Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Crypto Market Data Integrity Auditor

    1

    Audit crypto market datasets for missing candles, price anomalies, and integrity defects with a weighted scoring system.

    $39.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Crypto Market Data Integrity Auditor

    Crypto Market Data Integrity Auditor

    Example session with this skill installed

    Audit this bitstamp_btc_usd_1h.csv file. It covers Jan 2023 to June 2023. Check for missing candles and price spikes using a 3x MAD threshold.

    • Read your context and instructions
    • Compiled the crypto market data
    • Generated the data export

    The audit of bitstamp_btc_usd_1h.csv is complete. I identified 42 missing hourly candles and 3 price anomalies exceeding the 3x Median Absolute Deviation threshold.

    Crypto Market Data Integrity Report

    • Dataset / provider / symbol / timeframe: Bitstamp / BTC/USD / 1h
    • Coverage period and timezone: 2023-01-01 to 2023-06-30 (UTC)
    • Rows assessed: 4,320
    • Overall score and effective weights: 88.5/100 (C: 25%, U: 15%, T: 20%, V: 15%, O: 10%, X: 15%)
    • Confidence and limitations: High confidence; Cross-exchange consistency was not assessed (single source).

    Executive Summary

    The dataset is mostly intact but suffers from a significant 36-hour gap in March. OHLCV values are mathematically sound, though three candles show extreme price volatility that warrants manual review for liquidity gaps.

    Quality Metrics

    CheckStatusAffected / assessedScoreSeverityNotes
    CompletenessWarning42 / 436299.04HighLarge gap in March
    UniquenessPass0 / 4320100.00LowNo duplicates found
    Timestamp IntegrityPass0 / 4320100.00LowAll on-grid
    OHLCV ValidityPass0 / 4320100.00LowHigh/Low bounds valid
    Outlier ReviewWarning3 / 432099.93Medium3x MAD price spikes
    Cross-sourceN/A0 / 00.00N/ASingle source provided

    Findings Register

    IDIssueTime range / rowsEvidenceSeverityRecommended remediation
    F-01Missing Candles2023-03-12 04:00 to 2023-03-13 16:0036 consecutive missing barsHighRe-fetch from Bitstamp API
    F-02Price Outlier2023-05-19 14:00Return > 8.5% in 1h (3.2x MAD)MediumVerify against Kraken/Coinbase

    Remediation Plan

    1. Gap Fill: Query the Bitstamp v2 API for the missing period on 2023-03-12 to recover the 36 missing records.

    Outlier Verification: Cross-reference the May 19th candle with another high-liquidity venue to ensure the spike was not a local data artifact.
    3.

    Quarantine: If the missing data cannot be recovered, exclude the 2023-03-12 period from backtest results to avoid skewing volatility metrics.

    Next steps

    • Provide a secondary source (e.g., Coinbase JSON) to enable cross-exchange consistency checks.
    • Run the gap-fill script for the March 12th window.
    • Adjust the outlier threshold to 5x MAD if 3x is producing too many false positives for this asset.

    bitstamp_btc_usd_1h.csv

    CSV · data export

    Generated

    Example file from a real run - the skill writes it into your workspace.

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

    About this skill

    Low-quality crypto market data ruins backtests and production trading bots. This skill audits historical datasets and live feeds to find the gaps, duplicates, and price anomalies that skew your models. It provides a technical breakdown of data integrity with a reproducible scoring system.

    What it does

    • Inventory and profile: Extracts schema, null rates, and row counts to establish a data baseline.
    • Identify gaps: Detects missing candles based on exchange calendars and expected timeframes.
    • Validate OHLCV: Checks for impossible price relationships and negative volume spikes.
    • Anomaly detection: Flags price and volume outliers using robust statistical thresholds.
    • Cross-source audit: Compares data points across different exchanges to find venue-specific discrepancies.

    How it works

    1. Input ingestion: Provide a CSV, JSON, or Parquet export along with asset metadata and timezone rules.
    2. Technical audit: The agent runs a 12-step workflow covering everything from timestamp integrity to rolling quantile analysis.
    3. Integrity scoring: It calculates a weighted score across completeness, uniqueness, and validity.
    4. Report delivery: You receive a full markdown report with an issue register and a remediation plan.

    Frameworks & tools

    Works with standard crypto data formats (CSV, JSON, Parquet) and follows specific logic for OHLCV (Open, High, Low, Close, Volume) validation across major exchange timeframes.

    Why this beats prompting it yourself

    Writing prompts to catch specific crypto edge cases like off-grid candle starts or timezone mix-ups is error-prone. This skill uses a structured 100-point scoring system and specific cross-exchange alignment logic that ensures severe defects aren't hidden by simple averages.

    Use cases

    • Auditing historical CSVs before running backtests.
    • Validating a new API provider's data quality.
    • Investigating price spikes in production logs.
    • Sanitizing multi-exchange datasets for research.

    Known limitations

    Does not automatically label manipulation or fraud. Requires explicit metadata for high-confidence scoring. Cannot access private API keys or credentials.

    Requires asset pair and timeframe metadata for accurate gap detection. Scoring is based on configurable heuristics, not industry certification. Cannot check live feeds without authorized tool access.

    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 22 days ago

    Permissions

    Read Files
    Listed22 days ago

    What's inside

    Frequently Asked Questions

    This skill supports common data formats like CSV, JSON, and Parquet, and is specifically designed to handle OHLCV (Open, High, Low, Close, Volume) structures from all major crypto exchanges.

    The audit produces a comprehensive Markdown report featuring a 100-point integrity score, a detailed register of all identified gaps or anomalies, and a step-by-step remediation plan to fix the data.

    Unlike basic prompting, this skill uses a structured 12-step workflow and cross-exchange alignment logic to catch technical edge cases like off-grid candle starts and timezone shifts that generic AI queries often miss.

    While it identifies statistical outliers and price anomalies, it does not provide labels for market manipulation or fraud, and it requires you to provide the metadata (such as asset and timezone rules) for high-confidence scoring.

    No direct access is required; you simply provide the exported dataset (CSV, JSON, or Parquet) along with relevant metadata, ensuring your private API keys and credentials remain secure.