citation-management
Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.
Profile →npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill citation-management --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Manage citations systematically throughout the research and writing process. This skill provides tools and strategies for searching academic databases (Google Scholar, PubMed), extracting accurate metadata from multiple sources (CrossRef, PubMed, arXiv), validating citation information, and generating properly formatted BibTeX entries.
How it works
- Phase 1: Paper discovery and search using Google Scholar and PubMed, with commands such as:
- python scripts/search_google_scholar.py "CRISPR gene editing" --limit 50 --output results.json
- python scripts/search_pubmed.py "Alzheimer's disease treatment" --limit 100 --output alzheimers.json
- Phase 2: Metadata extraction from DOIs, PMIDs, arXiv IDs, or URLs using scripts like:
- python scripts/extract_metadata.py --doi 10.1038/s41586-021-03819-2
- python scripts/extract_metadata.py --pmid 34265844
- python scripts/extract_metadata.py --arxiv 2103.14030
- Phase 2.5: Mandatory metadata enrichment via web search to fill missing fields, including steps to:
- Scan for incomplete entries
- Use parallel_web.py in various modes (search, extract, crossref, scholar) with appropriate inputs and outputs
- Update BibTeX entries in references.bib by adding missing fields and logging fixes
- Handle unfindable metadata by adding a note field and logging the exception
- Phase 3: BibTeX formatting with commands for formatting, sorting, deduplication, and validation, for example:
- python scripts/format_bibtex.py references.bib --output formatted_references.bib
- python scripts/format_bibtex.py references.bib --sort key --output sorted_references.bib
- python scripts/format_bibtex.py references.bib --validate --report validation_report.txt
- Phase 4: Citation validation to verify DOIs, required fields, data consistency, duplicates, and format compliance, including:
- python scripts/validate_citations.py references.bib
- python scripts/validate_citations.py references.bib --auto-fix --output validated_references.bib
- python scripts/validate_citations.py references.bib --report validation_report.json --verbose
- Phase 5: Integration with writing workflow, building references for manuscripts, including search and metadata extraction steps.
When to use it
Use this skill when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.
What it can touch
Contains allowed-tools: Read, Write, Edit, Bash. The workflow relies on Python scripts such as:
- scripts/search_google_scholar.py
- scripts/search_pubmed.py
- scripts/extract_metadata.py
- scripts/parallel_web.py
- scripts/format_bibtex.py
- scripts/validate_citations.py These are invoked with commands shown in the steps above to perform discovery, extraction, enrichment, formatting, and validation.
Caveats
License is NOASSERTION. The skill describes expanding via web search to fill missing fields and logging fixes; it notes potential incomplete entries and ways to handle them. It emphasizes that metadata gaps should be enriched or annotated with a note if unrecoverable.
<!-- ╔══════════════════════════════════════════════════════════════╗ ║ 本文件为开源 Skill 原始文档，收录仅供学习与研究参考 ║ ║ CoPaper.AI 收集整理 | https://copaper.ai ║ ╚══════════════════════════════════════════════════════════════╝ 来源仓库: https://github.com/K-Dense-AI/claude-scientific-writer 项目名称: claude-scientific-writer 开源协议: MIT License 收录日期: 2026-04-02 声明: 本文件版权归原作者所有。此处收录旨在为社会科学实证研究者 提供 AI Agent Skills 的集中参考。如有侵权，
What does the citation-management skill do?
Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.
How do I install it?
Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill citation-management --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From brycewang-stanford/Auto-Empirical-Research-Skills, a repository with 3,244 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.