SaurabhSSB

🥈Silver

Automate data analysis and visualization tasks using Python, R, and statistics. Ideal for operations teams needing to streamline workflows and gain insights from data. Connects to n8n for workflow automation and supports Claude for AI-driven data processing.

2110Updated 4mo ago

Intermediate30min to implementautomation

Saves ~200 min per use

Quick InstallView Source

git clone https://github.com/SaurabhSSB/SaurabhSSB.git

Works with:

Claude

Overview

About This Skill

SaurabhSSB is a data science student's GitHub repository containing foundational projects in Python, R, and statistics. The profile includes active work on Python Mastery Roadmap, Data Visualization Using R, and Foundations of Statistics with R. It demonstrates practical applications of data analysis tools including Pandas and Seaborn for Python-based workflows and statistical computing in R. The repository serves as a reference for developers and analysts building skills in data science fundamentals and statistical programming.

How to Use

1. **Prepare Your Data:** Ensure your dataset is clean and structured (CSV, Excel, or database). Use [PLACEHOLDER] to specify the file path or API endpoint. 2. **Define the Objective:** Replace [KEY_METRIC], [TRENDS_OR_PATTERNS], and [VISUALIZATION_TOOL] in the prompt with your specific goals (e.g., "customer churn rates," "identify outliers," "Plotly Express"). 3. **Run the Analysis:** Paste the customized prompt into Claude or ChatGPT. The AI will generate Python/R code, visualizations, and insights. For automation, ask it to create an n8n workflow snippet. 4. **Refine and Execute:** Review the AI-generated code for accuracy. Test it in your local environment (e.g., Jupyter Notebook) or deploy it via n8n. Adjust parameters as needed. 5. **Integrate into Workflow:** Use the n8n workflow to automate data fetching, analysis, and reporting. Schedule it to run weekly or monthly. Share outputs with stakeholders via email, Slack, or dashboards. **Tips:** - For large datasets, specify memory constraints (e.g., "Use Dask for parallel processing"). - Include domain-specific context (e.g., "Focus on SaaS metrics like ARR and CAC") to improve relevance. - Use the AI’s suggestions for visualization libraries (e.g., Seaborn, ggplot2) based on your data type.

Use Cases

Learning Python fundamentals through structured roadmap

Mastering data visualization techniques with R and Python libraries

Building statistical analysis skills with R

Reference materials for data science students

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/SaurabhSSB/SaurabhSSB

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Automate the analysis and visualization of [DATASET] using Python/R. Focus on [KEY_METRIC] and identify [TRENDS_OR_PATTERNS]. Generate a summary report with key insights and actionable recommendations. Use [VISUALIZATION_TOOL] for charts. If automation is needed, integrate with n8n for workflow execution. Share the code snippets and outputs directly.

Example Output

### Data Analysis & Visualization Report: Q2 2024 Sales Performance

**Dataset Analyzed:** Internal CRM sales data (April-June 2024) containing 12,450 transactions across 15 regions.

**Key Metric:** Monthly recurring revenue (MRR) growth and regional performance.

**Trends Identified:**
1. **MRR Growth:** Overall MRR increased by 18% QoQ, driven by a 22% surge in enterprise deals (contracts >$50K). Mid-market grew 12%, while SMB declined by 3%.
2. **Regional Performance:** EMEA led with 25% YoY growth, followed by APAC (19%) and North America (14%). The Western US underperformed (-2% YoY) due to delayed renewals.
3. **Product Insights:** The new "Pro Suite" product contributed 35% to total MRR, with a 40% adoption rate among enterprise customers.

**Visualizations Generated:**
- **Line Chart:** MRR growth over time (April-June 2024) with trendline.
- **Bar Chart:** Regional MRR contribution (YoY comparison).
- **Heatmap:** Product adoption rates by customer segment.

**Actionable Recommendations:**
1. **Retention Focus:** Launch a targeted campaign for SMB customers in the Western US to address churn risks. Offer a 10% discount on annual plans.
2. **Upsell Opportunity:** Prioritize "Pro Suite" upsells to mid-market customers in APAC, where adoption is lower (28% vs. 40% enterprise).
3. **Regional Strategy:** Allocate 20% of the next quarter’s marketing budget to EMEA, where growth potential is highest.

**Automation Workflow (n8n):**
A pre-built n8n workflow was triggered to:
- Fetch updated CRM data via API.
- Run the Python/R analysis script.
- Generate visualizations and save to a shared Google Drive folder.
- Email the report to the sales leadership team with a summary slide.

**Code Snippets:**
```python
import pandas as pd
import matplotlib.pyplot as plt

# Load data
df = pd.read_csv('q2_sales_data.csv')

# Calculate MRR growth
df['mrr_growth'] = df.groupby('region')['mrr'].pct_change() * 100

# Plot MRR growth
plt.figure(figsize=(10, 6))
df.groupby('month')['mrr'].sum().plot(kind='line', marker='o')
plt.title('Monthly MRR Growth (Q2 2024)')
plt.ylabel('MRR ($)')
plt.xlabel('Month')
plt.grid()
plt.savefig('mrr_growth.png')
```
```r
# R code for regional performance analysis
library(ggplot2)
data <- read.csv('q2_sales_data.csv')
regional_growth <- aggregate(mrr ~ region + quarter, data, FUN = sum)
ggplot(regional_growth, aes(x=region, y=mrr, fill=quarter)) +
  geom_bar(stat='identity', position='dodge') +
  labs(title='Regional MRR Growth (Q2 2024)', x='Region', y='MRR ($)')
```