Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Research Claim Evidence Audit

    1

    Audit whether a research claim is supported by the cited source at the stated population, time, and level of certainty.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Research Claim Evidence Audit

    Research Claim Evidence Audit

    Example session with this skill installed

    Audit "The treatment caused better sleep in all adults." The supplied source says: "In 40 volunteers, treatment use was associated with higher self-reported sleep scores in an observational study."

    • Read your context and instructions
    • Compiled the research claim evidence

    Prepared editorial example; not a captured live test.

    Verdict: the supplied source does not support the claim's causal or population-wide
    scope. It describes an observational association in 40 volunteers and a self-report
    measure. Proposed narrower wording: "In an observational study of 40 volunteers,
    treatment use was associated with higher self-reported sleep scores." Locate the
    passage in the actual source before marking the citation fully verified.

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

    About this skill

    Audit whether a research claim is supported by the cited source at the stated population, time, and level of certainty. This independent English adaptation provides a focused agent workflow, explicit evidence limits, and a prepared example. Claim-to-source review from accessible material; no automatic full-text access, reference verification service, or statistical validity certification.

    Requires provided source text; no built-in API for paywalled journals. Does not perform statistical re-calculation or methodology validation. Portable edition excludes upstream CLI tools.

    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 any payment.

    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

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

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

    Trust & safety

    Security scan

    Security scan passed 22 days ago

    Requires

    AI agent with SKILL.md support

    Permissions

    No special permissions declared or detected

    Listed22 days ago

    What's inside

    Frequently Asked Questions

    This skill addresses 'hallucinated support,' where an AI or author cites a source that doesn't actually prove the specific claim. It detects nuanced discrepancies in population demographics, units of measurement, and statistical certainty that standard summaries often miss.

    The skill is framework-agnostic and works with any AI agent capable of processing text or PDF inputs. It is designed to be integrated into your existing workflow as a specialized logic layer for verification.

    You receive the specialized auditing logic, a structured claim ledger template for output, and a configuration guide. It does not include automated access to paywalled journals or external PDF scraping tools.

    No, this skill is focused on 'alignment'—it checks if Statement A is supported by Source B. It cannot determine if the original researcher's methodology was flawed or if the math in the source itself is incorrect.

    Setup is straightforward; you simply import the skill into your agent's environment and provide it with the text to be audited alongside the source excerpts. No complex coding or API configurations are required to begin verifying claims.

    New in Research & Analysis