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.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable, packed with executable code across Great Expectations, dbt, and data contracts, but it is a long monolithic document that pads in concepts Claude already knows and does not split detail into reference files or present a single guided validation workflow with checkpoints.

Suggestions

Move the detailed code patterns (Great Expectations suites/checkpoints, dbt tests, data contracts, the pipeline class) into separate files under references/ (e.g. references/great-expectations.md, references/dbt-tests.md) and keep SKILL.md as a concise overview with one-level-deep links — this improves both progressive_disclosure and conciseness.

Remove or drastically shrink the "Core Concepts" section (the data-quality-dimensions table and the testing-pyramid ASCII art), which explains concepts Claude already knows and adds tokens without earning their place.

Add a single explicit end-to-end workflow with numbered steps and validation checkpoints (e.g. define expectations → run checkpoint → review failures → fix and re-validate → only then promote/merge) to lift workflow_clarity from a pattern catalog to a guided process.

Dimension	Reasoning	Score
Conciseness	Most patterns are efficient concrete code, but the "Core Concepts" section explains data-quality dimensions in a table and a testing-pyramid ASCII diagram that Claude already knows, and the 583-line body could be tightened — matching the 'mostly efficient but includes some unnecessary explanation' anchor rather than the lean score-3.	2 / 3
Actionability	The body is dominated by fully executable, copy-paste-ready examples (pip/bash setup, Python expectation suites, YAML checkpoints, dbt test YAML and SQL, data-contract YAML, a complete pipeline class with usage), matching the 'fully executable code/commands; copy-paste ready' anchor and clearly above the pseudocode/incomplete score-2.	3 / 3
Workflow Clarity	The skill reads as a pattern catalog rather than a guided sequence; Pattern 6 does include a validation feedback loop (checking result.success and raising on failure), but there is no top-level numbered workflow with explicit validate-then-proceed checkpoints, so it sits at 'sequence present but checkpoints missing/implicit' rather than a 3.	2 / 3
Progressive Disclosure	At 583 lines everything is inline in SKILL.md with no bundle reference files (only external doc links), and content that should be split (full suites, dbt tests, contracts, pipeline class) is inline; it is well-sectioned so it is above the score-1 wall-of-text, but at this size it does not meet the score-3 'appropriately split into one-level-deep references' bar, and the <50-line simple-skill exception does not apply.	2 / 3
	Total	9 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise, uses third person, and cleanly answers both what the skill does and when to use it with specific, natural trigger terms and named tools. It is a strong, low-conflict description with no meaningful weaknesses.

Dimension	Reasoning	Score
Specificity	"Implement data quality validation with Great Expectations, dbt tests, and data contracts" lists multiple specific concrete actions paired with named tools, matching the 'Lists multiple specific concrete actions' anchor and exceeding the score-2 bar of naming only some actions.	3 / 3
Completeness	It states what it does ("Implement data quality validation...") and gives an explicit "Use when building data quality pipelines, implementing validation rules, or establishing data contracts" trigger, satisfying both what and when; the present 'Use when' clause avoids the score-2 cap.	3 / 3
Trigger Term Quality	Terms like "data quality pipelines", "validation rules", "data contracts", "Great Expectations", and "dbt tests" are exactly what a user would naturally say, giving good coverage rather than the partial coverage at score 2.	3 / 3
Distinctiveness Conflict Risk	The combination of Great Expectations, dbt tests, and data contracts carves a clear niche with distinct triggers unlikely to fire for unrelated skills, matching the score-3 anchor rather than the score-2 'could still overlap' case.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (588 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/data-quality-frameworks/SKILL.md
Commit: f627ab5

Reviewed: about 9 hours ago

Table of Contents

Discovery Implementation Validation

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.