{"id":"cbbc6258-2628-4cba-9210-65b0e293d130","entityType":"agent","slug":"clawhub-unisound-llm-unisound-blood-pressure-monitor-record","name":"unisound-blood-pressure-monitor-record","canonicalUrl":"https://www.xpersona.co/agent/clawhub-unisound-llm-unisound-blood-pressure-monitor-record","canonicalPath":"/agent/clawhub-unisound-llm-unisound-blood-pressure-monitor-record","generatedAt":"2026-10-14T23:48:41.939Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-12T00:17:10.913Z","emptyReason":null},"description":"病人端慢病管理血压监测记录。参考 HealthLog 的 vitals/measurements 部分，构建慢病管理基础记录能力。 Skill: unisound-blood-pressure-monitor-record Owner: unisound-llm Summary: 病人端慢病管理血压监测记录。参考 HealthLog 的 vitals/measurements 部分，构建慢病管理基础记录能力。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-07-16T07:54:30.646Z | user - Removed the skill-card.md file from the project. - Updated the SKILL.md to change the medical model from u1-insuremed to u2-med in the \"模型配置\" section. v1.0.0 | 2026-05-18T02:06:53.160Z | user Initial","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 969 downloads reported by the source. Last updated 10/12/2026.","installCommand":"clawhub skill install s1770nyybxj4gn0vk38n6wr6k584x8ea:unisound-blood-pressure-monitor-record","sourceUrl":"https://clawhub.ai/unisound-llm/unisound-blood-pressure-monitor-record","homepage":"https://clawhub.ai/unisound-llm/skills/unisound-blood-pressure-monitor-record","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/unisound-llm/unisound-blood-pressure-monitor-record","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/unisound-llm/skills/unisound-blood-pressure-monitor-record","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"病人端慢病管理血压监测记录。参考 HealthLog 的 vitals/measurements 部分，构建慢病管理基础记录能力。 Skill: unisound-blood-pressure-monitor-record Owner: unisound-llm Summary: 病人端慢病管理血压监测记录。参考 He"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-12T00:17:10.913Z","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":"2026-10-12T00:17:10.913Z","emptyReason":null},"stars":null,"forks":null,"downloads":969,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.0.2","tractionLabel":"969 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-12T00:17:10.901Z","emptyReason":null},"lastUpdatedAt":"2026-10-12T00:17:10.913Z","lastCrawledAt":"2026-10-12T00:17:10.901Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-13T00:17:10.901Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.2","createdAt":"2026-07-16T07:54:30.646Z","changelog":"- Removed the skill-card.md file from the project. - Updated the SKILL.md to change the medical model from u1-insuremed to u2-med in the \"模型配置\" section.","fileCount":5,"zipByteSize":10644},{"version":"1.0.0","createdAt":"2026-05-18T02:06:53.160Z","changelog":"Initial release of med-patient-blood-pressure-monitor-record: - Enables structured recording of patient blood pressure, heart rate, and measurement time for chronic disease management. - Strictly records only blood pressure data (no diagnosis, weight, sleep, mood, or account system extensions). - Supports multiple input formats: JSON, CSV/XLS, TXT, PDF/DOC, and image OCR. - Outputs standardized JSON with structured data and a concise natural language summary. - Requires Python 3.7+; external libraries/tools are only needed for