Works with the AI tools you already use
Citation Guard
Stop your agent citing papers that don't exist. Verifies every reference against live PubMed & Crossref — flags fabricated, mismatched, and retracted citations.
$12
/moSubscription · cancel anytime
Secure checkout via Stripe
- Always the latest version
- Delivered live to your agent via MCP
- Cancel anytime, access ends at period end
See it in action
You say
Polack FP, et al. Safety and Efficacy of the BNT162b2 mRNA Covid-19 Vaccine. N Engl J Med. 2020. PMID: 33301246
Smith J. A novel CRISPR therapy for migraine. J Neurol. 2019. PMID: 99999999
Wakefield AJ, et al. Ileal-lymphoid-nodular hyperplasia, non-specific colitis, and pervasive developmental disorder in children. Lancet. 1998.
Your agent does
| # | Citation | Verdict | Note | |---|----------|---------|------| | 1 | Polack FP et al., NEJM 2020 | ✅ VERIFIED | PMID 33301246 — title, author, journal, year match | | 2 | Smith J., migraine CRISPR 2019 | ⛔ NOT_FOUND | No PubMed/Crossref record — likely fabricated | | 3 | Wakefield AJ, Lancet 1998 | ⚠️ RETRACTED | Retracted — do not cite |
Bottom line: 1 of 3 verified. Do not submit — reference 2 appears fabricated and reference 3 is retracted.
What you get
About this skill
AI agents invent citations — plausible titles on fake PMIDs, real DOIs pointing at the wrong paper, references to retracted studies. In medical, scientific, and regulatory writing that's a manuscript-killer. Citation Guard turns citation accuracy into a hard gate. It checks each reference against the live PubMed and Crossref records using your agent's own web access — nothing to install — and returns one of five auditable verdicts: VERIFIED, MISMATCH, NOT_FOUND, RETRACTED, UNCERTAIN, each with the canonical record and the reason. It catches fabricated references, real identifiers pointing at the wrong paper, and retracted studies before they reach the reader. Maintained and served fresh so it stays current with citation and retraction standards. Works with Claude Code, Cursor, Codex CLI, OpenClaw, and any SKILL.md agent that can fetch a URL.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scanned
Verified clean 1 month ago
- 30-day refund guarantee
- Secure checkout via Stripe
Creator
PubsProToolkit builds rigor-first skills for AI agents — they write your docs and content properly, then adversarially review them to catch what's wrong before it ships. The result: cleaner output and a hard quality gate in one toolkit. Built by a CMPP-certified, PhD medical writer who brings regulated-industry standards to developer docs, content, compliance, and research integrity.
Frequently Asked Questions
Popular in AI Agents & LLM Ops
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.
Open Browser Use
Automate real Chrome profiles with a professional CLI, SDK, and MCP-ready automation stack for AI agents.
Making Complex Systems Agent-Readable with Grok (v1.0.1)
Turn complex system documentation into structured, agent-accessible knowledge bases optimized for MCP and AI tools.
Getting Started with OpenCode and Agensi (v1.1)
Bridge OpenCode to the Agensi marketplace to discover and install AI agent skills via MCP.