What makes unisound-clinical-trial-design notable?

966 downloads. Trust evidence available

How should unisound-clinical-trial-design 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-clinical-trial-design

药企药物研发辅助临床试验设计辅助。参考 Clinical Trial Protocol Skill 的 protocol design 部分，构建药研方法设计能力。 Skill: unisound-clinical-trial-design Owner: unisound-llm Summary: 药企药物研发辅助临床试验设计辅助。参考 Clinical Trial Protocol Skill 的 protocol design 部分，构建药研方法设计能力。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-07-16T08:05:21.935Z | user - Removed the file skill-card.md. - Updated internal medical model configuration from u1-insuremed to u2-med in SKILL.md. v1.0.0 | 2026-05-18T05:43:23.752Z | user med-pharma-clinical-trial-desi

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

966

Updated

Oct 12, 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. 966 downloads reported by the source. Last updated 10/12/2026.

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 12, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 12, 2026
Adoption signal: 966 downloadsadoption · observed Oct 12, 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
- Removed the file skill-card.md. - Updated internal medical model configuration from u1-insuremed to u2-med in SKILL.md.
Observed Jul 16, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s1770nyybxj4gn0vk38n6wr6k584x8ea:unisound-clinical-trial-design

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-clinical-trial-design/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

13,338 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: med-pharma-clinical-trial-design
description: 药企药物研发辅助临床试验设计辅助。参考 Clinical Trial Protocol Skill 的 protocol design 部分，构建药研方法设计能力。
metadata:
  {
    "openclaw":
      {
        "emoji": "📋"
      }
  }
---

# 临床试验设计辅助

概述
----
本 skill 对应：药企 / 药物研发辅助 / 临床试验设计辅助。

要求：药研方法设计。

来源核验
--------
- 匹配来源：Clinical Trial Protocol Skill
- 来源类型：公开 Agent Skill
- 来源链接：https://agent-skills.md/skills/anthropics/healthcare/clinical-trial-protocol-skill
- 匹配结论：匹配。该 skill 明确覆盖临床试验 protocol 设计、研究目的、入排标准、终点和访视安排。

参考部分
--------
只参考 Clinical Trial Protocol Skill 的 **protocol design** 部分：
- 研究目的
- 研究分期
- 研究类型
- 入排标准
- 主要/次要终点
- 访视安排

不参考部分
----------
- 不参考临床试验数据统计
- 不参考受试者招募管理
- 不参考监管递交文件生成
- 不扩展到药物靶点筛选或医学事务资料生成

构建方式
--------
OpenClaw 中应构建为一个独立的设计型 skill：
- 输入适应症、干预措施、试验分期和研究目的
- 整理研究设计、入排标准、终点和访视安排
- 输出临床试验设计辅助 JSON

建议输入字段
------------
- `indication`：适应症
- `intervention`：干预措施
- `phase`：试验分期
- `objective`：研究目的
- `population`：目标人群
- `control`：对照方式
- `randomization`：随机化方式
- `blinding`：盲法
- `endpoints`：终点列表
- `visits`：访视安排

建议输出字段
------------
- `skill`：`临床试验设计辅助`
- `indication`
- `intervention`
- `phase`
- `study_design`
- `population`
- `endpoints`
- `visit_schedule`

医疗边界
--------
本 skill 只做临床试验方法设计辅助，不替代伦理审查、法规审查、统计师或临床专家最终确认。

快速开始
--------
从本 skill 目录执行：

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

最小输入示例
------------
```json
{
  "indication": "非小细胞肺癌",
  "intervention": "研究药物A",
  "phase": "II期",
  "objective": "评价初步有效性和安全性",
  "population": "既往治疗失败患者",
  "control": "标准治疗",
  "randomization": "1:1",
  "blinding": "开放标签",
  "endpoints": ["ORR", "PFS"],
  "visits": ["筛选期", "基线", "每3周一次"]
}
```

输出约定
--------
输出 UTF-8 JSON，采用统一格式：

```json
{
  "skill": "技能名称",
  "status": "ok",
  "data": { /* 结构化数据 */ },
  "text": "API 生成的 Markdown/自然语言内容，OpenClaw 直接渲染给用户"
}
```

- `data`：本地预处理得到的结构化数据
- `text`：内部医疗大模型生成的自然语言解读/分析/提醒，Markdown 格式

支持的输入格式
--------------
除 JSON 外，还支持以下格式（通过 `--input-type` 自动检测或手动指定）：

| 格式 | 说明 |
|------|------|
| JSON | 默认，直接读取结构化输入 |
| CSV / XLSX / XLS | 表格数据，按列头自动映射字段 |
| TXT / MD | key:value 文本格式（支持中文/英文字段名） |
| PDF / DOC / DOCX | 文档，提取文本后解析 |
| PNG / JPG 等图片 | OCR 提取文本后解析 |

统一入口附加参数
----------------
- `--input-type auto|pdf|doc|docx|xls|xlsx|csv|txt|json`：输入类型；默认 `auto`。
- `--sheet STRING`：读取 Excel 时指定 sheet（可选）。
- `--encoding STRING`：`txt/csv` 编码（默认：`utf-8`）。
- `--save-prepared`：保存预处理后的 JSON，便于调试。
- `--appkey STRING`：**必填**。内部医疗大模型鉴权 key，由用户在 OpenClaw 中调用时提供。本 skill 强制通过 API 提供临床试验设计建议，无本地透传模式。

依赖
----
### 运行环境
- Python 3.7+

### Python 第三方包（可选，按输入格式需要）
| 包名 | 用途 | 必要条件 |
|------|------|---------|
| `openpyxl` | 读取 `.xlsx` 文件 | 输入为 xlsx 时必须 |
| `pypdf` | 提取 PDF 文本 | 输入为 pdf 时必须 |

### 外部工具（可选，按输入格式需要）
| 工具 | 用途 | 必要条件 |
|------|------|---------|
| LibreOffice (`soffice`) | 转换 `.doc` / `.xls` | 输入为 doc/xls 时必须 |
| `pdftotext`（poppler-utils） | 提取 PDF 文本 | 输入为 pdf 且未安装 pypdf 时 |
| `tesseract`（含 chi_sim+eng） | 图片 OCR | 输入为图片时必须 |

> 仅使用 JSON 输入时，无需安装任何第三方包或外部工具。

模型配置
--------
本 skill 执行时通过内

_meta.json

{
  "ownerId": "kn7ft98qwhxyrgcy7b7rzdhrrd8366k6",
  "slug": "unisound-clinical-trial-design",
  "version": "1.0.2",
  "publishedAt": 1784189121935
}

skill-card.md

## Description:

Assists drug-development teams with clinical trial method design by organizing study objectives, phase, population, endpoints, and visit schedules.

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:

Clinical research and drug-development teams use this skill to convert trial inputs such as indication, intervention, phase, objectives, population, endpoints, and visits into a structured clinical-trial design review. The output is decision support and still requires clinical, statistical, ethics, and regulatory review.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Clinical or proprietary R&D data may be processed through a remote medical-model endpoint and document-processing tools.

Mitigation: Use only approved environments and endpoints, prefer JSON input for sensitive work, and confirm data-handling approval before deployment.

Risk: Credentials can be supplied on the command line as an app key.

Mitigation: Avoid passing real app keys on the command line when possible and use an approved secret-handling path.

Risk: Document inputs and the external _shared preprocessing fallback can expand the execution and data-processing surface beyond the reviewed package.

Mitigation: Sandbox untrusted documents and review or remove the external _shared fallback before relying on the skill.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/unisound-llm/skills/unisound-clinical-trial-design)
- [Clinical Trial Protocol Skill reference](https://agent-skills.md/skills/anthropics/healthcare/clinical-trial-protocol-skill)

## Skill Output:

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

**Output Format:** [UTF-8 JSON containing structured trial-design data and Markdown guidance text]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Requires user-provided clinical-trial inputs and an app key for the remote medical-model endpoint.]

## Skill Version(s):

1.0.2 (source: 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 4d 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