鱼皮AI导航
鱼皮AI导航
  • 主页
  • 社区
  • AI工具
  • AI知识库
  • AI提示词
  • MCP
  • Skills
  • AI学习资源
  • AI资讯
  • GitHub开源
登录/注册

arxiv-search

支持从 arXiv 开放数据库中检索物理学、数学、计算机科学、定量生物学等领域的预印本论文,可按关键词查找最新研究成果、方法论文及跨学科应用文献,适用于追踪前沿学术动态和获取尚未正式发表的研究内容。

研究
访问 GitHub
文档Skills.MD
name
arxiv-search
description
Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields

arXiv Search Skill

This skill provides access to arXiv, a free distribution service and open-access archive for scholarly articles in physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering, systems science, and economics.

When to Use This Skill

Use this skill when you need to:

  • Find preprints and recent research papers before journal publication
  • Search for papers in computational biology, bioinformatics, or systems biology
  • Access mathematical or statistical methods papers relevant to biology
  • Find machine learning papers applied to biological problems
  • Get the latest research that may not yet be in PubMed

How to Use

The skill provides a Python script that searches arXiv and returns formatted results.

Basic Usage

Note: Always use the absolute path from your skills directory (shown in the system prompt above).

If running deepagents from a virtual environment:

▼
bash
复制代码
.venv/bin/python [YOUR_SKILLS_DIR]/arxiv-search/arxiv_search.py "your search query" [--max-papers N]

Or for system Python:

▼
bash
复制代码
python3 [YOUR_SKILLS_DIR]/arxiv-search/arxiv_search.py "your search query" [--max-papers N]

Replace [YOUR_SKILLS_DIR] with the absolute skills directory path from your system prompt (e.g., ~/.deepagents/agent/skills or the full absolute path).

Arguments:

  • query (required): The search query string (e.g., "neural networks protein structure", "single cell RNA-seq")
  • --max-papers (optional): Maximum number of papers to retrieve (default: 10)

Examples

Search for machine learning papers:

▼
bash
复制代码
.venv/bin/python ~/.deepagents/agent/skills/arxiv-search/arxiv_search.py "deep learning drug discovery" --max-papers 5

Search for computational biology papers:

▼
bash
复制代码
.venv/bin/python ~/.deepagents/agent/skills/arxiv-search/arxiv_search.py "protein folding prediction"

Search for bioinformatics methods:

▼
bash
复制代码
.venv/bin/python ~/.deepagents/agent/skills/arxiv-search/arxiv_search.py "genome assembly algorithms"

Output Format

The script returns formatted results with:

  • Title: Paper title
  • Summary: Abstract/summary text

Each paper is separated by blank lines for readability.

Features

  • Relevance sorting: Results ordered by relevance to query
  • Fast retrieval: Direct API access with no authentication required
  • Simple interface: Clean, easy-to-parse output
  • No API key required: Free access to arXiv database

Dependencies

This skill requires the arxiv Python package. The script will detect if it's missing and show an error.

If you see "Error: arxiv package not installed":

If running deepagents from a virtual environment (recommended), use the venv's Python:

▼
bash
复制代码
.venv/bin/python -m pip install arxiv

Or for system-wide install:

▼
bash
复制代码
python3 -m pip install arxiv

The package is not included in deepagents by default since it's skill-specific. Install it on-demand when first using this skill.

Notes

  • arXiv is particularly strong for:
    • Computer science (cs.LG, cs.AI, cs.CV)
    • Quantitative biology (q-bio)
    • Statistics (stat.ML)
    • Physics and mathematics
  • Papers are preprints and may not be peer-reviewed
  • Results include both recent uploads and older papers
  • Best for computational/theoretical work in biology
研究

快捷安装

复制到终端去安装 Skill

npxskillsaddlangchain-ai/deepagents--skill"arxiv-search"
站长:程序员鱼皮 老鱼简历 商务合作 增值电信业务经营许可证
2026 鱼皮AI导航 | 沪ICP备19026706号-6
站长:程序员鱼皮 老鱼简历 商务合作 增值电信业务经营许可证
2026 鱼皮AI导航 | 沪ICP备19026706号-6
🔥热门工具
朱雀AI检测朱雀AI检测
朱雀AI检测助手朱雀AI检测助手
LovartLovart
老鱼简历老鱼简历
WritePass官网WritePass官网
面多多面多多
CursorCursor
星月写作星月写作
朱雀AI检测助手朱雀AI检测助手
零感AI零感AI
Skills 推荐
prime-numbers
面向图论中的素数问题求解,提供素性判定、整数分解、素数分布分析及模运算定理验证等核心能力,支持从基础试除到概率化与确定性算法的多层次策略选择,适用于理论推导与计算验证相结合的研究场景。
research
面向技术方案的深度调研能力,通过网络搜索、GitHub 仓库分析和多源证据采集,支持在实施前全面评估技术选型,确保每个推荐方案均基于官方文档、活跃代码库及真实应用案例等至少两项可靠依据。
rank-tracker
持续监控关键词在传统搜索结果与AI生成内容中的排名变化,分析趋势波动并识别显著升降,支持多维度对比竞争格局与SERP特征占有情况,输出可视化报告及可执行优化建议,适用于搜索引擎营销策略的动态调整。
research-grants
面向 NSF、NIH、DOE 和 DARPA 等联邦机构的科研基金申请,提供从选题定位、立项依据、技术路线设计、创新性阐述、可行性论证到预算编制与合规性审查的全流程支持,强调科学严谨性、跨学科整合能力及社会价值转化路径。
gsea-enrichment
执行基因集富集分析时,需先将通路数据库文件加载为字典格式,再进行富集计算,确保使用正确的数据结构与物种参数,支持多类功能注释数据库的整合分析与可视化。