specific input types. - Integrates with internal medical AI for data analysis; local-only processing is not supported.","fileCount":5,"zipByteSize":10914}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s1770nyybxj4gn0vk38n6wr6k584x8ea:unisound-blood-pressure-monitor-record","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-unisound-blood-pressure-monitor-record/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-blood-pressure-monitor-record/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-blood-pressure-monitor-record/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-blood-pressure-monitor-record/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-blood-pressure-monitor-record/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-blood-pressure-monitor-record/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-14T23:48:41.938Z"}},"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-unisound-blood-pressure-monitor-record/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-blood-pressure-monitor-record/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-blood-pressure-monitor-record/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-blood-pressure-monitor-record/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":"2026-10-12T00:17:10.913Z","emptyReason":null},"readme":"Skill: unisound-blood-pressure-monitor-record\n\nOwner: unisound-llm\n\nSummary: 病人端慢病管理血压监测记录。参考 HealthLog 的 vitals/measurements 部分，构建慢病管理基础记录能力。\n\nTags: latest:1.0.2\n\nVersion history:\n\nv1.0.2 | 2026-07-16T07:54:30.646Z | user\n\n- Removed the skill-card.md file from the project.\n- Updated the SKILL.md to change the medical model from u1-insuremed to u2-med in the \"模型配置\" section.\n\nv1.0.0 | 2026-05-18T02:06:53.160Z | user\n\nInitial release of med-patient-blood-pressure-monitor-record:\n\n- Enables structured recording of patient blood pressure, heart rate, and measurement time for chronic disease management.\n- Strictly records only blood pressure data (no diagnosis, weight, sleep, mood, or account system extensions).\n- Supports multiple input formats: JSON, CSV/XLS, TXT, PDF/DOC, and image OCR.\n- Outputs standardized JSON with structured data and a concise natural language summary.\n- Requires Python 3.7+; external libraries/tools are only needed for specific input types.\n- Integrates with internal medical AI for data analysis; local-only processing is not supported.\n\nArchive index:\n\nArchive v1.0.2: 5 files, 10644 bytes\n\nFiles: _meta.json (157b), scripts/preprocess.py (8744b), scripts/run.py (9877b), skill-card.md (2197b), SKILL.md (4703b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: med-patient-blood-pressure-monitor-record\ndescription: 病人端慢病管理血压监测记录。参考 HealthLog 的 vitals/measurements 部分，构建慢病管理基础记录能力。\nmetadata:\n {\n \"openclaw\":\n {\n \"emoji\": \"❤️\"\n }\n }\n---\n\n# 血压监测记录\n\n概述\n----\n本 skill 对应：病人端 / 慢病管理 / 血压监测记录。\n\n要求：慢病管理基础记录能力。\n\n来源核验\n--------\n- 匹配来源：HealthLog\n- 来源类型：公开开源自托管健康记录 App\n- 来源链接：https://healthlog.dev/\n- 匹配结论：匹配。HealthLog 明确支持 blood pressure、heart rate 等 vitals 记录，并提供趋势图、自托管和 Docker 部署方式。