Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Literature Citation Audit

    1

    Verify academic references, DOI metadata, and whether cited papers actually support specific claims, using full-text evidence when available.

    $9.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    1 useSecurity scanned
    Literature Citation Audit

    Literature Citation Audit

    Example session with this skill installed

    Perform a full citation audit in English using APA 7 style: (Dinev & Hart, 2006) argue that personal interest in the Internet significantly predicts the willingness to provide personal information.

    • Read your context and instructions
    • Compiled the literature citation audit

    The audit of the provided passage is complete. The in-text citation was identified, the full text was retrieved, and the claim was verified against the source's empirical results.

    Literature Evidence Table

    Bibliographic information and linkSource evidenceClaims supported and relevance to the current studyOverall alignment score
    Dinev, T., & Hart, P. (2006). An Extended Privacy Calculus Model for E-Commerce Transactions. Information Systems Research, 17(1), 61–80. https://doi.org/10.1287/isre.1060.0080"Personal interest in the Internet was found to be a significant predictor of the willingness to provide personal information... the coefficient was 0.24 (p < 0.01)." (p. 72, Results section)The source provides direct empirical evidence for the claim. The construct "personal interest" and the outcome "willingness to provide information" match the user's text exactly.98%

    Audit Issues

    No issues found. The evidence directly supports the claim as stated.

    Reference Metadata Issues

    No metadata issues found. The DOI is verified and resolves to the correct article.

    Next steps

    1. Ensure this source is included in your final reference list using the provided metadata.
    2. If you have additional paragraphs from this section, submit them for a batch audit.
    3. Review the "Privacy Calculus" context if your study focuses specifically on non-e-commerce transactions.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Literature Citation Audit

    An AI-powered academic citation auditing skill designed for researchers, graduate students, and academic writers.

    Verify whether cited publications actually exist, whether their bibliographic information is accurate, and whether they provide evidence for the specific claims attributed to them.

    Key Features

    • Reference Authenticity: Check whether cited publications exist and identify potentially fabricated or unverifiable references.
    • DOI and Metadata Verification: Examine DOI accuracy and consistency across titles, authors, publication years, journals, and other bibliographic details.
    • Claim-Level Evidence Verification: Evaluate whether cited sources actually support the corresponding statements, using full-text evidence when available.
    • In-Text Citation Matching: Identify references from in-text citations and check their correspondence with bibliography entries.
    • Issue-Focused Reports: Report identified errors, unsupported claims, and unverifiable information without unnecessarily rewriting the manuscript.
    • Academic Writing Support: Assist with reference checking before journal submission, thesis submission, or manuscript revision.

    Typical Use Cases

    • Auditing references in journal manuscripts and dissertations.
    • Identifying potentially fabricated AI-generated citations.
    • Checking DOI mismatches and incorrect bibliographic metadata.
    • Evaluating whether cited studies support specific academic claims.
    • Reviewing citation accuracy before manuscript submission.

    Known Limitations

    Web search or equivalent external retrieval capabilities are required for source verification. Full-text examination depends on access to the relevant publications, including open-access availability and publisher restrictions. Sources that cannot be retrieved or verified are reported as such.

    This skill supports academic reference verification and does not guarantee that every citation error will be detected.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Research & Analysis.

    Requires web access for full-text retrieval. Audits are unscored if full text cannot be verified. Metadata checks do not flag layout/italics issues in metadata-only mode.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    1 use

    Times used to date

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 5 days ago

    Software
    Web search
    orinternet access
    Optional
    Access to academic full-text PDFs

    Web access is required for online citation verification. Full-text evidence checks depend on accessible publications or user-provided PDFs. No API keys or external accounts are required by the skill itself.

    Permissions

    Network Access
    Browser
    Read Files

    Requires internet access to verify academic references, DOI metadata, and supporting evidence through scholarly databases and publisher websites. May read user-provided manuscripts and PDFs for citation auditing. No specific external account or API key is required.

    Listed5 days ago

    What's inside

    Frequently Asked Questions

    The skill verifies citation metadata through DOI records and available scholarly sources, then examines the original publication when accessible. It checks whether the evidence supports the specific cited claim and flags unsupported or unverifiable statements. This helps identify fabricated or misleading citations, although no automated audit can guarantee error-free results.

    The skill is designed for AI agents supporting the SKILL.md standard, including Claude Code, Codex CLI, Cursor, and other compatible environments. Internet access is required for online reference verification, and full-text auditing depends on the agent's available retrieval tools and source access.

    The report includes bibliographic information, DOI verification results, source evidence where accessible, claim-level support assessments, and identified citation or metadata errors. Evidence alignment scores and page-specific references are provided when supported by the available source material and the skill's assessment criteria. Unverifiable information is explicitly flagged.

    The skill can use open-access publications and PDFs provided by the user. Access to subscription-only articles depends on the user's available access and the AI agent's capabilities. When full text cannot be obtained, the report distinguishes verified metadata from evidence that could not be independently checked.

    Yes. The skill can identify when a claim relies on a secondary source, such as a literature review, and attempt to trace the underlying original study. When the primary source is accessible, it evaluates the original evidence directly. If the source cannot be verified, that limitation is reported.

    New in Research & Analysis