data-analysis

You can analyze large CSV and JSON files locally by ingesting them into an embedded DuckDB engine, which automatically detects formats and allows you to run standard SQL queries to derive actionable insights without manual scripting.

Yes, DuckDB supports querying Parquet files and automatically caches Parquet-processed results, enabling fast subsequent SQL queries and file-level profiling on your ingested datasets.

The best way to profile large data dumps locally is using an embedded DuckDB engine to ingest JSON, CSV, or Parquet formats, allowing you to generate file-level insights and structured summaries directly on your machine.

Yes, you can run standard SQL queries on JSON files of any size by ingesting them into the embedded DuckDB engine, which handles large datasets efficiently and avoids manual file handling.

You need to install DuckDB as the core dependency before ingesting large datasets, as the Skill relies on this embedded engine to process JSON, CSV, and Parquet files and generate structured analyses.

The local data analysis tool auto-detects JSON, CSV, and Parquet formats, but it is limited to these specific file types for profiling and querying, requiring DuckDB to execute the standard SQL operations on your data.