to authorized operators.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/unisound-llm/skills/med-critical-disease-review)\n- [Publisher profile](https://clawhub.ai/user/unisound-llm)\n- [Assessment service base URL](https://skills-medical.hivoice.cn)\n- [Assessment API endpoint](https://skills-medical.hivoice.cn/api/v1/assessment/assess/{disease})\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with shell commands; runtime outputs are raw JSON and natural-language text files.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires a disease identifier, an input medical-record artifact or JSON payload, and an API key for the assessment service.]\n\n## Skill Version(s):\n\n1.0.2 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"重大疾病理赔智能评估（支持 28 种病种）。输入住院病历结构化数据，调用内网评估接口，输出原始 JSON 与自然语言结论（结论 + 证据）。 Skill: med-critical-disease-review Owner: unisound-llm Summary: 重大疾病理赔智能评估（支持 28 种病种）。输入住院病历结构化数据，调用内网评估接口，输出原始 JSON 与自然语言结论（结论 + 证据）。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-07-16T06:07:59.548Z | user - 更新评估服务 API 地址与鉴权方式，现需通过 Authorization: Bearer <LLM_API_KEY> 请求头访问新接口域名 https://skills-medical.hivoice.cn - 输入字段建议规范化，移除原始接口特有参数，补充病例标识字段说明 - 明确接口响应判定与常见错误提示，完善判定流程说明 - 参数列表中新增 --appkey（必填）与 --base，调整说明顺序 -","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1011,"uniquenessScore":56,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T22:53:06.148Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T22:53:06.148Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-14T00:24:13.964Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}