{"id":"8d301c29-88c0-43bb-99b4-0ae0cd989020","entityType":"agent","slug":"clawhub-unisound-llm-med-chronic-disease-review","name":"med-chronic-disease-review","canonicalUrl":"https://www.xpersona.co/agent/clawhub-unisound-llm-med-chronic-disease-review","canonicalPath":"/agent/clawhub-unisound-llm-med-chronic-disease-review","generatedAt":"2026-10-13T23:45:56.637Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T18:58:51.794Z","emptyReason":null},"description":"门诊慢病审核（糖尿病/高血压）。输入 OCR 结果数组 JSON，由内部医疗大模型输出审核结论与原因（原始 JSON + 自然语言结论）。 Skill: med-chronic-disease-review Owner: unisound-llm Summary: 门诊慢病审核（糖尿病/高血压）。输入 OCR 结果数组 JSON，由内部医疗大模型输出审核结论与原因（原始 JSON + 自然语言结论）。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-07-16T06:06:28.455Z | user - 移除文档 skill-card.md，相关信息现由 SKILL.md 统一维护。 - 核心审核引擎由后端 API 改为内部医疗大模型，需通过 --appkey 参数鉴权。 - 调整预处理与推理链路，依赖 _shared/doc-preprocess 公共库，确保结构化 OCR 及文档支持。 - 命令行参数和调用方式更新，增加 --dry-run 用于本地链路校验。 - 文档精简与调整，突出依赖、输入输出格式，以及","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s1770nyybxj4gn0vk38n6wr6k584x8ea:med-chronic-disease-review","sourceUrl":"https://clawhub.ai/unisound-llm/med-chronic-disease-review","homepage":"https://clawhub.ai/unisound-llm/skills/med-chronic-disease-review","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/unisound-llm/med-chronic-disease-review","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/unisound-llm/skills/med-chronic-disease-review","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"门诊慢病审核（糖尿病/高血压）。输入 OCR 结果数组 JSON，由内部医疗大模型输出审核结论与原因（原始 JSON + 自然语言结论）。 Skill: med-chronic-disease-review Owner: unisound-llm Summary: 门诊慢病审核（糖尿病/高血压）。输入 OCR 结果数组"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T18:58:51.794Z","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":"2026-10-11T18:58:51.794Z","emptyReason":null},"stars":null,"forks":null,"downloads":1006,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.0.2","tractionLabel":"1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T18:58:51.781Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T18:58:51.794Z","lastCrawledAt":"2026-10-11T18:58:51.781Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T18:58:51.781Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.2","createdAt":"2026-07-16T06:06:28.455Z","changelog":"- 移除文档 skill-card.md，相关信息现由 SKILL.md 统一维护。 - 核心审核引擎由后端 API 改为内部医疗大模型，需通过 `--appkey` 参数鉴权。 - 调整预处理与推理链路，依赖 `_shared/doc-preprocess` 公共库，确保结构化 OCR 及文档支持。 - 命令行参数和调用方式更新，增加 `--dry-run` 用于本地链路校验。 - 文档精简与调整，突出依赖、输入输出格式，以及大模型接口调用说明。","fileCount":6,"zipByteSize":14578},{"version":"1.0.1","createdAt":"2026-04-24T03:27:42.799Z","changelog":"- 新增统一入口脚本 scripts/run.py，支持直接处理 pdf/doc/docx/xls/xlsx/csv/txt/json 等多种输入格式。 - 支持输入文件自动预处理归一化，无需手动生成 OCR 结果数组。 - SKILL.md 增加了多格式输入说明、依赖要求及工具安装指引。 - 保持向下兼容，原始 scripts/chronic_disease_review.py 接口仍可直接使用。 - 丰富参数说明与输出约定，便于初学者快速上手。","fileCount":6,"zipByteSize":14483},{"version":"1.0.0","createdAt":"2026-04-16T08:38:27.947Z","changelog":"- Initial release of med-chronic-disease-review skill for outpatient chronic disease review (diabetes/hypertension). - Given a JSON array of OCR results, outputs both original review JSON and a natural language summary (decision and reasoning). - Strong privacy controls: strict de-identification, no local persistence, minimum necessary data handling, and clear medical boundaries. - Flexible command-line interface supporting disease selection, custom input files, and export of both JSON and natural language