\n\n参考部分\n--------\n只参考 HealthLog 的 **vitals/measurements** 部分：\n- 血压记录\n- 心率记录\n- 测量时间记录\n- 历史趋势展示\n- JSON/CSV 数据导出思路\n\n不参考部分\n----------\n- 不参考 HealthLog 的完整账号系统\n- 不参考 Withings 同步\n- 不参考 AI 健康报告\n- 不扩展到体重、睡眠、情绪等非本 skill 能力\n\n构建方式\n--------\nOpenClaw 中应构建为一个独立的记录型 skill：\n- 输入患者本次血压测量信息\n- 结构化收缩压、舒张压、心率、测量时间\n- 输出标准血压记录 JSON\n- 可追加输出简短自然语言确认\n\n建议输入字段\n------------\n- `systolic`：收缩压\n- `diastolic`：舒张压\n- `heart_rate`：心率\n- `unit`：默认 `mmHg`\n- `measured_at`：测量时间\n- `note`：备注\n\n建议输出字段\n------------\n- `skill`：`血压监测记录`\n- `record_type`：`blood_pressure`\n- `systolic`\n- `diastolic`\n- `heart_rate`\n- `unit`\n- `measured_at`\n- `note`\n\n医疗边界\n--------\n本 skill 只做血压记录，不做诊断，不替代医生判断。\n\n快速开始\n--------\n从本 skill 目录执行：\n\n```bash\npython3 scripts/run.py --input input.json --output output.json --appkey YOUR_KEY\n```\n\n最小输入示例\n------------\n```json\n{\n \"systolic\": 128,\n \"diastolic\": 82,\n \"heart_rate\": 76,\n \"unit\": \"mmHg\",\n \"measured_at\": \"2026-04-29 08:00\",\n \"note\": \"\"\n}\n```\n\n输出约定\n--------\n输出 UTF-8 JSON，采用统一格式：\n\n```json\n{\n \"skill\": \"技能名称\",\n \"status\": \"ok\",\n \"data\": { /* 结构化数据 */ },\n \"text\": \"API 生成的 Markdown/自然语言内容，OpenClaw 直接渲染给用户\"\n}\n```\n\n- `data`：本地预处理得到的结构化数据\n- `text`：内部医疗大模型生成的自然语言解读/分析/提醒，Markdown 格式\n\n支持的输入格式\n--------------\n除 JSON 外，还支持以下格式（通过 `--input-type` 自动检测或手动指定）：\n\n| 格式 | 说明 |\n|------|------|\n| JSON | 默认，直接读取结构化输入 |\n| CSV / XLSX / XLS | 表格数据，按列头自动映射字段 |\n| TXT / MD | key:value 文本格式（支持中文/英文字段名） |\n| PDF / DOC / DOCX | 文档，提取文本后解析 |\n| PNG / JPG 等图片 | OCR 提取文本后解析 |\n\n文本格式示例\n-----------\n```\n收缩压：130\n舒张压：85\n心率：72\n```\n\nCSV 格式示例\n-----------\n```\n收缩压,舒张压,心率\n130,85,72\n```\n\n统一入口附加参数\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 JSON，便于调试。\n- `--appkey STRING`：**必填**。调用内部医疗大模型的鉴权 key，由平台分配。\n\n依赖\n----\n### 运行环境\n- Python 3.7+\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 |\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` | 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 |\n| `tesseract`（含 chi_sim+eng） | 图片 OCR | 输入为图片时必须 |\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模型配置\n--------\n本 skill 执行时通过内部医疗大模型进行推理：\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> 本 skill 强制走 API 推理，无本地透传模式。\n\nFile v1.0.2:_meta.json\n\n{\n \"ownerId\": \"kn7ft98qwhxyrgcy7b7rzdhrrd8366k6\",\n \"slug\": \"unisound-blood-pressure-monitor-record\",\n \"version\": \"1.0.2\",\n \"publishedAt\": 1784188470646\n}\n\nFile v1.0.2:skill-card.md\n\n## Description:\n\nRecords patient blood pressure measurements for chronic disease management, producing structured JSON and patient-facing Markdown guidance.\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\nExternal users and chronic-care workflows use this skill to capture systolic pressure, diastolic pressure, heart rate, measurement time, and notes from supported input files. The skill returns structured blood-pressure records and concise Markdown guidance without replacing clinical judgment.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Blood-pressure records and notes may contain sensitive health information and are sent to an external medical model.\n\nMitigation: Use the skill only when users understand this data flow, avoid identifiers in notes, and provide only the minimum necessary health data.\n\nRisk: Broad document and image parsing increases exposure to malformed or untrusted input files.\n\nMitigation: Prefer JSON or CSV input when possible and avoid untrusted documents or images.