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

70%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/data-engineering/skills/data-quality-frameworks/SKILL.md

Quality

Content

53%Weight 40%Scale 1-5

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

The body has solid structure, a useful dimensions table, and good progressive disclosure to a real references file, but a malformed code section (broken heading, orphaned unfenced code, missing class definition) drags down conciseness and actionability. Fixing that section is the highest-impact improvement.

Suggestions

Fix the broken code block around the '## Summary' heading: open a proper ```python fence, include the missing DataQualityPipeline class definition, and remove the orphaned f-string fragment from the heading.

Present the validation workflow as an explicit numbered sequence with a validation checkpoint (build suite -> run checkpoint -> inspect failures -> raise/fail pipeline) rather than only as inline code.

Trim the duplicated framing between the intro line and the 'When to Use This Skill' list to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	The structured parts (dimensions table, Quick Start, best-practices lists) are mostly efficient, but the malformed '## Summary: {total_passed}/{total_tables} tables passed' heading and ~35 lines of orphaned, unfenced code add substantial noise that could be tightened.	3 / 5
Actionability	The Great Expectations Quick Start provides executable code, but the second example references a DataQualityPipeline class whose definition is missing and whose code fence is unbalanced, leaving key details incomplete.	3 / 5
Workflow Clarity	An implicit workflow (setup, create suites, validate, fail on failure via raise ValueError) exists with a validation checkpoint, but it is not presented as an explicitly sequenced multi-step process with checkpoints.	3 / 5
Progressive Disclosure	Clear section structure with a well-signaled one-level-deep reference to references/details.md (verified to exist), but the inlined broken code block is a minor organization gap that should be fixed or moved.	4 / 5
	Total	13 / 20 Passed

Description

87%Weight 40%Scale 1-5

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 strong: it explicitly states both capabilities and trigger conditions, names concrete tools, and occupies a distinct niche. Minor improvement could come from adding more action verb variety and common synonyms like 'data testing'.

Dimension	Reasoning	Score
Specificity	Names the domain and three concrete technologies ('Great Expectations, dbt tests, and data contracts') with the action 'Implement data quality validation', giving several specific actions, though the action verbs are less varied than the anchor-5 example.	4 / 5
Completeness	Explicitly 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 concrete trigger phrases.	5 / 5
Trigger Term Quality	'Use when building data quality pipelines, implementing validation rules, or establishing data contracts' covers natural phrases a user would say, with good keyword coverage, though synonyms like 'data testing' or 'data checks' are missing.	4 / 5
Distinctiveness Conflict Risk	The data-quality niche with named tools (Great Expectations, dbt, data contracts) gives clear distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: wshobson/agents
Path: plugins/data-engineering/skills/data-quality-frameworks/SKILL.md
Commit: d6837ae

Reviewed: about 12 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.