Overview
- Skill Key
- abinww/clinical-data-extractor
- Author
- abinww
- Source Repo
- openclaw/skills
- Version
- -
- Source Path
- skills/abinww/clinical-data-extractor
- Latest Commit SHA
- c41975a4403e76897d17c231bd8025c3d05681b2
Stars
0
Installs
0
Status
ACTIVE
Visibility
PUBLIC
直接复制以下提示词,发送给你的 AI 助手即可完成安装。
请先检查是否已安装 SkillHub 商店,若未安装,请根据 https://skillhub-1388575217.cos.ap-guangzhou.myqcloud.com/install/skillhub.md 安装 SkillHub 商店,然后安装 Clinical Data Extractor 技能。 若已安装,则直接安装 Clinical Data Extractor 技能。
# Clinical Data Extractor
## Overview
This skill enables extracting structured clinical trial data from pharmaceutical conference websites (ASCO, ESMO, EHA, etc.) and saving it as a markdown file with standardized format.
## Configuration
**输出路径**: `~/.openclaw/workspace`
**命名格式**: `{药品名称}@{适应症}.md`
**文件名清理规则**:
- 替换空格为下划线
- 移除特殊字符
**常见终点缩写列表** - 以下缩写在表格中无需写中文全称:
- ORR (客观缓解率)
- cORR (确认缓解率)
- DCR (疾病控制率)
- mPFS/rPFS (中位无进展生存期)
- mOS (中位总生存期)
- mDOR (中位缓解持续时间)
- PSA50/PSA90 (PSA缓解率)
- CR (完全缓解)
- PR (部分缓解)
- SD (疾病稳定)
- PD (疾病进展)
- AE (不良事件)
⚠️ 如需修改配置,请直接编辑本配置区域
⚠️ 注意:`~` 需在执行时展开为实际用户 home directory
⚠️ 注意:不在列表中的终点数据应写中文全称以清晰说明
⚠️ 注意:本技能会尝试自动提取网页图片,但对于受限平台(微信公众号等)需要手动截图
## Requirements
This skill requires the following tools to be available in the OpenClaw runtime environment:
### Core Dependencies
- **browser**: Built-in OpenClaw tool for webpage automation and content extraction (no installation required)
- Requires: Chrome browser installed on the host system
- Usage: `browser action=start profile=openclaw target=host`
- **read/write**: Built-in OpenClaw tools for file operations (no installation required)
### Browser System Requirements
For browser automation to work correctly:
- **Chrome browser**: Must be installed on the host system (typically at `/usr/bin/google-chrome` or similar path)
- **Display server**: Desktop environment with X11/Wayland (for non-headless mode) or headless mode support
- **Network connectivity**: Required for loading webpages
### Optional Dependencies (For PDF Processing)
The following tools are used for PDF extraction. The skill will attempt each method in order:
1. **nano-pdf CLI** (recommended)
- Installation: Usually pre-installed with OpenClaw
- Alternative: If unavailable, file size reduction or O...
# Clinical Data Extractor
Clinical Data Extractor 是一个专业的临床数据提取技能,可以从制药会议网站(如 ASCO、ESMO)或 PDF 文档中提取结构化临床试验数据,并生成标准化的 Markdown 报告。
## 功能特性
- 📄 **多源数据提取**:支持 URL 网页和 PDF 文档
- 📊 **结构化数据整理**:自动提取药品名称、生产厂家、适应症、临床阶段、疗效和安全性数据
- 📋 **标准表格格式**:生成符合临床研究规范的 Markdown 表格
- 🎯 **专家点评生成**:从医学专家角度提供专业分析
- 🏷️ **灵活配置**:自定义输出路径、常见终点缩写列表等
## 使用场景
当你需要:
- 提取 ASCO、ESMO 等会议的临床试验摘要数据
- 从 PDF 公告中提取药物临床结果
- 生成标准化的临床试验数据报告
- 分析新药的疗效和安全 性数据
## 输入格式
- **URL**:提供制药会议网站或学术文章链接
- **PDF**:上传包含临床数据的 PDF 文档
## 输出格式
生成标准化的 Markdown 文件,包含:
```markdown
# {药品名称} - {适应症} 临床数据
## 基本信息
| 药品名称 | ... |
| 生产厂家 | ... |
| 适应症 | ... |
| 临床阶段 | ... |
| 临床名称 | ... |
| 学术会议 | ... |
## 药品有效性和安全性
| 指标 | 实验组 | 对照组 |
|------|--------|--------|
| N | ... | ... |
| ORR | ... | ... |
| ...
## 试验设计
...
## 专家点评
...
## 数据来源
...
```
## 表格格式规范
- 表格内容第一行必须列出各组入组人数(列名:N)
- 必须明确标注 cohort 的具体信息(如剂量组),避免使用"最大剂量组"等笼统表述
- 不同终点基于不同分析人群时,需分别分列
- 常见终点使用英文缩写(ORR、cORR、DCR、mPFS、mOS 等)
- 不要写 95% CI 置信区间
- 时间指标只写数字,不写单位
- 缺失数据标注为 N/A
## 安装方法
### 方法 1:通过 ClawHub 安装(推荐)
1. 访问 [ClawHub.com](https://clawhub.com)
2. 搜索 "clinical-data-extractor"
3. 点击安装
### 方法 2:手动安装
1. 将本仓库下载到 skills 目录:
```bash
git clone https://github.com/abinww/clinical-data-extractor.git ~/.openclaw/skills/clinical-data-extractor
```
2. 重启 OpenClaw 或重新加载技能
## 使用示例
### 提取网页数据
```
提取 https://mp.weixin.qq.com/s/example 的临床数据
```
### 提取 PDF 数据
发送 PDF 文件,然后说:
```
提取临床数据
```
## 配置
可以在 SKILL.md 的 Config...
heyixuan2
Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pipeline: search → generate → analyze → colorize → preview → open BS → user slice → print → monitor. Supports all 9 Bambu Lab printers (A1 Mini, A1, P1S, P2S, X1C, X1E, H2C, H2S, H2D).
edholofy
University for AI agents. 92 courses, 4400+ scenarios, any model via OpenRouter. Auto-training loops generate per-model SKILL.md documents. Works with Claude Code, OpenClaw, Cursor, Windsurf. No fine-tuning required.
lethehades
macOS WPS Office workflow helper skill for safer document preparation, conversion, export, and compatibility guidance
capt-marbles
Generative Engine Optimization (GEO) for AI search visibility. Optimize content to appear in ChatGPT, Perplexity, Claude, and Google AI Overviews. Use when optimizing websites, pages, or content for LLM discoverability and citation.
carev01
Full-text search across structured Markdown documentation archives using SQLite FTS5. Use when you need to search large collections of Markdown articles that are separated by "---" delimiters and contain source URLs (marked with "*Source:" pattern). Provides fast BM25-ranked search with automatic source URL extraction for citations. Ideal for research, documentation lookups, and knowledge base exploration. Requires indexing documentation first with `docs.py index`.
caqlayan
Tweet Processor Skill