{"id":"e234c0d6-9ee4-46a7-922a-c6bea09a8230","entityType":"agent","slug":"clawhub-unisound-llm-unisound-med-knowledge-qa","name":"unisound-med-knowledge-qa","canonicalUrl":"https://www.xpersona.co/agent/clawhub-unisound-llm-unisound-med-knowledge-qa","canonicalPath":"/agent/clawhub-unisound-llm-unisound-med-knowledge-qa","generatedAt":"2026-10-12T22:47:03.776Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T23:00:21.513Z","emptyReason":null},"description":"医学考试、专科问答、文献阅读理解、名词规范解释与术语同义匹配等知识问答。由调用方传入题目，经内部医疗大模型作答；通过 --task 选择具体场景提示词；仅含 `scripts/run.py`，可独立拷贝部署。 Skill: unisound-med-knowledge-qa Owner: unisound-llm Summary: 医学考试、专科问答、文献阅读理解、名词规范解释与术语同义匹配等知识问答。由调用方传入题目，经内部医疗大模型作答；通过 --task 选择具体场景提示词；仅含 scripts/run.py，可独立拷贝部署。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-07-16T06:36:29.146Z | user - Default model updated from u1-insuremed to u2-med. - Removed sample file: skill-card.md. v1.0.0 | 2026-05-19T09:31:31.317Z | user med-llm-knowledge-qa v1.0.0 — Initial Release","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 980 downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s1770nyybxj4gn0vk38n6wr6k584x8ea:unisound-med-knowledge-qa","sourceUrl":"https://clawhub.ai/unisound-llm/unisound-med-knowledge-qa","homepage":"https://clawhub.ai/unisound-llm/skills/unisound-med-knowledge-qa","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/unisound-llm/unisound-med-knowledge-qa","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/unisound-llm/skills/unisound-med-knowledge-qa","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"医学考试、专科问答、文献阅读理解、名词规范解释与术语同义匹配等知识问答。由调用方传入题目，经内部医疗大模型作答；通过 --task 选择具体场景提示词；仅含 `scripts/run.py`，可独立拷贝部署。 Skill: unisound-med-knowledge-qa Owner: unisound-llm Su"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T23:00:21.513Z","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":"2026-10-11T23:00:21.513Z","emptyReason":null},"stars":null,"forks":null,"downloads":980,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.0.2","tractionLabel":"980 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T23:00:21.500Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T23:00:21.513Z","lastCrawledAt":"2026-10-11T23:00:21.500Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T23:00:21.501Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.2","createdAt":"2026-07-16T06:36:29.146Z","changelog":"- Default model updated from `u1-insuremed` to `u2-med`. - Removed sample file: `skill-card.md`.","fileCount":4,"zipByteSize":8129},{"version":"1.0.0","createdAt":"2026-05-19T09:31:31.317Z","changelog":"med-llm-knowledge-qa v1.0.0 — Initial Release - Provides medical exam, specialty Q&A, literature comprehension, terminology explanations, and synonym matching via an internal medical LLM. - Supports task-specific prompts using --task for flexible scenario switching. - Accepts questions via command line, input file (including .jsonl/.json/text), or stdin. - Outputs structured JSON with model responses and meta info; offers text-only mode. - Allows full control of LLM parameters (model, API URL, temperature, etc.). - Clearly states compliance/disclaimer requirements for sensitive