paper reference checker

This skill should be used when the user asks to "check paper citations", "verify references", "detect fake citations", "validate bibliography", "check if pap...

Security Scan

The skill's instructions, required resources, and scope align with its stated purpose of verifying academic citations; it is an instruction-only skill that reads user-supplied documents and queries public academic databases and does not request unrelated credentials or install code.

Purpose & Capability

Name and description match the instructions: extracting citations from PDFs/Overleaf/links and querying Google Scholar, arXiv, CNKI, Crossref, etc. The skill does not request unrelated environment variables, binaries, or config paths.

Instruction Scope

Instructions focus on targeted extraction and multi-database querying (DOI/arXiv/Google Scholar/CNKI/etc.). This is appropriate, but the SKILL.md assumes the agent will perform web queries/scraping (e.g., Google Scholar) without discussing rate limits, terms-of-service, or how to handle private Overleaf projects — users should expect the agent to read uploaded PDFs or any public links they provide.

Install Mechanism

No install spec and no code files — instruction-only. No downloads or packages are requested, which minimizes disk/write risk.

Credentials

The skill requests no environment variables, credentials, or config paths. This is proportionate to the stated purpose; however, the skill assumes access to publicly-queryable databases and user-supplied documents/links.

Persistence & Privilege

always is false and there is no indication the skill attempts to persist or modify agent/system configuration. Autonomous invocation is allowed by default, which is normal and not by itself concerning here.

Assessment

This skill is instruction-only and coherent with its purpose, but before installing/using it consider: (1) it will read any PDFs or Overleaf links you provide — do not upload sensitive or private documents unless you consent; (2) queries to Google Scholar and other databases may involve scraping and could be rate-limited or violate a provider's terms of service — expect possible blocking or incomplete results; (3) private Overleaf projects require credentials which the skill does not request — the agent can't access private content without you providing access; and (4) there is no install code or external service where your data is sent, but you should still avoid sharing confidential material. If you need checks against subscription-only databases, plan for providing appropriate access tokens and verify compliance with those services' policies.

Systematically verify academic references to detect AI-hallucinated or fabricated citations. Queries Google Scholar, arXiv, CNKI, and other databases.

---

Core Workflow

Phase 1: Citation Extraction (Token-Efficient First)

ALWAYS use targeted extraction before full-document reading — saves 80–95% tokens.

Input Type	Primary Method	Fallback
arXiv link	arxiv.org/html/{ID} → find references section	Full HTML, then PDF
PDF file	Last 15–20% of pages only	Expand to 30% → 50% → full
Overleaf link	Regex cite-keys from .tex → filter .bib/.bbl	Inline bibitem in .tex
Pasted list	Parse directly	—

Phase 2: Multi-Platform Querying (Priority Order)

1. DOI → https://doi.org/{DOI} — resolves = ✅ confirmed
2. arXiv ID → https://arxiv.org/abs/{ID} — match = ✅ confirmed
3. Google Scholar → search "Full Title"
4. arXiv search → arxiv.org/search/
5. CNKI → cnki.net
6. Fallbacks: Semantic Scholar · PubMed · IEEE Xplore · ACM DL · DBLP

Phase 3: Authenticity Judgment

Status	Label	Criteria
✅	VERIFIED	Found in ≥1 authoritative DB
⚠️	UNCERTAIN	Partial match
❌	NOT FOUND	No match across all queried channels
🔴	FABRICATED	Non-existent venue, unresolvable DOI
🔗	BROKEN CITATION	[?] marker in PDF body

Phase 4: Report Output

See examples/sample-report.md for full example.

Support Files

File	Purpose
references/citation-extraction.md	Format rules
references/search-strategies.md	Per-database query tactics
references/verification-criteria.md	Decision flowchart
scripts/extract_references.md	Full decision tree
examples/sample-report.md	Complete report example
examples/bibtex-example.bib	Annotated BibTeX

Databases

Google Scholar · arXiv · CNKI · Semantic Scholar · PubMed · IEEE Xplore · ACM DL · DBLP · DOI Resolver · Crossref