{"id":"d2c46737-5b40-4515-862b-da7aa04e355a","entityType":"agent","slug":"clawhub-unisound-llm-unisound-med-mental-health","name":"unisound-med-mental-health","canonicalUrl":"https://www.xpersona.co/agent/clawhub-unisound-llm-unisound-med-mental-health","canonicalPath":"/agent/clawhub-unisound-llm-unisound-med-mental-health","generatedAt":"2026-10-14T10:32:48.148Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T23:22:34.628Z","emptyReason":null},"description":"心理健康疏导与心理卫生知识问答。通过 --task 区分咨询与科普场景；仅含 `scripts/run.py`，可独立拷贝部署。 Skill: unisound-med-mental-health Owner: unisound-llm Summary: 心理健康疏导与心理卫生知识问答。通过 --task 区分咨询与科普场景；仅含 scripts/run.py，可独立拷贝部署。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-07-16T06:37:46.703Z | user - 默认模型从 u1-insuremed 更新为 u2-med。 - 移除 skill-card.md 文件，精简了技能包内容。 v1.0.0 | 2026-05-19T09:32:54.498Z | user Initial release of med-llm-mental-health - Provides psychological support responses and mental health knowledge","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 977 downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s1770nyybxj4gn0vk38n6wr6k584x8ea:unisound-med-mental-health","sourceUrl":"https://clawhub.ai/unisound-llm/unisound-med-mental-health","homepage":"https://clawhub.ai/unisound-llm/skills/unisound-med-mental-health","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/unisound-llm/unisound-med-mental-health","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/unisound-llm/skills/unisound-med-mental-health","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"心理健康疏导与心理卫生知识问答。通过 --task 区分咨询与科普场景；仅含 `scripts/run.py`，可独立拷贝部署。 Skill: unisound-med-mental-health Owner: unisound-llm Summary: 心理健康疏导与心理卫生知识问答。通过 --task 区分咨询与科"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T23:22:34.628Z","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":"2026-10-11T23:22:34.628Z","emptyReason":null},"stars":null,"forks":null,"downloads":977,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.0.2","tractionLabel":"977 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T23:22:34.616Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T23:22:34.628Z","lastCrawledAt":"2026-10-11T23:22:34.616Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T23:22:34.616Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.2","createdAt":"2026-07-16T06:37:46.703Z","changelog":"- 默认模型从 u1-insuremed 更新为 u2-med。 - 移除 skill-card.md 文件，精简了技能包内容。","fileCount":4,"zipByteSize":7826},{"version":"1.0.0","createdAt":"2026-05-19T09:32:54.498Z","changelog":"Initial release of med-llm-mental-health - Provides psychological support responses and mental health knowledge Q&A via command line. - Supports two main tasks: psych-care (psychological counseling) and psych-qa (knowledge Q&A), switchable with --task. - Accepts questions through --question, --input (supports .jsonl/.json/text), or stdin. - Outputs structured JSON by default, including status, task, question, answer, etc. - Integrates with internal medical LLM endpoint; requires --appkey for authentication. - Includes options for batch processing, customization, and dry-run mode for input parsing.","fileCount":4,"zipByteSize":7753}]},"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-mental-health","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-mental-health/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-med-mental-health/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-med-mental-health/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-med-mental-health/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-med-mental-health/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-med-mental-health/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-14T10:32:48.148Z"}},"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-mental-health/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-med-mental-health/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-med-mental-health/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-med-mental-health/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":"2026-10-11T23:22:34.628Z","emptyReason":null},"readme":"Skill: unisound-med-mental-health\n\nOwner: unisound-llm\n\nSummary: 心理健康疏导与心理卫生知识问答。通过 --task 区分咨询与科普场景；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 | 2026-07-16T06:37:46.703Z | user\n\n- 默认模型从 u1-insuremed 更新为 u2-med。\n- 移除 skill-card.md 文件，精简了技能包内容。\n\nv1.0.0 | 2026-05-19T09:32:54.498Z | user\n\nInitial release of med-llm-mental-health\n\n- Provides psychological support responses and mental health knowledge Q&A via command line.\n- Supports two main tasks: psych-care (psychological counseling) and psych-qa (knowledge Q&A), switchable with --task.\n- Accepts questions through --question, --input (supports .jsonl/.json/text), or stdin.\n- Outputs structured JSON by default, including status, task, question, answer, etc.