
Citation Verification
FreeEnsure accurate citations in academic writing.
Free · Opens the source repo
What Citation Verification does
The Citation Verification skill is designed to support researchers and academic writers in maintaining the integrity of their citations. It provides a structured approach to verifying references, ensuring that every citation is accurate and properly formatted. This is particularly crucial in the context of academic writing, where citation errors can lead to serious consequences, including paper rejections and damage to one's academic reputation.
The skill emphasizes proactive verification during the writing process, encouraging users to check citations as they are added rather than waiting until the paper is complete. It outlines a clear workflow that integrates verification into the writing routine, utilizing canonical scholarly sources such as DOI, arXiv, and publisher landing pages for accurate metadata verification. By following these principles, users can significantly reduce the risk of including fake citations or incorrect information in their work.
Additionally, the skill addresses common citation issues such as inconsistent formatting and missing citations. It provides best practices for preventing these problems, including the importance of using reliable sources and confirming details like authorship and publication year. With an emphasis on the high error rate of AI-generated citations, this skill serves as a crucial tool for anyone engaged in academic writing, ensuring that their references are both credible and verifiable.
Ultimately, the Citation Verification skill is an essential resource for researchers who want to uphold the standards of academic integrity in their work. It not only offers practical guidance on citation verification but also integrates seamlessly with existing writing workflows, making it a valuable addition to any academic writer's toolkit.
When to use it
Use this skill during the academic writing process when adding citations to ensure their accuracy and credibility.
When not to use it
This skill may not be necessary for informal writing or non-academic contexts where citation standards are less stringent.
What you can build with it
Verifying a Journal Article Citation
When writing a research paper, you can use this skill to verify the details of a journal article citation by checking its DOI and confirming the metadata.
Preventing Citation Errors in AI-Assisted Writing
If you're using AI tools to generate citations, this skill can help you verify those citations to ensure they are accurate and credible.
Checking References Before Submission
Before submitting your paper, utilize this skill to systematically verify all citations, ensuring they meet academic standards.
How to install Citation Verification
View source1. Install with the skills CLI
npx skills add galaxy-dawn/claude-scholar/citation-verification --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by galaxy-dawnCitation 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:
- Paper rejection or retraction
- Damage to academic reputation
- Reviewers questioning research rigor
Special risk with AI-assisted writing: AI-generated citations have approximately 40% error rate; every citation must be verified via WebSearch.
Verification Principles
This skill provides verification principles based on canonical scholarly metadata and claim-level checking:
1. Proactive Verification (Verify During Writing)
Core idea: Verify immediately when adding a citation, rather than checking after writing is complete.
- Search for the paper via WebSearch each time a citation is needed
- Confirm the paper exists on Google Scholar
- Add to bibliography only after verification passes
2. Canonical Metadata Verification
Preferred authority order:
- DOI / publisher landing page
- arXiv ID or arXiv landing page
- CrossRef
- Semantic Scholar
- Zotero metadata imported from a verified identifier
- Google Scholar only for manual discovery or fallback lookup
Verification steps:
- Find a DOI, arXiv ID, publisher URL, or verified Zotero item.
- Confirm title, first author, year, venue, and identifier.
- Fetch BibTeX from CrossRef, arXiv, publisher metadata, Zotero, or another programmatic source when possible.
- If only Google Scholar can find the item, mark it as manual verification and do not treat the BibTeX as final until metadata is checked elsewhere.
3. Information Matching Verification
Information that must match:
- Title (minor differences allowed, e.g., capitalization)
- Authors (at least the first author must match)
- Year (±1 year difference allowed, considering preprints)
- Publication venue (conference/journal name)
4. Claim Verification
Key principle: When citing a specific claim, you must confirm the claim actually appears in the paper.
- Use WebSearch to access the paper PDF
- Search for relevant keywords
- Confirm the accuracy of the claim
- Record the section/page where the claim appears
Verification Workflow
Integration into Writing Process
Need a citation during writing
↓
Find DOI / arXiv ID / publisher page / verified Zotero item
↓
Verify metadata with CrossRef / arXiv / Semantic Scholar / publisher / Zotero
↓
Confirm paper details
↓
Get BibTeX
↓
(If citing a specific claim) Verify the claim
↓
Add to bibliography
Key point: Verification is part of the writing process, not a separate post-processing step.
