Verified:GitHub

literature-verifier

Verify literature citations across DOIs, titles, URLs, ISBNs, and Chinese records.

Updated Apr 17, 2026

Search Tags:#hallucination detection #reference list #citation audit #literature verification #doi validation #cnki verification

Ready to run

npx skills add https://github.com/RenJW418/RenJW-Research_skill --skill literature-verifier

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: literature-verifier
Source: https://github.com/RenJW418/RenJW-Research_skill/tree/main/literature-verifier
Command: npx skills add https://github.com/RenJW418/RenJW-Research_skill --skill literature-verifier

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill verifies whether user-provided literature references are real and accurately reported, and it detects hallucinated or fabricated citations in both English and Chinese sources.

Core Features & Use Cases

Reference authenticity verification: Checks existence and validates core metadata such as title, authors, venue/journal, year, DOI, ISBN, and URLs across multiple source types.
Identifier-based workflows: Uses DOI resolution (CrossRef/doi.org), CrossRef title/author search, and URL reachability/metadata extraction; supports books via ISBN lookups.
Chinese literature核查 (中文文献核查): Prioritizes CNKI direct search via Chrome CDP (MCP tools) and falls back to required multi-step WebSearch across CNKI/Wanfang/Baidu Scholar when CDP is unavailable.
Hallucination pattern guidance: When verification fails, it recommends relevant hallucination patterns from provided reference docs to explain likely fabrication vs metadata errors.
Batch reference auditing: Produces per-item verdicts and a summary table with confidence levels suitable for reference list cleanup.

Quick Start

Ask the AI to verify the reference list and return a table of confirmed vs likely real vs likely fabricated vs metadata-error results.

Frequently Asked Questions about literature-verifier

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I detect hallucinated citations and fabricated references in a paper?▼

Hallucinated citation detection verifies the authenticity of your reference list by validating DOIs, titles, URLs, and ISBNs against authoritative sources to identify fabricated academic references.

How do I verify Chinese literature references on CNKI and Wanfang?▼

Chinese literature verification prioritizes CNKI direct search via Chrome CDP, applying a mandatory multi-source WebSearch fallback across Wanfang and Baidu Scholar to confirm Chinese academic records.

Can I batch audit an entire reference list for DOI validation errors?▼

Batch reference auditing supports full reference list cleanup by producing per-item verdicts and a summary table categorizing references as confirmed, likely real, likely fabricated, or metadata-error.

Does DOI validation work for conference papers, preprints, and monographs?▼

DOI validation applies across journal articles, conference papers, preprints, books, monographs, dissertations, and government documents, using CrossRef and doi.org resolution to verify source existence.

Why does a citation verification fail and how are hallucination patterns identified?▼

When verification fails, the system recommends relevant hallucination patterns from reference docs to explain whether the failure indicates likely fabrication or a metadata error in the citation.