- Home
- Skills
- Data & Databases
- Data Analyst: CSV & Excel to Verified Insights
Works with the AI Agents you already use
Data Analyst: CSV & Excel to Verified Insights
Analyze CSV, Excel, and JSON data with verified Python/SQL code to find trends, segments, and business insights.
Free
Data Analyst: CSV & Excel to Verified Insights
Example session with this skill installed
Analyze this sales_data.csv. Why did revenue dip in Q3, and which customer segments are still growing? Use pandas for the analysis and provide a summary with charts.
- Read your context and instructions
- Compiled the data analyst
- Generated the data export
I have analyzed sales_data.csv, performed a cleaning pass on date formats, and executed a segment-wise contribution analysis to identify the Q3 revenue drivers.
Executive Summary
- Revenue declined 14.2% in Q3, driven primarily by a 30% drop in the "Electronics" category.
- Enterprise segments grew by 8% despite the overall dip, showing high resilience.
- New customer acquisition fell 22% in August, correlating with a decrease in marketing spend.
- Data quality is high, with 99.4% of records successfully parsed and reconciled.
- Average Order Value (AOV) remained stable at $142, suggesting the issue is volume-based, not price-based.
Key Findings
| Metric | Q2 Value | Q3 Value | % Change | Primary Driver |
|---|---|---|---|---|
| Total Revenue | $1.2M | $1.03M | -14.2% | Electronics Volume |
| Enterprise Sales | $410k | $443k | +8.0% | Upsell Campaigns |
| Retail Sales | $790k | $587k | -25.7% | Supply Chain Delay |
| Active Customers | 8,400 | 7,120 | -15.2% | Acquisition Drop |
# Analysis Code Snippet: Segment Growth
import pandas as pd
df = pd.read_csv('clean_sales_data.csv')
df['date'] = pd.to_datetime(df['date'])
q3_data = df[df['date'].dt.quarter == 3]
# Calculate growth by segment
growth = q3_data.groupby('segment')['revenue'].sum().pct_change()
print(growth)
Recommended Actions
- Product Team: Investigate inventory levels for Electronics to resolve the volume bottleneck.
- Marketing: Reallocate budget from underperforming Retail channels to the growing Enterprise segment.
- Sales: Launch a re-engagement campaign for the 1,280 customers who churned in August.
Next steps
- Download the
clean_sales_data.csvandanalysis_script.pyfrom the files. - Review the "Supply Chain Delay" correlation chart in the appendix.
- Run the provided script on next month's data to track recovery.
sales_data.csv
CSV · data export
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Manual data exploration is slow and prone to calculation errors. This skill transforms raw files into boardroom-ready reports by executing verified Python and SQL code to uncover the "why" behind your metrics.
What it does
- Data Profiling runs automated checks for missing values, duplicates, and data type inconsistencies.
- Automated Cleaning standardizes categories and parses complex date formats while maintaining a detailed audit log.
- Statistical Analysis computes cohorts, RFM segments, Pareto distributions, and YoY growth rates.
- Anomaly Detection identifies outliers using IQR or z-scores to flag potential errors or fraud.
- Visualization generates clean charts with Matplotlib or Seaborn that focus on a single, clear insight per graphic.
How it works
- Frame the business problem and define the specific questions the data needs to answer.
- Profile and Clean the dataset using pandas or DuckDB, outputting a
clean.csvfor transparency. - Execute Analysis modules like retention funnels, seasonal forecasting, or correlation matrices.
- Verify Results by reconciling totals against raw inputs to ensure 100% numerical accuracy.
Frameworks & tools
This skill uses Python with the pandas and matplotlib libraries for data manipulation and visualization. It utilizes DuckDB for high-performance SQL queries on large CSV or Parquet files.
Why this beats prompting it yourself
Standard LLM prompts often hallucinate numbers or miss subtle data quality issues like mixed locales. This skill enforces a "code-first" verification loop where every digit in the summary is cross-checked against executed script outputs.
Use cases
- Analyze sales drops by segmenting products, regions, and channels to find the driver.
- Calculate customer retention cohorts to measure the long-term impact of a feature.
- Build a monthly KPI dashboard from a CSV export with automated % change metrics.
- Perform RFM segmentation to identify high-value customers for a marketing campaign.
Known limitations
Best suited for structured data in CSV, Excel, or JSON formats. Analysis quality depends on data cleanliness; extremely messy datasets may require manual cleaning steps.
Requires Python environment with pandas/matplotlib. Analysis is limited to structured files like CSV, Excel, and JSON. Forecasts are statistical estimates, not guarantees.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 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
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 1 day ago
- Free with an Agensi account