Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    open world research audit

    1

    A rigorous audit tool to stress-test research claims, map evidence, and identify decision-reversal conditions.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    open world research audit

    open world research audit

    Example session with this skill installed

    Audit this expansion strategy memo against the attached Q3 regional data. Identify the claims that control the 'Go' decision and tell me when that decision should change.

    • Read your context and instructions
    • Compiled the open world research

    I have completed the audit of the "EMEA Expansion Strategy v2.1" using the provided Q3 Regional Data CSV. The audit focused on the material claims triggering the Phase 1 rollout.

    Audit Findings: MATERIAL_ISSUES_FOUND

    Scope Record

    • Report: EMEA Expansion Strategy v2.1
    • Evidence: Q3 Regional Sales Data, Logistics Capacity Report
    • Status: 2 claims UNSUPPORTED, 1 UNDERDETERMINED
    IDClaim LocatorTypeStatusMateriality
    C01"Market demand in Poland exceeds 20% YoY"FactUNSUPPORTEDHigh (Primary Trigger)
    C02"Existing Berlin hub can handle Warsaw volume"InferencePARTIALLY_SUPPORTEDMedium
    C03"Regulatory approval is a formality"HypothesisUNDERDETERMINEDHigh (Blocker)

    Detailed Assessment

    C01 Evidence Gap: The Q3 data (E01) shows only 12% growth for the Polish market. The 20% figure in the memo appears to be an extrapolation of a single week in August, not the quarterly average.

    C02 Dependency: Support for the Berlin hub capacity (E02) assumes a 24-hour shift rotation which is not currently active. Without this shift change, the claim is UNSUPPORTED.

    Decision Boundary: The 'Go' decision for Poland is currently unsupported by the provided evidence. A reversal to 'Proceed' requires evidence of 18%+ growth or a finalized labor contract for the Berlin hub expansion.

    Strongest Supported Conclusion
    The evidence permits a pilot in the Czech Republic (15% growth, verified capacity) but does not support the full Poland expansion as proposed.

    Next steps

    1. Provide the source for the 20% YoY growth figure to resolve C01.
    2. Verify if the Berlin 24-hour shift rotation has been approved by the works council.
    3. Attach the specific regulatory filing referenced in C03.

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

    About this skill

    Research reports and strategy memos often suffer from logical leaps, hidden assumptions, and unverified claims. This skill provides a rigorous audit framework to stress-test existing documents against supplied evidence, separating what is proven from what is merely inferred.

    What it does

    • Claim extraction identifies decision-bearing statements and maps them to specific report locators.
    • Evidence mapping traces claims to supplied source documents while flagging unverified assertions.
    • Support classification rates each claim as supported, partially supported, underdetermined, or unsupported.
    • Assumption exposure surface hidden definitions or numeric probability bands that lack a statistical basis.
    • Decision boundary analysis determines the specific conditions under which a recommendation should change.

    How it works

    1. Scope freeze records the report version, available evidence, and the user's intended decision or thesis.
    2. Materiality audit extracts 5 to 8 pivotal claims and tests their factual dependencies separately from risk preferences.
    3. Verification assigns source IDs to evidence and tests for entailment, contradictions, and jurisdictional relevance.
    4. Calibration produces a decision boundary report highlighting permitted actions, missing evidence, and reversal conditions.

    Frameworks & tools

    This tool uses a structured audit protocol incorporating a failure taxonomy and evidence rubric. It processes Markdown, PDF excerpts, and text-based memos.

    Why this beats prompting it yourself

    Standard prompting often results in the AI agreeing with the report's tone or hallucinating supporting facts. This skill enforces a strict evidence-to-claim mapping protocol that prevents silent browsing and requires explicit locators for every judgment.

    Use cases

    • Strategy memo review to find logical gaps before a high-stakes board meeting.
    • Market analysis stress-test to identify which trends are backed by data versus expert opinion.
    • Due diligence support for auditing claims made in investment pitches against provided data rooms.
    • Deep Research verification to ensure AI-generated reports haven't drifted from their primary sources.

    Known limitations

    This skill does not perform research from scratch or provide legal, medical, or investment advice. It requires an existing report and is limited to the evidence provided in the context window.

    Requires existing report text. External verification is only possible if specific tools are enabled. Does not provide final legal or investment determinations.

    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 1 month ago

    Permissions

    No special permissions declared or detected

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Unlike standard AI prompts that often mirror a report's tone, this skill uses a strict evidence-to-claim mapping protocol that requires explicit locators for every judgment, preventing the AI from 'agreeing' with unsupported conclusions.

    The skill is compatible with AI agents that support file uploads or long-context text input, and it is optimized for processing Markdown, PDF excerpts, and text-based memos.

    The skill requires an existing report and a corresponding set of evidence; it does not perform external research or provide professional legal, medical, or investment advice.

    You will receive the full 'Open World Research Audit' protocol and instructions for your agent, enabling features like claim extraction, evidence mapping, and decision boundary analysis.

    Setup is immediate; once added to your preferred AI agent, you simply provide the report you wish to audit and the supporting evidence to begin the 'Scope Freeze' phase.

    Yes, the skill is designed to identify 'reversal conditions'—the specific factual changes or missing data points that would make your current recommendation or strategy invalid.

    New in Research & Analysis