\n- Integrates with internal medical LLM endpoint; requires --appkey for authentication.\n- Includes options for batch processing, customization, and dry-run mode for input parsing.\n\nArchive index:\n\nArchive v1.0.2: 4 files, 7826 bytes\n\nFiles: _meta.json (145b), scripts/run.py (12948b), skill-card.md (2275b), SKILL.md (2991b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: med-llm-mental-health\ndescription: 心理健康疏导与心理卫生知识问答。通过 --task 区分咨询与科普场景；仅含 `scripts/run.py`，可独立拷贝部署。\nmetadata:\n {\n \"openclaw\":\n {\n \"emoji\": \"🩺\"\n }\n }\n---\n\n# 心理健康咨询与科普\n\n## 概述\n\n提供心理支持性回应与健康科普，遇危机风险须提示寻求专业帮助。\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| `psych-care` | 心理健康咨询与疏导 |\n| `psych-qa` | 心理健康知识问答 |\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 psych-care --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 psych-care --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-mental-health\",\n \"version\": \"1.0.2\",\n \"publishedAt\": 1784183866703\n}\n\nFile v1.0.2:skill-card.md\n\n## Description:\n\nProvides mental-health support responses and psychological health Q&A through task-specific prompts to a remote medical chat-completions 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 integrators use this skill to route user-provided mental-health consultation or education prompts to a medical language model and receive structured responses. It supports direct questions, JSON, JSONL, plain text, stdin, dry-run parsing, and optional saved output.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Sensitive patient or mental-health text can be sent to a configurable remote API with a bearer key.\n\nMitigation: Use only a trusted HTTPS endpoint, avoid overriding --api-url unless the destination is controlled, use a scoped key, and de-identify real patient or personal mental-health information before use.\n\nRisk: The model output is supportive or educational assistance and may be mistaken for formal diagnosis or treatment advice.\n\nMitigation: Review outputs before clinical or operational use and direct crisis-risk cases to professional help and local emergency procedures.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/unisound-llm/skills/unisound-med-mental-health)\n- [Publisher profile](https://clawhub.ai/user/unisound-llm)\n- [Default medical chat-completions endpoint](https://maas-api.hivoice.cn/v1/chat/completions)\n\n## Skill Output:\n\n**Output Type(s):** [text, JSON, shell commands, configuration, guidance]\n\n**Output Format:** [JSON by default, plain text with --text-only, or NDJSON for batch output]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Can write UTF-8 JSON or NDJSON to a file; dry-run mode emits parsed request data without calling the model.]\n\n## Skill Version(s):\n\n1.0.2 (source: server release metadata; artifact _meta.json lists 2.0.0)\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, 7753 bytes\n\nFiles: _meta.json (145b), scripts/run.py (12954b), skill-card.md (2274b), SKILL.md (2997b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: med-llm-mental-health\ndescription: 心理健康疏导与心理卫生知识问答。通过 --task 区分咨询与科普场景；仅含 `scripts/run.py`，可独立拷贝部署。\nmetadata:\n {\n \"openclaw\":\n {\n \"emoji\": \"🩺\"\n }\n }\n---\n\n# 心理健康咨询与科普\n\n## 概述\n\n提供心理支持性回应与健康科普，遇危机风险须提示寻求专业帮助。\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| `psych-care` | 心理健康咨询与疏导 |\n| `psych-qa` | 心理健康知识问答 |\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 psych-care --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 psych-care --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-mental-health\",\n \"version\": \"1.0.0\",\n \"publishedAt\": 1779183174498\n}\n\nFile v1.0.0:skill-card.md\n\n## Description:
\nProvides mental-health support responses and mental-health knowledge Q&A through task-specific prompts for counseling and education.
\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 integrators use this command-line skill to send mental-health support or mental-health knowledge questions to a configured medical LLM and receive structured answers.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Mental-health prompts and saved outputs may contain sensitive personal or patient data.
\nMitigation: De-identify real patient data before use, avoid secrets in prompts, and protect terminal logs and --output files.
\nRisk: Questions are sent to the configured remote medical LLM endpoint.
\nMitigation: Use this skill only when that data flow is acceptable for the deployment environment and keep the required app key protected.
\nRisk: Model-assisted mental-health responses can be incomplete or inappropriate for crisis or clinical decision needs.
\nMitigation: Review outputs before relying on them and route crisis, diagnosis, or treatment decisions to qualified professionals.