results.","fileCount":4,"zipByteSize":6306}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s1770nyybxj4gn0vk38n6wr6k584x8ea:med-chronic-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-chronic-disease-review/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-med-chronic-disease-review/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-med-chronic-disease-review/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-med-chronic-disease-review/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-med-chronic-disease-review/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-med-chronic-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":"2026-10-13T23:45:56.637Z"}},"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-chronic-disease-review/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-med-chronic-disease-review/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-med-chronic-disease-review/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-med-chronic-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":"2026-10-11T18:58:51.794Z","emptyReason":null},"readme":"Skill: med-chronic-disease-review\n\nOwner: unisound-llm\n\nSummary: 门诊慢病审核（糖尿病/高血压）。输入 OCR 结果数组 JSON，由内部医疗大模型输出审核结论与原因（原始 JSON + 自然语言结论）。\n\nTags: latest:1.0.2\n\nVersion history:\n\nv1.0.2 | 2026-07-16T06:06:28.455Z | user\n\n- 移除文档 skill-card.md，相关信息现由 SKILL.md 统一维护。\n- 核心审核引擎由后端 API 改为内部医疗大模型，需通过 `--appkey` 参数鉴权。\n- 调整预处理与推理链路，依赖 `_shared/doc-preprocess` 公共库，确保结构化 OCR 及文档支持。\n- 命令行参数和调用方式更新，增加 `--dry-run` 用于本地链路校验。\n- 文档精简与调整，突出依赖、输入输出格式，以及大模型接口调用说明。\n\nv1.0.1 | 2026-04-24T03:27:42.799Z | user\n\n- 新增统一入口脚本 scripts/run.py，支持直接处理 pdf/doc/docx/xls/xlsx/csv/txt/json 等多种输入格式。\n- 支持输入文件自动预处理归一化，无需手动生成 OCR 结果数组。\n- SKILL.md 增加了多格式输入说明、依赖要求及工具安装指引。\n- 保持向下兼容，原始 scripts/chronic_disease_review.py 接口仍可直接使用。\n- 丰富参数说明与输出约定，便于初学者快速上手。\n\nv1.0.0 | 2026-04-16T08:38:27.947Z | user\n\n- Initial release of med-chronic-disease-review skill for outpatient chronic disease review (diabetes/hypertension).\n- Given a JSON array of OCR results, outputs both original review JSON and a natural language summary (decision and reasoning).\n- Strong privacy controls: strict de-identification, no local persistence, minimum necessary data handling, and clear medical boundaries.\n- Flexible command-line interface supporting disease selection, custom input files, and export of both JSON and natural language results.\n\nArchive index:\n\nArchive v1.0.2: 6 files, 14578 bytes\n\nFiles: _meta.json (145b), scripts/chronic_disease_review.py (10755b), scripts/format_review_nl.py (3390b), scripts/run.py (14248b), skill-card.md (2477b), SKILL.md (6606b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: med-chronic-disease-review\ndescription: 门诊慢病审核（糖尿病/高血压）。输入 OCR 结果数组 JSON，由内部医疗大模型输出审核结论与原因（原始 JSON + 自然语言结论）。\nmetadata:\n  {\n    \"openclaw\":\n      {\n        \"emoji\": \"🩺\"\n      }\n  }\n---\n\n# 门诊慢病审核\n\n概述\n----\n给定一份 OCR 结果数组（每项包含 `fileName/page/docType/ocrText`），本技能会：\n\n- 调用内部医疗大模型进行慢病审核推理\n- 输出结构化 JSON（含 `final_decision`、`reasoning`）\n- 输出自然语言摘要（结论 + 原因）\n\n数据安全、隐私与伦理声明\n------------------------\n- **最小必要原则**：仅处理审核所必需的文本内容；不要求也不鼓励提供与审核无关的身份信息。\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，会调用内部医疗大模型接口；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**：本技能输出为审核规则匹配与原因摘要的辅助信息，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输入格式\n--------\n输入必须是 JSON 数组（list），示例：\n\n```json\n[\n  {\"fileName\":\"xxx.pdf\",\"page\":1,\"docType\":\"出院记录\",\"ocrText\":\"...