data.","fileCount":4,"zipByteSize":7966}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s1770nyybxj4gn0vk38n6wr6k584x8ea:unisound-med-knowledge-qa","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-med-knowledge-qa/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-med-knowledge-qa/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-med-knowledge-qa/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-med-knowledge-qa/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-med-knowledge-qa/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-med-knowledge-qa/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-12T22:47:03.776Z"}},"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-med-knowledge-qa/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-med-knowledge-qa/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-med-knowledge-qa/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-med-knowledge-qa/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":"2026-10-11T23:00:21.513Z","emptyReason":null},"readme":"Skill: unisound-med-knowledge-qa\n\nOwner: unisound-llm\n\nSummary: 医学考试、专科问答、文献阅读理解、名词规范解释与术语同义匹配等知识问答。由调用方传入题目，经内部医疗大模型作答；通过 --task 选择具体场景提示词；仅含 `scripts/run.py`，可独立拷贝部署。\n\nTags: latest:1.0.2\n\nVersion history:\n\nv1.0.2 | 2026-07-16T06:36:29.146Z | user\n\n- Default model updated from `u1-insuremed` to `u2-med`.\n- Removed sample file: `skill-card.md`.\n\nv1.0.0 | 2026-05-19T09:31:31.317Z | user\n\nmed-llm-knowledge-qa v1.0.0 — Initial Release\n\n- Provides medical exam, specialty Q&A, literature comprehension, terminology explanations, and synonym matching via an internal medical LLM.\n- Supports task-specific prompts using --task for flexible scenario switching.\n- Accepts questions via command line, input file (including .jsonl/.json/text), or stdin.\n- Outputs structured JSON with model responses and meta info; offers text-only mode.\n- Allows full control of LLM parameters (model, API URL, temperature, etc.).\n- Clearly states compliance/disclaimer requirements for sensitive data.\n\nArchive index:\n\nArchive v1.0.2: 4 files, 8129 bytes\n\nFiles: _meta.json (144b), scripts/run.py (13392b), skill-card.md (2543b), SKILL.md (3248b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: med-llm-knowledge-qa\ndescription: 医学考试、专科问答、文献阅读理解、名词规范解释与术语同义匹配等知识问答。由调用方传入题目，经内部医疗大模型作答；通过 --task 选择具体场景提示词；仅含 `scripts/run.py`，可独立拷贝部署。\nmetadata:\n {\n \"openclaw\":\n {\n \"emoji\": \"🩺\"\n }\n }\n---\n\n# 医学知识与专科问答\n\n## 概述\n\n覆盖医学知识检索、理解与规范表述类问答，依赖医疗大模型专业能力，按任务类型切换提示词。\n\n具体场景通过 **`--task`** 切换系统提示词（见下表），能力依赖内部医疗大模型；集成方也可通过 `--system-prompt` 完全自定义。\n\n| `--task` | 能力 |\n| --- | --- |\n| `exam` | 医学考试单项选择题 |\n| `lit-qa` | 医学文献阅读理解问答 |\n| `spe-qa` | 医学专科问答 |\n| `synonym` | 医学术语同义匹配 |\n| `term` | 医学名词规范解释 |\n\n本能力与具体业务请求解耦：平台或调用方如何组织用户输入由集成方决定；此处只约定**如何把题目交给脚本**（见下）。\n\n## 题目输入（三选一）\n\n1. **`--question`**：直接传入完整题干字符串。 \n2. **`--input PATH`**： \n - `.jsonl`：每行一个 JSON 对象，须含非空字符串字段 `question`；可用 `--index` / `--batch` / `--match-id` 选取记录； \n - `.json`：单个对象，须含 `question`； \n - 其他扩展名：按 UTF-8 纯文本整文件作为题干。 \n - 传 `-` 时从 **stdin** 读取一条 JSON（含 `question`）或纯文本。 \n3. **stdin**（且未传 `--question` / `--input`、且 stdin 非 TTY）：读入 JSON 对象或纯文本，规则同 `-`。\n\n可在 JSON 的 `other.task` 中指定任务类型（与 `--task` 等价；命令行 `--task` 优先）。\n\n## 模型\n\n- 默认 `u2-med`，接口 `https://maas-api.hivoice.cn/v1/chat/completions`（可通过参数覆盖）。\n\n## 用法示例\n\n```bash\n# 指定任务类型与题干\npython3 scripts/run.py --task exam --question \"题干……\" --appkey YOUR_KEY\n\n# 从 jsonl 取题（other.task 可省略若命令行已传 --task）\npython3 scripts/run.py --task exam --input /path/to/items.jsonl --index 0 --appkey YOUR_KEY\n```\n\n## 参数\n\n- `--task`：**必填**（除非 `other.task` 已给出）。