Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    alternative data event corroborator

    1

    Validate and score alternative data anomalies using independent source corroboration and z-score analysis.

    $13

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    alternative data event corroborator

    alternative data event corroborator

    Example session with this skill installed

    Analyze the anomaly in the provided retail_footfall.json against credit_card_velocity.json. Identify if the 15% spike is corroborated by independent source groups.

    • Read your context and instructions
    • Compiled the alternative data event

    I have completed the corroboration analysis for the retail footfall anomaly. The analysis indicates a high z-score with corroboration across two independent source groups, though significant reporting latency was observed.

    Alternative-Data Corroboration Report

    MetricValueIndependence GroupNotes
    Target Event15.2% Footfall SpikeGroup A (Sensor)Observed at T+0, reported at T+2h
    Corroborating Data12.8% Transaction LiftGroup B (Payment Processor)Observed at T+0, reported at T+24h
    Baseline Mean2.1% GrowthN/A30-day trailing window
    Z-Score4.82N/AHigh statistical significance
    Source Latency22 HoursN/ACredit card data lag vs sensors
    Independence StatusVerified2 GroupsNo shared underlying syndication detected

    Interpretation

    The footfall anomaly is corroborated by transaction velocity. However, the transaction data arrived with a 22-hour delay relative to the sensor data. The z-score of 4.82 suggests the move is non-random, but the operator should account for selection bias in the sensor placement before scaling.

    Next steps

    • Verify if the seasonal basis for the 30-day window accounts for the recent holiday weekend.
    • Map the store_id entities in the transaction dataset to confirm 1:1 coverage with sensor locations.
    • Run the primary-source follow-up script to check for regional power outages that might impact sensor uptime.

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

    About this skill

    The problem

    Traders often struggle to verify if a numeric anomaly in alternative data is a genuine signal or just noise from a single, unreliable source. Relying on uncorroborated data leads to false positives and poor execution decisions.

    What it does

    • Normalizes units, entity mapping, and seasonal basis across disparate datasets.
    • Assigns independence groups to sources to prevent double-counting syndicated reports.
    • Calculates z-scores for numeric anomalies to measure statistical deviation from the baseline.
    • Tracks reporting latency by recording the gap between event occurrence and data availability.
    • Generates ranked event candidates with specific coverage and selection bias caveats.

    Frameworks & tools

    Python 3 for analysis scripts, JSON for data contracts, and standard statistical methods for z-score calculations.

    Why this beats prompting it yourself

    Standard LLM prompts often hallucinate correlations or fail to account for source independence. This skill enforces a rigorous methodology that separates operator assertions from helper calculations, ensuring you don't treat two copies of the same report as independent confirmation.

    Use cases

    • Verifying supply chain disruptions by cross-referencing shipping logs with inventory data.
    • Analyzing foot traffic anomalies against point-of-sale datasets.
    • Corroborating private company revenue estimates using alternative payroll and tax data.

    Known limitations

    Supports numeric series only. Does not perform satellite/web ingestion, automatic entity resolution, or causal inference. Requires pre-mapped data following the internal contract.

    Limited to numeric series analysis. No built-in satellite/web scraping or automatic entity resolution. Requires manual mapping to the runtime contract.

    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

    Requires

    Python

    Permissions

    Terminal / Shell
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    It calculates a supplied-series z-score, records reporting delay, and counts distinct corroboration groups declared in the input. It does not establish statistical significance, verify source independence, or determine whether an anomaly is a trading signal.

    The skill requires data provided in a specific JSON format; it does not handle the initial scraping or ingestion of satellite imagery or web data itself.

    The helper runs with Python 3.10+ and normalized JSON. Any agent or workflow that can prepare the documented series and corroborator fields may use it; no data-provider or pipeline integration is included.

    It counts corroborator independence groups supplied in the input rather than counting every source record separately. The group labels must be reviewed externally; the helper does not determine whether providers share an original report.

    Upon purchase, you receive the Python-based analysis scripts, the JSON data contract documentation for input mapping, and the statistical framework for z-score and latency calculation.

    It analyzes supplied numeric series only. It does not scrape satellite or web data, resolve entities, adjust for seasonality, establish causality, classify sentiment, or provide an alpha guarantee.

    New in Trading & Investing