What does this skill do?

The Explore Data skill helps an agent profile a table or file before business analysis — understanding its shape, quality, and patterns so the analysis starts on solid ground.

It classifies columns and profiles table- and column-level metrics — null rates, distinct counts, distributions, and date ranges — then flags data-quality issues by severity.

For a business analyst, it surfaces the best dimensions to slice by, the key metrics to track, and a short list of recommended follow-up analyses.

  • Profiles a dataset's shape and quality

  • Flags nulls, duplicates, and suspicious values

  • Surfaces the best dimensions and metrics to analyze

  • Recommends concrete follow-up analyses

How it works

1

Access the data

The agent resolves a warehouse table or reads an uploaded file and infers column types.

2

Profile the dataset

It computes table- and column-level metrics, from null rates and distinct counts to numeric percentiles and date ranges.

3

Flag quality issues

It surfaces high null rates, duplicates, suspicious values, and distribution skew with severity for a business context.

4

Recommend the analysis

It suggests the best dimensions and metrics and recommends specific follow-up analyses to pursue.

Best use cases for this skill

  • Analysis kickoff: Profile a dataset before a business analysis project.

  • Data quality: Flag issues that would distort downstream analysis.

  • Metric discovery: Identify the metrics and dimensions that matter.

  • Analysis planning: Get a shortlist of high-value follow-up analyses.

Frequently asked questions

What does this skill do?

It profiles and explores a dataset to reveal its shape, quality, and patterns, then flags issues and recommends the dimensions, metrics, and analyses worth pursuing.

When should an agent use it?

Use it at the start of a business analysis — when encountering a new table or file, checking data quality, or deciding which dimensions and metrics to analyze.

What inputs does it accept?

A warehouse table via a connected warehouse, or an uploaded file such as CSV, Excel, Parquet, or JSON.

What does the output include?

An overview, per-column details, flagged data-quality issues with severity, and a numbered list of recommended follow-up analyses.

Use from source

Ask your Buda agent to install this community skill.

Copy this prompt into your own Buda agent. It includes the source repository and install command so the agent can complete the setup in natural language.

Prompt to send to your Buda agent
Please install the "Explore Data Skill" skill into this Buda agent.

Source repository: https://github.com/anthropics/knowledge-work-plugins
Install command: npx skills add anthropics/knowledge-work-plugins --skill explore-data -y -a universal

Please run the install command, verify the skill is available, and tell me any setup notes or follow-up steps from the source repository.
Explore marketplace

Install workflow

  1. 1Copy the prompt
  2. 2Send it to your Buda agent
  3. 3Done