见上表。\n- `--question` / `--input`：见上，与 stdin 三选一（`--question` 与 `--input` 不可同时使用）。\n- `--appkey STRING`：**必填**（`--dry-run` 时除外）。内部医疗大模型鉴权 key。\n- `--index`、`--match-id`、`--batch`：仅对 `.jsonl` 生效。\n- `--dry-run`：不调用模型，仅输出解析后的题目 JSON。\n- `--model`、`--api-url`、`--temperature`、`--timeout`、`--system-prompt`：调模型参数。\n- `--output PATH`：另存完整 JSON（批量为 NDJSON）。\n- `--text-only`：标准输出仅打印模型答案文本。\n\n## 输出\n\n默认可解析 JSON：含 `status`、`task`、`task_title`、`question`、`answer`、`record_index`、`meta`、`model`、`input_mode`、`input_path` 等；`skill` 为本 skill 标题。\n\n## 合规说明\n\n输出为模型辅助信息，不构成正式诊疗决策；涉及真实患者数据须先脱敏并遵守院内流程。\n\nFile v1.0.2:_meta.json\n\n{\n \"ownerId\": \"kn7ft98qwhxyrgcy7b7rzdhrrd8366k6\",\n \"slug\": \"unisound-med-knowledge-qa\",\n \"version\": \"1.0.2\",\n \"publishedAt\": 1784183789146\n}\n\nFile v1.0.2:skill-card.md\n\n## Description:\n\nProvides medical exam, specialty Q&A, literature reading comprehension, medical term explanation, and terminology synonym matching by sending caller-provided questions to the configured medical model.\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\nDevelopers and medical knowledge workflow owners use this skill to route caller-supplied medical questions into task-specific prompts for exams, specialty Q&A, literature comprehension, term explanations, and synonym matching. Outputs are model-assisted information and are not formal clinical decisions.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Caller-provided medical questions are sent to the documented external medical model endpoint.\n\nMitigation: Confirm the endpoint is approved for the intended data before use and de-identify real patient information.\n\nRisk: The required app key can grant access to the external model service.\n\nMitigation: Protect the --appkey value as a secret and avoid placing it in shared logs, command history, or committed files.\n\nRisk: Saved outputs can contain the original question and metadata.\n\nMitigation: Choose --output paths carefully and apply the same access controls used for the input data.\n\nRisk: Model-assisted medical answers may be unsuitable as final clinical decisions.\n\nMitigation: Route outputs through qualified review and applicable clinical or institutional processes before use in patient care.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/unisound-llm/skills/unisound-med-knowledge-qa)\n- [Publisher profile](https://clawhub.ai/user/unisound-llm)\n- [Configured medical model API endpoint](https://maas-api.hivoice.cn/v1/chat/completions)\n\n## Skill Output:\n\n**Output Type(s):** [Text, JSON]\n\n**Output Format:** [JSON object or NDJSON by default, with optional plain text answer output.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Outputs can include the original question, task, metadata, model, input mode, and generated answer; batch input produces one JSON object per line.]\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: 4 files, 7966 bytes\n\nFiles: _meta.json (144b), scripts/run.py (13398b), skill-card.md (2131b), SKILL.md (3254b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: med-llm-knowledge-qa\ndescription: 医学考试、专科问答、文献阅读理解、名词规范解释与术语同义匹配等知识问答。由调用方传入题目，经内部医疗大模型作答；通过 --task 选择具体场景提示词；仅含 `scripts/run.py`，可独立拷贝部署。\nmetadata:\n {\n \"openclaw\":\n {\n \"emoji\": \"🩺\"\n }\n }\n---\n\n# 医学知识与专科问答\n\n## 概述\n\n覆盖医学知识检索、理解与规范表述类问答，依赖医疗大模型专业能力，按任务类型切换提示词。\n\n具体场景通过 **`--task`** 切换系统提示词（见下表），能力依赖内部医疗大模型；集成方也可通过 `--system-prompt` 完全自定义。