$ ~/registry/skill/anthropics-data-skills-explore-data

SKILL

explore-data

Name: explore-data
Author: anthropics

Profile new datasets to assess structure, quality, distributions, and analysis priorities.

Stars

★ 22,528

Source

GitHub

Updated

2026-07-11

// securityCaution

Prompt only, no code
Open source

Summary

The materials indicate this is essentially an open-source prompt-only data exploration skill with no required secrets and no declared fixed remote endpoints. Overall risk is low, though its documented workflow includes routine file access and profiling queries against connected data warehouses, so users should still watch the permission scope of attached data sources.

CredentialsLow risk

The materials explicitly state that no keys or environment variables are required; there is no request for API tokens, database passwords, or other sensitive credentials, so credential exposure appears minimal.

Network egressLow risk

No remote endpoint is declared; as a prompt-only skill, it appears to be an analysis workflow description rather than a standalone networked component. The README only mentions querying an already connected data warehouse MCP, with no evidence of data being exfiltrated to unknown or unrelated third parties.

Code executionLow risk

The materials do not describe spawning local processes, executing scripts, installing dependencies, or invoking system commands; the content is primarily guidance on profiling steps and query logic.

Data accessCaution

The README explicitly supports reading user-provided CSV/Excel/Parquet/JSON files and, when a data warehouse is connected, querying table metadata and live data. This is routine for a data analysis skill, but it means the skill may access table contents and characteristics such as distributions, duplicates, and anomalous values; use least-privilege access and non-sensitive or controlled datasets where possible.

Supply chainLow risk

The source is an open-source GitHub repository, anthropics/knowledge-work-plugins, and the code is auditable, which is a strong risk-reducing factor. While the license is unspecified, stars are 0, and maintenance status is unknown, creating some governance uncertainty, there is no sign of closed-source behavior, uncontrolled outbound traffic, or malicious installation patterns.

Recommendations

Use this skill only with non-sensitive or sanitized data, and connect data warehouses with read-only, least-privilege accounts.
Check uploaded files for personal data, secrets, or business-sensitive columns before use.
Review the referenced open-source repository before deployment to confirm it is only a prompt/workflow asset and does not introduce extra execution components.

Audited by: gpt-5.4 · 2026-06-17

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "explore-data" skill from askskill:
1. Download https://raw.githubusercontent.com/anthropics/knowledge-work-plugins/main/data/skills/explore-data/SKILL.md
2. Save it as ~/.claude/skills/explore-data/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// examples

Check a new table's quality

Prompt

Please analyze this dataset's basic structure, including row count, column count, field types, null rates, duplicate records, and key value distributions for each column, then point out obvious data quality issues.

Expected

A dataset profile report with structure stats, null and duplicate analysis, anomaly flags, and a summary of data quality risks.

Identify suspicious columns

Prompt

Help me inspect which columns in this dataset contain suspicious values, such as extreme outliers, unreasonable dates, inconsistent formats, or messy category spellings, and rank them by risk.

Expected

A column-by-column anomaly review describing issue types, sample values, and recommended remediation priorities.

Choose dimensions and metrics

Prompt

Based on this dataset's fields, help me determine suitable dimensions and metrics for analysis, and suggest a few business questions or chart directions to explore first.

Expected

An analysis plan with usable dimensions, core metrics, priority questions, and recommended visualization directions.

// docs

/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

2. Understand Structure

Before analyzing any data, understand its structure:

Table-level questions:

How many rows and columns?
What is the grain (one row per what)?
What is the primary key? Is it unique?
When was the data last updated?
How far back does the data go?

Column classification — categorize each column as one of:

Identifier: Unique keys, foreign keys, entity IDs
Dimension: Categorical attributes for grouping/filtering (status, type, region, category)
Metric: Quantitative values for measurement (revenue, count, duration, score)
Temporal: Dates and timestamps (created_at, updated_at, event_date)
Text: Free-form text fields (description, notes, name)
Boolean: True/false flags
Structural: JSON, arrays, nested structures

3. Generate Data Profile

Run the following profiling checks:

Table-level metrics:

Total row count
Column count and types breakdown
Approximate table size (if available from metadata)
Date range coverage (min/max of date columns)

All columns:

Null count and null rate
Distinct count and cardinality ratio (distinct / total)
Most common values (top 5-10 with frequencies)
Least common values (bottom 5 to spot anomalies)

Numeric columns (metrics):

min, max, mean, median (p50)
standard deviation
percentiles: p1, p5, p25, p75, p95, p99
zero count
negative count (if unexpected)

String columns (dimensions, text):

min length, max length, avg length
empty string count
pattern analysis (do values follow a format?)
case consistency (all upper, all lower, mixed?)
leading/trailing whitespace count

Date/timestamp columns:

min date, max date
null dates
future dates (if unexpected)
distribution by month/week
gaps in time series

Boolean columns:

true count, false count, null count
true rate

Present the profile as a clean summary table, grouped by column type (dimensions, metrics, dates, IDs).

4. Identify Data Quality Issues

Apply the quality assessment framework below. Flag potential problems:

High null rates: Columns with >5% nulls (warn), >20% nulls (alert)
Low cardinality surprises: Columns that should be high-cardinality but aren't (e.g., a "user_id" with only 50 distinct values)
High cardinality surprises: Columns that should be categorical but have too many distinct values
Suspicious values: Negative amounts where only positive expected, future dates in historical data, obviously placeholder values (e.g., "N/A", "TBD", "test", "999999")
Duplicate detection: Check if there's a natural key and whether it has duplicates
Distribution skew: Extremely skewed numeric distributions that could affect averages
Encoding issues: Mixed case in categorical fields, trailing whitespace, inconsistent formats

5. Discover Relationships and Patterns

After profiling individual columns:

Foreign key candidates: ID columns that might link to other tables

…

View full docs ↗

anthropicsGet→

// similar tools

MCP

data-explore

Explore CSV datasets with summaries, cleaning, correlations, and statistical tests.