What makes unisound-abnormal-items notable?

1K downloads. Trust evidence available

How should unisound-abnormal-items 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-abnormal-items

体检异常指标专项解读。针对体检报告中的每项异常，逐一说明"是什么/为何异常/有何影响/如何干预"，并分析多指标关联，语言通俗易懂（JSON + 专项解读文字）。 Skill: unisound-abnormal-items Owner: unisound-llm Summary: 体检异常指标专项解读。针对体检报告中的每项异常，逐一说明"是什么/为何异常/有何影响/如何干预"，并分析多指标关联，语言通俗易懂（JSON + 专项解读文字）。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-07-16T07:50:43.979Z | user - Updated default model used from u1-insuremed to u2-med in SKILL.md. - Removed the file skill-card.md from the skill package. v1.0.0 | 2026-05-18T01:54:12.356Z | user - Initial release of the health-ex

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.0k

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. 1K 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: 1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.2release · observed Jul 16, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s1770nyybxj4gn0vk38n6wr6k584x8ea:unisound-abnormal-items

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-abnormal-items/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

12,524 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: health-exam-abnormal-items
description: 体检异常指标专项解读。针对体检报告中的每项异常，逐一说明"是什么/为何异常/有何影响/如何干预"，并分析多指标关联，语言通俗易懂（JSON + 专项解读文字）。
metadata:
  {
    "openclaw":
      {
        "emoji": "🔍"
      }
  }
---

# 异常指标专项解读

概述
----
面向**体检中心/健康管理机构**，对体检报告中出现的每一项异常指标进行深度专项解读，本技能会：

- 用通俗语言解释每个指标的含义
- 分析可能的异常原因（结合受检者个人背景）
- 说明对健康的潜在影响
- 给出生活方式干预建议和就医建议
- 分析多个异常指标之间的内在关联（如代谢综合征）
- 标注紧急程度

与"体检报告整体解读"的区别：本技能聚焦**逐项深度解读**，面向用户感知强的异常项，内容更详尽；整体解读侧重全局评级和优先行动。

数据安全、隐私与伦理声明
------------------------
- **最小必要原则**：仅处理指标解读所必需的检查数据；不要求包含直接身份标识。
- **严格脱敏**：发送前对可识别身份信息进行脱敏处理。
- **不做本地持久化**：仅在内存中短暂处理；**本次调用结束即销毁**。
- **医疗边界**：本技能解读为健康教育参考，不替代医生诊断；存在异常时请就医确认。

输入格式
--------
纯文本（UTF-8），可输入完整体检报告（会自动提取异常项），也可只输入异常指标列表，例如：

```text
受检者：男，45岁，轻体力劳动，BMI 26.8
异常指标：
- 甘油三酯（TG）：2.8mmol/L（↑，参考：<1.7mmol/L）
- 总胆固醇（TC）：5.9mmol/L（↑，参考：<5.2mmol/L）
- 空腹血糖（FBG）：6.2mmol/L（↑，参考：3.9-6.1mmol/L）
- 谷丙转氨酶（ALT）：52U/L（↑，参考：0-40U/L）
- 血压：142/90mmHg（↑，参考：<130/80mmHg）
超声提示：轻度脂肪肝
```

也支持 JSON 格式（包含 `text`/`content`/`report` 字段的对象）。

快速开始
--------

```bash
# 从 skills 目录运行
python3 health-exam/report-interpret/abnormal-items/scripts/run.py \
  --input data/health-exam-abnormal/case-001.txt \
  --appkey <your-appkey>

# 保存输出到文件
python3 health-exam/report-interpret/abnormal-items/scripts/run.py \
  --input data/health-exam-abnormal/case-001.txt \
  --appkey <your-appkey> \
  --output runs/health-exam-abnormal/case-001.json
```

