Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Data Analyst Toolkit

    1

    A full-stack data analysis suite for cleaning, quality auditing, SQL engineering, and BI reporting across major platforms.

    $10

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Data Analyst Toolkit

    Data Analyst Toolkit

    Example session with this skill installed

    I have a sales dataset with missing dates and duplicate transaction IDs. I need to clean it, calculate a 7-day rolling average in Oracle SQL, and design a Power BI dashboard.

    • Read your context and instructions
    • Compiled the data analyst toolkit

    I have processed your sales dataset request. I first identified the cleaning requirements for the duplicate IDs, defined the SQL logic for the rolling average, and drafted the BI dashboard specifications.

    Data Analysis Plan and Deliverables

    1. Data Cleaning Results

    IssueDetection RuleRemediation Action
    Duplicate IDsCOUNT(trans_id) > 1Records consolidated by latest timestamp.
    Missing Datessale_date IS NULLApplied forward-fill based on transaction sequence.

    2. Oracle SQL Transformation

    -- 7-Day Rolling Average Calculation
SELECT 
    sale_date,
    daily_amount,
    AVG(daily_amount) OVER (
        ORDER BY sale_date 
        RANGE BETWEEN INTERVAL '6' DAY PRECEDING AND CURRENT ROW
    ) AS rolling_avg_7d
FROM (
    SELECT 
        TRUNC(sale_date) as sale_date, 
        SUM(amount) as daily_amount
    FROM sales_cleaned
    GROUP BY TRUNC(sale_date)
)
ORDER BY sale_date;

    3. Power BI Dashboard Design

    • KPIs: Total Revenue (Sum), 7D Trend (Line Chart), Transaction Volume (Gauge).

    DAX Measure: RollingAvg = CALCULATE(SUM(Sales[Amount]), DATESINPERIOD(Sales[Date], LASTDATE(Sales[Date]), -7, DAY)) / 7

    • Visuals: A dual-axis line chart showing daily_amount bars against the rolling_avg_7d trend line.

    Next steps

    1. Run the provided SQL against your Oracle instance to generate the analytical view.
    2. Import the cleaned view into Power BI and apply the provided DAX measure.
    3. Mask the customer_email field before sharing the final dashboard with external stakeholders.

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

    About this skill

    Data engineering and analytics projects often stall when specialized tasks like SQL optimization, data cleaning, and BI reporting are handled in silos. This package provides an integrated suite of six skills to coordinate the entire data lifecycle, from raw ingestion to executive-level dashboards.

    What it does

    • Orchestrate workflows using a central coordinator to route tasks between cleaning, quality auditing, and reporting specialists.
    • Clean and transform data by identifying duplicates, handling missing values via mean/median/mode imputation, and standardizing types.
    • Audit data quality through evidence-based assessments that measure defect rates and prioritize remediation based on business impact.
    • Engineer analytical features including date durations, categorical encoding, and grouped aggregates while preventing data leakage.
    • Write expert SQL with a focus on Oracle conventions, analytic functions, and complex joins across multiple dialects.
    • Generate BI reports for Tableau, Power BI, Looker, and Excel, complete with KPI definitions and platform-specific formulas like DAX or LookML.

    How it works

    1. Initialize the data-analyst-workflow to assess the scope of your dataset and project goals.
    2. Invoke specialized skills for data profiling, quality auditing, or cleaning as required by the pipeline.
    3. Use the sql-expert or feature-engineering skills to prepare the final analytical layer.
    4. Finalize outputs via bi-expert to produce dashboard specifications, formulas, or formatted reports.

    Frameworks & tools

    Supported tools include Oracle SQL, Python/Pandas, Excel, Google Sheets, Tableau, Power BI, Looker, Qlik, and Informatica IDMC.

    Why this beats prompting it yourself

    Generic prompts often fail to maintain consistency across the data lifecycle, leading to metric drift between cleaning and reporting. These skills enforce strict grain validation and coordinate assumptions across every phase of the analysis.

    Use cases

    • Auditing a messy CRM export to identify duplicate records and referential integrity failures.
    • Drafting complex DAX measures and dashboard layouts for a retail sales performance report.
    • Building a reproducible feature engineering pipeline for temporal prediction models.

    Known limitations

    Does not support processing PCI DSS, PHI, or PII without prior masking. Cannot execute SQL or modify source databases directly unless a tool-specific execution environment is provided.

    Cannot process PCI/PHI/PII data. Does not direct-connect to live databases or execute code without an external tool environment. Standardizes on Oracle SQL unless otherwise specified.

    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 today

    Permissions

    Read Files
    Write Files
    Terminal / Shell
    Listedtoday

    What's inside

    Frequently Asked Questions

    This suite bridges the gap between raw data and final insights by coordinating specialized tasks like SQL engineering, data auditing, and BI reporting, ensuring your metrics remain consistent throughout the entire pipeline.

    You receive a comprehensive package of six specialized skills, including a central workflow coordinator, a SQL expert, a data cleaning specialist, a quality auditor, a feature engineer, and a BI reporting specialist.

    The skills are designed for cross-platform compatibility, supporting major BI tools like Tableau and Power BI, database dialects such as Oracle SQL, and data processing frameworks like Python/Pandas.

    No, for security reasons, these skills generate optimized code, formulas, and cleaning logic for you to review and run; they do not require direct write-access to your source databases.

    Yes, the suite is regularly updated to include the latest syntax for BI platforms (like new DAX functions) and refined SQL optimization strategies for modern data warehouses.

    New in LLM Ops