\n\n\n## Reference(s):
\n- [ClawHub skill page](https://clawhub.ai/unisound-llm/unisound-med-mental-health)
\n- [Configured medical LLM API endpoint](https://maas-api.hivoice.cn/v1/chat/completions)
\n\n\n## Skill Output:
\n**Output Type(s):** [text, JSON, guidance]
\n**Output Format:** [Structured JSON by default, answer text with --text-only, or NDJSON for batch output.]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Can write complete results to --output; --dry-run emits parsed input without calling the model.]
\n\n## Skill Version(s):
\n1.0.0 (source: server-resolved release metadata)
\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-mental-health Owner: unisound-llm Summary: 心理健康疏导与心理卫生知识问答。通过 --task 区分咨询与科普场景；仅含 scripts/run.py，可独立拷贝部署。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-07-16T06:37:46.703Z | user - 默认模型从 u1-insuremed 更新为 u2-med。 - 移除 skill-card.md 文件，精简了技能包内容。 v1.0.0 | 2026-05-19T09:32:54.498Z | user Initial release of med-llm-mental-health - Provides psychological support responses and mental health knowledge","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"# 指定任务类型与题干\npython3 scripts/run.py --task psych-care --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 psych-care --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 psych-care --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 psych-care --input /path/to/items.jsonl --index 0 --appkey YOUR_KEY"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: med-llm-mental-health\ndescription: 心理健康疏导与心理卫生知识问答。通过 --task 区分咨询与科普场景；仅含 `scripts/run.py`，可独立拷贝部署。\nmetadata:\n {\n \"openclaw\":\n {\n \"emoji\": \"🩺\"\n }\n }\n---\n\n# 心理健康咨询与科普\n\n## 概述\n\n提供心理支持性回应与健康科普，遇危机风险须提示寻求专业帮助。\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| `psych-care` | 心理健康咨询与疏导 |\n| `psych-qa` | 心理健康知识问答 |\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 psych-care --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 psych-care --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-mental-health\",\n \"version\": \"1.0.2\",\n \"publishedAt\": 1784183866703\n}"},{"path":"skill-card.md","content":"## Description:\n\nProvides mental-health support responses and psychological health Q&A through task-specific prompts to a remote medical chat-completions 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 integrators use this skill to route user-provided mental-health consultation or education prompts to a medical language model and receive structured responses. It supports direct questions, JSON, JSONL, plain text, stdin, dry-run parsing, and optional saved output.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Sensitive patient or mental-health text can be sent to a configurable remote API with a bearer key.\n\nMitigation: Use only a trusted HTTPS endpoint, avoid overriding --api-url unless the destination is controlled, use a scoped key, and de-identify real patient or personal mental-health information before use.\n\nRisk: The model output is supportive or educational assistance and may be mistaken for formal diagnosis or treatment advice.\n\nMitigation: Review outputs before clinical or operational use and direct crisis-risk cases to professional help and local emergency procedures.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/unisound-llm/skills/unisound-med-mental-health)\n- [Publisher profile](https://clawhub.ai/user/unisound-llm)\n- [Default medical chat-completions endpoint](https://maas-api.hivoice.cn/v1/chat/completions)\n\n## Skill Output:\n\n**Output Type(s):** [text, JSON, shell commands, configuration, guidance]\n\n**Output Format:** [JSON by default, plain text with --text-only, or NDJSON for batch output]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Can write UTF-8 JSON or NDJSON to a file; dry-run mode emits parsed request data without calling the model.]\n\n## Skill Version(s):\n\n1.0.2 (source: server release metadata; artifact _meta.json lists 2.0.0)\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":"心理健康疏导与心理卫生知识问答。通过 --task 区分咨询与科普场景；仅含 `scripts/run.py`，可独立拷贝部署。 Skill: unisound-med-mental-health Owner: unisound-llm Summary: 心理健康疏导与心理卫生知识问答。通过 --task 区分咨询与科普场景；仅含 scripts/run.py，可独立拷贝部署。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-07-16T06:37:46.703Z | user - 默认模型从 u1-insuremed 更新为 u2-med。 - 移除 skill-card.md 文件，精简了技能包内容。 v1.0.0 | 2026-05-19T09:32:54.498Z | user Initial release of med-llm-mental-health - Provides psychological support responses and mental health knowledge","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":869,"uniquenessScore":55,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T23:22:34.628Z","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":"2026-10-11T23:22:34.628Z","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":"2026-10-14T10:32:48.148Z","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"}]}}}