\n\n| `--task` | 能力 |\n| --- | --- |\n| `exam` | 医学考试单项选择题 |\n| `lit-qa` | 医学文献阅读理解问答 |\n| `spe-qa` | 医学专科问答 |\n| `synonym` | 医学术语同义匹配 |\n| `term` | 医学名词规范解释 |\n\n本能力与具体业务请求解耦：平台或调用方如何组织用户输入由集成方决定；此处只约定**如何把题目交给脚本**（见下）。\n\n## 题目输入（三选一）\n\n1. **`--question`**：直接传入完整题干字符串。 \n2. **`--input PATH`**： \n - `.jsonl`：每行一个 JSON 对象，须含非空字符串字段 `question`；可用 `--index` / `--batch` / `--match-id` 选取记录； \n - `.json`：单个对象，须含 `question`； \n - 其他扩展名：按 UTF-8 纯文本整文件作为题干。 \n - 传 `-` 时从 **stdin** 读取一条 JSON（含 `question`）或纯文本。 \n3. **stdin**（且未传 `--question` / `--input`、且 stdin 非 TTY）：读入 JSON 对象或纯文本，规则同 `-`。\n\n可在 JSON 的 `other.task` 中指定任务类型（与 `--task` 等价；命令行 `--task` 优先）。\n\n## 模型\n\n- 默认 `u1-insuremed`，接口 `https://maas-api.hivoice.cn/v1/chat/completions`（可通过参数覆盖）。\n\n## 用法示例\n\n```bash\n# 指定任务类型与题干\npython3 scripts/run.py --task exam --question \"题干……\" --appkey YOUR_KEY\n\n# 从 jsonl 取题（other.task 可省略若命令行已传 --task）\npython3 scripts/run.py --task exam --input /path/to/items.jsonl --index 0 --appkey YOUR_KEY\n```\n\n## 参数\n\n- `--task`：**必填**（除非 `other.task` 已给出）。见上表。\n- `--question` / `--input`：见上，与 stdin 三选一（`--question` 与 `--input` 不可同时使用）。\n- `--appkey STRING`：**必填**（`--dry-run` 时除外）。内部医疗大模型鉴权 key。\n- `--index`、`--match-id`、`--batch`：仅对 `.jsonl` 生效。\n- `--dry-run`：不调用模型，仅输出解析后的题目 JSON。\n- `--model`、`--api-url`、`--temperature`、`--timeout`、`--system-prompt`：调模型参数。\n- `--output PATH`：另存完整 JSON（批量为 NDJSON）。\n- `--text-only`：标准输出仅打印模型答案文本。\n\n## 输出\n\n默认可解析 JSON：含 `status`、`task`、`task_title`、`question`、`answer`、`record_index`、`meta`、`model`、`input_mode`、`input_path` 等；`skill` 为本 skill 标题。\n\n## 合规说明\n\n输出为模型辅助信息，不构成正式诊疗决策；涉及真实患者数据须先脱敏并遵守院内流程。\n\nFile v1.0.0:_meta.json\n\n{\n \"ownerId\": \"kn7ft98qwhxyrgcy7b7rzdhrrd8366k6\",\n \"slug\": \"unisound-med-knowledge-qa\",\n \"version\": \"1.0.0\",\n \"publishedAt\": 1779183091317\n}\n\nFile v1.0.0:skill-card.md\n\n## Description:
\nProvides medical exam, specialty Q&A, literature comprehension, terminology explanation, and synonym-matching answers by sending caller-provided questions to a configurable medical language model.
\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:
\nDevelopers and integrators use this skill to route medical knowledge questions into task-specific prompts for exams, specialty Q&A, literature comprehension, terminology explanations, and synonym matching. The output is model-assisted information and is not a formal clinical decision.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Questions are sent to the configured medical model API, which can expose sensitive health or patient-identifying information.
\nMitigation: Use the skill only with trusted, approved model endpoints and do not include patient-identifying, confidential, or regulated health data unless the workflow is authorized.
\nRisk: Medical answers may be mistaken for formal diagnosis or treatment decisions.
\nMitigation: Treat outputs as model-assisted information and require qualified review before clinical or operational use.
\n\n\n## Reference(s):
\n- [ClawHub skill page](https://clawhub.ai/unisound-llm/unisound-med-knowledge-qa)
\n\n\n## Skill Output:
\n**Output Type(s):** [text, JSON, files]
\n**Output Format:** [JSON or plain text; batch output may be NDJSON]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Can write full UTF-8 JSON results to a file and can emit answer text only when requested.]