\n\nRisk: The skill accepts the model app key through a command-line argument.\n\nMitigation: Use a safer secret mechanism than command-line app keys when the host platform provides one.\n\n## Reference(s):\n\n- [HealthLog](https://healthlog.dev/)\n- [ClawHub skill page](https://clawhub.ai/unisound-llm/skills/unisound-blood-pressure-monitor-record)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, configuration]\n\n**Output Format:** [UTF-8 JSON with structured data and a Markdown text field]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires a user-provided app key for the external medical model; supports JSON, CSV, Excel, text, Markdown, PDF, Word, and image inputs.]\n\n## Skill Version(s):\n\n1.0.2 (source: server release evidence)\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 v1.0.0: 5 files, 10914 bytes\n\nFiles: _meta.json (157b), scripts/preprocess.py (8744b), scripts/run.py (9883b), skill-card.md (2967b), SKILL.md (4709b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: med-patient-blood-pressure-monitor-record\ndescription: 病人端慢病管理血压监测记录。参考 HealthLog 的 vitals/measurements 部分，构建慢病管理基础记录能力。\nmetadata:\n {\n \"openclaw\":\n {\n \"emoji\": \"❤️\"\n }\n }\n---\n\n# 血压监测记录\n\n概述\n----\n本 skill 对应：病人端 / 慢病管理 / 血压监测记录。\n\n要求：慢病管理基础记录能力。\n\n来源核验\n--------\n- 匹配来源：HealthLog\n- 来源类型：公开开源自托管健康记录 App\n- 来源链接：https://healthlog.dev/\n- 匹配结论：匹配。HealthLog 明确支持 blood pressure、heart rate 等 vitals 记录，并提供趋势图、自托管和 Docker 部署方式。\n\n参考部分\n--------\n只参考 HealthLog 的 **vitals/measurements** 部分：\n- 血压记录\n- 心率记录\n- 测量时间记录\n- 历史趋势展示\n- JSON/CSV 数据导出思路\n\n不参考部分\n----------\n- 不参考 HealthLog 的完整账号系统\n- 不参考 Withings 同步\n- 不参考 AI 健康报告\n- 不扩展到体重、睡眠、情绪等非本 skill 能力\n\n构建方式\n--------\nOpenClaw 中应构建为一个独立的记录型 skill：\n- 输入患者本次血压测量信息\n- 结构化收缩压、舒张压、心率、测量时间\n- 输出标准血压记录 JSON\n- 可追加输出简短自然语言确认\n\n建议输入字段\n------------\n- `systolic`：收缩压\n- `diastolic`：舒张压\n- `heart_rate`：心率\n- `unit`：默认 `mmHg`\n- `measured_at`：测量时间\n- `note`：备注\n\n建议输出字段\n------------\n- `skill`：`血压监测记录`\n- `record_type`：`blood_pressure`\n- `systolic`\n- `diastolic`\n- `heart_rate`\n- `unit`\n- `measured_at`\n- `note`\n\n医疗边界\n--------\n本 skill 只做血压记录，不做诊断，不替代医生判断。\n\n快速开始\n--------\n从本 skill 目录执行：\n\n```bash\npython3 scripts/run.py --input input.json --output output.json --appkey YOUR_KEY\n```\n\n最小输入示例\n------------\n```json\n{\n \"systolic\": 128,\n \"diastolic\": 82,\n \"heart_rate\": 76,\n \"unit\": \"mmHg\",\n \"measured_at\": \"2026-04-29 08:00\",\n \"note\": \"\"\n}\n```\n\n输出约定\n--------\n输出 UTF-8 JSON，采用统一格式：\n\n```json\n{\n \"skill\": \"技能名称\",\n \"status\": \"ok\",\n \"data\": { /* 结构化数据 */ },\n \"text\": \"API 生成的 Markdown/自然语言内容，OpenClaw 直接渲染给用户\"\n}\n```\n\n- `data`：本地预处理得到的结构化数据\n- `text`：内部医疗大模型生成的自然语言解读/分析/提醒，Markdown 格式\n\n支持的输入格式\n--------------\n除 JSON 外，还支持以下格式（通过 `--input-type` 自动检测或手动指定）：\n\n| 格式 | 说明 |\n|------|------|\n| JSON | 默认，直接读取结构化输入 |\n| CSV / XLSX / XLS | 表格数据，按列头自动映射字段 |\n| TXT / MD | key:value 文本格式（支持中文/英文字段名） |\n| PDF / DOC / DOCX | 文档，提取文本后解析 |\n| PNG / JPG 等图片 | OCR 提取文本后解析 |\n\n文本格式示例\n-----------\n```\n收缩压：130\n舒张压：85\n心率：72\n```\n\nCSV 格式示例\n-----------\n```\n收缩压,舒张压,心率\n130,85,72\n```\n\n统一入口附加参数\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 JSON，便于调试。\n- `--appkey STRING`：**必填**。调用内部医疗大模型的鉴权 key，由平台分配。