data-quality-frameworks
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.
84
66%
Does it follow best practices?
Impact
97%
1.46xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/data-engineering/skills/data-quality-frameworks/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description that clearly identifies its niche in data quality validation with specific tooling references and an explicit 'Use when' clause. Its main weakness is that the capability actions are somewhat high-level ('implement', 'building', 'establishing') rather than listing granular concrete actions like creating expectation suites or writing specific test types.
Suggestions
Add more specific concrete actions, e.g., 'Create expectation suites, write dbt schema/data tests, define and enforce data contract schemas' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (data quality validation) and specific tools (Great Expectations, dbt tests, data contracts), but doesn't list multiple concrete actions beyond 'implement' and 'building/establishing'. It could be more specific about what actions are performed (e.g., 'create expectation suites, write dbt schema tests, define contract schemas'). | 2 / 3 |
Completeness | Clearly answers both 'what' (implement data quality validation with Great Expectations, dbt tests, and data contracts) and 'when' (Use when building data quality pipelines, implementing validation rules, or establishing data contracts) with an explicit 'Use when...' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'data quality', 'Great Expectations', 'dbt tests', 'data contracts', 'validation rules', 'data quality pipelines'. These are terms a user working in this domain would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of Great Expectations, dbt tests, and data contracts creates a very specific niche. This is unlikely to conflict with general data engineering or testing skills due to the specific tooling and domain focus. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, executable examples across Great Expectations, dbt, and data contracts, which is its primary strength. However, it is severely over-long and monolithic—cramming 400+ lines of patterns into a single file with no progressive disclosure or bundle structure. The verbosity and lack of organization undermine its usability as a skill file, and basic concepts like data quality dimensions waste tokens explaining things Claude already knows.
Suggestions
Split content into bundle files: move Pattern 1-2 into great_expectations.md, Pattern 3-4 into dbt_tests.md, Pattern 5 into data_contracts.md, and Pattern 6 into quality_pipeline.md, with SKILL.md serving as a concise overview with links.
Remove the 'Core Concepts' section entirely—Claude already knows data quality dimensions and the testing pyramid adds no actionable value.
Add an explicit end-to-end workflow section showing the sequence: define contract → implement GE suite → add dbt tests → wire into pipeline → validate → handle failures, with clear checkpoints.
Consolidate the Quick Start and Pattern 1 which heavily overlap—keep only the Pattern 1 version as the canonical GE example.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 400+ lines with significant redundancy. The 'Core Concepts' table explains basic data quality dimensions Claude already knows. Pattern 1 and the Quick Start overlap heavily. The data contract YAML, full pipeline class, and extensive dbt examples could be drastically condensed or split into bundle files. The testing pyramid ASCII art adds no value. | 1 / 3 |
Actionability | Provides fully executable code across multiple frameworks: complete Great Expectations suite building, runnable checkpoint configs, dbt schema YAML with real test definitions, custom SQL tests, and a full Python pipeline class. All examples are copy-paste ready with realistic field names and values. | 3 / 3 |
Workflow Clarity | The Quick Start shows a basic sequence (install → init → create suite → validate), and Pattern 6 orchestrates validation with failure handling. However, there's no clear end-to-end workflow tying the patterns together, no explicit validation checkpoints between steps (e.g., verify GE context before running checkpoint), and no error recovery guidance beyond raising exceptions. | 2 / 3 |
Progressive Disclosure | Monolithic wall of content with no references to external files and no bundle files to support splitting. All six patterns, the data contract spec, the full pipeline class, and best practices are inlined in a single massive document. This content desperately needs to be split into separate files (e.g., great_expectations_patterns.md, dbt_tests.md, data_contracts.md). | 1 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (584 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- wshobson/agents
- Commit
112197c
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.