What makes unisound-med-knowledge-qa notable?

980 downloads. Trust evidence available

How should unisound-med-knowledge-qa be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

unisound-med-knowledge-qa

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

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

980

Updated

Oct 11, 2026

Version

1.0.2

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 980 downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 980 downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.2release · observed Jul 16, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 1.0.2release
- Default model updated from `u1-insuremed` to `u2-med`. - Removed sample file: `skill-card.md`.
Observed Jul 16, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s1770nyybxj4gn0vk38n6wr6k584x8ea:unisound-med-knowledge-qa

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: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-med-knowledge-qa/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

10,309 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: med-llm-knowledge-qa
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。
metadata:
  {
    "openclaw":
      {
        "emoji": "🩺"
      }
  }
---

# 医学知识与专科问答

## 概述

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。

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。

| `--task` | 能力 |
| --- | --- |
| `exam` | 医学考试单项选择题 |
| `lit-qa` | 医学文献阅读理解问答 |
| `spe-qa` | 医学专科问答 |
| `synonym` | 医学术语同义匹配 |
| `term` | 医学名词规范解释 |

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）。

## 题目输入（三选一）

1. **`--question`**：直接传入完整题干字符串。  
2. **`--input PATH`**：  
   - `.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；  
   - `.json`：单个对象，须含 `question`；  
   - 其他扩展名：按 UTF-8 纯文本整文件作为题干。  
   - 传 `-` 时从 **stdin** 读取一条 JSON（含 `question`）或纯文本。  
3. **stdin**（且未传 `--question` / `--input`、且 stdin 非 TTY）：读入 JSON 对象或纯文本，规则同 `-`。

可在 JSON 的 `other.task` 中指定任务类型（与 `--task` 等价；命令行 `--task` 优先）。

## 模型

- 默认 `u2-med`，接口 `https://maas-api.hivoice.cn/v1/chat/completions`（可通过参数覆盖）。

## 用法示例

```bash
# 指定任务类型与题干
python3 scripts/run.py --task exam --question "题干……" --appkey YOUR_KEY

# 从 jsonl 取题（other.task 可省略若命令行已传 --task）
python3 scripts/run.py --task exam --input /path/to/items.jsonl --index 0 --appkey YOUR_KEY
```

## 参数

- `--task`：**必填**（除非 `other.task` 已给出）。见上表。
- `--question` / `--input`：见上，与 stdin 三选一（`--question` 与 `--input` 不可同时使用）。
- `--appkey STRING`：**必填**（`--dry-run` 时除外）。内部医疗大模型鉴权 key。
- `--index`、`--match-id`、`--batch`：仅对 `.jsonl` 生效。
- `--dry-run`：不调用模型，仅输出解析后的题目 JSON。
- `--model`、`--api-url`、`--temperature`、`--timeout`、`--system-prompt`：调模型参数。
- `--output PATH`：另存完整 JSON（批量为 NDJSON）。
- `--text-only`：标准输出仅打印模型答案文本。

## 输出

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。

## 合规说明

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。

_meta.json

{
  "ownerId": "kn7ft98qwhxyrgcy7b7rzdhrrd8366k6",
  "slug": "unisound-med-knowledge-qa",
  "version": "1.0.2",
  "publishedAt": 1784183789146
}

skill-card.md

## Description:

Provides 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.

This skill is ready for commercial/non-commercial use.

## Publisher:

[unisound-llm](https://clawhub.ai/user/unisound-llm)

### License/Terms of Use:

MIT-0

## Use Case:

Developers 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.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Caller-provided medical questions are sent to the documented external medical model endpoint.

Mitigation: Confirm the endpoint is approved for the intended data before use and de-identify real patient information.

Risk: The required app key can grant access to the external model service.

Mitigation: Protect the --appkey value as a secret and avoid placing it in shared logs, command history, or committed files.

Risk: Saved outputs can contain the original question and metadata.

Mitigation: Choose --output paths carefully and apply the same access controls used for the input data.

Risk: Model-assisted medical answers may be unsuitable as final clinical decisions.

Mitigation: Route outputs through qualified review and applicable clinical or institutional processes before use in patient care.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/unisound-llm/skills/unisound-med-knowledge-qa)
- [Publisher profile](https://clawhub.ai/user/unisound-llm)
- [Configured medical model API endpoint](https://maas-api.hivoice.cn/v1/chat/completions)

## Skill Output:

**Output Type(s):** [Text, JSON]

**Output Format:** [JSON object or NDJSON by default, with optional plain text answer output.]

**Output Parameters:** [1D]

**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.]

## Skill Version(s):

1.0.2 (source: server release evidence)

## Ethical Considerations:

Users 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.

Github ReposUpdated 3d agoRank 70

AionUi

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!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

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

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular