什么是 Clinical Trial Search 技能？

Clinical Trial Search 技能是一个专门的技术工具，旨在弥合人类查询与复杂生物医学数据库之间的差距。通过将此功能集成到 Openclaw Skills 生态系统中，开发人员和研究人员可以使用对话提示以编程方式查询试验数据。它处理实体提取和参数映射的繁重工作，确保从类似于 ClinicalTrials.gov 的数据库中获得高精度结果。

该技能对于需要导航试验阶段、药物模态和招募状态而无需手动过滤的生命科学专业人员特别有价值。它简化了 Openclaw Skills 框架内肿瘤学研究、药物开发跟踪和竞争情报的数据检索过程。

下载入口:https://github.com/openclaw/skills/tree/main/skills/bombert/clinical-trail

安装与下载

1. ClawHub CLI

从源直接安装技能的最快方式。

2. 手动安装

将技能文件夹复制到以下位置之一

优先级：工作区 > 本地 > 内置

3. 提示词安装

将此提示词复制到 OpenClaw 即可自动安装。

Clinical Trial Search 技能 应用场景

• 跟踪特定试验阶段（例如 Phase 3），针对 NSCLC 或结直肠癌等特定适应症。
• 识别由特定制药公司在不同地理位置资助的试验。
• 通过搜索特定的生物靶点或药物特征（如双特异性抗体）来监测药物开发管线。
• 使用特定的 NCT 标识符检索临床试验结果摘要和疗效数据。

1. AI 代理分析用户的对话意图，以提取药物名称、适应症和试验阶段等实体。
2. 识别出的实体被映射到结构化参数架构，并在必要时利用逻辑运算符 (OR/AND)。
3. 该技能执行一个基于 Python 的搜索脚本，与后端临床数据库 API 进行交互。
4. 处理结果并返回相关的试验元数据，包括 NCT IDs、标题和招募状态，以开发人员友好的格式呈现。

Clinical Trial Search 技能 配置指南

要在您的 Openclaw Skills 环境中部署此技能，请确保您已安装 Python 3.8+ 并执行以下步骤：

# Install the required HTTP library
pip install requests

# Set your API authentication token
export NOAH_API_TOKEN='your_token_from_noah_bio'

用户必须在 noah.bio 注册以获取用于身份验证的 API 密钥。

Clinical Trial Search 技能 数据架构与分类体系

该技能将数据组织到严格的架构中以确保查询准确性。以下是参数映射的分类：

复杂字段如 target 或 drug_modality 使用 JSON 格式：{"logic": "or", "data": ["term1", "term2"]}。

name: clinical-trial-search
description: "Search clinical trial databases similar to ClinicalTrials.gov. Use this skill whenever the user asks about clinical trials, drug trials, indications, targets, drug names, trial phases, NCT IDs, enrollment, or recruitment. Automatically parses natural language questions into structured query parameters and calls the backend API to return matching trial records. Trigger words include: clinical trial, NCT, drug development, indication, target, phase, enrollment, recruitment, sponsor, cohort, arm, endpoint, efficacy, safety data."

Clinical Trial Search Skill

This skill converts natural language questions into structured API queries against a clinical trial database, then presents the results in a readable format.

Workflow

1. Parse user intent — Extract key entities from the user's question
2. Build query parameters — Map entities to the ClinicalTrialSearchData schema
3. Execute the query — Run scripts/search.py
4. Present results — Format and display trials to the user

Step 1: Extract Keywords

Identify the following entity types from the user's question:

Dict field format:

{"logic": "or", "data": ["value1", "value2"]}

• logic controls how multiple values are combined: "or" (any match) or "and" (all must match). Default to "or" unless the user explicitly wants all terms to apply simultaneously.
• data is the list of keyword strings to match.

Type rules:

• indication, acronym, company, nctid, phase → plain List[str]
• target, drug_name, drug_modality, drug_feature, location, route_of_administration → dict with logic and data
• Default to page_num: 0, page_size: 5 unless the user specifies otherwise
• Prefer English keywords (the database is indexed in English); translate non-English terms

Step 2: Execute the Query

python scripts/search.py --params ''

Or using a parameter file:

python scripts/search.py --params-file /tmp/query.json

Add --raw to receive the unformatted JSON response.

Step 3: Interpret Results

The response contains:

• total — total number of matching trials
• trials — current page of results, each with NCT ID, title, phase, status, indication, drugs, sponsor, etc.

If results exceed 100, prompt the user to narrow the query. If no results are returned, suggest relaxing one or more filters.

Conversion Examples

User: "Find Phase 3 trials of PD-1 antibodies in lung cancer that have results"

Parameters:

{
  "target": {"logic": "or", "data": ["PD-1"]},
  "drug_modality": {"logic": "or", "data": ["antibody"]},
  "indication": ["lung cancer"],
  "phase": ["Phase 3"],
  "has_result_summary": true,
  "page_num": 0,
  "page_size": 10
}

User: "Look up NCT04280783"

Parameters:

{
  "nctid": ["NCT04280783"],
  "page_num": 0,
  "page_size": 1
}

User: "Roche bispecific antibody trials in China"

Parameters:

{
  "company": ["Roche"],
  "location": {"logic": "or", "data": ["China"]},
  "drug_feature": {"logic": "or", "data": ["bispecific"]},
  "page_num": 0,
  "page_size": 10
}

User: "Oral small molecule KRAS G12C inhibitors in colorectal cancer"

Parameters:

{
  "target": {"logic": "or", "data": ["KRAS G12C"]},
  "drug_modality": {"logic": "or", "data": ["small molecule"]},
  "route_of_administration": {"logic": "or", "data": ["oral"]},
  "indication": ["colorectal cancer"],
  "page_num": 0,
  "page_size": 10
}

Dependencies

• Python 3.8+
• requests library (pip install requests)
• Environment variable NOAH_API_TOKEN — API authentication token (required)
  • Register for a free account at noah.bio to obtain your API key.