\n\n依赖\n----\n### 运行环境\n- Python 3.7+\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 |\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` | 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 |\n| `tesseract`（含 chi_sim+eng） | 图片 OCR | 输入为图片时必须 |\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模型配置\n--------\n本 skill 执行时通过内部医疗大模型进行推理：\n\n- endpoint：`https://maas-api.hivoice.cn/v1/chat/completions`\n- model：`u1-insuremed`\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> 本 skill 强制走 API 推理，无本地透传模式。\n\nFile v1.0.0:_meta.json\n\n{\n \"ownerId\": \"kn7ft98qwhxyrgcy7b7rzdhrrd8366k6\",\n \"slug\": \"unisound-blood-pressure-monitor-record\",\n \"version\": \"1.0.0\",\n \"publishedAt\": 1779070013160\n}\n\nFile v1.0.0:skill-card.md\n\n## Description:
\nRecords patient blood-pressure measurements, structures systolic pressure, diastolic pressure, heart rate, measurement time, and notes, and returns JSON plus a concise Markdown summary.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[unisound-llm](https://clawhub.ai/user/unisound-llm)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nExternal users and care-management workflows use this skill to turn blood-pressure readings from JSON, tables, text, documents, or images into standardized records and a patient-facing summary. It is for record keeping and informational summaries, not diagnosis or a substitute for clinician judgment.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Sensitive blood-pressure readings, heart rate, timestamps, and notes are sent to a remote medical model.
\nMitigation: Use the skill only with appropriate consent and data-handling approval, and provide only the minimum information needed for the record.
\nRisk: The generated summary may read like health guidance even though the skill is intended for record keeping.
\nMitigation: Treat the Markdown output as informational and non-diagnostic; route medical decisions or abnormal readings to qualified clinical review.
\nRisk: The required app key is a sensitive credential.
\nMitigation: Provide the app key through a secret-management mechanism and avoid storing it in prompts, input files, logs, or source control.
\nRisk: Document and image preprocessing can extract unrelated sensitive content if broad files are supplied.
\nMitigation: Use focused input files containing only the intended blood-pressure record fields and review prepared data before remote submission when possible.
\n\n\n## Reference(s):
\n- [ClawHub release page](https://clawhub.ai/unisound-llm/unisound-blood-pressure-monitor-record)
\n- [Publisher profile](https://clawhub.ai/user/unisound-llm)
\n- [HealthLog](https://healthlog.dev/)
\n- [Remote medical model endpoint](https://maas-api.hivoice.cn/v1/chat/completions)
\n\n\n## Skill Output:
\n**Output Type(s):** [JSON, Markdown, text, files]
\n**Output Format:** [UTF-8 JSON containing structured blood-pressure records and a Markdown text summary.]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Can write results to a JSON file or stdout. Requires an app key and remote model access; optional preprocessing supports JSON, CSV/XLS, text, PDF/DOC, and image inputs.]
\n\n## Skill Version(s):
\n1.0.0 (source: server release metadata and artifact _meta.json)
\n\n## Ethical Considerations:
\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.
