data-analysis
Use this skill when the user uploads Excel (.xlsx/.xls) or CSV files and wants to perform data analysis, generate statistics, create summaries, pivot tables, SQL queries, or any form of structured data exploration. Supports multi-sheet Excel workbooks, aggregation, filtering, joins, and exporting results to CSV/JSON/Markdown.
Security Assessment
About data-analysis
The data-analysis skill provides users with a powerful toolset for exploring, analyzing, and summarizing structured data from Excel and CSV files. By leveraging an in-process analytical SQL engine, it enables users to perform complex data manipulations and gain insights without manually processing large datasets. This skill addresses the common challenge of efficiently exploring multi-sheet workbooks or large CSV files, providing a seamless workflow for inspecting file structures, generating summaries, running queries, and exporting results in multiple formats. It simplifies the process of understanding dataset schemas and deriving actionable insights quickly, making it ideal for both technical and non-technical users who need structured data analysis.
FAQ
Which file formats are supported by this skill?
The skill supports Excel files (.xlsx, .xls) including multi-sheet workbooks, and CSV files. Each sheet in an Excel workbook is treated as a separate table.
How can I execute custom queries on my uploaded data?
You can run arbitrary SQL queries against the uploaded files using the '--action query' parameter along with the '--sql' parameter containing your SQL statement. Results can optionally be exported using '--output-file' with a CSV, JSON, or Markdown extension.
Can I summarize numeric and string data?
Yes, the skill provides statistical summaries for numeric columns including count, mean, standard deviation, min, percentiles, max, and null counts. For string columns, it returns count, number of unique values, top value, frequency, and null counts.
Are there any limitations on file size or performance?
The skill uses DuckDB's columnar engine to handle large files efficiently. While it supports large datasets, performance may vary depending on system resources and file size.
How does table naming work for multiple files?
For Excel files, each sheet becomes a table named after the sheet, and CSV files use the filename without extension. All tables from multiple files are available in the same query context, and special characters or spaces in names are auto-sanitized.
Install data-analysis
Quick Setup:
- Copy the skill folder to
.claude/skills/ - Claude will automatically detect and use the skill
Repository
bytedance/deer-flow