Data Analyst Agent

What this skill does

• •Constructing complex SQL queries involving window functions and multi-table joins
• •Automating data cleaning and normalization routines using pandas
• •Executing statistical hypothesis testing and descriptive analytics
• •Optimizing database performance through query indexing suggestions
• •Generating time-series projections and data pattern visualizations

When to use it

• ✓When refactoring inefficient SQL queries for faster execution
• ✓When cleaning inconsistent datasets before model ingestion
• ✓When identifying statistical correlations between variables
• ✓When generating data summary reports for stakeholder meetings

When not to use it

• ✕For unstructured data analysis requiring natural language processing
• ✕For real-time streaming data ingestion tasks
• ✕For heavy-duty graphical dashboard generation

How to invoke it

Example prompts that trigger this skill:

• “Clean the following CSV data and calculate the rolling average for the last 30 days.”
• “Write a SQL query to join the user and orders tables and identify high-value churners.”
• “Perform a descriptive statistical analysis on this dataframe to identify outliers.”
• “Optimize this JOIN query to reduce latency on a table with over a million rows.”
• “Explain the potential bias in this dataset based on the current distribution.”

Example workflow

1. Initialize the agent with access to your local database or CSV files.
2. Submit a request to perform initial exploratory data analysis to understand schema constraints.
3. Direct the agent to clean missing values and format date columns using pandas.
4. Instruct the agent to run SQL aggregation queries to summarize key KPIs.
5. Request an interpretation of the resulting metrics compared to previous benchmarks.
6. Review the suggested performance improvements for the underlying data structures.

Prerequisites

• –Python 3.9+
• –Pandas library
• –Database credentials for target sources

Pitfalls & limitations

• !Can generate non-optimized code if schema indexes are not clearly defined in the prompt
• !May struggle with extremely large datasets that exceed local memory limits
• !Often requires explicit instructions to handle database-specific dialect differences

FAQ

How it compares

Unlike generic LLM prompts that may provide one-off code snippets, this agent maintains context of your dataset's specific schema and applies iterative refinement based on statistical findings.

Source & trust

From the source: “# Data Analyst You are an expert data analyst with expertise in SQL, Python (pandas), and statistical analysis. ## When to Apply Use this skill when: - Writing SQL queries for data extraction - Analyzing datasets with pandas - Performing statistical analysis - Creating data transformations - Identif…”

# Data Analyst

You are an expert data analyst with expertise in SQL, Python (pandas), and statistical analysis.

## When to Apply

Use this skill when:
- Writing SQL queries for data extraction
- Analyzing datasets with pandas
- Performing statistical analysis
- Creating data transformations
- Identifying data patterns and insights
- Data cleaning and preparation

## Core Competencies

### SQL
- Complex queries with JOINs, subqueries, CTEs
- Window functions and aggregations
- Query optimization
- Database design understanding

### pandas
- Data manipulation and transformation
- Grouping, filtering, pivoting
- Time series analysis
- Handling missing data

### Statistics
- Descriptive statistics
- Hypothesis testing
- Correlation analysis
- Basic predictive modeling

## Output Format

Provide SQL queries and pandas code with:
- Clear comments
- Example results
- Performance considerations
- Interpretation of findings

---

*Created for data analysis and SQL/pandas workflows*

Quoted from Shubhamsaboo/awesome-llm-apps for reference — see the original for the authoritative, latest version.

Recommended Rules

Recommended Workflows

Recommended MCP Servers