AI Citation Verification for Manuscripts: Accurate and Reliable

AI Citation Verification for Manuscripts: Accurate and Reliable

This AI agent skill provides a methodical approach to verifying citation metadata and supporting manuscript claims during drafting or pre-submission phases. It does not invent references, ensuring accuracy and integrity in scholarly work.

What this skill does

• Reads the manuscript, alongside its bibliography and any existing `Evidence ID` records, to compile a list of unique citation keys and identify each location where a specific scientific claim is supported by these citations.
• Resolves metadata using primary or authoritative scholarly sources such as DOI registrations, publisher databases, conference proceedings, or arXiv versions. It verifies details like title, authors, venue, year, identifier, and the specific version cited.
• Examines the source material of claim-dependent citations to document the specific section, table, figure, or page that supports the claim. Metadata verification alone is insufficient to confirm claim support.
• Categorizes each citation as `verified`, `metadata-only`, `claim-not-supported`, `unresolved`, `conflicted`, or `replace/remove`. The system strictly avoids inferring missing metadata or creating fictitious citations.
• Maintains the canonical identifiers, retrieval details, and exact support information for significant sources, including local artifacts when available. Records results in the `docs/11_pre_submission_audit.md` file under the section “引文核验”.

Who it is for

This skill is tailored for developers and teams utilizing AI coding agents like Claude Code, Cursor, and Codex. It is particularly beneficial for scholars, researchers, and editors involved in drafting and verifying academic manuscripts.

Use cases

• Academic researchers interested in ensuring the accuracy and legitimacy of cited works within their manuscripts.
• Editors needing to validate citation support for claims prior to manuscript submission.
• Development teams integrating citation verification into AI agent workflows for comprehensive manuscript checks.

Technical details

This citation verification skill is designed for use with AI applications, specifically offering compatibility with agent-skills packages for platforms such as Claude Code, Cursor, and Codex. It focuses on efficiently managing workflows related to scholarly citation verification without promising specific business outcomes.

Source & Licence

This package is built on open-source work published by wangyi0403 (wangyi0403/dl-research-workflow) and distributed under MIT. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted, provided the original copyright and licence notice are retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.