Usage Guide
Using with ml-paper-writing
The verification principles of this skill are integrated into the Citation Workflow of the ml-paper-writing skill.
Auto-trigger: Citation verification is automatically executed when writing papers with the ml-paper-writing skill.
Manual reference: Refer to this skill when you need detailed verification principles.
Verification Step Example
Scenario: Need to cite the Transformer paper
Step 1: WebSearch lookup
Query: "Attention is All You Need Vaswani 2017"
Result: Found multiple sources for the paper
Step 2: Google Scholar verification
Query: "site:scholar.google.com Attention is All You Need Vaswani"
Result: ✅ Paper exists, 50,000+ citations, NeurIPS 2017
Step 3: Confirm details
- Title: "Attention is All You Need"
- Authors: Vaswani, Ashish; Shazeer, Noam; Parmar, Niki; ...
- Year: 2017
- Venue: NeurIPS (NIPS)
Step 4: Get BibTeX
- Click "Cite" on Google Scholar
- Select BibTeX format
- Copy BibTeX entry
Step 5: Add to bibliography
- Paste into .bib file
- Use \cite{vaswani2017attention} in the paper
Handling Verification Failures
If the paper cannot be verified through canonical sources:
- Check spelling - Is the title or author name correct?
- Try different queries - Use different keyword combinations
- Find alternative sources - Try arXiv, DOI, CrossRef, Semantic Scholar, publisher pages, or Zotero
- Mark as pending - Use
[CITATION NEEDED]marker - Notify the user - Clearly state the citation cannot be verified
If information doesn't match:
- Confirm the source - Did you find the correct paper?
- Check versions - Preprint vs. published version
- Update information - Use the most accurate version
- Record discrepancies - Note the reason for differences
Best Practices
Preventing Fake Citations
- Never generate citations from memory - AI-generated citations have 40% error rate
- Use WebSearch to find - Verify every citation through WebSearch
- Confirm on Google Scholar - Verify paper existence on Google Scholar
- Verify promptly - Verify when adding citations, don't wait until finished
Handling Verification Failures
- Don't guess - If you can't find the paper, don't fabricate information
- Mark clearly - Use
[CITATION NEEDED]to mark explicitly - Notify the user - Clearly state which citations cannot be verified
- Provide reasons - Explain why verification failed (not found, info mismatch, etc.)
Improving Verification Accuracy
- Complete queries - Include title, author, year
- Check citation count - Citation count on Google Scholar is a credibility indicator
- Confirm venue - Verify conference/journal name is correct
- Verify claims - When citing specific claims, confirm they exist in the paper
Common Pitfalls
❌ Wrong approach:
- Generating BibTeX from memory
- Skipping Google Scholar verification
- Assuming a paper exists
- Not marking unverifiable citations
✅ Correct approach:
- Search every citation with WebSearch
- Confirm on Google Scholar
- Copy BibTeX from Google Scholar
- Clearly mark unverifiable citations
Summary
Core Principle: Proactively verify every citation during the writing process using WebSearch and Google Scholar.
Key Steps:
- WebSearch to find the paper
- Google Scholar to verify existence
- Confirm details
- Get BibTeX
- Verify claims (if needed)
- Add to bibliography
Failure handling: When verification fails, mark as [CITATION NEEDED] and clearly notify the user.
Integration: The principles of this skill are integrated into the ml-paper-writing skill for automatic verification.
Frequently asked questions about Citation Verification
Similar skills
Scientific Problem Selection
Streamline your research problem selection process.
Nextflow Development
Run nf-core bioinformatics pipelines with ease.
Nature Reviewer Assessment
Simulate peer review for scientific manuscripts.
Research Writing Pipeline
Streamline your scientific writing with structured proposal-first methodologies.
Nature Literature Downloader
Efficiently download academic literature from various sources.
Auto Research
Streamline your NeMo-RL experiments with automated workflows.
