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-code

Installs 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

  1. Verify Citation Presence: Every factual claim must have a citation
  2. Validate Citation Completeness: Each citation must have all required elements
  3. Assess Source Quality: Rate each source using the A-E quality scale
  4. Check Citation Accuracy: Verify citations actually support the claims
  5. Detect Hallucinations: Identify claims with no supporting sources
  6. Format Consistency: Ensure uniform citation format throughout

Citation Completeness Requirements

Every Citation Must Include:

  1. Author/Organization - Who created the content
  2. Publication Date - When it was published (YYYY format)
  3. Source Title - Name of the work
  4. URL/DOI - Direct link to verify
  5. 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

More from liangdabiao/claude-code-stock-deep-research-agent

All 3
1jorgealves avatarskill-validatorjorgealves/agent_skillsValidates agent skill definitions against agentskills.io and AGENTS.md rules. Use when creating or modifying skills to ensure they are machine-readable and docu216skills.sh installs
2langchain-ai avatarcudf-analyticslangchain-ai/deepagentsUse for GPU-accelerated data analysis on datasets, CSVs, or tabular data using NVIDIA cuDF. Triggers when tasks involve groupby aggregations, statistical summar216skills.sh installs
3aktsmm avatarvscode-extension-guideaktsmm/agent-skillsGuide for creating VS Code extensions and plugins from scratch through Marketplace publication. Use when developing a VS Code extension/plugin, adding commands 215skills.sh installs
4arpitg1304 avatarrobotics-testingarpitg1304/robotics-agent-skills>215skills.sh installs
5el-feo avatarcucumber-gherkinel-feo/ai-contextBDD testing with Cucumber and Gherkin for Ruby and Rails applications. Use when writing feature files (.feature), step definitions, hooks, or implementing Behav215skills.sh installs
6jorgealves avatarpython-venv-managerjorgealves/agent_skillsSetup and validate Python virtual environments (venv, virtualenv, conda). Use to ensure isolated dependencies and correct Python versions for projects.215skills.sh installs