Agent skill

citation-management

用于学术研究的综合文献引用管理工具。可搜索 Google Scholar 和 PubMed 论文数据库,提取准确的元数据,验证引用信息,并生成规范格式的 BibTeX 条目。当需要查找论文、核对引用信息、将 DOI 转换为 BibTeX,或在科学写作中确保参考文献准确性时,应使用此功能。

majiayu000github.com/majiayu000GitHub ↗
claude-codecan modify filesMIT
Install
npx skills add majiayu000/claude-skill-registry --skill citation-management-victory-hugo-s2-agent-skill --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 32 KB
Bundled scripts: none
Allowed tools: ReadWriteEditBash
Path: skills/analysis/citation-management-victory-hugo-s2-agent-skill/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

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

  • Provides workflows for Phase 1: Paper Discovery and Search, including scripts to search Google Scholar and PubMed with examples that output JSON files.
  • Phase 2: Metadata Extraction, with commands to extract metadata from DOIs, PMIDs, arXiv IDs, or URLs using specific Python scripts that read identifiers and produce BibTeX entries; metadata sources include CrossRef, PubMed E-utilities, arXiv API, and DataCite API.
  • Phase 3: BibTeX Formatting, detailing entry types (@article, @inproceedings, @book) and examples of required fields; includes commands to format, sort, deduplicate, and validate BibTeX files.
  • Phase 4: Citation Validation, covering comprehensive checks (DOI resolution, required fields, data consistency, duplicates, format compliance) and commands to auto-fix and generate reports.
  • Phase 5: Integration with Writing Workflow, outlining end-to-end steps from search to final bib file usage in LaTeX, and interaction with a literature-review skill for a combined workflow.

When to use it

Use when searching for papers on Google Scholar or PubMed, converting DOIs/PMIDs/arXiv IDs to BibTeX, extracting complete metadata, validating citations, cleaning BibTeX files, or building a bibliography for manuscripts.

What it can touch

  • Tools: Read, Write, Edit, Bash are declared as allowed tools.
  • It instructs using Python scripts (e.g., python scripts/search_google_scholar.py, python scripts/doi_to_bibtex.py, python scripts/extract_metadata.py, python scripts/format_bibtex.py, python scripts/validate_citations.py).

Caveats

  • License: MIT. No explicit risk statements beyond standard validation steps; all checks and operations are described as commands to run. No outcomes guaranteed beyond described procedures.
From the SKILL.md

# Citation Management ## Overview 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. Critical for maintaining citation accuracy, avoiding reference errors, and ensuring reproducible research. Integrates seamlessly with the literature-review skill for comprehensive research workflows. ## When to Use This Skill Use this skill when: - Searching for specific papers on Google Scholar or PubMed - Converting DOIs, PMIDs, or arXiv IDs to properly formatted BibTeX - Extracting complete metadata for citations (authors, title, journal, year, etc.) - Validating existing citations for accuracy - Cleaning and formatting BibTeX files - Finding highly cited papers in a specific field - Verifying that citation information matches the actual publication - Building a bibliography for a manuscript or thesis - Checking for duplicate citations - Ensuring consistent citation formatting ## Visual Enhancement with Scientific

What's inside
Steps it walks through
  1. Overview
  2. When to Use This Skill
  3. Visual Enhancement with Scientific Schematics
  4. Core Workflow
  5. Phase 1: Paper Discovery and Search
  6. Phase 2: Metadata Extraction
  7. Phase 3: BibTeX Formatting
  8. Phase 4: Citation Validation
  9. Phase 5: Integration with Writing Workflow
  10. Search Strategies
  11. Google Scholar Best Practices
  12. PubMed Best Practices
  13. Tools and Scripts
  14. searchgooglescholar.py
Ships with 1 file
  • metadata.json
Commands it runs
python scripts/generate_schematic.py "your diagram description" -o figures/output.png
Search for papers on a topic
python scripts/search_google_scholar.py "CRISPR gene editing" \
Search with year filter
python scripts/search_google_scholar.py "machine learning protein folding" \
Search PubMed
python scripts/search_pubmed.py "Alzheimer's disease treatment" \
Search with MeSH terms and filters
python scripts/search_pubmed.py \
Convert single DOI
More from claude-skill-registry
All skills →
About this skill
What does the citation-management skill do?

用于学术研究的综合文献引用管理工具。可搜索 Google Scholar 和 PubMed 论文数据库,提取准确的元数据,验证引用信息,并生成规范格式的 BibTeX 条目。当需要查找论文、核对引用信息、将 DOI 转换为 BibTeX,或在科学写作中确保参考文献准确性时,应使用此功能。

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill citation-management-victory-hugo-s2-agent-skill --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 majiayu000/claude-skill-registry, a repository with 534 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.

Keep going