Finance Paper Daily

每日金融学术论文自动抓取并生成 Excel 报告。从 arXiv (q-fin)、Semantic Scholar、OpenAlex、Google Scholar 四个来源获取最新金融领域论文（量化金融、资产定价、风险管理、算法交易、FinTech等），整理成格式化 Excel 文件保存到用户桌面，文件名为 YY...

Security Scan

The skill's code and instructions match its description: it fetches papers from public APIs/scraping libs and writes a formatted Excel to the user's Desktop; it does not request unrelated credentials or hidden external endpoints.

Purpose & Capability

Name/description (fetch finance papers from arXiv, Semantic Scholar, OpenAlex, Google Scholar and produce an Excel on Desktop) align with the included script which queries those public APIs and builds an Excel file.

Instruction Scope

SKILL.md tells the user to install openpyxl and scholarly and run scripts/fetch_papers.py; the script performs only network calls to the stated APIs, local Excel generation, and writes to ~/Desktop. Note: Google Scholar access uses the scholarly library (unofficial scraping) and is explicitly documented as unstable; the script may auto-install missing Python packages at runtime.

Install Mechanism

No install spec in registry (instruction-only). The script may call pip at runtime (subprocess.check_call) to install openpyxl and scholarly if missing. This is expected for a Python script but means packages will be fetched from PyPI at runtime rather than a reviewed install manifest.

Credentials

The skill does not request environment variables, credentials, or access to system config paths. Its network calls go to public API endpoints (arXiv, semanticscholar.org, api.openalex.org) and use a mailto parameter with a placeholder email; no secret exfiltration is requested or present.

Persistence & Privilege

always:false and no modifications to other skills or system-wide settings. The script writes output only to the user's Desktop directory (created under the user's home) which is consistent with its purpose.

Assessment

This skill appears coherent, but review and run cautiously: (1) inspect scripts/fetch_papers.py before running. (2) Run inside a Python virtualenv rather than using --break-system-packages to avoid altering system packages. (3) Be aware the script will access the internet (arXiv, Semantic Scholar, OpenAlex, and Google Scholar via the scholarly scraper) and may auto-install openpyxl/scholarly from PyPI. (4) Google Scholar scraping is unofficial and may be rate-limited or blocked — expect intermittent failures. (5) If you prefer, copy the script to a controlled environment, confirm the install commands, and run with network access only to the listed public APIs.

每日金融学术论文抓取 → 桌面 Excel 报告。

数据源

来源	API	覆盖方向
arXiv	官方免费	q-fin 全分类（量化金融）
Semantic Scholar	官方免费	金融关键词全文搜索
OpenAlex	官方免费（无需 key）	Economics/Finance 概念
Google Scholar	scholarly 库（非官方）	广泛覆盖，尽力而为

使用方式

运行脚本：

pip3 install openpyxl scholarly --break-system-packages -q
python3 scripts/fetch_papers.py

输出

• 路径：~/Desktop/YYYY-MM-DD_finance_papers.xlsx
• Sheet1「每日论文」：按日期倒序，含标题/作者/摘要/来源/链接，颜色区分来源
• Sheet2「来源统计」：各来源论文数量汇总

注意

• 首次运行需安装依赖：pip3 install openpyxl scholarly --break-system-packages
• Google Scholar 抓取不稳定，失败时自动跳过
• 每次运行覆盖同一天的文件（重复运行安全）