\"},\n  {\"fileName\":\"xxx.pdf\",\"page\":2,\"docType\":\"检验报告\",\"ocrText\":\"...\"}\n]\n```\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 `ocr_array.json`（每项含 `fileName/page/docType/ocrText`），再调用医疗大模型审核。\n\n快速开始\n--------\n从 `skills` 目录执行：\n\n```bash\n# 糖尿病\npython3 insurance/claims-review/chronic-disease/scripts/run.py \\\n  --disease-code diabetes \\\n  --appkey <your-appkey> \\\n  --input data/med-chronic-disease-review/糖尿病_ocr_task_result.json\n\n# 高血压\npython3 insurance/claims-review/chronic-disease/scripts/run.py \\\n  --disease-code hypertension \\\n  --appkey <your-appkey> \\\n  --input data/med-chronic-disease-review/高血压_ocr_task_result.json\n\n# 本地校验（不调模型）\npython3 insurance/claims-review/chronic-disease/scripts/run.py \\\n  --disease-code diabetes \\\n  --dry-run \\\n  --input data/med-chronic-disease-review/糖尿病_ocr_task_result.json\n\n# 或继续直接使用原始 OCR 数组入口\npython3 insurance/claims-review/chronic-disease/scripts/chronic_disease_review.py \\\n  --disease-code diabetes \\\n  --appkey <your-appkey> \\\n  --input data/med-chronic-disease-review/糖尿病_ocr_task_result.json\n```\n\n参数说明\n--------\n- `--disease-code STRING`：**必填**。糖尿病/高血压（也支持 `diabetes/hypertension/dm/htn` 别名）。本 skill 每次只审核一个病种。\n- `--review-type STRING`：可选。默认 `慢病审核`。\n- `--appkey STRING`：**必填**（`--dry-run` 时除外）。内部医疗大模型鉴权 key，由平台分配。\n- `--input PATH`：OCR 数组 JSON（UTF-8）或经 `run.py` 支持的文档格式。\n- `--base URL`：大模型 base（默认：`https://maas-api.hivoice.cn/v1`）。\n- `--model STRING`：模型名（默认：`u2-med`）。\n- `--timeout SECONDS`：HTTP 超时（默认：120）。\n- `--dry-run`：跳过模型调用，输出占位结论（用于联调预处理链路）。\n- `--output-json PATH`：保存原始返回 JSON（默认：`../runs/med-chronic-disease-review/{scenario}_resp.json`）。\n- `--output-text PATH`：保存自然语言摘要（默认：`../runs/med-chronic-disease-review/{scenario}_resp.txt`）。\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`：输入类型；默认 `auto`。\n- `--sheet STRING`：读取 Excel 时指定 sheet（可选）。\n- `--encoding STRING`：`txt/csv` 编码（默认：`utf-8`）。\n- `--save-prepared`：保存预处理后的 OCR 数组 JSON，便于调试。\n\n输出约定\n--------\n- 若输出路径父目录不存在，会自动创建。\n- 自然语言摘要重点字段：\n  - `final_decision`：通过/不通过/待补充\n  - `reasoning`：原因（可选）\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### 模型配置\n本 skill 通过内部医疗大模型进行推理（不再依赖商保后端审核 flow API）：\n\n- endpoint：`https://maas-api.hivoice.cn/v1/chat/completions`\n- model：`u2-med`\n- 协议：OpenAI Chat Completions（兼容标准 `/v1/chat/completions`）\n- 鉴权：通过 `--appkey` 参数传入 Bearer token，由用户在 OpenClaw 中调用时提供\n\n> 强制通过 `--appkey` 调用内部医疗大模型；`--dry-run` 仅用于本地链路校验。\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-chronic-disease-review\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1784181988455\n}\n\nFile v1.0.2:skill-card.md\n\n## Description:\n\nReviews outpatient chronic disease materials for diabetes or hypertension from OCR or document inputs and produces an internal medical model assessment with a structured JSON decision and natural-language rationale.\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\nInsurance and healthcare operations teams use this skill to review submitted chronic disease materials for diabetes or hypertension and summarize whether the provided records support the requested outpatient chronic disease review. The output is administrative review support and not a medical diagnosis or treatment recommendation.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Raw medical records and bearer tokens can be sent to a configurable model endpoint.