\n\n## Skill Version(s):
\n1.0.0 (source: server release metadata and changelog)
\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-med-knowledge-qa Owner: unisound-llm Summary: 医学考试、专科问答、文献阅读理解、名词规范解释与术语同义匹配等知识问答。由调用方传入题目，经内部医疗大模型作答；通过 --task 选择具体场景提示词；仅含 scripts/run.py，可独立拷贝部署。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-07-16T06:36:29.146Z | user - Default model updated from u1-insuremed to u2-med. - Removed sample file: skill-card.md. v1.0.0 | 2026-05-19T09:31:31.317Z | user med-llm-knowledge-qa v1.0.0 — Initial Release ","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"# 指定任务类型与题干\npython3 scripts/run.py --task exam --question \"题干……\" --appkey YOUR_KEY\n\n# 从 jsonl 取题（other.task 可省略若命令行已传 --task）\npython3 scripts/run.py --task exam --input /path/to/items.jsonl --index 0 --appkey YOUR_KEY"},{"language":"bash","snippet":"# 指定任务类型与题干\npython3 scripts/run.py --task exam --question \"题干……\" --appkey YOUR_KEY\n\n# 从 jsonl 取题（other.task 可省略若命令行已传 --task）\npython3 scripts/run.py --task exam --input /path/to/items.jsonl --index 0 --appkey YOUR_KEY"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: med-llm-knowledge-qa\ndescription: 医学考试、专科问答、文献阅读理解、名词规范解释与术语同义匹配等知识问答。由调用方传入题目，经内部医疗大模型作答；通过 --task 选择具体场景提示词；仅含 `scripts/run.py`，可独立拷贝部署。\nmetadata:\n {\n \"openclaw\":\n {\n \"emoji\": \"🩺\"\n }\n }\n---\n\n# 医学知识与专科问答\n\n## 概述\n\n覆盖医学知识检索、理解与规范表述类问答，依赖医疗大模型专业能力，按任务类型切换提示词。\n\n具体场景通过 **`--task`** 切换系统提示词（见下表），能力依赖内部医疗大模型；集成方也可通过 `--system-prompt` 完全自定义。\n\n| `--task` | 能力 |\n| --- | --- |\n| `exam` | 医学考试单项选择题 |\n| `lit-qa` | 医学文献阅读理解问答 |\n| `spe-qa` | 医学专科问答 |\n| `synonym` | 医学术语同义匹配 |\n| `term` | 医学名词规范解释 |\n\n本能力与具体业务请求解耦：平台或调用方如何组织用户输入由集成方决定；此处只约定**如何把题目交给脚本**（见下）。\n\n## 题目输入（三选一）\n\n1. **`--question`**：直接传入完整题干字符串。 \n2. **`--input PATH`**： \n - `.jsonl`：每行一个 JSON 对象，须含非空字符串字段 `question`；可用 `--index` / `--batch` / `--match-id` 选取记录； \n - `.json`：单个对象，须含 `question`； \n - 其他扩展名：按 UTF-8 纯文本整文件作为题干。 \n - 传 `-` 时从 **stdin** 读取一条 JSON（含 `question`）或纯文本。 \n3. **stdin**（且未传 `--question` / `--input`、且 stdin 非 TTY）：读入 JSON 对象或纯文本，规则同 `-`。\n\n可在 JSON 的 `other.task` 中指定任务类型（与 `--task` 等价；命令行 `--task` 优先）。\n\n## 模型\n\n- 默认 `u2-med`，接口 `https://maas-api.hivoice.cn/v1/chat/completions`（可通过参数覆盖）。\n\n## 用法示例\n\n```bash\n# 指定任务类型与题干\npython3 scripts/run.py --task exam --question \"题干……\" --appkey YOUR_KEY\n\n# 从 jsonl 取题（other.task 可省略若命令行已传 --task）\npython3 scripts/run.py --task exam --input /path/to/items.jsonl --index 0 --appkey YOUR_KEY\n```\n\n## 参数\n\n- `--task`：**必填**（除非 `other.task` 已给出）。见上表。\n- `--question` / `--input`：见上，与 stdin 三选一（`--question` 与 `--input` 不可同时使用）。\n- `--appkey STRING`：**必填**（`--dry-run` 时除外）。内部医疗大模型鉴权 key。\n- `--index`、`--match-id`、`--batch`：仅对 `.jsonl` 生效。\n- `--dry-run`：不调用模型，仅输出解析后的题目 JSON。\n- `--model`、`--api-url`、`--temperature`、`--timeout`、`--system-prompt`：调模型参数。\n- `--output PATH`：另存完整 JSON（批量为 NDJSON）。\n- `--text-only`：标准输出仅打印模型答案文本。\n\n## 输出\n\n默认可解析 JSON：含 `status`、`task`、`task_title`、`question`、`answer`、`record_index`、`meta`、`model`、`input_mode`、`input_path` 等；`skill` 为本 skill 标题。\n\n## 合规说明\n\n输出为模型辅助信息，不构成正式诊疗决策；涉及真实患者数据须先脱敏并遵守院内流程。"