Data Quality Checker
Generate dbt tests and Great Expectations suites to validate data pipelines
What You Can Do
You can analyze your data structure and content to identify quality risks, then generate production-ready dbt tests and Great Expectations validation suites. Claude creates schema conformance checks, uniqueness constraints, referential integrity validations, completeness gap detection, and data freshness monitoring—all in code-first formats (YAML and Python) that integrate seamlessly with modern data stacks.
Features
detects data type mismatches, unexpected columns, and structural anomalies
enforces foreign key relationships and cross-table dependencies
identifies missing values and incomplete records across datasets
flags stale data and latency issues in your pipelines
creates YAML-based tests for uniqueness, not-null, and custom SQL assertions
builds statistical and rule-based validation profiles in Python
enforces business logic constraints on numeric, categorical, and temporal data
sets up statistical thresholds for outliers and distribution changes
Example Output
Example 1: dbt Tests for Orders Table
version: 2
models:
- name: orders
columns:
- name: order_id
tests:
- unique
- not_null
- name: customer_id
tests:
- relationships:
to: ref('customers')
field: customer_id
- name: order_date
tests:
- dbt_utils.accepted_values:
values: ['2024-01-01', '2024-01-02']
Example 2: Great Expectations Checkpoint
validation_results = context.run_checkpoint(
checkpoint_name='orders_validation',
validations=[
{'expectation_suite_name': 'orders.full'},
{'batch_request': {'datasource_name': 'postgres', 'data_connector_name': 'default'}}
]
)
Example 3: Data Freshness Alert Detects orders table not updated in last 24 hours and flags upstream dependency failures in your pipeline orchestrator.
What's Included
- SKILL.md instruction file with comprehensive framework for data quality rule generation:
- dbt test templates for schema, uniqueness, referential integrity, and custom SQL validations:
- Great Expectations suite builder: Python configuration templates for statistical profiling
- Data freshness checklist: timestamp validation patterns and staleness detection queries
- Quality rules documentation: YAML and Python code-first reference formats for version control
Who It's For
- Data engineers building or maintaining dbt projects and analytics engineering workflows
- Analytics engineers establishing data governance and quality frameworks
- Data quality specialists implementing validation suites across enterprise pipelines
- Data platform teams inheriting legacy pipelines and establishing baseline quality controls
- DevOps and infrastructure engineers automating data validation in CI/CD workflows
Best For
- Creating dbt test suites for new fact and dimension tables in dimensional warehouses
- Generating Great Expectations validation profiles from existing data structures
- Implementing referential integrity and schema conformance checks in inherited pipelines
- Building data freshness monitors and staleness detection rules for real-time dashboards
- Establishing completeness and value range constraints for regulatory compliance workflows
You might also like
You can evaluate unfamiliar locations objectively against your specific production needs—whether that's crane access, parking capacity, noise restrictions, or permit requirements. The skill generates comprehensive scout reports that compare multiple sites using weighted evaluation matrices, flag deal-breakers early, and document infrastructure limitations so your production team makes informed decisions before committing resources to visits.
by skillslib
You'll design robust SCADA system architectures, configure industrial protocols (Modbus, Profibus, OPC-UA, DNP3), and diagnose connectivity and performance issues across distributed control networks. Get step-by-step configuration guidance, integration workflows, and troubleshooting decision trees tailored to your specific hardware and protocol stack.
by skillslib
You can establish systematic color grading workflows that accelerate project delivery, ensure visual consistency across episodes and projects, and maintain broadcast-quality standards. Claude generates reusable templates, quality control checklists, and grading decision frameworks tailored to your project's color science and deliverable requirements.
by skillslib
Generate customized legal documents and client communications automatically from your MyCase case data. This skill extracts case details, client information, and matter status to populate document templates, send email updates, and create batch processing workflows. Reduce manual data entry and standardize your document generation process while maintaining client communication consistency.
by skillslib
You can convert raw ESG metrics and narratives into professionally structured impact reports that satisfy regulatory and investor requirements. The skill automatically verifies alignment with SASB materiality categories, GRI standards, and TCFD recommendations; constructs defensible materiality matrices from stakeholder feedback; standardizes impact metrics to IRIS+ and SDG frameworks; and identifies compliance gaps between your draft and mandatory disclosure requirements.
by skillslib
Use Claude to automate your entire collection workflow, from first touch to recovery, with legally sound escalation protocols. You'll recover more money in less time, reduce bad debt write-offs by 25-40%, and build defensible collection records that withstand legal scrutiny. Claude handles customized demand letters, compliance validation, debtor profiling, and escalation strategies tailored to account age, debtor behavior, and jurisdiction.
by skillslib
You can quantify how interest rate changes will affect your bond holdings through duration and convexity analysis, calculate precise hedge ratios for Treasury futures and other instruments, and stress-test portfolios across multiple yield curve scenarios. This skill handles complex securities including callable bonds and mortgage-backed securities, enabling you to compare different portfolio structures and evaluate positioning against interest rate forecasts.
by skillslib
This skill helps you troubleshoot Wwise integration issues, diagnose audio performance bottlenecks, and generate comprehensive documentation for interactive audio specifications. You'll get step-by-step fixes for common implementation problems, performance optimization strategies, and best practices for audio systems across different game engines and platforms.
by skillslib