citation-management

TravisCao's avatarfrom TravisCao

DOI转BibTeX、文献搜索、元数据提取、引用验证。用于论文引用管理。

⭐0stars🔀0forks📁View on GitHub🕐Updated Jan 8, 2026
[Academic Research]

When & Why to Use This Skill

This Claude skill provides a comprehensive suite for academic citation management, enabling users to automate DOI-to-BibTeX conversion, perform advanced Google Scholar searches, extract publication metadata from multiple identifiers (DOI, PMID, arXiv), and validate BibTeX files for formatting accuracy and completeness.

Use Cases

  • Automated BibTeX Generation: Quickly convert single or batch DOIs into standardized BibTeX entries for seamless integration into LaTeX or Overleaf research papers.
  • Literature Discovery and Harvesting: Search Google Scholar for specific research topics with customized year filters and automatically extract metadata for the top results.
  • Multi-Source Metadata Extraction: Retrieve detailed publication information directly from arXiv IDs, PubMed IDs (PMID), or journal URLs to build organized research databases.
  • Citation Quality Assurance: Validate existing BibTeX files to identify missing mandatory fields (author, title, year) and ensure bibliographic data meets submission standards.
namecitation-management
descriptionDOI转BibTeX、文献搜索、元数据提取、引用验证。用于论文引用管理。

Citation Management

工具列表

脚本 功能
doi_to_bibtex.py DOI 转 BibTeX
search_google_scholar.py Google Scholar 搜索
extract_metadata.py 从 DOI/PMID/arXiv/URL 提取元数据
validate_citations.py 验证 BibTeX 文件

用法

DOI 转 BibTeX

# 单个DOI
uvx scripts/doi_to_bibtex.py 10.1109/TPWRS.2023.1234567

# 批量（从文件读取）
uvx scripts/doi_to_bibtex.py -i dois.txt -o references.bib

# 输出JSON格式
uvx scripts/doi_to_bibtex.py 10.1109/xxx --format json

Google Scholar 搜索

# 基础搜索
uvx scripts/search_google_scholar.py "smart grid optimization" --limit 20

# 按年份过滤
uvx scripts/search_google_scholar.py "deep reinforcement learning" \
  --year-start 2020 --year-end 2024 --limit 50

# 使用代理（降低被封风险）
uvx scripts/search_google_scholar.py "query" --use-proxy

注意：Google Scholar 有反爬机制，建议：

  • 每次请求间隔 10-30 秒
  • 单次不要查太多（<50篇）
  • 被封了换IP或等一段时间

提取元数据

# 从DOI提取
uvx scripts/extract_metadata.py 10.1109/TPWRS.2023.1234567

# 从arXiv ID提取
uvx scripts/extract_metadata.py 2301.00001

# 从URL提取
uvx scripts/extract_metadata.py "https://arxiv.org/abs/2301.00001"

# 批量提取
uvx scripts/extract_metadata.py -i identifiers.txt -o metadata.json

验证引用

# 验证BibTeX文件
uvx scripts/validate_citations.py references.bib

# 输出JSON格式的验证报告
uvx scripts/validate_citations.py references.bib --format json -o report.json

检查内容：

  • 必填字段是否完整（author, title, year等）
  • 推荐字段是否存在（volume, pages, doi等）
  • 格式是否正确