More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Data Analysis Fundamentals

    1

    Master SQL, Python, EDA, cleaning, statistics, Excel and Sheets. 10 ordered skills, starting with Data Analytics, Analytical SQL, Python for Data Analysis.

    Free

    Security scanned
    Data Analysis Fundamentals

    Data Analysis Fundamentals

    Example session with this skill installed

    I have two CSVs, orders.csv and users.csv. I need a Python script to join them, handle missing signup dates, and give me a monthly revenue summary per user segment.

    • Read your context and instructions
    • Compiled the data analysis fundamentals
    • Generated the data export

    I have prepared a pandas script to merge your datasets and generate the monthly revenue summary. I used a left join to ensure no order data is lost and applied nullable integer types to maintain ID integrity.

    Monthly Revenue Analysis Script

    import pandas as pd
    import numpy as np
    
    # Load data with explicit types to prevent silent truncation
    orders = pd.read_csv('orders.csv', parse_dates=['order_date'], dtype={'order_id': str, 'user_id': str})
    users = pd.read_csv('users.csv', parse_dates=['signup_date'], dtype={'user_id': str})
    
    # Profile before join
    print(f"Unique users in orders: {orders['user_id'].nunique()}")
    print(f"Unique users in user table: {users['user_id'].nunique()}")
    
    # Merge and validate grain
    # Assumption: orders is the primary table; users provides metadata
    df = orders.merge(users, on='user_id', how='left', validate='many_to_one')
    
    # Handle missing signup dates - fill with a sentinel or drop depending on business logic
    # Here we flag them as 'Unknown' for the segment analysis
    df['segment'] = df['segment'].fillna('Uncategorized')
    df['signup_date'] = df['signup_date'].fillna(pd.Timestamp('1900-01-01'))
    
    # Aggregate by month and segment
    monthly_revenue = (
        df.assign(month=df['order_date'].dt.to_period('M'))
        .groupby(['month', 'segment'])
        .agg(
            total_revenue=('revenue', 'sum'),
            order_count=('order_id', 'count'),
            unique_customers=('user_id', 'nunique')
        )
        .reset_index()
    )
    
    print(monthly_revenue.head())
    

    Next steps

    1. Check the Uncategorized segment in the output to see if missing user profiles are skewing the revenue totals.
    2. Verify if the revenue column in orders.csv includes tax and shipping, as this impacts the gross vs net definitions.
    3. Export the monthly_revenue dataframe to a CSV for use in your reporting dashboard.

    orders.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

    The problem

    Beginner analysts and business professionals often need a repeatable process, not a one-off prompt. This pack targets: Master SQL, Python, EDA, cleaning, statistics, Excel and Sheets.

    What's inside (10 skills, suggested learning order)

    1. Data Analytics — Extract insights from data for business decisions.
    2. Analytical SQL — Query and aggregate data in relational databases.
    3. Python for Data Analysis — Manipulate and analyze data with pandas.
    4. Exploratory Data Analysis (EDA) — Profile and understand datasets.
    5. Data Cleaning and Preparation — Fix quality issues and inconsistencies.
    6. Descriptive and Inferential Statistics — Statistical foundations for decisions.
    7. Hypothesis Testing and A/B Testing — Statistical experimentation.
    8. Advanced Excel — Pivot tables, formulas and financial models.
    9. Google Sheets and Apps Script — Automate cloud spreadsheets.
    10. Corporate Data Literacy — Train teams to use data.

    Why a skill pack instead of a one-off prompt

    Each skill gives the agent a defined trigger, step-by-step procedure and output format, so results are consistent across sessions and easier to review.

    How to use

    1. Install the pack in your SKILL.md-compatible agent.
    2. Ask for the task in plain language.
    3. Review the output against the skill's quality checks before using it.

    Known limitations

    • Outputs are drafts that need human review; they are not professional, legal or financial advice.
    • Tools, APIs and prices change; check current vendor documentation before relying on version-specific details.
    • Quality depends on the context you give the agent (data, requirements, constraints).
    • Tested only where stated in the Compatibility note.

    Also by Rodrigo Santos

    Specialized Agents and Distribution; AI Agents: Fundamentals and Protocols; Model Fine-Tuning and Alignment

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

    Not for big data (millions of rows) in Excel. Skips machine learning architecture and VBA security. Requires user-provided data samples for accurate schema mapping.

    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

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 3 days ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Read Files
    Listed3 days ago

    What's inside

    Frequently Asked Questions

    This toolkit is framework-agnostic and designed to integrate with any LLM-based agent that supports Python, SQL, or spreadsheet API calls, including AutoGPT, BabyAGI, and custom LangChain agents.

    Unlike standard prompts that might miss data nuances, this skill enforces defensive coding practices like join-grain validation and null-handling to prevent the 'silent errors' that often lead to incorrect business metrics.

    While the skill can write high-performance SQL for large data warehouses like Snowflake or BigQuery, its spreadsheet capabilities are best suited for datasets under 100,000 rows to ensure stability and performance.

    You receive the full suite of specialized analysis workflows, a library of 'defensive' SQL and Python templates, and pre-configured logic for statistical testing and automated reporting.

    No specialized installation is required beyond the standard environment for your chosen tool (e.g., a Python runtime or SQL workbench), as the skill provides the logic and structures to run within your existing data stack.

    New in Data & Databases

    Free