Explore Data

anthropics/knowledge-work-pluginsOfficial

This is a comprehensive data profiling workflow that goes well beyond basic row counts and null checks. It walks Claude through categorizing columns by role (identifier, dimension, metric, temporal), running distribution analysis on each type, and flagging quality issues like high null rates, suspicious placeholder values, and referential integrity problems. The real value is in the structured approach to pattern discovery and the framework for assessing completeness, consistency, and accuracy across columns. It concludes by suggesting specific follow-up analyses based on what it finds, like cohort analysis or correlation studies. Best used when you need to understand a new dataset's quirks before building dashboards or reports on top of it.

skills.sh installs: 6K
GitHub stars: 35.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add anthropics/knowledge-work-plugins --skill explore-data --agent claude-code

Installs into .claude/skills of the current project.

Files

/explore-data - Profile and Explore a Dataset

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Generate a comprehensive data profile for a table or uploaded file. Understand its shape, quality, and patterns before diving into analysis.

Usage

/explore-data <table_name or file>

Workflow

1. Access the Data

If a data warehouse MCP server is connected:

Resolve the table name (handle schema prefixes, suggest matches if ambiguous)
Query table metadata: column names, types, descriptions if available
Run profiling queries against the live data

If a file is provided (CSV, Excel, Parquet, JSON):

Read the file and load into a working dataset
Infer column types from the data

If neither:

Ask the user to provide a table name (with their warehouse connected) or upload a file
If they describe a table schema, provide guidance on what profiling queries to run