← Back to Skills Marketplace
shixiangwang

Bioinfo Daily

by ShixiangWang · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ✓ Security Clean
368
Downloads
2
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install bioinfo-daily-skill
Description
每日生物信息学与肿瘤学研究进展日报生成器。使用 PubMed API 自动搜索前一天的 CNS 及 Nature Index 期刊文献,筛选生物信息学、肿瘤免疫、单细胞测序、空间转录组等领域的高影响力研究,生成包含中文亮点介绍的日报。使用场景:(1) 设置定时任务每天自动获取研究进展并发送到飞书 (2) 手动查询...
README (SKILL.md)

Bioinfo Daily - 生物信息学日报

概述

本技能使用 PubMed E-utilities API 自动搜索并汇总前一天的生物信息学和肿瘤学研究进展,聚焦 CNS(Cell/Nature/Science)及子刊、Nature Index 等高影响力期刊,每天推荐 10 篇左右重要文献,并生成中文亮点介绍。

功能特点

  • 🔍 自动搜索: 使用 PubMed API 搜索前一天新增文献(限定 cancer 相关)
  • 📊 高影响力筛选: 仅筛选 CNS 及 Nature Index 期刊
  • 🎯 精准分类: 生物信息学、肿瘤免疫、单细胞测序、空间转录组、临床进展
  • 💡 中文亮点: 每篇文献 30 字左右中文亮点介绍
  • 📝 智能摘要: 日报抬头自动生成精选文章 summary
  • 🔥 智能优选: 文章多时会自动优选创新性强、方向有区分的文章(最多10篇)
  • 📰 日报格式: 结构化日报,便于阅读和分享

使用方法

1. 手动生成日报

python3 ~/.openclaw/workspace/skills/bioinfo-daily/scripts/pubmed_search.py

2. 查看定时任务

openclaw cron list

3. 测试搜索(特定主题)

# 编辑脚本中的 SEARCH_TOPICS 添加自定义主题

数据源

PubMed API: https://eutils.ncbi.nlm.nih.gov/entrez/eutils

搜索范围:

  • 🧬 生物信息学算法与工具
  • 🦠 肿瘤免疫学最新研究
  • 🔬 单细胞测序技术
  • 🧪 空间转录组技术
  • 💊 癌症免疫治疗临床进展

期刊筛选:

  • Nature, Science, Cell 主刊及子刊
  • Nature Index 期刊
  • 其他高影响力期刊(Lancet、JAMA、PNAS 等)

输出格式

日报包含:

  1. 📅 日期和文献总数
  2. 📚 每篇文献:标题、期刊、作者、亮点、链接
  3. 📊 数据来源说明

配置

API 配置(使用环境变量):

  • NCBI_EMAIL: 你的邮箱地址
  • NCBI_API_KEY: 你的 PubMed API Key

获取 API Key: https://ncbiinsights.ncbi.nlm.nih.gov/2017/11/02/new-api-keys-for-the-e-utilities/

配置方式(任选其一):

方式 1 - OpenClaw 配置文件 ~/.openclaw/openclaw.json:

{
  "env": {
    "NCBI_EMAIL": "[email protected]",
    "NCBI_API_KEY": "your_api_key"
  }
}

方式 2 - 环境变量:

export NCBI_EMAIL="[email protected]"
export NCBI_API_KEY="your_api_key"

定时任务:

  • 执行时间:每天早上 8:00(北京时间)
  • 搜索范围:前一天新增文献

脚本

  • scripts/pubmed_search.py - PubMed API 搜索和日报生成

⚠️ 安全注意事项

1. API Key 配置

2. .env 文件安全

  • 如果使用 .env 文件,只放置 NCBI 相关凭证
  • 不要在同一文件放其他不相关的 secrets
  • .env 文件已加入 .gitignore,不会提交到 Git

3. 网络活动说明

  • pubmed_search.py: 直接调用 PubMed API(ncbi.nlm.nih.gov)
  • search_bioinfo.py: 调用 OpenClaw 的 web_search 工具(会发送到配置的搜索提供商)
  • 如需限制网络访问,可在隔离环境中运行

4. 飞书上传(如需自动发布)

