Citation Verification

When you're writing academic papers with AI assistance, this catches the citation errors before they bite you. It walks through a verification workflow using WebSearch, Google Scholar, CrossRef, and arXiv to confirm every reference actually exists and matches what you're claiming. The approach is pragmatic: verify as you write, not after, and always mark citations you can't confirm with [CITATION NEEDED]. Especially useful given that AI-generated citations fail about 40% of the time. It's designed to work alongside ml-paper-writing but you can reference the principles directly when you need the detailed verification steps or claim-checking guidance.

skills.sh installs: 1.5K
GitHub stars: 6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add galaxy-dawn/claude-scholar --skill citation-verification --agent claude-code

Installs into .claude/skills of the current project.

Files

Citation Verification Reference Guide

A reference guide for citation verification in academic paper writing, providing verification principles and best practices.

Core Principle: Proactively verify every citation during the writing process using programmatic or canonical scholarly sources first: arXiv, DOI/CrossRef, Semantic Scholar, publisher landing pages, and Zotero metadata. Google Scholar is useful for manual discovery, but it is not the canonical verification authority.

Core Problems

Citation issues in academic papers seriously impact research integrity:

Fake citations - Citing non-existent papers (common issue with AI-generated citations)
Incorrect information - Mismatched authors, titles, years, etc.
Inconsistent formatting - Mixed citation formats
Missing citations - Referenced but uncited work

These issues can lead to: