What makes unisound-recheck-reminder notable?

1K downloads. Trust evidence available

How should unisound-recheck-reminder 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-recheck-reminder

复查提醒。从体检报告中提取所有需复查项目，按紧急程度分级（2周/1-3月/3-6月/6-12月），给出复查检查项、就诊科室和准备事项（JSON + 面向受检者的复查提醒）。 Skill: unisound-recheck-reminder Owner: unisound-llm Summary: 复查提醒。从体检报告中提取所有需复查项目，按紧急程度分级（2周/1-3月/3-6月/6-12月），给出复查检查项、就诊科室和准备事项（JSON + 面向受检者的复查提醒）。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-07-16T07:49:58.756Z | user - Removed the file: skill-card.md - Changed default model from u1-insuremed to u2-med in parameter说明 section - Updated skill name to health-exam-recheck-reminder in metadata - No functional chan

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-recheck-reminder

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-recheck-reminder/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

12,648 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: health-exam-recheck-reminder
description: 复查提醒。从体检报告中提取所有需复查项目，按紧急程度分级（2周/1-3月/3-6月/6-12月），给出复查检查项、就诊科室和准备事项（JSON + 面向受检者的复查提醒）。
metadata:
  {
    "openclaw":
      {
        "emoji": "🔔"
      }
  }
---

# 复查提醒

概述
----
面向**体检中心/健康管理机构**，给定受检者体检报告，本技能会：

- 识别所有需要复查的异常项目
- 按紧急程度分级（紧急2周内/短期1-3月/中期3-6月/长期6-12月）
- 为每项指定复查检查项目、就诊科室和建议机构
- 给出复查前注意事项（空腹/停药等）
- 区分"需到医院就诊"、"可在体检机构复查"、"可居家自测"三类
- 生成面向受检者的友好提醒通知

与"检后随访管理"的区别：本技能聚焦**复检闭环**，输出更轻量（以提醒清单为主），适合直接推送给受检者；随访管理则包含健康指导等更宽泛的检后服务。

数据安全、隐私与伦理声明
------------------------
- **最小必要原则**：仅处理生成复查提醒所必需的体检数据；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**：复查提醒为健康管理服务，具体复查方案由接诊医生决定。

输入格式
--------
纯文本（UTF-8），可输入完整体检报告，例如：

```text
受检者：女，42岁，体检日期：2026年5月
主要异常发现：
- 宫颈液基细胞学（TCT）：ASCUS（不典型鳞状细胞，意义不明）
- 乳腺超声：右乳3mm低回声结节，BI-RADS 3类
- 甲状腺超声：左叶6mm低回声结节，TI-RADS 3类
- TG：2.3mmol/L（轻度升高）
- 空腹血糖：5.9mmol/L（正常高值）
- 血压：128/82mmHg
- 骨密度：腰椎T值-1.1（骨量减少）
```

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/post-exam-mgmt/recheck-reminder/scripts/run.py \
  --input data/health-exam-recheck/case-001.txt \
  --appkey <your-appkey>

# 保存输出到文件
python3 health-exam/post-exam-mgmt/recheck-reminder/scripts/run.py \
  --input data/health-exam-recheck/case-001.txt \
  --appkey <your-appkey> \
  --output runs/health-exam-recheck/case-001.json
```

参数说明
--------
- `--input PATH`：**必填**。体检报告文件路径（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**：

```json
{
  "recheck_count": 6,
  "has_urgent": false,
  "items": [
    {
      "item": "宫颈TCT（ASCUS）",
      "current_finding": "ASCUS（不典型鳞状细胞，意义不明）",
      "recheck_urgency": "短期（1-3个月）",
      "recheck_exam": "HPV分型检测 + TCT复查",
      "recheck_venue": "二级及以上医院",
      "recheck_department": "妇科",
      "purpose": "明确是否存在高危型HPV感染，判断是否需要阴道镜检查",
      "preparation": ["月经干净后3-5天就诊", "就诊前24小时避免同房和阴道冲洗"],
      "what_to_watch": "如出现同房后出血或异常白带，提前就诊"
    },
    {
      "item": "甲油三酯（TG）轻度升高",
      "current_finding": "TG 2.3mmol/L（轻度升高）",
      "recheck_urgency": "中期（3-6个月）",
      "recheck_exam": "血脂四项复查",
      "recheck_venue": "体检机构",
      "recheck_department": null,
      "purpose": "评估生活方式干预后血脂控制效果",
      "preparation": ["空腹8-12小时", "复查前3天避免高脂饮食"],
      "what_to_watch": null
    }
  ],
  "grouped_by_venue": {
    "urgent_medical_referral": [],
    "followup_at_exam_center": ["血脂四项复查", "血糖复查", "骨密度复查"],
    "self_monitoring": ["每周测量血压1-2次"]
  }
}
```

**复查提醒**：以"【复查提醒】"开头，用清晰友好的语言提醒受检者需要跟进的复查事项。

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
----
- TI-RADS/BI-RADS 分类随访时间遵循国际超声学会标准
- has_urgent 为 true 时，输出文字会特别强调紧急就诊的必要性
- **

_meta.json

{
  "ownerId": "kn7ft98qwhxyrgcy7b7rzdhrrd8366k6",
  "slug": "unisound-recheck-reminder",
  "version": "1.0.2",
  "publishedAt": 1784188198756
}

skill-card.md

## Description:

Generates a structured recheck reminder from a health exam report by identifying follow-up items, urgency windows, recommended exams, departments, venues, and preparation notes.

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 exam centers and health management organizations use this skill to turn report findings into a follow-up checklist and recipient-facing reminder. It supports post-exam recheck coordination, while final medical decisions remain with the receiving clinician.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Health exam report contents are sent to a remote model endpoint.

Mitigation: Remove names, IDs, phone numbers, addresses, and other direct identifiers before use, and only process reports whose disclosure to the configured service is approved.

Risk: The documented de-identification posture is stronger than the artifact behavior.

Mitigation: Add or require local redaction before invoking the model, then verify the redaction path with representative reports before deployment.

Risk: The API base URL can be changed at runtime.

Mitigation: Restrict --base to an approved HTTPS endpoint for the exact app key and environment.

## Reference(s):

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

## Skill Output:

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

**Output Format:** [JSON followed by plain-language reminder text.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Can print to stdout or write the combined output to a user-specified file path.]

## 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.