","readmeExcerpt":"Skill: unisound-blood-pressure-monitor-record Owner: unisound-llm Summary: 病人端慢病管理血压监测记录。参考 HealthLog 的 vitals/measurements 部分，构建慢病管理基础记录能力。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-07-16T07:54:30.646Z | user - Removed the skill-card.md file from the project. - Updated the SKILL.md to change the medical model from u1-insuremed to u2-med in the \"模型配置\" section. v1.0.0 | 2026-05-18T02:06:53.160Z | user Initial ","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"python3 scripts/run.py --input input.json --output output.json --appkey YOUR_KEY"},{"language":"json","snippet":"{\n \"systolic\": 128,\n \"diastolic\": 82,\n \"heart_rate\": 76,\n \"unit\": \"mmHg\",\n \"measured_at\": \"2026-04-29 08:00\",\n \"note\": \"\"\n}"},{"language":"json","snippet":"{\n \"skill\": \"技能名称\",\n \"status\": \"ok\",\n \"data\": { /* 结构化数据 */ },\n \"text\": \"API 生成的 Markdown/自然语言内容，OpenClaw 直接渲染给用户\"\n}"},{"language":"text","snippet":"收缩压：130\n舒张压：85\n心率：72"},{"language":"text","snippet":"收缩压,舒张压,心率\n130,85,72"},{"language":"bash","snippet":"python3 scripts/run.py --input input.json --output output.json --appkey YOUR_KEY"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: med-patient-blood-pressure-monitor-record\ndescription: 病人端慢病管理血压监测记录。参考 HealthLog 的 vitals/measurements 部分，构建慢病管理基础记录能力。\nmetadata:\n {\n \"openclaw\":\n {\n \"emoji\": \"❤️\"\n }\n }\n---\n\n# 血压监测记录\n\n概述\n----\n本 skill 对应：病人端 / 慢病管理 / 血压监测记录。\n\n要求：慢病管理基础记录能力。\n\n来源核验\n--------\n- 匹配来源：HealthLog\n- 来源类型：公开开源自托管健康记录 App\n- 来源链接：https://healthlog.dev/\n- 匹配结论：匹配。HealthLog 明确支持 blood pressure、heart rate 等 vitals 记录，并提供趋势图、自托管和 Docker 部署方式。\n\n参考部分\n--------\n只参考 HealthLog 的 **vitals/measurements** 部分：\n- 血压记录\n- 心率记录\n- 测量时间记录\n- 历史趋势展示\n- JSON/CSV 数据导出思路\n\n不参考部分\n----------\n- 不参考 HealthLog 的完整账号系统\n- 不参考 Withings 同步\n- 不参考 AI 健康报告\n- 不扩展到体重、睡眠、情绪等非本 skill 能力\n\n构建方式\n--------\nOpenClaw 中应构建为一个独立的记录型 skill：\n- 输入患者本次血压测量信息\n- 结构化收缩压、舒张压、心率、测量时间\n- 输出标准血压记录 JSON\n- 可追加输出简短自然语言确认\n\n建议输入字段\n------------\n- `systolic`：收缩压\n- `diastolic`：舒张压\n- `heart_rate`：心率\n- `unit`：默认 `mmHg`\n- `measured_at`：测量时间\n- `note`：备注\n\n建议输出字段\n------------\n- `skill`：`血压监测记录`\n- `record_type`：`blood_pressure`\n- `systolic`\n- `diastolic`\n- `heart_rate`\n- `unit`\n- `measured_at`\n- `note`\n\n医疗边界\n--------\n本 skill 只做血压记录，不做诊断，不替代医生判断。\n\n快速开始\n--------\n从本 skill 目录执行：\n\n```bash\npython3 scripts/run.py --input input.json --output output.json --appkey YOUR_KEY\n```\n\n最小输入示例\n------------\n```json\n{\n \"systolic\": 128,\n \"diastolic\": 82,\n \"heart_rate\": 76,\n \"unit\": \"mmHg\",\n \"measured_at\": \"2026-04-29 08:00\",\n \"note\": \"\"\n}\n```\n\n输出约定\n--------\n输出 UTF-8 JSON，采用统一格式：\n\n```json\n{\n \"skill\": \"技能名称\",\n \"status\": \"ok\",\n \"data\": { /* 结构化数据 */ },\n \"text\": \"API 生成的 Markdown/自然语言内容，OpenClaw 直接渲染给用户\"\n}\n```\n\n- `data`：本地预处理得到的结构化数据\n- `text`：内部医疗大模型生成的自然语言解读/分析/提醒，Markdown 格式\n\n支持的输入格式\n--------------\n除 JSON 外，还支持以下格式（通过 `--input-type` 自动检测或手动指定）：\n\n| 格式 | 说明 |\n|------|------|\n| JSON | 默认，直接读取结构化输入 |\n| CSV / XLSX / XLS | 表格数据，按列头自动映射字段 |\n| TXT / MD | key:value 文本格式（支持中文/英文字段名） |\n| PDF / DOC / DOCX | 文档，提取文本后解析 |\n| PNG / JPG 等图片 | OCR 提取文本后解析 |\n\n文本格式示例\n-----------\n```\n收缩压：130\n舒张压：85\n心率：72\n```\n\nCSV 格式示例\n-----------\n```\n收缩压,舒张压,心率\n130,85,72\n```\n\n统一入口附加参数\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 JSON，便于调试。\n- `--appkey STRING`：**必填**。