CSV Data Summarizer skill
A Claude skill that analyzes an uploaded CSV without asking questions: statistics, missing values, correlations and charts built with pandas and matplotlib
- 476 ★ on the repository
- Last commit
Extended access
Why this level
- The skill runs a Python script on your machine and reads the CSV you point it at
- Charts are saved to the current folder under fixed names and overwrite earlier files
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/csv-data-summarizerDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The skill runs a Python script on your machine and reads the CSV you point it at
- Charts are saved to the current folder under fixed names and overwrite earlier files
This is third-party code. Review the repository files before installing.
What it does
CSV Data Summarizer fires when you upload a CSV file to Claude or ask for a summary of tabular data. The skill immediately, without clarifying questions, runs the analyze.py script: it reads the file into pandas, identifies column types and picks an analysis to fit the data. It treats sales, customers, finance, operational metrics and surveys differently, and uses a generic set for any other table. The report covers an overview of rows, columns and types, key statistics, missing-data analysis and conclusions about the patterns it finds. Charts are drawn only where the data supports them: time series when date columns exist, a correlation heatmap when there are several numeric columns, distribution histograms and bar charts by category. The script saves the images to the current folder: correlation_heatmap.png, time_series_analysis.png, distributions.png and categorical_distributions.png. The repository includes a ready csv-data-summarizer.zip archive to upload to Claude.ai, a demo P&L table covering 15 months and 25 metrics, and a sample.csv. The script needs Python 3.8 or newer, pandas, matplotlib and seaborn.
Who it is for. For managers, analysts and entrepreneurs who need a fast overview of a table with a report and charts without writing code.
Good fit when
- You were sent a sales export as CSV and want revenue trends and strong products within a minute
- A customer table needs to be broken down by segment and region with distributions
- Before working with an unknown file you want to see how many values are missing and which columns correlate
- A survey with ratings and categorical answers needs frequencies and cross-tabulations
- You want a demonstration of how a Claude skill runs a pandas script and draws charts
Not a fit when
- You need a question-and-answer session or a specific calculation: the skill always produces a general overview and does not ask about the task
- The file is not CSV: the skill works with CSV, and the catalog has separate MCP servers for Excel
- The data is huge and does not fit in memory: the script reads the whole file into pandas
- You need an interactive dashboard: the script saves static PNG images
Example request
Here's sales_data.csv. Can you summarize this file?Limitations
The skill is tuned for no-dialogue behavior: SKILL.md states in large type to ask no questions, offer no options and deliver the full analysis at once. If you need a narrow answer you must say so explicitly, and the skill may ignore the request. The script reads the CSV whole with `pd.read_csv`, so large files run into memory limits. All charts are saved to the current folder under fixed names and overwrite earlier files. Python 3.8 or newer and the pandas, matplotlib and seaborn packages from requirements.txt are required. The README targets Claude.ai with a manual archive upload in the Skills settings, and for Claude Code it describes only cloning the repository.
How to disable. In Claude.ai disable or delete the skill under Settings, Capabilities, Skills. If you cloned the repository, delete the folder. Generated PNG images stay in the folder where the script ran.
FAQ
How do I install CSV Data Summarizer in Claude?
Download csv-data-summarizer.zip from the repository or releases, open Claude.ai, Settings, Capabilities, Skills, upload the archive and enable the skill. After that upload any CSV and the analysis runs on its own. Developers can clone the repository and run `pip install -r requirements.txt`.
Which charts does the skill draw?
Only those the data supports: time charts when date columns exist, a correlation heatmap with several numeric columns, distribution histograms and bar charts of categories. Files are named correlation_heatmap.png, time_series_analysis.png, distributions.png and categorical_distributions.png.
Why does the skill ask no questions?
SKILL.md says so: the skill must deliver the full analysis at once, with no choices or clarifications. The author assumes a user wants a finished result right after uploading the file.
What is the demo data in the repository?
The file examples/showcase_financial_pl_data.csv holds a profit and loss report for 15 months: three product lines (SaaS, Enterprise, Services) and 25 metrics including revenue, expenses, margin, CAC and LTV. There is also a small resources/sample.csv.
Which Python and package versions are needed?
Python 3.8 or newer, pandas 2.0 or later, matplotlib 3.7 or later, seaborn 0.12 or later. Versions are given in the SKILL.md metadata and in requirements.txt.
Discussion
No questions or reviews yet.
Related
SkillsA data visualization skill for agents: turns data into polished interactive HTML charts and full reports with one visual language
SciPilot Figure
scipilot-figure-skill
A scientific visualization advisor skill: it profiles the data and picks a chart for the argument first, then renders it to journal-grade quality
High-Stakes Analytics Lab
High-Stakes Analytics & Decision Lab
An evidence-gated analytics skill for high-stakes decisions: profiles data, picks a method the evidence supports, can answer with a data request
A CLI and 13 skills for Claude Code: the Power BI data model, DAX measures, row-level security and PBIR report pages straight from chat
Tufte Claude Skill
tufte-claude-skill
A skill turning a make-a-chart request into a chart by Edward Tufte's principles: style presets, SVG templates, sparklines and small multiples
A Python library for typed, versioned datasets over S3, GCS, and Azure, with a datachain skill install command that teaches Claude Code, Cursor, and Codex your
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| CSV Data Summarizer (this entry) | no | 476 | ||
| Excel MCP Server | no | not required | 4,256 | an MCP server for creating and editing Excel files, without a one-off CSV overview |
| AntV Chart Visualization Skills | no | 512 | AntV skills for choosing and building a chart type, without a statistical overview of the table |
README in short
The README starts with a banner and a feature list: adapting to the data type, statistics, automatic charts, quality checks and support for different industries. Download buttons for the archive and the demo table follow, the repository tree, a four-step workflow and two installation guides for Claude.ai and for developers. It ends with usage examples, technical details and a sample console output.
README badge
Original SKILL.md
--- name: csv-data-summarizer description: Analyzes CSV files, generates summary stats, and plots quick visualizations using Python and pandas. metadata: version: 2.1.0 dependencies: python>=3.8, pandas>=2.0.0, matplotlib>=3.7.0, seaborn>=0.12.0 --- # CSV Data Summarizer This Skill analyzes CSV files and provides comprehensive summaries with statistical insights and visualizations. ## When to Use This Skill Claude should use this Skill whenever the user: - Uploads or references a CSV file - Asks to summarize, analyze, or visualize tabular data - Requests insights from CSV data - Wants to understand data structure and quality ## How It Works ## ⚠️ CRITICAL BEHAVIOR REQUIREMENT ⚠️ **DO NOT ASK THE USER WHAT THEY WANT TO DO WITH THE DATA.** **DO NOT OFFER OPTIONS OR CHOICES.** **DO NOT SAY "What would you like me to help you with?"** **DO NOT LIST POSSIBLE ANALYSES.** **IMMEDIATELY AND AUTOMATICALLY:** 1. Run the comprehensive analysis 2. Generate ALL relevant visualizations 3. Present complete results 4. NO questions, NO options, NO waiting for user input **THE USER WANTS A FULL ANALYSIS RIGHT AWAY - JUST DO IT.** ### Automatic Analysis Steps: **The skill intelligently adapts to different data types and industries by inspecting the data first, then determining what analyses are most relevant.** 1. **Load and inspect** the CSV file into pandas DataFrame 2. **Identify data structure** - column types, date columns, numeric columns, categories 3. **Determine relevant analyses** based on what's actually in the data: - **Sales/E-commerce data** (order dates, revenue, products): Time-series trends, revenue analysis, product performance