},{"path":"_meta.json","content":"{\n \"ownerId\": \"kn7ft98qwhxyrgcy7b7rzdhrrd8366k6\",\n \"slug\": \"unisound-med-knowledge-qa\",\n \"version\": \"1.0.2\",\n \"publishedAt\": 1784183789146\n}"},{"path":"skill-card.md","content":"## Description:\n\nProvides medical exam, specialty Q&A, literature reading comprehension, medical term explanation, and terminology synonym matching by sending caller-provided questions to the configured medical model.\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\nDevelopers and medical knowledge workflow owners use this skill to route caller-supplied medical questions into task-specific prompts for exams, specialty Q&A, literature comprehension, term explanations, and synonym matching. Outputs are model-assisted information and are not formal clinical decisions.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Caller-provided medical questions are sent to the documented external medical model endpoint.\n\nMitigation: Confirm the endpoint is approved for the intended data before use and de-identify real patient information.\n\nRisk: The required app key can grant access to the external model service.\n\nMitigation: Protect the --appkey value as a secret and avoid placing it in shared logs, command history, or committed files.\n\nRisk: Saved outputs can contain the original question and metadata.\n\nMitigation: Choose --output paths carefully and apply the same access controls used for the input data.\n\nRisk: Model-assisted medical answers may be unsuitable as final clinical decisions.\n\nMitigation: Route outputs through qualified review and applicable clinical or institutional processes before use in patient care.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/unisound-llm/skills/unisound-med-knowledge-qa)\n- [Publisher profile](https://clawhub.ai/user/unisound-llm)\n- [Configured medical model API endpoint](https://maas-api.hivoice.cn/v1/chat/completions)\n\n## Skill Output:\n\n**Output Type(s):** [Text, JSON]\n\n**Output Format:** [JSON object or NDJSON by default, with optional plain text answer output.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Outputs can include the original question, task, metadata, model, input mode, and generated answer; batch input produces one JSON object per line.]\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":"医学考试、专科问答、文献阅读理解、名词规范解释与术语同义匹配等知识问答。由调用方传入题目，经内部医疗大模型作答；通过 --task 选择具体场景提示词；仅含 `scripts/run.py`，可独立拷贝部署。 Skill: unisound-med-knowledge-qa Owner: unisound-llm Summary: 医学考试、专科问答、文献阅读理解、名词规范解释与术语同义匹配等知识问答。由调用方传入题目，经内部医疗大模型作答；通过 --task 选择具体场景提示词；仅含 scripts/run.py，可独立拷贝部署。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-07-16T06:36:29.146Z | user - Default model updated from u1-insuremed to u2-med. - Removed sample file: skill-card.md. v1.0.0 | 2026-05-19T09:31:31.317Z | user med-llm-knowledge-qa v1.0.0 — Initial Release","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":913,"uniquenessScore":53,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T23:00:21.513Z","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":"2026-10-11T23:00:21.513Z","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":"2026-10-12T22:47:03.776Z","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"}]}}}