Fact Check

    2

    Automated factual verification using tiered official sources to eliminate hallucinations and circular reasoning.

    Free

    17 uses5.0 (1 review)

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Fact Check

    Example session with this skill installed

    Fact check this AI-generated summary of the 2023 tech subsidy policy. It claims a 500 million grant was issued on March 15th.

    • Read your context and instructions
    • Compiled the fact check

    Claim: 500 million grant issued on March 15.
    Rating: ⚠️ Deviated
    Evidence: Official filing [link] shows the grant was 450 million. The March 15 date refers to the media report date; the actual policy execution started on March 10.
    Source: Ministry of Industry T0 Archive.

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

    About this skill

    The problem

    Manually verifying claims in news drafts, reports, or AI-generated content is slow and prone to oversight. Relying on search engine snippets often leads to circular reasoning where the source being checked is the one providing the verification.

    What it does

    • Extracts every factual claim including dates, amounts, and entities using a "verbatim capture" principle to ensure no detail is missed.
    • Forces external cross-referencing against a tiered source hierarchy, prioritizing official government filings (T0) and authoritative media (T1).
    • Detects sophisticated misinformation tactics like time-shifting (using old news as current), title-body mismatch, and AI hallucinations.
    • Generates structured verification reports with deep-link evidence, categorizing claims as accurate, incorrect, biased, or unverifiable.

    Frameworks & tools

    Python 3, Cue API, and official financial/regulatory data sources like SSE, HKEX, and EDGAR.

    Why this beats prompting it yourself

    Standard LLM prompting often results in internal hallucinations or "lazy" verification that accepts surface-level search results. This skill implements a strict anti-circular-reasoning firewall and a forced deep-search protocol that bypasses homepages to find primary source documents.

    Use cases

    • Fact-checking PR drafts against historical financial reports and official corporate filings.
    • Verifying AI-generated industry analysis to catch hallucinated statistics and fabricated market data.
    • Vetting social media content for "zombie news" where old events are rebranded as breaking stories.

    Known limitations

    Does not verify subjective opinions, private data, or content behind paywalls. Not designed for real-time breaking news where official sources haven't yet commented.

    Requires CUE_API_KEY. Does not verify subjective opinions or private data. Cannot bypass paywalls or provide official legal testimony.

    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

    5.0
    1 review
    5
    1
    4
    0
    3
    0
    2
    0
    1
    0

    This skill has been used 17 times.

    Trust & safety

    Security scan

    Security scan passed 3 months ago

    • Free with an Agensi account

    Requires

    Cuecue

    Permissions

    Environment Variables

    Allowed Hosts

    cuecue.cn
    Listed3 months ago

    What's inside

    Frequently Asked Questions

    Unlike standard prompts that might rely on their own internal training data, this skill uses a "verbatim capture" protocol to extract claims and forces a cross-reference against primary regulatory databases like SEC EDGAR and HKEX.

    The Fact Check skill is built for seamless integration with any agent running on the Cue framework or Python-based environments; you will receive the necessary API configurations and documentation upon purchase.

    The skill outputs a structured report that categorizes every claim as accurate, incorrect, biased, or unverifiable, complete with deep-link evidence to the source document.

    Your purchase includes the full skill codebase, integration instructions, and lifetime access to version updates as we add new T0 and T1 source tiers.

    It cannot verify subjective opinions, private/proprietary data not in the public domain, or content hidden behind paywalls that prevent automated crawlers.

    Yes, the skill is specifically engineered to detect "zombie news" by comparing the timestamps of claimed events against the original publication dates in official archives.

    New in Agents & Orchestration