
Citation & Reference Integrity Manager
Audit, verify, and format academic citations across AMA, APA, and Vancouver styles to eliminate AI hallucinations.
- Identify and flag fabricated or 'hallucinated' academic sources
- Ensure in-text citations and reference lists are perfectly synchronized
- Reformat bibliographies into professional AMA, APA, or Vancouver styles
$14
· or 70 creditsSecure checkout via Stripe
Included in download
- Identify and flag fabricated or 'hallucinated' academic sources
- Ensure in-text citations and reference lists are perfectly synchronized
- file_read automation included
- Ready for Cursor
Sample input
Check the citations in this excerpt and format the references in AMA.
Text: Statin therapy reduced cardiovascular events in high-risk patients.1 Adherence remained the main barrier to benefit.2
References:
- Smith J, Lee K. Statins and cardiovascular outcomes. N Engl J Med. 2019;380(9):812-820. doi:10.1056/NEJMoa1900001
- Patel R. Medication adherence in chronic disease. Lancet. 2020;395:doi:10.fake/123
Sample output
REFERENCE INTEGRITY NOTE — 2 references checked, style: AMA
- SYNC: All in-text markers (1, 2) map to a reference-list entry; no orphan or uncited references.
- INTEGRITY: Ref 2 — DOI "10.fake/123" is malformed and volume/page data is missing; reference UNVERIFIED.
- IDENTIFIERS: Ref 1 DOI is well-formed; consider adding a PMID. Ref 2 missing valid DOI and page range.
- FORMATTING: Both references conform to AMA; Ref 2 incomplete pending verification. VERDICT: FAIL — 1 unverifiable reference (Ref 2) must be confirmed against the journal before submission.
Corrected reference list (AMA):
- Smith J, Lee K. Statins and cardiovascular outcomes. N Engl J Med. 2019;380(9):812-820. doi:10.1056/NEJMoa1900001
- Patel R. Medication adherence in chronic disease. Lancet. 2020;395:[volume/pages and valid DOI required — UNVERIFIED].
Audit, verify, and format academic citations across AMA, APA, and Vancouver styles to eliminate AI hallucinations.
$14
· or 70 creditsSecure checkout via Stripe
Also available in a bundle
Content Trust Suite
3 skills · $31
Save 31%Medical & Scientific Writing Suite — Publication-Grade Rigor for AI-Assisted Manuscripts
3 skills · $44
Save 21%Research & Citation Integrity Suite — Trust Your Sources, Ground Your Claims, Get Your Citations Right
3 skills · $30
Save 23%Included in download
- Identify and flag fabricated or 'hallucinated' academic sources
- Ensure in-text citations and reference lists are perfectly synchronized
- file_read automation included
- Ready for Cursor
- Instant install
Sample input
Check the citations in this excerpt and format the references in AMA.
Text: Statin therapy reduced cardiovascular events in high-risk patients.1 Adherence remained the main barrier to benefit.2
References:
- Smith J, Lee K. Statins and cardiovascular outcomes. N Engl J Med. 2019;380(9):812-820. doi:10.1056/NEJMoa1900001
- Patel R. Medication adherence in chronic disease. Lancet. 2020;395:doi:10.fake/123
Sample output
REFERENCE INTEGRITY NOTE — 2 references checked, style: AMA
- SYNC: All in-text markers (1, 2) map to a reference-list entry; no orphan or uncited references.
- INTEGRITY: Ref 2 — DOI "10.fake/123" is malformed and volume/page data is missing; reference UNVERIFIED.
- IDENTIFIERS: Ref 1 DOI is well-formed; consider adding a PMID. Ref 2 missing valid DOI and page range.
- FORMATTING: Both references conform to AMA; Ref 2 incomplete pending verification. VERDICT: FAIL — 1 unverifiable reference (Ref 2) must be confirmed against the journal before submission.
