Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    AI Claim Evidence Checker

    1

    Check AI-generated claims against the sources you provide. Identify which claims are supported, partially supported, unsupported, overstated, or contradicted, and show where stronger evidence is needed.

    Free

    4 usesSecurity scanned
    AI Claim Evidence Checker

    AI Claim Evidence Checker

    Example session with this skill installed

    Audit this summary of the new compliance policy against the attached PDF. Check for any claims about deadlines or penalties that aren't explicitly in the source.

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

    Audit Summary

    Claims checked: 3
    Supported: 1
    Partially supported: 1
    Unsupported: 1
    Unverified: 0

    The AI summary overstates the penalty amounts and confuses a proposed deadline with a hard requirement.

    [Claim-Evidence Table...]

    Safer Corrected Answer

    [Revised text...]

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

    About this skill

    The problem

    AI-generated answers can sound reliable while containing unsupported details, source mismatches, outdated information, or claims that go further than the evidence actually allows. Manually checking every claim against its sources is slow and easy to miss.

    What it does

    • Extracts the important factual claims from an AI-generated answer, report, or summary.
    • Splits compound claims into testable statements when needed.
    • Maps each claim to the source material you provide.
    • Labels claims as Supported, Partially Supported, Unsupported, or Unverified.
    • Detects scope, date, version, and wording mismatches between a claim and its evidence.
    • Highlights the highest-risk evidence gaps.
    • Produces a safer corrected version that stays within what the available sources actually support.

    Why use this instead of a general prompt?

    A general “fact-check this” prompt can produce another confident summary without clearly showing what was verified. This skill uses a fixed claim-to-evidence workflow and requires every important claim to receive an explicit evidence status.

    Typical output

    • Claim-evidence audit table
    • Supported / Partially Supported / Unsupported / Unverified status for each claim
    • Up to three highest-risk evidence gaps
    • A corrected version of the original AI answer

    Use cases

    • Checking AI-generated research or summaries against supplied sources.
    • Verifying reports against data sheets, documentation, or source files.
    • Reviewing AI-generated customer support or internal drafts before sending them.
    • Comparing product claims against official manuals or specifications.
    • Checking whether citations actually support the claims attached to them.

    Known limitations

    This skill can only verify sources the host agent can actually access and inspect. If a source is missing or inaccessible, the relevant claim is marked Unverified. It is a source-support audit, not a general truth detector.

    Requires both the AI text and the source materials to be accessible. Cannot verify claims if the agent is blocked by paywalls or inaccessible file types.

    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

    4 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 2 months ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed2 months ago

    What's inside

    Frequently Asked Questions

    This skill extracts specific factual claims from AI-generated text and audits them against your source documents to identify hallucinations, overstatements, and evidence gaps. It replaces manual verification with an automated workflow that labels every statement as Supported, Unsupported, or Unverified.

    The skill provides a detailed claim-evidence audit table, a risk report highlighting the most dangerous evidence gaps, and a corrected version of your text that only includes verified information. You'll see exactly which parts of your content are safe to publish and which need more research.

    This skill can verify claims against any text-based sources the host agent has access to, including PDF manuals, research papers, data sheets, and internal documentation. If a claim refers to a source that isn't provided or accessible, the skill will flag it as 'Unverified' rather than guessing.

    No, this skill is a 'source-support audit' rather than a general truth engine; it only checks if your AI's claims match the specific evidence you provide. It cannot verify the absolute truth of a statement if the supporting information is not contained within your uploaded sources.

    Yes, this skill is designed to integrate with most major AI agent platforms that support multi-step workflows. Once installed, you can trigger the audit by providing the AI-generated draft and the corresponding reference files.

    New in Agents & Orchestration