百度学术助手 (Baidu Scholar Helper)

一键搜索学术论文，自动下载PDF，智能总结核心工作与创新点。支持百度学术+arXiv，按引用量排序，科研必备工具。

Security Scan

The skill's code, instructions, and declared permissions are consistent with a paper-search-and-download helper: it scrapes Baidu Xueshu and arXiv, downloads PDFs to ~/Desktop/papers, extracts text/images with poppler tools, and summarizes content — no unexplained credential requests or hidden endpoints were found.

Purpose & Capability

Name/description (paper search, PDF download, summarization) align with included scripts and declared dependencies (requests, BeautifulSoup, poppler). The required file-write/network permissions and use of pdftotext/pdfimages are proportional to extracting PDFs and model figures.

Instruction Scope

Runtime instructions and scripts perform web requests to Baidu Xueshu, arXiv, and Semantic Scholar, parse pages, and download PDFs into ~/Desktop/papers. They also run local external tools (pdftotext/pdfimages) on downloaded PDFs. These actions are consistent with the stated purpose, but the SKILL.md's '一次性完成所有操作，不要分步骤' (perform all steps at once) gives the agent broad discretion to download many files in one run — users should be aware of network, captcha, and disk impact.

Install Mechanism

No remote arbitrary binary downloads. Dependencies are standard Python packages (pip) and OS package manager installation of poppler-utils (pdfimages/pdftotext). This is a common, low-risk install pattern.

Credentials

The skill requests no environment variables, no credentials, and declares only network and file-write permissions. There are no requests for unrelated secrets or system config paths. Network calls go to expected services (xueshu.baidu.com, arxiv.org, semanticscholar API).

Persistence & Privilege

always is false and there is no code that modifies other skills or system agent configuration. The skill writes files only under ~/Desktop/papers and uses /tmp for temp work as declared.

Assessment

This skill appears coherent with its stated purpose, but consider the following before installing: 1) It will download PDFs from the web into ~/Desktop/papers — check disk space and run in a directory you control (not as root). 2) It scrapes Baidu Xueshu and may trigger captchas or unexpected redirects; downloaded links can point to arbitrary hosts, so inspect downloads before opening. 3) The scripts call local tools (pdftotext/pdfimages) — install poppler from your OS package manager to avoid third‑party binaries. 4) Because SKILL.md advises performing all steps in one run, the agent may autonomously download multiple papers; run first in a sandbox or manually invoke scripts to verify behavior. 5) If you need stricter privacy/firmware policies, review the scripts yourself (they are included) before use.

百度学术助手 (Baidu Scholar Helper) V1.0.0

一键搜索学术论文，自动下载PDF，智能总结核心工作与创新点。

功能清单

百度学术

• ✅ 关键词搜索 + 年份筛选
• ✅ 按引用量排序（高引用在前）
• ✅ 每次显示5-10篇论文
• ✅ 自动提取核心工作
• ✅ 自动提取创新点
• ✅ 显示模型图（如有）
• ✅ 显示论文链接
• ✅ 自动下载PDF

arXiv

• ✅ 关键词搜索（官方API）
• ✅ 按相关度排序
• ✅ 自动提取核心工作
• ✅ 自动提取创新点
• ✅ 显示arXiv分类
• ✅ 显示论文链接
• ✅ 自动下载PDF

---

安装指南

1. 安装 Python 依赖

pip install requests beautifulsoup4 Pillow

2. 安装系统依赖（用于提取PDF模型图）

Ubuntu/Debian:

sudo apt-get install -y poppler-utils

macOS:

brew install poppler

Fedora/CentOS:

sudo dnf install -y poppler-utils
# 或
sudo yum install -y poppler-utils

3. 验证安装

# 检查 poppler-utils 是否安装成功
which pdftotext pdfimages

---

PDF保存规则

保存位置

~/Desktop/papers/<论文方向>/

每次搜索会自动创建以关键词命名的文件夹，方便分类管理。

命名格式

标题_年份_J.pdf   # 期刊论文
标题_年份_C.pdf   # 会议论文

arXiv预印本也按此格式命名（根据分类自动判断J/C）。

---

使用方法

命令行

# 百度学术
python scripts/search.py baidu 大模型
python scripts/search.py baidu 人工智能 2024

# arXiv
python scripts/search.py arxiv transformer
python scripts/search.py arxiv "deep learning" 5

对话方式

用户：百度学术搜索 大模型
AI：运行脚本，返回论文列表 + 核心工作 + 创新点 + PDF下载

用户：arXiv GPT 5
AI：搜索arXiv并下载前5篇论文

---

输出示例

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📄 【1】引用量：⭐1523
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📌 标题：Attention Is All You Need
👥 作者：Vaswani A, Shazeer N, Parmar N
📚 来源：NeurIPS 2017
🔗 链接：https://...

🧠 【核心工作】
   本文提出了一种新的简单网络架构——Transformer，完全基于注意力机制，
   彻底摒弃了循环和卷积。

💡 【创新点】
   提出多头注意力机制，在机器翻译任务上取得了最优性能，同时训练速度大幅提升。

🖼️ 【模型图】
   https://...

⬇️  下载PDF...
✅ 已下载：Attention Is All You Need_2017_C.pdf

---

脚本说明

脚本	说明
main.py	百度学术搜索脚本
arxiv_search_v2.py	arXiv API搜索脚本
search.py	统一入口脚本
extract_model_figure.py	PDF模型图提取脚本

---

注意事项

1. 百度学术可能触发验证码拦截
2. arXiv API有速率限制，脚本已内置重试机制
3. 下载的PDF请用于学术研究，尊重版权
4. 引用量数据来自百度学术，仅供参考
5. 模型图提取功能需要安装 poppler-utils

---

系统要求

• Python 3.7+
• 网络连接（访问百度学术/arXiv）
• 磁盘空间（存储下载的PDF）