参数说明
--------
- `--input PATH`：**必填**。体检报告或异常指标文件路径（txt 或 json，UTF-8）。
- `--appkey STRING`：**必填**。调用内部医疗大模型的鉴权 key，由平台分配。
- `--output PATH`：输出文件路径（默认：打印到 stdout）。
- `--base URL`：内部大模型 base URL（默认：`https://maas-api.hivoice.cn/v1`）。
- `--model STRING`：模型名称（默认：`u2-med`）。
- `--timeout SECONDS`：HTTP 超时秒数；`0` 表示一直等待（默认：0）。
- `--encoding STRING`：输入文件编码（默认：`utf-8`）。

输出约定
--------
输出分两部分：

**JSON 结构**（每个异常指标一条详细解读）：

```json
{
  "abnormal_count": 5,
  "items": [
    {
      "item_name": "甘油三酯 TG",
      "value": "2.8mmol/L",
      "reference_range": "<1.7mmol/L",
      "deviation": "偏高",
      "deviation_degree": "轻度",
      "plain_explanation": "甘油三酯是血液中一种脂肪，主要来自饮食中的油脂和糖分转化",
      "possible_causes": ["饮食油腻或高糖", "运动量不足", "超重"],
      "health_impact": "长期偏高增加动脉硬化、心脑血管疾病和胰腺炎风险",
      "intervention": {
        "lifestyle": ["减少油炸食品和含糖饮料", "增加有氧运动", "控制体重"],
        "medical": "定期监测，3个月后复查血脂"
      },
      "urgency": "定期复查"
    }
  ],
  "correlations": [
    "血脂升高（TG、TC）+ 血糖偏高 + 超重 + 脂肪肝，提示代谢综合征风险，是心脑血管疾病的重要危险因素组合，建议系统评估和干预"
  ]
}
```

**专项解读文字**：以"【专项解读】"开头，用通俗语言逐项向受检者解释异常指标。

依赖
----
### 运行环境
- Python 3.7+（仅使用标准库，无需额外安装）

### 外部 API
- 内部医疗大模型：`https://maas-api.hivoice.cn/v1/chat/completions`

备注
----
- 输入可以是完整报告（技能会自动提取异常项），也可以只粘贴异常指标列表
- 若受检者有已知慢性病史，在输入中注明可获得更精准的解读
- **发布约束**：示例输入、运行输出均放在 skill 包外（`data/`、`runs/`），skill 目录内仅保留可发布的核心文件

_meta.json

{
  "ownerId": "kn7ft98qwhxyrgcy7b7rzdhrrd8366k6",
  "slug": "unisound-abnormal-items",
  "version": "1.0.2",
  "publishedAt": 1784188243979
}

skill-card.md

## Description:

Interprets abnormal health exam indicators one by one, explaining what each item means, why it may be abnormal, potential health impact, suggested interventions, and cross-indicator correlations in accessible language.

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:

Health management staff, physical examination centers, and developers use this skill to turn abnormal exam report items into structured JSON and Chinese patient-facing explanations. It supports health education workflows by summarizing possible causes, health impact, lifestyle and medical follow-up suggestions, urgency, and correlations such as metabolic syndrome patterns.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Sensitive medical reports may be sent to a remote API without code-enforced de-identification.

Mitigation: Pre-redact patient identifiers and unnecessary details before use, and review data handling requirements before submitting real patient data.

Risk: A custom base URL can redirect reports and the app key to an endpoint outside the expected service.

Mitigation: Use only a verified trusted API endpoint and restrict app key handling to approved environments.

Risk: Generated medical explanations may be incomplete or incorrect for clinical decision-making.

Mitigation: Treat outputs as health education material and require clinician review for diagnosis, treatment, or urgent-care decisions.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/unisound-llm/skills/unisound-abnormal-items)
- [Publisher profile](https://clawhub.ai/user/unisound-llm)
- [Unisound MaaS chat completions endpoint](https://maas-api.hivoice.cn/v1/chat/completions)

## Skill Output:

**Output Type(s):** [text, JSON, guidance]

**Output Format:** [JSON object followed by Chinese explanatory text headed with 【专项解读】]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May print to stdout or write to a user-specified output file; generated content is health education guidance and not a substitute for medical diagnosis.]

## 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 2d 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.