- Home
- Skills
- Data & Databases
- askmydata- AI Data Analyst
Works with the AI Agents you already use
askmydata- AI Data Analyst
Turn raw CSV, JSON, and Excel files into a local SQL-queryable database for instant analysis and reporting.
Free
askmydata- AI Data Analyst
Example session with this skill installed
I've uploaded sales_report.csv. Analyse the sales performance, show total revenue by region, identify the top-performing products, compare monthly trends and highlight any significant drops in sales.
- Read your context and instructions
- Compiled the askmydata- ai data
Sales Performance Analysis
The dataset was prepared and cleaned successfully. The analysis below is based on the uploaded sales data.
1. Overall Sales Summary
| Metric | Result |
|---|---|
| Total Revenue | Calculated from dataset |
| Total Transactions | Calculated from dataset |
| Average Order Value | Calculated from dataset |
2. Revenue by Region
| Region | Total Revenue |
|---|---|
| South | Calculated from dataset |
| North | Calculated from dataset |
| East | Calculated from dataset |
| West | Calculated from dataset |
3. Top Performing Products
Identify the five products with the highest revenue.
4. Monthly Sales Trends
Compare revenue across months and identify growth or decline.
5. Business Insights
Highlight significant sales changes and potential areas for improvement.
All results are calculated from the uploaded dataset. Recommendations are suggestions based on the available data.
Connects securely to your tools. The creator never sees your data.
About this skill
Raw data files are often too messy or structured incorrectly for immediate analysis. Manual cleaning in Excel or writing custom Python scripts for every new CSV, JSON, or Parquet file is time-consuming and error-prone. This skill automates the ingestion, cleaning, and querying of local data files using SQL. What it does Automated Data Cleaning flattens nested JSON, standardizes column names, removes duplicates, and handles null values. Type Conversion transforms currency strings and text-based dates into queryable numeric and datetime formats. SQL-Powered Analysis executes DuckDB queries against your local files to generate precise answers. Trend and Comparison Analysis calculates month-over-month changes, growth percentages, and identifying outliers or significant drops.
- Natural Language to Table converts vague business questions into structured Markdown tables and plain-English summaries. How it works
- Prepare the data using a CLI command to ingest and clean the file, creating a local workspace.
- Inspect the schema to understand available columns and data types generated during preparation.
- Query the data using DuckDB SQL via the CLI to extract specific insights or respond to user questions.
- Iterate on queries automatically if errors occur or if filters return empty results by relaxing constraints or matching case-insensitively. Frameworks & tools This skill uses Python, Pandas for data manipulation, DuckDB for high-performance SQL querying, and PyArrow for Parquet support. Why this beats prompting it yourself Generic prompts often fail at complex data types, currency formatting, or large file contexts. This skill uses a specialized CLI to pre-process data into a structured DuckDB instance, ensuring the AI works with a clean schema and real SQL execution rather than hallucinating calculations. Use cases Sales Performance identifying top-selling products, regional revenue trends, and growth drops. Customer Analysis segmenting users by activity or calculating lifetime value from raw logs. Inventory Audits finding low-stock items or discrepancies across multiple product categories. Data Exploration quickly understanding the contents and quality of a new, unknown JSON or CSV dataset.
Known limitations Requires local installation of pandas, duckdb, pyarrow, and openpyxl. Only SELECT/WITH SQL queries are supported. Operations are limited to the first sheet of Excel files.
DEVELOPED BY Prathima S and Masani Varun Jointly developed as an independent project
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Data & Databases.
Requires local installation of pandas, duckdb, pyarrow, and openpyxl. Supports only SELECT/WITH queries. Excel support is limited to the first sheet.
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 buying a skill.
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 to use
No account required to browse
Trust & safety
Security scan
Security scan passed 2 days ago
- Free with an Agensi account
- Software
Python
Python must be installed. Install the required dependencies before running the skill. Use synthetic or non-confidential datasets for testing.