\n\nMitigation: Use only authorized data, pre-redact patient identifiers before use, and keep --base pinned to a trusted HTTPS endpoint.\n\nRisk: Sensitive raw JSON, text summaries, or prepared OCR arrays can be written to disk.\n\nMitigation: Write outputs only to a private controlled directory, avoid --save-prepared unless needed, and remove retained files according to local data-handling policy.\n\nRisk: Administrative review results could be mistaken for clinical judgment.\n\nMitigation: Treat the output as review support only and defer clinical diagnosis or treatment decisions to qualified medical professionals.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/unisound-llm/skills/med-chronic-disease-review)\n- [Default internal medical model API endpoint](https://maas-api.hivoice.cn/v1/chat/completions)\n\n## Skill Output:\n\n**Output Type(s):** [text, json, shell commands, configuration]\n\n**Output Format:** [Structured JSON response plus natural-language text summary, with command output that reports saved file paths and a preview.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Supports dry-run validation; normal execution writes raw JSON and text summary files to the configured output paths.]\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, 14483 bytes\n\nFiles: _meta.json (145b), scripts/chronic_disease_review.py (6410b), scripts/format_review_nl.py (3390b), scripts/run.py (20474b), skill-card.md (2462b), SKILL.md (5569b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: med-chronic-disease-review\ndescription: 门诊慢病审核（糖尿病/高血压）。输入 OCR 结果数组 JSON，输出审核结论与原因（原始 JSON + 自然语言结论）。\nmetadata:\n  {\n    \"openclaw\":\n      {\n        \"emoji\": \"🩺\"\n      }\n  }\n---\n\n# 门诊慢病审核\n\n概述\n----\n给定一份 OCR 结果数组（每项包含 `fileName/page/docType/ocrText`），本技能会：\n\n- 输出审核接口原始 JSON\n- 输出自然语言摘要（结论 + 原因）\n\n数据安全、隐私与伦理声明\n------------------------\n- **最小必要原则**：仅处理审核所必需的文本内容；不要求也不鼓励提供与审核无关的身份信息。\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**：本技能输出为审核规则匹配与原因摘要的辅助信息，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输入格式\n--------\n输入必须是 JSON 数组（list），示例：\n\n```json\n[\n  {\"fileName\":\"xxx.pdf\",\"page\":1,\"docType\":\"出院记录\",\"ocrText\":\"...\"},\n  {\"fileName\":\"xxx.pdf\",\"page\":2,\"docType\":\"检验报告\",\"ocrText\":\"...\"}\n]\n```\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 `ocr_array.json`（每项含 `fileName/page/docType/ocrText`），再调用本 skill 的原始审核逻辑。\n\n快速开始\n--------\n从 `skills` 目录执行：\n\n```bash\n# 糖尿病\npython3 scripts/run.py \\\n  --disease-code diabetes \\\n  --input data/med-chronic-disease-review/糖尿病_ocr_task_result.json\n\n# 高血压\npython3 scripts/run.py \\\n  --disease-code hypertension \\\n  --input data/med-chronic-disease-review/高血压_ocr_task_result.json\n\n# 或继续直接使用原始 OCR 数组入口\npython3 scripts/chronic_disease_review.py \\\n  --disease-code diabetes \\\n  --input data/med-chronic-disease-review/糖尿病_ocr_task_result.json\n\n# 高血压\npython3 scripts/chronic_disease_review.py \\\n  --disease-code hypertension \\\n  --input data/med-chronic-disease-review/高血压_ocr_task_result.json\n```\n\n参数说明\n--------\n- `--disease-code STRING`：**必填**。糖尿病/高血压（也支持 `diabetes/hypertension/dm/htn` 别名）。本 skill 每次只审核一个病种。\n- `--review-type STRING`：可选。默认 `慢病审核`（也可传 `大病审核` 等服务支持的值）。\n- `--input PATH`：OCR 数组 JSON（UTF-8）。\n- `--base URL`：后端 base（默认：`http://10.10.20.15:9011`）。\n- `--llm-model STRING`：可选。模型名。\n- `--timeout SECONDS`：HTTP 超时；`0` 表示一直等待（默认：0）。\n- `--output-json PATH`：保存原始返回 JSON（默认：`../runs/med-chronic-disease-review/{scenario}_resp.json`）。