Xpersona
U

unisound-pre-existing-review

CLAWHUB · Unverified

理赔既往症审核。由调用方传入完整题干（病历/材料 + 关系类型与报销结论格式），经内部医疗大模型判断其他诊断与主诊断关系及是否报销；仅含 scripts/run.py，无 _shared 依赖。 Skill: unisound-pre-existing-review Owner: unisound-llm Summary: 理赔既往症审核。由调用方传入完整题干（病历/材料 + 关系类型与报销结论格式），经内部医疗大模型判断其他诊断与主诊断关系及是否报销；仅含 scripts/run.py，无 _shared 依赖。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-07-16T06:08:46.047Z | user - Removed the file skill-card.md. - Updated default model from u1-insuremed to u2-med in documentation. v1.0.0 | 2026-05-18T02:04:46.203Z | user - Initial release of med-pre-existi

62
Rank
84
Safety
994
Downloads

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 994 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

Install and run

Setup complexity: low.

clawhub skill install s1770nyybxj4gn0vk38n6wr6k584x8ea:unisound-pre-existing-review
  1. Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
  2. 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-pre-existing-review/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

9,095 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: med-pre-existing-review
description: 理赔既往症审核。由调用方传入完整题干（病历/材料 + 关系类型与报销结论格式），经内部医疗大模型判断其他诊断与主诊断关系及是否报销；仅含 scripts/run.py，无 _shared 依赖。
metadata:
  {
    "openclaw":
      {
        "emoji": "📋"
      }
  }
---

# 既往症审核

## 概述

面向理赔材料中的**病历叙述或 OCR 文书**，在调用方给定的分类下，判断**其他诊断与主诊断的关系**（常见为 **并发症 / 疑似既往症 / 无关疾病**）并给出**是否报销**（**报销 / 不报销**），按题干规定的**固定行格式**输出。

本 skill **直连公司内部医疗大模型**，输入输出约定与 `insurance/claims-review/chronic-injury` 等脚本一致；不替代承保条款与人工核赔结论。

## 数据与合规

- 姓名、证件号、账户等须在调用方侧**脱敏**后再组题干；本脚本默认不落盘输入（除非 `--output`）。
- 输出为辅助审核意见，**不构成**法律或最终理赔决定。

## 题目输入（三选一）

1. **`--question`**：完整题干。  
2. **`--input PATH`**：`.json` / `.jsonl` 为对象或**单元素对象数组**；须含 **`input`** 或 **`question`**。纯文本文件则整段作为题干。`-` 表示 stdin。  
3. **stdin**：非 TTY 时同 `-`。

可选 **`meta`** / **`other`**：透传至结果 JSON 的 `meta` 字段。

## 典型题干结构（由调用方拼装）

- 病历或材料摘录（可含 OCR 噪声）  
- 关系类型与是否报销的**枚举说明**  
- 严格输出模板（三行：`关系类型：` / `是否报销：` / `判断依据：`）

## 运行结果

默认可解析 JSON：`skill` 为 `既往症审核`，`status` 为 `ok`，`answer` 为模型文本，`question` 为本次用户消息全文。

## 用法

```bash
python3 scripts/run.py --input case.json --appkey YOUR_KEY
```

## 参数

与 `chronic-injury` 相同：`--question`、`--input`、`--appkey`、`--dry-run`、`--index`、`--match-id`、`--batch`、`--model`、`--api-url`、`--temperature`、`--timeout`、`--system-prompt`、`--output`、`--text-only`。

## 模型

默认 `u2-med`，`https://maas-api.hivoice.cn/v1/chat/completions`。

_meta.json

{
  "ownerId": "kn7ft98qwhxyrgcy7b7rzdhrrd8366k6",
  "slug": "unisound-pre-existing-review",
  "version": "1.0.2",
  "publishedAt": 1784182126047
}

skill-card.md

## Description:

Reviews medical claim materials to classify the relationship between other diagnoses and the primary diagnosis, then returns a reimbursement recommendation in the requested fixed-line format.

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:

Claims reviewers and developers use this skill to send de-identified medical claim text to an internal medical model and receive an auxiliary pre-existing-condition relationship assessment and reimbursement recommendation. The output does not replace policy terms or final human claims decisions.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Sensitive claim text and a bearer API key can be sent to a user-configurable network endpoint.

Mitigation: Use the documented internal HTTPS API endpoint, avoid overriding the API URL in production, provide a narrowly scoped key, and de-identify claim materials before submission.

Risk: Outputs may contain sensitive medical or claims information.

Mitigation: Treat stdout and output files as sensitive claims data and apply the same storage, access-control, and retention rules used for source claim materials.

Risk: The model response is an auxiliary review opinion rather than a final benefits determination.

Mitigation: Require human claims review against policy terms before making legal, coverage, or payment decisions.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/unisound-llm/skills/unisound-pre-existing-review)
- [Publisher profile](https://clawhub.ai/user/unisound-llm)

## Skill Output:

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

**Output Format:** [JSON by default, or plain text when text-only output is requested]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Returns the model answer, original question, model name, input mode, record index, and optional metadata; batch input can produce NDJSON.]

## Skill Version(s):

1.0.2 (source: server release metadata)

## 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.

Sponsored

Ads related to unisound-pre-existing-review and adjacent AI workflows.