  • generate_daily.sh 引用飞书文档创建步骤
  • 需要配置飞书 API 凭证才能自动上传
  • 如未配置凭证,脚本会生成文件供手动上传

依赖

  • Python 3.6+
  • requests 库

使用示例

# 生成今日日报
cd ~/.openclaw/workspace/skills/bioinfo-daily
python3 scripts/pubmed_search.py

# 输出保存至 /tmp/bioinfo_daily_YYYYMMDD.txt
Usage Guidance
This skill appears to do what it says: fetch PubMed results, filter high‑impact journals, and generate a Chinese daily report. Before installing: (1) be aware you must provide NCBI_EMAIL and NCBI_API_KEY (the skill will read them from environment, ~/.openclaw/openclaw.json, or a .env in the skill dir) — the registry listing currently omits this; (2) if you enable automated upload, you will need to provide Feishu credentials — otherwise the script only writes files for manual upload; (3) search_bioinfo.py invokes 'openclaw web_search' (which uses your configured search provider) — confirm that web_search is configured to a provider you trust; (4) run the scripts in an isolated environment if you are concerned about network activity; and (5) because the source is 'unknown' and the package metadata points to a GitHub repo, consider reviewing or running the code locally before granting it cron/automatic execution.
Capability Analysis
Type: OpenClaw Skill Name: bioinfo-daily-skill Version: 1.0.1 The skill bundle is a legitimate tool for generating bioinformatics research reports by querying the PubMed API. The code in `scripts/pubmed_search.py` and `scripts/search_bioinfo.py` performs standard API requests to NCBI and uses the OpenClaw `web_search` utility as intended. Sensitive credentials like API keys are handled via environment variables or `.env` files, and there is no evidence of data exfiltration, malicious execution, or prompt injection.
Capability Assessment
Purpose & Capability
The skill implements a PubMed-based daily-report generator and only requests capabilities that make sense for that purpose (calling PubMed E-utilities, filtering high‑impact journals, optional Feishu upload). However, the registry metadata claims no required environment variables while SKILL.md and the scripts clearly require NCBI_EMAIL and NCBI_API_KEY. This is an inconsistency in metadata (likely oversight) but not malicious.
Instruction Scope
Runtime instructions and scripts stay within the declared scope: they read a local .env in the skill directory (or environment/openclaw config), call PubMed APIs (ncbi.nlm.nih.gov), optionally use OpenClaw's web_search tool, generate a /tmp text/markdown report, and optionally prepare content for Feishu. There are no instructions to read unrelated system secrets or transmit data to unknown endpoints.
Install Mechanism
This is effectively instruction-plus-scripts (no install spec that downloads external archives). All code is included in the skill bundle; there are no network downloads or non-standard install steps in the package files provided.
Credentials
The scripts legitimately require NCBI_EMAIL and NCBI_API_KEY (and optionally Feishu credentials for auto-upload). Those environment variables are appropriate for the task. The concern is that the registry-level 'Required env vars' field is empty, so the platform metadata under-reports required credentials — the omission should be corrected before automated installs.
Persistence & Privilege
The skill does not request always:true, does not modify other skills, and its runtime artifacts are limited to reading local config/.env and writing report files under /tmp and within the skill directory. Cron wrappers are provided but nothing forces permanent or elevated privileges.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install bioinfo-daily-skill
  3. After installation, invoke the skill by name or use /bioinfo-daily-skill
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- Added a new "安全注意事项" (Security Notes) section in the documentation, covering API Key requirements, .env file safety, network activity, and Feishu (飞书) upload options. - Clarified that `.env` files are included in `.gitignore` and should only contain NCBI credentials. - The script now displays a warning if the required API Key is missing. - Documentation improvements throughout to better guide secure usage and automated publishing workflows.
v1.0.0
Bioinfo Daily skill v1.0.0 – 自动生成生物信息学/肿瘤学高水平研究日报: - 支持每日通过 PubMed API 自动获取 CNS 及 Nature Index 期刊相关前沿文献 - 智能筛选生物信息学、肿瘤免疫、单细胞、空间转录组等领域重点内容 - 为每篇文献生成 30 字中文亮点及结构化摘要 - 支持定时任务每日自动生成与手动查询最新文献 - 输出格式规范,便于团队阅读和分享 - 简单配置 API Key 和定时任务,易于集成至工作流
Metadata
Slug bioinfo-daily-skill
Version 1.0.1
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 2
Frequently Asked Questions

What is Bioinfo Daily?

每日生物信息学与肿瘤学研究进展日报生成器。使用 PubMed API 自动搜索前一天的 CNS 及 Nature Index 期刊文献,筛选生物信息学、肿瘤免疫、单细胞测序、空间转录组等领域的高影响力研究,生成包含中文亮点介绍的日报。使用场景:(1) 设置定时任务每天自动获取研究进展并发送到飞书 (2) 手动查询... It is an AI Agent Skill for Claude Code / OpenClaw, with 368 downloads so far.

How do I install Bioinfo Daily?

Run "/install bioinfo-daily-skill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Bioinfo Daily free?

Yes, Bioinfo Daily is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Bioinfo Daily support?

Bioinfo Daily is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Bioinfo Daily?

It is built and maintained by ShixiangWang (@shixiangwang); the current version is v1.0.1.

💬 Comments