调用内部医疗大模型的鉴权 key，由平台分配。\n\n依赖\n----\n### 运行环境\n- Python 3.7+\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 |\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` | 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 |\n| `tesseract`（含 chi_sim+eng） | 图片 OCR | 输入为图片时必须 |\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模型配置\n--------\n本 skill 执行时通过内部医疗大模型进行推理：\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> 本 skill 强制走 API 推理，无本地透"},{"path":"_meta.json","content":"{\n \"ownerId\": \"kn7ft98qwhxyrgcy7b7rzdhrrd8366k6\",\n \"slug\": \"unisound-blood-pressure-monitor-record\",\n \"version\": \"1.0.2\",\n \"publishedAt\": 1784188470646\n}"},{"path":"skill-card.md","content":"## Description:\n\nRecords patient blood pressure measurements for chronic disease management, producing structured JSON and patient-facing Markdown guidance.\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\nExternal users and chronic-care workflows use this skill to capture systolic pressure, diastolic pressure, heart rate, measurement time, and notes from supported input files. The skill returns structured blood-pressure records and concise Markdown guidance without replacing clinical judgment.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Blood-pressure records and notes may contain sensitive health information and are sent to an external medical model.\n\nMitigation: Use the skill only when users understand this data flow, avoid identifiers in notes, and provide only the minimum necessary health data.\n\nRisk: Broad document and image parsing increases exposure to malformed or untrusted input files.\n\nMitigation: Prefer JSON or CSV input when possible and avoid untrusted documents or images.\n\nRisk: The skill accepts the model app key through a command-line argument.\n\nMitigation: Use a safer secret mechanism than command-line app keys when the host platform provides one.\n\n## Reference(s):\n\n- [HealthLog](https://healthlog.dev/)\n- [ClawHub skill page](https://clawhub.ai/unisound-llm/skills/unisound-blood-pressure-monitor-record)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, configuration]\n\n**Output Format:** [UTF-8 JSON with structured data and a Markdown text field]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires a user-provided app key for the external medical model; supports JSON, CSV, Excel, text, Markdown, PDF, Word, and image inputs.]\n\n## Skill Version(s):\n\n1.0.2 (source: server release evidence)\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":"病人端慢病管理血压监测记录。参考 HealthLog 的 vitals/measurements 部分，构建慢病管理基础记录能力。 Skill: unisound-blood-pressure-monitor-record Owner: unisound-llm Summary: 病人端慢病管理血压监测记录。参考 HealthLog 的 vitals/measurements 部分，构建慢病管理基础记录能力。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-07-16T07:54:30.646Z | user - Removed the skill-card.md file from the project. - Updated the SKILL.md to change the medical model from u1-insuremed to u2-med in the \"模型配置\" section. v1.0.0 | 2026-05-18T02:06:53.160Z | user Initial","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":969,"uniquenessScore":52,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-12T00:17:10.913Z","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":"2026-10-12T00:17:10.913Z","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":"2026-10-14T23:48:41.939Z","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"}]}}}