Data Quality Frameworks Skill for Claude Code: Great Expectations and dbt

A guide that helps your agent add data quality checks to pipelines with Great Expectations, dbt tests and data contracts.

Installs: 11.5K; on skills.sh
Stars: 42.1K; on GitHub
Files: 1; besides SKILL.md
Updated: Oct 2026; last repo commit

This skill teaches your agent six data quality dimensions: completeness, uniqueness, validity, accuracy, consistency and timeliness. Each one maps to a Great Expectations check, such as expect_column_values_to_not_be_null. It also describes a testing pyramid of schema tests, single-column unit tests and cross-table integration tests.

The Quick Start installs great_expectations with pip, runs great_expectations init and builds an expectation suite. Six worked patterns in references/details.md cover suites, checkpoints, dbt tests, custom dbt tests, data contracts and an automated quality pipeline. One checkpoint example sends a Slack message on failure, using a webhook from the environment.

Good for

Data engineers adding validation to pipelines
Analytics engineers writing dbt test suites
Teams agreeing on data contracts between producers and consumers

Install data-quality-frameworks

Claude Code

Copy this prompt.

Install the data-quality-frameworks skill in Claude Code. Run this command:

/plugin marketplace add wshobson/agents
/plugin install data-engineering@claude-code-workflows

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Pick one route. The plugin routes install the whole data-engineering plugin: 2 agents, 2 commands and 4 skills (counted from the plugin folder in the repo tree, which has no hooks or MCP config files). The skills-only routes install just this skill, with no agents or commands. The skill needs Python, and Great Expectations or dbt in your own project for the patterns you use.

From the project README. Source.

What's in the skill

When it loads

Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.

Sections in SKILL.md

When to Use This Skill
Core Concepts
1. Data Quality Dimensions
2. Testing Pyramid for Data
Quick Start
Great Expectations Setup
Detailed patterns and worked examples
Summary: {total_passed}/{total_tables} tables passed")
Best Practices
Do's
Don'ts

Key facts

Author: wshobson (owner of wshobson/agents)
Repo: wshobson/agents, folder plugins/data-engineering/skills/data-quality-frameworks
Installs on skills.sh: 11,481 as of 2026-11-02
GitHub stars: 42,081 for the whole wshobson/agents repo, 2026-11-02
License: MIT
Last repo commit: 2026-10-30
What is inside: 2 files: SKILL.md and references/details.md
Install routes in the README: The wshobson/agents README documents a plugin route and a skills-only route with `npx skills add` or `gh skill install`

What it includes

Six dimensions, each with an example check.
Completeness, uniqueness, validity, accuracy, consistency and timeliness.
Read · Data quality dimensions
Schema tests, unit tests and cross-table integration tests.
A way to decide where each check belongs.
Read · Testing pyramid for data
Install, initialize and create a datasource and a first suite.
The commands are pip install great_expectations, great_expectations init and great_expectations datasource new.
Runs code · Great Expectations quick start
Python code that defines expectations for a table.
Starts with checks like not-null and unique on an ID column.
Write · Pattern 1: Great Expectations suite
A checkpoint config with a Slack notification on failure.
The Slack action reads a webhook URL from SLACK_WEBHOOK.
Write · Pattern 2: Great Expectations checkpoint
A YAML models file with tests.
Example path models/marts/core/_core__models.yml.
Write · Pattern 3: dbt data tests
Reusable tests you write yourself.
For rules the built-in dbt tests do not cover.
Write · Pattern 4: custom dbt tests
A contract file for a table such as orders.
Example path contracts/orders_contract.yaml.
Write · Pattern 5: data contracts
Runs every table's suite, writes a report and fails the pipeline on any failure.
Python code that raises an error when data quality checks fail.
Runs code · Pattern 6: automated quality pipeline

From the official docs

Permissions

Low risk

The Quick Start installs a Python package and creates project files, and one example posts to Slack. Work in a virtual environment and read what the agent adds.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

It installs a Python package
The Quick Start runs pip install for Great Expectations. Use a virtual environment so it stays out of your system Python. github.com
A pipeline example fails your job on bad data
The automated pipeline pattern raises an error when any table fails. Add it to CI only after you have tuned the checks. github.com
The Slack example needs a webhook
Failure messages go to the Slack webhook you set in SLACK_WEBHOOK, so table names and observed values can appear in that channel. github.com

Technical details

Turning on read-only	No switch. Ask for a review of existing checks if you do not want files written.
Talks to	PyPI, for pip install great_expectations. Slack, through the webhook in the checkpoint example, if you configure it
Sign-in and keys	The checkpoint example reads a Slack webhook from the SLACK_WEBHOOK environment variable.
Scopes	Runs pip install great_expectations and great_expectations init Writes expectation suites, checkpoints, dbt tests and contract files in your repo Validation code you run reads your tables

Questions

What does the data-quality-frameworks skill do?

It helps your agent add data quality checks with Great Expectations, dbt tests and data contracts. It covers six quality dimensions and six worked patterns.

How do I install it?

Use the install box at the top of this page. It offers the data-engineering plugin (4 skills, 2 agents, 2 commands, no hooks or MCP config; counts from the repo tree) or just this skill through the skills CLI or GitHub CLI. The skills-only routes add no agents or commands.

Does it need Great Expectations or dbt installed?

Yes for running anything. The Quick Start runs pip install great_expectations. dbt is used in the dbt patterns but SKILL.md gives no dbt install command.

Can it send alerts?

One checkpoint example sends a Slack message when a check fails, through a webhook read from SLACK_WEBHOOK. You provide the webhook and set it up.

Does it need an API key?

SKILL.md names none. The only secret in the reference file is the optional Slack webhook URL in the checkpoint example.

Is it safe to use?

It bundles no scripts. The agent may install a Python package, initialize a Great Expectations project and write validation code in your repo, so work on a branch and check what it adds.

Information

updated Nov 2, 2026

Repository: wshobson/agents
Folder: plugins/data-engineering/skills/data-quality-frameworks

wshobson/agents skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 5

https://github.com/wshobson/agents/blob/HEAD/plugins/data-engineering/skills/data-quality-frameworks/SKILL.md · github.com
wshobson/agents README · github.com
data-engineering plugin.json · github.com
wshobson/agents marketplace.json · github.com
data-quality-frameworks details.md · github.com