Data Analysis

When to use this skill

• Data exploration: Understand a new dataset
• Report generation: Derive data-driven insights
• Quality validation: Check data consistency
• Decision support: Make data-driven recommendations

Instructions

Step 1: Load and explore data

Python (Pandas):

import pandas as pd
import numpy as np

# Load CSV
df = pd.read_csv('data.csv')

# Basic info
print(df.info())
print(df.describe())
print(df.head(10))

# Check missing values
print(df.isnull().sum())

# Data types
print(df.dtypes)

SQL:

-- Inspect table schema
DESCRIBE table_name;

-- Sample data
SELECT * FROM table_name LIMIT 10;

-- Basic stats
SELECT
    COUNT(*) as total_rows,
    COUNT(DISTINCT column_name) as unique_values,
    MIN(numeric_column) as min_val,
    MAX(numeric_column) as max_val,
    AVG(numeric_column) as avg_val
FROM table_name;

Step 2: Data cleaning

# Handle missing values
df['column'].fillna(df['column'].mean(), inplace=True)
df.dropna(subset=['required_column'], inplace=True)

# Remove duplicates
df.drop_duplicates(inplace=True)

# Type conversions
df['date'] = pd.to_datetime(df['date'])
df['category'] = df['category'].astype('category')

# Remove outliers (IQR method)
Q1 = df['value'].quantile(0.25)
Q3 = df['value'].quantile(0.75)
IQR = Q3 - Q1
df = df[(df['value'] >= Q1 - 1.5*IQR) & (df['value'] <= Q3 + 1.5*IQR)]

Step 3: Statistical analysis

# Descriptive statistics
print(df['numeric_column'].describe())

# Grouped analysis
grouped = df.groupby('category').agg({
    'value': ['mean', 'sum', 'count'],
    'other': 'nunique'
})
print(grouped)

# Correlation
correlation = df[['col1', 'col2', 'col3']].corr()
print(correlation)

# Pivot table
pivot = pd.pivot_table(df,
    values='sales',
    index='region',
    columns='month',
    aggfunc='sum'
)

Step 4: Visualization

import matplotlib.pyplot as plt
import seaborn as sns

# Histogram
plt.figure(figsize=(10, 6))
df['value'].hist(bins=30)
plt.title('Distribution of Values')
plt.savefig('histogram.png')

# Boxplot
plt.figure(figsize=(10, 6))
sns.boxplot(x='category', y='value', data=df)
plt.title('Value by Category')
plt.savefig('boxplot.png')

# Heatmap (correlation)
plt.figure(figsize=(10, 8))
sns.heatmap(correlation, annot=True, cmap='coolwarm')
plt.title('Correlation Matrix')
plt.savefig('heatmap.png')

# Time series
plt.figure(figsize=(12, 6))
df.groupby('date')['value'].sum().plot()
plt.title('Time Series of Values')
plt.savefig('timeseries.png')

Step 5: Derive insights

# Top/bottom analysis
top_10 = df.nlargest(10, 'value')
bottom_10 = df.nsmallest(10, 'value')

# Trend analysis
df['month'] = df['date'].dt.to_period('M')
monthly_trend = df.groupby('month')['value'].sum()
growth = monthly_trend.pct_change() * 100

# Segment analysis
segments = df.groupby('segment').agg({
    'revenue': 'sum',
    'customers': 'nunique',
    'orders': 'count'
})
segments['avg_order_value'] = segments['revenue'] / segments['orders']

Output format

Analysis report structure

how to use data-analysis
CursorClaude CodeClineCodexWindsurfGooseGitHub CopilotVS CodeGemini CLIKiloOpencodeKimi CLIRoo ClineAiderContinueZedBolt.newLovablev0Replit AgentSweepSmol DeveloperDevinCavemanAmpAntigravity
How to use data-analysis on Cursor
AI-first code editor with Composer
1
Prerequisites
Before installing skills in Cursor, ensure your development environment meets these requirements:
›Cursor installed and configured on your development machine
›Node.js version 16.0+ with npm package manager (verify with node --version)
›Active project directory or workspace where you want to add data-analysis
2
Execute installation command
Execute the skills CLI command in your project's root directory to begin installation:
$npx skills add https://github.com/supercent-io/skills-template --skill data-analysiscopy
The skills CLI fetches data-analysis from GitHub repository supercent-io/skills-template and configures it for Cursor.
3
Select Cursor when prompted
The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:
◆ Which agents do you want to install to?
│
│ ── Universal (.agents/skills) ── always included ────
│   • Amp
│   • Antigravity
│   • Cline
│   • Codex
│ ●Cursor(selected)
│   • Cursor
│   • Windsurf
4
Verify installation
Confirm successful installation by checking the skill directory location:
.cursor/skills/data-analysis
Reload or restart Cursor to activate data-analysis. Access the skill through slash commands (e.g., /data-analysis) or your agent's skill management interface.
⚠
Security & Verification Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.
Additional Resources
›View source code on GitHub›Skills CLI documentation›Learn more about Cursor›What are agent skills?