Corrected reference list (AMA):
- Smith J, Lee K. Statins and cardiovascular outcomes. N Engl J Med. 2019;380(9):812-820. doi:10.1056/NEJMoa1900001
- Patel R. Medication adherence in chronic disease. Lancet. 2020;395:[volume/pages and valid DOI required — UNVERIFIED].
About This Skill
Stop AI Hallucinations in Scholarly Writing
AI agents are notorious for "hallucinating" plausible-sounding but non-existent citations. The Citation & Reference Integrity Manager is a specialized audit tool designed for developers and researchers building high-stakes document workflows where accuracy is non-negotiable.
What it does
This skill executes a rigorous five-pass Quality Control (QC) process on any AI-generated text. It doesn't just reformat text; it monitors sync between in-text markers and the bibliography, validates DOI/PMID structures, and flags suspicious references that lack a real-world footprint.
Key Features
- Integrity Auditing: Identifies fabricated authors, journals, or malformed DOIs.
- Style Enforcement: Native support for AMA (11th ed.), Vancouver (ICMJE), and APA (7th ed.).
- Sync Logic: Catches orphan citations and uncited references automatically.
- Structural Validation: Ensures sequential numbering and correct journal abbreviations.
Why use this skill?
Unlike a standard LLM prompt which often struggles to maintain a numbering system or "double-checks" its own lies, this skill follows a structured verification protocol. It produces a professional Reference Integrity Note and a verdict, giving you a programmatic way to block "hallucinated" research from shipping to clients or journals.
Use Cases
- Identify and flag fabricated or 'hallucinated' academic sources
- Ensure in-text citations and reference lists are perfectly synchronized
- Reformat bibliographies into professional AMA, APA, or Vancouver styles
- Validate the structure of DOIs and PubMed IDs for every source
- Generate a formal Reference Integrity Note for peer-review readiness
Known Limitations
Flags references as likely fabricated or unverified based on structural and consistency checks; it does not perform live database lookups, so confirm any UNVERIFIED reference against the journal or a citation database before final submission.
How to Install
mkdir -p ~/.claude/skills && curl -sL https://www.agensi.io/api/install/citation-reference-integrity-manager -o /tmp/citation-reference-integrity-manager.zip && unzip -o /tmp/citation-reference-integrity-manager.zip -d ~/.claude/skills && rm /tmp/citation-reference-integrity-manager.zipFree skills install directly. Paid skills require purchase - use the download button above after buying.
Reviews
No reviews yet - be the first to share your experience.
Only users who have downloaded or purchased this skill can leave a review.
Early access skill
Be the first to review this skill.
Only users who have downloaded or purchased this skill can leave a review.
Security Scanned
Passed automated security review
Permissions
File Scopes
Read-only. The skill needs read access to the document being audited so it can check its citations and reference list. It does not write files, run commands, or access the network.
Tags
Compatible with SKILL.md-compatible agents including Claude Code, Cursor, and GitHub Copilot Extensions.
Creator
PubsProToolkit builds adversarial "gate" skills for AI agents — they catch problems before your output ships, instead of just generating more. From code, security, and infrastructure to content, hiring, contracts, and finance. Built by a CMPP-certified, PhD medical writer who brings regulated-industry rigor to every domain.
Also available in a bundle
Content Trust Suite
3 skills · $31
Save 31%Medical & Scientific Writing Suite — Publication-Grade Rigor for AI-Assisted Manuscripts
3 skills · $44
Save 21%Research & Citation Integrity Suite — Trust Your Sources, Ground Your Claims, Get Your Citations Right
3 skills · $30
Save 23%Frequently Asked Questions
Learn More About AI Agent Skills
More Premium Skills
endless-loop
Autonomous research and task loop that builds on previous findings to solve complex objectives while you sleep.
research-to-decision-pro-skill
Turn messy research into rigorous, evidence-backed decision memos with specialized modes for technical and business leads.
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.
ai-automation-qa-pack
Professional QA & UAT documentation generator for AI automation agencies and complex agent deployments.