What makes unisound-chronic-injury notable?

1K downloads. Trust evidence available

How should unisound-chronic-injury 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-chronic-injury

理赔陈旧伤审核。由调用方传入完整题干（常见为影像报告 + 指定部位 + 输出格式），经内部医疗大模型判断伤情类别；仅含 scripts/run.py，无 _shared 依赖。 Skill: unisound-chronic-injury Owner: unisound-llm Summary: 理赔陈旧伤审核。由调用方传入完整题干（常见为影像报告 + 指定部位 + 输出格式），经内部医疗大模型判断伤情类别；仅含 scripts/run.py，无 _shared 依赖。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-07-16T06:07:06.492Z | user - Updated default model from u1-insuremed to u2-med. - Clarified and generalized references to direct medical LLM Q&A scripts in interface descriptions. - Removed file: skill-card.md. v1.0.0 | 2

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-chronic-injury

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-chronic-injury/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

10,125 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: med-chronic-injury-review
description: 理赔陈旧伤审核。由调用方传入完整题干（常见为影像报告 + 指定部位 + 输出格式），经内部医疗大模型判断伤情类别；仅含 scripts/run.py，无 _shared 依赖。
metadata:
  {
    "openclaw":
      {
        "emoji": "🦴"
      }
  }
---

# 陈旧伤审核

## 概述

面向**理赔材料中的影像/检查报告文字**（可由 OCR 或人工整理），在调用方给定的分类体系下（常见为 **陈旧伤 / 新伤 / 无伤 / 未提及**），对**指定解剖部位**做出伤情类别判断，并按题干要求的**固定行格式**输出。

本 skill **不接院内 PACS**，题干由上游拼装；与慢病/大病审核（走后端业务接口）不同，本包**直连公司内部医疗大模型**，接口与参数约定同医疗大模型直连问答脚本（`--question` / `--input` / `--appkey` 等）。

## 数据与合规

- 送入模型前应对姓名、证件号、影像号等做**脱敏**（由调用方完成）；本脚本不落盘用户内容（除非使用 `--output` 显式保存结果）。
- 输出为辅助审核意见，**不构成**法医鉴定或最终理赔决定。

## 题目输入（三选一）

1. **`--question`**：完整题干字符串。  
2. **`--input PATH`**：  
   - `.json` / `.jsonl`：根为**对象**，或**仅含 1 个对象的 JSON 数组**；对象须含非空 **`input`** 或 **`question`**。  
   - 其他扩展名：整文件 UTF-8 纯文本作为题干。  
   - 传 `-` 时从 stdin 读。  
3. **stdin**（未传 `--question` / `--input`、且非 TTY）：规则同 `-`。

可选字段 **`meta`** / **`other`**：任意 JSON 对象，原样进入运行结果中的 `meta`。

## 题干与输出格式（由调用方约定）

典型题干中会包含：

- 影像检查报告摘录（影像描述 / 影像诊断等）  
- 指定检查部位与所见依据  
- 待选类别列表  
- 严格输出模板（例如两行：`伤情类别：…` / `判断依据：…`）

模型须**完全遵守**题干中的格式与类别用词；默认系统提示词与上述约束对齐。

## 运行结果（stdout）

默认可解析 JSON：`skill` 为 `陈旧伤审核`，`status` 为 `ok`，`answer` 为模型文本，`question` 为本次用户消息全文，`meta` 等为透传/溯源字段（含义同 `doctor/icd-drg/drg-grouping` 等脚本）。

## 用法示例

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

## 参数

- `--question` / `--input`：与 stdin 三选一（二者不可同时）。  
- `--appkey STRING`：**必填**（`--dry-run` 除外）。  
- `--index`、`--match-id`、`--batch`：仅 `.jsonl`。  
- `--dry-run`、`--model`、`--api-url`、`--temperature`、`--timeout`、`--system-prompt`、`--output`、`--text-only`：同仓库内其他直连大模型脚本。

## 模型

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

_meta.json

{
  "ownerId": "kn7ft98qwhxyrgcy7b7rzdhrrd8366k6",
  "slug": "unisound-chronic-injury",
  "version": "1.0.2",
  "publishedAt": 1784182026492
}

skill-card.md

## Description:

Reviews insurance claim imaging or examination report text for a specified anatomical site and classifies the finding under the caller's injury categories.

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 use this skill to submit de-identified imaging or examination report text and receive a structured auxiliary classification for chronic injury review. The result supports insurance review workflows and is not a forensic opinion or final claim decision.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Sensitive claim text or credentials could be sent to an unintended API endpoint.

Mitigation: Use only a trusted HTTPS API endpoint and protect and scope the appkey.

Risk: Claim materials may contain personal or medical identifiers.

Mitigation: De-identify claim materials before use.

Risk: Using output persistence can store the question, metadata, and model answer on disk.

Mitigation: Avoid --output unless disk storage of those contents is acceptable.

## Reference(s):

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

## Skill Output:

**Output Type(s):** [text, JSON, shell commands, 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 skill name, status, selected model, input provenance fields, optional metadata, the original question, and the model answer.]

## 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.