bibtex-management-guide

name	bibtex-management-guide
description	Clean, format, deduplicate, and manage BibTeX bibliography files for LaTeX
metadata	{"openclaw":{"emoji":"🗃️","category":"writing","subcategory":"citation","keywords":["BibTeX formatting","BibTeX conversion","bibliography cleanup","reference deduplication","citation management"],"source":"wentor"}}

BibTeX Management Guide

A skill for maintaining clean, consistent, and complete BibTeX bibliography files. Covers formatting standards, deduplication, common errors, and automated cleanup workflows essential for LaTeX-based academic writing.

BibTeX Entry Standards

Required Fields by Entry Type

% Article in a journal
@article{smith2024deep,
  author    = {Smith, John A. and Doe, Jane B.},
  title     = {Deep Learning for Climate Prediction: A Comparative Study},
  journal   = {Nature Machine Intelligence},
  year      = {2024},
  volume    = {6},
  number    = {3},
  pages     = {234--248},
  doi       = {10.1038/s42256-024-00001-1}
}

% Conference proceedings
@inproceedings{lee2024attention,
  author    = {Lee, Wei and Chen, Li},
  title     = {Attention Mechanisms for Scientific Document Understanding},
  booktitle = {Proceedings of the 62nd Annual Meeting of the ACL},
  year      = {2024},
  pages     = {1123--1135},
  publisher = {Association for Computational Linguistics},
  doi       = {10.18653/v1/2024.acl-main.89}
}

% Book
@book{bishop2006pattern,
  author    = {Bishop, Christopher M.},
  title     = {Pattern Recognition and Machine Learning},
  publisher = {Springer},
  year      = {2006},
  isbn      = {978-0387310732}
}

Automated BibTeX Cleanup

Deduplication

import re
from collections import defaultdict

 () -> []:
    
    entries = []
    pattern = 
    matches = re.finditer(pattern, bib_content, re.DOTALL)

       matches:
        entry = {
            : .group().lower(),
            : .group().strip(),
            : .group(),
            : {}
        }

        fields_str = .group()
        field_pattern = 
         field_match  re.finditer(field_pattern, fields_str, re.DOTALL):
            entry[][field_match.group().lower()] = field_match.group().strip()

        entries.append(entry)

     entries


 () -> :
    
    seen_dois = {}
    seen_titles = {}
    duplicates = []
    unique = []

     entry  entries:
        doi = entry[].get(, ).lower().strip()
        title = entry[].get(, ).lower().strip()
        title_normalized = re.sub(, , title)

        is_duplicate = 

        
         doi  doi  seen_dois:
            duplicates.append({
                : entry[],
                : seen_dois[doi],
                : 
            })
            is_duplicate = 
         doi:
            seen_dois[doi] = entry[]

        
          is_duplicate  title_normalized:
             title_normalized  seen_titles:
                duplicates.append({
                    : entry[],
                    : seen_titles[title_normalized],
                    : 
                })
                is_duplicate = 
            :
                seen_titles[title_normalized] = entry[]

          is_duplicate:
            unique.append(entry)

     {
        : (unique),
        : (duplicates),
        : duplicates,
        : unique
    }