\n- `--output-text PATH`：保存自然语言摘要（默认：`../runs/med-chronic-disease-review/{scenario}_resp.txt`）。\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`：输入类型；默认 `auto`。\n- `--sheet STRING`：读取 Excel 时指定 sheet（可选）。\n- `--encoding STRING`：`txt/csv` 编码（默认：`utf-8`）。\n- `--save-prepared`：保存预处理后的 OCR 数组 JSON，便于调试。\n\n输出约定\n--------\n- 若输出路径父目录不存在，会自动创建。\n- 自然语言摘要重点字段：\n  - `final_decision`：通过/不通过\n  - `reasoning`：原因（可选）\n\n依赖\n----\n### 运行环境\n- Python 3.7+\n\n### 外部 API\n- 后端审核服务：`https://shangbao.yunzhisheng.cn/skills/chronic-disease`\n  - 方法：POST `/api/v1/review/flow/by-ocr`\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-chronic-disease-review\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1777001262799\n}\n\nFile v1.0.1:skill-card.md\n\n## Description: <br>\nReviews outpatient chronic disease records for diabetes or hypertension and returns a raw JSON review result plus a natural-language decision summary. <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>\nHealthcare operations and review teams can use this skill to prepare OCR-derived medical record text, submit diabetes or hypertension review requests, and receive decision-oriented summaries for administrative review. It is an aid for document review and does not provide medical diagnosis or treatment advice. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Sensitive OCR medical text may be sent to a remote or user-selected endpoint. <br>\nMitigation: Use only de-identified records, verify the endpoint operator and privacy terms, and avoid overriding the service base URL unless the endpoint is trusted. <br>\nRisk: Raw PDFs and Office files can carry parsing and document-handling risk before review. <br>\nMitigation: Prefer JSON OCR input for untrusted sources and process other file types only in a controlled environment. <br>\nRisk: The default HTTP timeout can wait indefinitely. <br>\nMitigation: Set a finite timeout for operational use. <br>\nRisk: Generated review outputs and prepared OCR files may contain sensitive medical information. <br>\nMitigation: Delete generated output and prepared OCR files when they are no longer needed. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/unisound-llm/med-chronic-disease-review) <br>\n- [Publisher profile](https://clawhub.ai/user/unisound-llm) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, JSON, Shell commands, Guidance] <br>\n**Output Format:** [JSON files and natural-language text summaries] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Outputs include raw review JSON, a human-readable decision summary, and optional prepared OCR JSON for debugging.] <br>\n\n## Skill Version(s): <br>\n1.0.1 (source: server release evidence) <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, 6306 bytes\n\nFiles: _meta.json (145b), scripts/chronic_disease_review.py (6410b), scripts/format_review_nl.py (3390b), SKILL.md (3463b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: med-chronic-disease-review\ndescription: 门诊慢病审核（糖尿病/高血压）。输入 OCR 结果数组 JSON，输出审核结论与原因（原始 JSON + 自然语言结论）。\nmetadata:\n  {\n    \"openclaw\":\n      {\n        \"emoji\": \"🩺\"\n      }\n  }\n---\n\n# 门诊慢病审核\n\n概述\n----\n给定一份 OCR 结果数组（每项包含 `fileName/page/docType/ocrText`），本技能会：\n\n- 输出审核接口原始 JSON\n- 输出自然语言摘要（结论 + 原因）\n\n数据安全、隐私与伦理声明\n------------------------\n- **最小必要原则**：仅处理审核所必需的文本内容；不要求也不鼓励提供与审核无关的身份信息。