data analyzer

    1

    Automated data quality auditing, statistical profiling, and cleaning script generation for AI training and analytics.

    $3

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    data analyzer

    Example session with this skill installed

    Analyze 'customer_records.csv', detect anomalies in the 'transaction_amount' column, and generate a Python cleaning script to handle missing email values.

    • Read your context and instructions
    • Compiled the data analyzer
    • Generated the data export

    I have analyzed 'customer_records.csv' and generated a quality report and cleaning pipeline.

    Dataset Analysis and Cleaning Pipeline

    The initial scan of 10,000 rows identified 153 quality issues, primarily concentrated in the 'transaction_amount' and 'email' fields. The 'transaction_amount' column shows a right-skewed distribution with a mean of 124.50 and five significant outliers.

    Data Quality Scorecard

    DimensionScoreIssues FoundSeverity
    Completeness94%600 missing emailsMedium
    Consistency98%12 date format variantsLow
    Accuracy92%5 price outliers (Z > 3)High
    Uniqueness99%12 duplicate IDsMedium

    Anomaly Detection Results

    RowColumnValueZ-scoreRecommendation
    1247transaction_amount9847.004.2Flag for manual review
    3891age1653.8Drop (Data entry error)

    Cleaning Script

    import pandas as pd
    import numpy as np
    
    def clean_customer_data(file_path):
        df = pd.read_csv(file_path)
        
        # Handle missing emails
        df['email'] = df['email'].fillna('unknown@example.com')
        
        # Handle transaction_amount outliers (IQR Method)
        Q1 = df['transaction_amount'].quantile(0.25)
        Q3 = df['transaction_amount'].quantile(0.75)
        IQR = Q3 - Q1
        lower_bound = Q1 - 1.5 * IQR
        upper_bound = Q3 + 1.5 * IQR
        df = df[(df['transaction_amount'] >= lower_bound) & (df['transaction_amount'] <= upper_bound)]
        
        # Standardize types
        df['id'] = df['id'].astype(str)
        
        return df
    
    cleaned_df = clean_customer_data('customer_records.csv')
    cleaned_df.to_csv('customer_records_cleaned.csv', index=False)
    

    Next steps

    • Review the flagged outliers in row 1247 before final deployment.
    • Run the generated script to produce the cleaned CSV.
    • Integrate the validation rules into your CI/CD pipeline.

    customer_records.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

    Messy datasets lead to skewed models and broken analytics pipelines. Data Analyzer Pro automates the tedious exploration and cleaning process, providing a systematic way to audit, profile, and transform data before it hits your production code.

    What it does

    • Quality Assessment checks for completeness, consistency, accuracy, and duplicates using systematic validation rules.
    • Statistical Profiling generates distributions, central tendencies, and dispersion metrics for numerical, categorical, and text fields.
    • Anomaly Detection identifies outliers using Z-score, IQR, and isolation forests to flag data entry errors or logic violations.
    • Cleaning Pipelines creates reproducible Python scripts for imputation, format normalization, and scaling.
    • Format Conversion handles CSV, JSON, Parquet, SQL, and NoSQL exports with optimized schema inference.
    • Metadata Documentation generates YAML and Markdown data dictionaries to track provenance and transformations.

    How it works

    1. Ingest the raw dataset through a file path or stream to perform an initial structural scan and memory estimation.
    2. Audit the data by running the quality assessment matrix and statistical profiling suite.
    3. Execute the cleaning pipeline to handle missing values, standardize formats, and remove detected anomalies.
    4. Export the cleaned dataset alongside a machine-readable documentation file and a reproducible Python cleaning script.

    Frameworks & tools

    The skill is optimized for environments like Cursor and Claude Code. It generates code compatible with Python data science stacks including Pandas, Scikit-learn, and NumPy, supporting file formats like Parquet, JSONL, and CSV.

    Why this beats prompting it yourself

    Generic prompts often miss edge cases like fuzzy duplicates or complex distribution shifts. This skill uses structured workflows and specific statistical methods to ensure nothing is overlooked in large datasets.

    Use cases

    • Fine-tuning Preparation to clean conversational datasets for LLM training.
    • Analytics Pipeline Audit to catch price anomalies and inventory logic errors.
    • Data Consolidation to merge customer records using fuzzy deduplication.

    Known limitations

    Memory-intensive for datasets exceeding local environment limits. Requires manual confirmation for high-severity business logic violations.

    Memory-intensive for datasets exceeding local environment limits. Requires manual confirmation for high-severity business logic violations.

    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
    Updated27 days ago

    What's inside

    Frequently Asked Questions

    The Data Analyzer is designed for developer-centric AI environments like Cursor and Claude Code, generating code that integrates seamlessly with Python-based data science stacks.

    The skill goes beyond simple cleaning by providing full statistical profiles, anomaly detection using Z-score and Isolation Forests, and machine-readable data dictionaries for long-term documentation.

    It natively supports CSV, JSON, Parquet, and SQL formats, and can even export to JSONL specifically for fine-tuning LLM models.

    You receive the core Data Analyzer workflow, pre-configured validation rules, and the ability to generate reproducible Python cleaning scripts using Pandas and Scikit-learn.

    While highly automated, the skill identifies high-severity business logic violations and flags them for manual review to ensure no critical data is deleted without your oversight.

    New in Research & Analysis