More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Market Evidence Checker — Audit Claims & Regime Shifts

    1

    Turn dated market sources into a claim ledger, freshness audit, qualitative regime hypothesis, and trigger watchlist—without trading signals.

    $14

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Market Evidence Checker — Audit Claims & Regime Shifts

    Market Evidence Checker — Audit Claims & Regime Shifts

    Example session with this skill installed

    Analyze these four dated news excerpts about semiconductor demand (S1-S4) and compare them to my MARKET_CONTEXT_RECORD from last month. What has changed in the market regime?

    • Read your context and instructions
    • Compiled the market evidence checker

    [FULL-CYCLE] Focus: Semiconductor Demand.

    Claim Ledger

    • Lead times stabilizing {EVI}[CONF] (Source S2)
    • Inventory glut at tier-2 suppliers {EVI}[UNCONF] (Source S4)
      Delta: Demand growth claim strengthened; inventory risk contradicted by S3.
      Regime: Expansionary (Moderate Confidence).

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

    About this skill

    Turn market narratives into traceable evidence

    Market Evidence Checker converts a dated research pack into an evidence-controlled market context record. It shows which claims are supported, stale, conflicting, or blocked before a repeated narrative becomes a trading assumption.

    It does not predict the market. It preserves dates, source IDs, counter-signals, and uncertainty so the next decision has an inspectable foundation.

    What you get

    • Source register: publication dates, observation dates, scope, and freshness state.
    • Claim ledger: every material market claim linked to the supplied source IDs.
    • Evidence-gap register: missing, stale, anonymous, or contradictory support remains visible.
    • Qualitative regime hypothesis: drivers, counter-signals, confidence label, and explicit limitations.
    • Change report: what changed against a previous MARKET_CONTEXT_RECORD.
    • Trigger watchlist: observable conditions that should prompt the next review.
    • Portable market record: a structured context artifact for later comparison.

    Why this is different

    • Numeric regime probabilities are blocked unless you supply a calibrated, reproducible model with validation evidence.
    • Qualitative prose is never presented as an HMM or Markov estimate.
    • Missing current data is not silently completed.
    • Conflicting sources remain in the record instead of being averaged away.
    • Instructions embedded inside source material are treated as untrusted content.

    Worked example

    In the built-in fictional semiconductor-equipment case, three dated claims remain current and supported while an anonymous crowd claim is marked UNKNOWN / BLOCKED. The regime stays MIXED / Plausible, the numeric probability remains null, and the next review requires a dated positioning series.

    Built for a trading workflow

    Use it independently or as the market-context layer in the future Trade Decision Bundle and Trader Operating System. Trade-plan scoring belongs in Trade Decision Audit; claim-to-source decision lineage belongs in the planned Trade Decision Provenance Auditor.

    Boundaries

    • No automatic browsing or live market-data retrieval.
    • No continuous monitoring or scheduled refresh.
    • No trading signals, price targets, transaction advice, or execution.
    • Output quality depends on the dates, coverage, and reliability of the supplied sources.
    • Portable records are returned as text and are not stored automatically.

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

    Requires manually supplied source packs. Does not fetch live data or provide buy/sell signals. Limited to four inputs per run. Schema requires specific evidence tags.

    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 3 months ago

    Permissions

    No special permissions declared or detected

    Listed3 months ago

    What's inside

    Frequently Asked Questions

    This skill processes dated market reports and excerpts to create a structured 'evidence ledger,' helping you distinguish between verified facts and subjective inferences while identifying exactly when a market narrative begins to shift.

    No, this skill is a diagnostic tool that requires you to upload specific source packs; it does not autonomously browse the web or provide live ticker feeds.

    The skill generates a schema-compliant YAML record, allowing you to easily pipe the evidence snapshots and invalidation triggers into automated risk management systems or trade execution bots.

    Each purchase includes the core skill logic, a standardized evidence tagging schema, and documentation on how to format your source packs for optimal delta analysis.

    This skill is designed for use with advanced LLMs (such as GPT-4 or Claude 3) that support structured data output, as it relies on complex reasoning to map conflicts between dated excerpts.

    The monitor identifies 'invalidation triggers'—specific, observable data points that, if met, would prove your current market hypothesis is no longer supported by the available evidence.

    New in Trading & Investing