\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**：本技能输出为审核规则匹配与原因摘要的辅助信息，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输入格式\n--------\n输入必须是 JSON 数组（list），示例：\n\n```json\n[\n  {\"fileName\":\"xxx.pdf\",\"page\":1,\"docType\":\"出院记录\",\"ocrText\":\"...\"},\n  {\"fileName\":\"xxx.pdf\",\"page\":2,\"docType\":\"检验报告\",\"ocrText\":\"...\"}\n]\n```\n\n快速开始\n--------\n从 `skills` 目录执行：\n\n```bash\n# 糖尿病\npython3 scripts/chronic_disease_review.py \\\n  --disease-code diabetes \\\n  --input data/med-chronic-disease-review/糖尿病_ocr_task_result.json\n\n# 高血压\npython3 scripts/chronic_disease_review.py \\\n  --disease-code hypertension \\\n  --input data/med-chronic-disease-review/高血压_ocr_task_result.json\n```\n\n参数说明\n--------\n- `--disease-code STRING`：**必填**。糖尿病/高血压（也支持 `diabetes/hypertension/dm/htn` 别名）。本 skill 每次只审核一个病种。\n- `--review-type STRING`：可选。默认 `慢病审核`（也可传 `大病审核` 等服务支持的值）。\n- `--input PATH`：OCR 数组 JSON（UTF-8）。\n- `--base URL`：后端 base（默认：`http://10.10.20.15:9011`）。\n- `--llm-model STRING`：可选。模型名。\n- `--timeout SECONDS`：HTTP 超时；`0` 表示一直等待（默认：0）。\n- `--output-json PATH`：保存原始返回 JSON（默认：`../runs/med-chronic-disease-review/{scenario}_resp.json`）。\n- `--output-text PATH`：保存自然语言摘要（默认：`../runs/med-chronic-disease-review/{scenario}_resp.txt`）。\n\n输出约定\n--------\n- 若输出路径父目录不存在，会自动创建。\n- 自然语言摘要重点字段：\n  - `final_decision`：通过/不通过\n  - `reasoning`：原因（可选）\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-chronic-disease-review\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1776328707947\n}","readmeExcerpt":"Skill: med-chronic-disease-review Owner: unisound-llm Summary: 门诊慢病审核（糖尿病/高血压）。输入 OCR 结果数组 JSON，由内部医疗大模型输出审核结论与原因（原始 JSON + 自然语言结论）。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-07-16T06:06:28.455Z | user - 移除文档 skill-card.md，相关信息现由 SKILL.md 统一维护。 - 核心审核引擎由后端 API 改为内部医疗大模型，需通过 --appkey 参数鉴权。 - 调整预处理与推理链路，依赖 _shared/doc-preprocess 公共库，确保结构化 OCR 及文档支持。 - 命令行参数和调用方式更新，增加 --dry-run 用于本地链路校验。 - 文档精简与调整，突出依赖、输入输出格式，以及","codeSnippets":[],"executableExamples":[{"language":"json","snippet":"[\n  {\"fileName\":\"xxx.pdf\",\"page\":1,\"docType\":\"出院记录\",\"ocrText\":\"...\"},\n  {\"fileName\":\"xxx.pdf\",\"page\":2,\"docType\":\"检验报告\",\"ocrText\":\"...\"}\n]"},{"language":"bash","snippet":"# 糖尿病\npython3 insurance/claims-review/chronic-disease/scripts/run.py \\\n  --disease-code diabetes \\\n  --appkey <your-appkey> \\\n  --input data/med-chronic-disease-review/糖尿病_ocr_task_result.json\n\n# 高血压\npython3 insurance/claims-review/chronic-disease/scripts/run.py \\\n  --disease-code hypertension \\\n  --appkey <your-appkey> \\\n  --input data/med-chronic-disease-review/高血压_ocr_task_result.json\n\n# 本地校验（不调模型）\npython3 insurance/claims-review/chronic-disease/scripts/run.py \\\n  --disease-code diabetes \\\n  --dry-run \\\n  --input data/med-chronic-disease-review/糖尿病_ocr_task_result.json\n\n# 或继续直接使用原始 OCR 数组入口\npython3 insurance/claims-review/chronic-disease/scripts/chronic_disease_review.py \\\n  --disease-code diabetes \\\n  --appkey <your-appkey> \\\n  --input data/med-chronic-disease-review/糖尿病_ocr_task_result.json"},{"language":"json","snippet":"[\n  {\"fileName\":\"xxx.pdf\",\"page\":1,\"docType\":\"出院记录\",\"ocrText\":\"...\"},\n  {\"fileName\":\"xxx.pdf\",\"page\":2,\"docType\":\"检验报告\",\"ocrText\":\"...