fact check desk

    1

    A human-led fact-checking desk for verifying video claims against primary sources and generating blog write-ups.

    $15

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    fact check desk

    Example session with this skill installed

    Initialize a new fact-check for a TikTok video about a new tax law, then help me extract the claims from this transcript: 'The new bill raises property tax by 5% starting this Friday.'

    • Read your context and instructions
    • Compiled the fact check desk

    I have initialized the project folder and extracted the factual claims from your transcript. All claims have been logged in the tracker with unique IDs for verification.

    Fact-Check Initialization and Claim Extraction

    IDClaim CategoryClaim TextVerification StatusNotes
    C1Numeric / TaxBill raises property tax by 5%PendingNeeds primary source (text of the bill)
    C2Date / EventTax hike starts this FridayPendingCross-reference with effective date in bill
    O1Opinion"New tax law"LoggedContextual label for the subject

    Claim Tracker (claims.json)

    {
      "check_id": "tax-law-tiktok-001",
      "status": "in-progress",
      "claims": [
        {
          "id": "C1",
          "text": "The new bill raises property tax by 5%",
          "type": "factual",
          "verdict": null,
          "source": null
        },
        {
          "id": "C2",
          "text": "starting this Friday",
          "type": "factual",
          "verdict": null,
          "source": null
        }
      ]
    }
    

    Next steps

    1. Locate the primary source (the official legislative text or government gazette).
    2. Update the tracker with the exact passage confirming or contradicting the 5% figure.
    3. Run fact-check-desk checklist to see if the publish gate is ready.
    Claim Tracker (claims.json

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

    About this skill

    Fact-check a TikTok or news video the way a human checker does — get the transcript, extract every claim, verify each one against its primary source, write a verdict with corrections, and publish an honest blog write-up. Includes the checklist runner, verdict renderer, claim tracker and blog-writeup templates. Human-led: nothing is verified automatically. Built from the fact-checks published on kelickhub.com.ng.

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

    No automated scraping or verification. Cannot detect deepfakes. Requires manual transcript input. Verdicts depend entirely on human-provided primary sources.

    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

    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 4 days ago

    Software
    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listed4 days ago

    What's inside

    Frequently Asked Questions

    Unlike general AI agents that may hallucinate, this skill enforces a strict methodology where no verdict is rendered without a verified link to a primary source like a legal document or raw dataset.

    The skill includes the Python-based processing engine, the POSIX shell scaffolding tools, and a suite of structured Markdown and JSON templates for claim tracking.

    No, this skill is designed for high-integrity manual verification; it requires a human to provide the transcript and conduct the primary source research to ensure total accuracy.

    It is compatible with any AI agent or environment that supports Python 3.10 and POSIX shell commands, making it ideal for local development or integrated newsroom workflows.

    This skill uses a rigorous seven-tier verdict system (e.g., 'mostly-accurate', 'misleading') to provide nuanced context that goes far beyond a simple true/false toggle.

    New in Writing & Content