data-analyst

Analyze datasets using SQL queries, pandas transformations, and chart-ready reports.

1|Updated Apr 24, 2026
One-click install
npx skills add https://github.com/itsadijmbt/SecureMCP-Servers --skill data-analyst-itsadijmbt
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-analyst
Source: https://github.com/itsadijmbt/SecureMCP-Servers/tree/main/TEST_SERVERS/PORTED_TO_SECUREMCP/alibabacloud-rds-openapi-mcp-server/skill/data-analyst
Command: npx skills add https://github.com/itsadijmbt/SecureMCP-Servers --skill data-analyst-itsadijmbt

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill helps you turn messy raw datasets into reliable analysis and decisions by guiding SQL exploration, spreadsheet cleaning, visualization, and report drafting.

Core Features & Use Cases

  • SQL queries for exploration and insights: Write templates for counts, column stats, time-series trends, cohorts, and funnels.
  • Spreadsheet/CSV analysis: Load CSV/Excel with Python (pandas), clean data, and compute grouped summaries and pivots.
  • Reporting and visualization: Create chart-ready summaries and structure executive-ready reports with methodology and recommendations.
  • Data cleaning and statistical analysis: Detect nulls, duplicates, outliers, and inconsistent formats; run descriptive stats and quick reference tests.

Quick Start

Ask the Skill to analyze a CSV of transactions by producing a daily aggregation, cleaning obvious data quality issues (nulls, duplicates, type fixes), and generating a short markdown report with key metrics and recommendations.

Frequently Asked Questions about data-analyst

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I clean messy CSV data and generate summary reports using pandas?

To clean messy CSV data and generate summary reports, you load spreadsheets with pandas, detect nulls and duplicates, fix type inconsistencies, and compute grouped statistical summaries for structured reporting.

What is the best way to run cohort and funnel analysis on raw spreadsheet data?

Running cohort and funnel analysis requires executing time-based transformations on your spreadsheet data, segmenting users into cohorts, tracking conversion steps, and producing chart-ready outputs to visualize behavioral patterns.

Can I use SQL queries for data exploration and trend analysis within Python scripts?

You can use SQL query templates for data exploration and trend analysis by applying reusable patterns to compute counts, column statistics, and time-series trends directly within your Python analysis scripts.

How do I detect data quality issues like outliers and inconsistent formats in a dataset?

Detecting data quality issues involves scanning the dataset to identify nulls, duplicates, outliers, and inconsistent formatting, then applying pandas-based transformations to clean and standardize the raw data.

How do I turn raw dataset findings into executive-ready reports with recommendations?

Turning raw dataset findings into executive-ready reports involves structuring your statistical summaries, adding methodology details, and formulating actionable recommendations alongside chart-ready visualization outputs.