\"}\n]"},{"language":"bash","snippet":"# 糖尿病\npython3 scripts/run.py \\\n  --disease-code diabetes \\\n  --input data/med-chronic-disease-review/糖尿病_ocr_task_result.json\n\n# 高血压\npython3 scripts/run.py \\\n  --disease-code hypertension \\\n  --input data/med-chronic-disease-review/高血压_ocr_task_result.json\n\n# 或继续直接使用原始 OCR 数组入口\npython3 scripts/chronic_disease_review.py \\\n  --disease-code diabetes \\\n  --input data/med-chronic-disease-review/糖尿病_ocr_task_result.json\n\n# 高血压\npython3 scripts/chronic_disease_review.py \\\n  --disease-code hypertension \\\n  --input data/med-chronic-disease-review/高血压_ocr_task_result.json"},{"language":"json","snippet":"[\n  {\"fileName\":\"xxx.pdf\",\"page\":1,\"docType\":\"出院记录\",\"ocrText\":\"...\"},\n  {\"fileName\":\"xxx.pdf\",\"page\":2,\"docType\":\"检验报告\",\"ocrText\":\"...\"}\n]"},{"language":"bash","snippet":"# 糖尿病\npython3 scripts/chronic_disease_review.py \\\n  --disease-code diabetes \\\n  --input data/med-chronic-disease-review/糖尿病_ocr_task_result.json\n\n# 高血压\npython3 scripts/chronic_disease_review.py \\\n  --disease-code hypertension \\\n  --input data/med-chronic-disease-review/高血压_ocr_task_result.json"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: med-chronic-disease-review\ndescription: 门诊慢病审核（糖尿病/高血压）。输入 OCR 结果数组 JSON，由内部医疗大模型输出审核结论与原因（原始 JSON + 自然语言结论）。\nmetadata:\n  {\n    \"openclaw\":\n      {\n        \"emoji\": \"🩺\"\n      }\n  }\n---\n\n# 门诊慢病审核\n\n概述\n----\n给定一份 OCR 结果数组（每项包含 `fileName/page/docType/ocrText`），本技能会：\n\n- 调用内部医疗大模型进行慢病审核推理\n- 输出结构化 JSON（含 `final_decision`、`reasoning`）\n- 输出自然语言摘要（结论 + 原因）\n\n数据安全、隐私与伦理声明\n------------------------\n- **最小必要原则**：仅处理审核所必需的文本内容；不要求也不鼓励提供与审核无关的身份信息。\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，会调用内部医疗大模型接口；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**：本技能输出为审核规则匹配与原因摘要的辅助信息，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输入格式\n--------\n输入必须是 JSON 数组（list），示例：\n\n```json\n[\n  {\"fileName\":\"xxx.pdf\",\"page\":1,\"docType\":\"出院记录\",\"ocrText\":\"...\"},\n  {\"fileName\":\"xxx.pdf\",\"page\":2,\"docType\":\"检验报告\",\"ocrText\":\"...\"}\n]\n```\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 `ocr_array.json`（每项含 `fileName/page/docType/ocrText`），再调用医疗大模型审核。\n\n快速开始\n--------\n从 `skills` 目录执行：\n\n```bash\n# 糖尿病\npython3 insurance/claims-review/chronic-disease/scripts/run.py \\\n  --disease-code diabetes \\\n  --appkey <your-appkey> \\\n  --input data/med-chronic-disease-review/糖尿病_ocr_task_result.json\n\n# 高血压\npython3 insurance/claims-review/chronic-disease/scripts/run.py \\\n  --disease-code hypertension \\\n  --appkey <your-appkey> \\\n  --input data/med-chronic-disease-review/高血压_ocr_task_result.json\n\n# 本地校验（不调模型）\npython3 insurance/claims-review/chronic-disease/scripts/run.py \\\n  --disease-code diabetes \\\n  --dry-run \\\n  --input data/med-chronic-disease-review/糖尿病_ocr_task_result.json\n\n# 或继续直接使用原始 OCR 数组入口\npython3 insurance/claims-review/chronic-disease/scripts/chronic_disease_review.py \\\n  --disease-code diabetes \\\n  --appkey <your-appkey> \\\n  --input data/med-chronic-disease-review/糖尿病_ocr_task_result.json\n```\n\n参数说明\n--------\n- `--disease-code STRING`：**必填**。糖尿病/高血压（也支持 `diabetes/hypertension/dm/htn` 别名）。本 skill 每次只审核一个病种。\n- `--review-type STRING`：可选。默认 `慢病审核`。\n- `--appkey STRING`：**必填**（`--dry-run` 时除外）。内部医疗大模型鉴权 key，由平台分配。\n- `--input PATH`：OCR 数组 JSON（UTF-8）或经 `run.py` 支持的文档格式。\n- `--base URL`：大模型 base（默认：`https://maas-api.hivoice.cn/v1`）。\n- `--model STRING`：模型名（默认：`u2-med`）。\n- `--timeout SECONDS`：HTTP 超时（默认：120）。\n- `--dry-run`：跳过模型调用，输出占位结论（用于联调预处理链路）。\n- `--output-json PATH`：保存原始返回 JSON（默认：`../runs/med-chronic-disease-review/{scenario}_resp.json`）。\n- `--output-text PATH`：保存自然语言摘要（默认：`../runs/med-chronic-disease-review/{scenario}_resp.txt`）。