data science analytics agent

    1

    Clean, analyze, and visualize structured datasets using Python and SQL for professional data science insights.

    $5

    Secure checkout via Stripe

    30-day refund guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+22 more

    data science analytics agent

    Example session with this skill installed

    I have a sales_data.csv with columns 'date', 'revenue', 'region', and 'product_id'. Clean the data for missing values and give me a monthly revenue trend analysis by region.

    • Read your context and instructions
    • Compiled the data science analytics

    I have completed the data cleaning and performed a monthly trend analysis on your sales dataset. The data was inspected for null values in the revenue column and date inconsistencies before aggregation.

    Data Analysis Report: Monthly Revenue Trends

    Data Quality Summary

    • Initial Rows: 1,250
    • Missing Values: 12 rows with null revenue were dropped.
    • Date Standardization: 'date' column converted to datetime objects; 3 invalid formats corrected.
    • Duplicates: 5 redundant entries removed.

    Monthly Revenue by Region (USD)

    MonthNorthSouthEastWest
    2023-1045,20038,15052,00041,800
    2023-1148,90039,40055,20043,500
    2023-1262,10051,20068,40058,900

    Key Findings

    Seasonal Growth: All regions showed a significant spike (avg +28%) in December, likely due to end-of-year activity.

    • Top Performer: The East region consistently outperforms others, accounting for 30% of total revenue.
    • Stability: The South region shows the lowest volatility but also the slowest growth rate (3.2% MoM).

    Visualization Code (Python)

    import pandas as pd
import matplotlib.pyplot as plt

# Load and group data
df = pd.read_csv('sales_data_cleaned.csv')
df['date'] = pd.to_datetime(df['date'])
monthly_sales = df.groupby([df['date'].dt.to_period('M'), 'region'])['revenue'].sum().unstack()

# Plotting
monthly_sales.plot(kind='line', marker='o', figsize=(10, 6))
plt.title('Monthly Revenue Trend by Region')
plt.ylabel('Revenue (USD)')
plt.grid(True)
plt.show()

    Next steps

    1. Review the dropped records in cleaning_log.txt to identify upstream data entry issues.
    2. Conduct a cohort analysis on the December spike to see if those customers are returning in Q1.
    3. Run a forecast model to estimate Q1 revenue based on these seasonal trends.

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

    About this skill

    Handling messy data and extracting actual business value requires more than just running scripts. This skill provides a structured framework for end-to-end data science, transforming raw CSV or Excel files into validated insights, reproducible Python code, and executive-ready reports. It eliminates the guesswork in data preparation by enforcing rigorous cleaning protocols and statistical standards.

    What it does

    • Data Auditing identifies missing values, duplicates, outliers, and data types to assess overall quality before analysis.
    • Automated Cleaning generates reproducible Python scripts for standardizing formats, handling nulls, and resolving inconsistencies.
    • Exploratory Analysis calculates descriptive statistics, correlations, and trend detection to uncover underlying patterns.
    • Statistical Testing executes hypothesis tests, reporting p-values, confidence intervals, and effect sizes for evidence-based decisions.
    • ML Scaffolding designs machine learning workflows including feature selection, baseline comparisons, and cross-validation strategies.
    • Business Reporting synthesizes technical findings into executive summaries with prioritized recommendations and KPI definitions.

    How it works

    1. Intake the dataset and define the specific business or research question to be answered.
    2. Inspection of the data structure and quality to flag potential biases or privacy concerns.
    3. Execution of cleaning and analysis using Python (pandas, NumPy) or SQL queries.
    4. Synthesis of results into structured reports with executable visualization code.

    Frameworks & tools

    Python, pandas, NumPy, scikit-learn, SciPy, statsmodels, Matplotlib, and SQL.

    Why this beats prompting it yourself

    Generic prompts often lead to "hallucinated" statistics or data leakage in machine learning models. This skill enforces a professional data science workflow that separates training from testing, validates assumptions before testing, and ensures every calculation is transparent and reproducible.

    Use cases

    • Analyze sales CSVs to identify regional performance trends and churn risks.
    • Clean and standardize inconsistent marketing data for cross-channel reporting.
    • Build baseline regression or classification models for customer segmentation.
    • Generate SQL queries to aggregate monthly revenue and unit economics by product.

    Known limitations

    Does not support real-time streaming data analysis. Requires structured data formats like CSV, Excel, or SQL tables. Accuracy depends on the quality and representativeness of the provided dataset.

    How to use

    Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    30-day refund

    Not a fit? Get your money back

    Trust & safety

    Security scanned

    Verified clean 2 days ago

    • Passed all security checks, Safe to install

    Listed2 days ago

    What's inside

    Frequently Asked Questions