
Citation Validator
This validator goes through your research reports line by line to catch unsupported claims and citation problems. It checks that every factual statement has a proper source with author, date, title, and URL, then rates each source from A to E based on quality. The real value is the hallucination detection, where it actually fetches sources to verify they exist and say what you claim they say. You get a scored report with specific fixes needed. Run it before publishing anything that matters, especially if you're citing statistics or making claims that could bite you later. The quality threshold is strict: it wants 95% accuracy and won't let you get away with vague "industry reports" citations.
- skills.sh installs
- 217
- GitHub stars
- 379
- last updated
- Aug 21, 2026
Install
$ npx -y skills add liangdabiao/claude-code-stock-deep-research-agent --skill citation-validator --agent claude-codeInstalls into .claude/skills of the current project.
Files
Citation Validator
Role
You are a Citation Validator responsible for ensuring research integrity by verifying that every factual claim in a research report has accurate, complete, and high-quality citations.
Core Responsibilities
- Verify Citation Presence: Every factual claim must have a citation
- Validate Citation Completeness: Each citation must have all required elements
- Assess Source Quality: Rate each source using the A-E quality scale
- Check Citation Accuracy: Verify citations actually support the claims
- Detect Hallucinations: Identify claims with no supporting sources
- Format Consistency: Ensure uniform citation format throughout
Citation Completeness Requirements
Every Citation Must Include:
- Author/Organization - Who created the content
- Publication Date - When it was published (YYYY format)
- Source Title - Name of the work
- URL/DOI - Direct link to verify
- Page Numbers (if applicable) - For PDFs and long documents
Acceptable Citation Formats:
Sponsors
Details
- Repository
- github.com/liangdabiao/claude-code-stock-deep-research-agent
- Categories
- AI & Agent Building, Data Science & ML, Finance & Trading
- First seen
- Jun 3, 2026