\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`：输入类型；默认 `auto`。\n- `--sheet STRING`：读取 Excel 时指定 sheet（可选）。\n- `--encoding STRING`：`txt/csv` 编码（默认：`utf-8`）。\n- `--save-prepared`：保存预处理后的 OCR 数组 JSON，便于调试。\n\n输出约定\n--------\n- 若输出路径父目录不存在，会自动创建。\n- 自然语言摘要重点字段：\n  - `final_decision`：通过/不通过/待补充\n  - `reasoning`：原因（可选）\n\n"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7ft98qwhxyrgcy7b7rzdhrrd8366k6\",\n  \"slug\": \"med-chronic-disease-review\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1784181988455\n}"},{"path":"skill-card.md","content":"## Description:\n\nReviews outpatient chronic disease materials for diabetes or hypertension from OCR or document inputs and produces an internal medical model assessment with a structured JSON decision and natural-language rationale.\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\nInsurance and healthcare operations teams use this skill to review submitted chronic disease materials for diabetes or hypertension and summarize whether the provided records support the requested outpatient chronic disease review. The output is administrative review support and not a medical diagnosis or treatment recommendation.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Raw medical records and bearer tokens can be sent to a configurable model endpoint.\n\nMitigation: Use only authorized data, pre-redact patient identifiers before use, and keep --base pinned to a trusted HTTPS endpoint.\n\nRisk: Sensitive raw JSON, text summaries, or prepared OCR arrays can be written to disk.\n\nMitigation: Write outputs only to a private controlled directory, avoid --save-prepared unless needed, and remove retained files according to local data-handling policy.\n\nRisk: Administrative review results could be mistaken for clinical judgment.\n\nMitigation: Treat the output as review support only and defer clinical diagnosis or treatment decisions to qualified medical professionals.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/unisound-llm/skills/med-chronic-disease-review)\n- [Default internal medical model API endpoint](https://maas-api.hivoice.cn/v1/chat/completions)\n\n## Skill Output:\n\n**Output Type(s):** [text, json, shell commands, configuration]\n\n**Output Format:** [Structured JSON response plus natural-language text summary, with command output that reports saved file paths and a preview.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Supports dry-run validation; normal execution writes raw JSON and text summary files to the configured output paths.]\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":"门诊慢病审核（糖尿病/高血压）。输入 OCR 结果数组 JSON，由内部医疗大模型输出审核结论与原因（原始 JSON + 自然语言结论）。 Skill: med-chronic-disease-review Owner: unisound-llm Summary: 门诊慢病审核（糖尿病/高血压）。输入 OCR 结果数组 JSON，由内部医疗大模型输出审核结论与原因（原始 JSON + 自然语言结论）。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-07-16T06:06:28.455Z | user - 移除文档 skill-card.md，相关信息现由 SKILL.md 统一维护。 - 核心审核引擎由后端 API 改为内部医疗大模型，需通过 --appkey 参数鉴权。 - 调整预处理与推理链路，依赖 _shared/doc-preprocess 公共库，确保结构化 OCR 及文档支持。 - 命令行参数和调用方式更新，增加 --dry-run 用于本地链路校验。 - 文档精简与调整，突出依赖、输入输出格式，以及","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":924,"uniquenessScore":54,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T18:58:51.794Z","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":"2026-10-11T18:58:51.794Z","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":"2026-10-13T23:45:56.637Z","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"}]}}}