data-quality-auditor

Audit datasets for completeness, consistency, accuracy, and validity. Profile data distributions, detect anomalies and outliers, surface structural issues, and produce an actionable remediation plan. Use when the user asks to check data quality, profile a dataset, hunt outliers or missing values, or validate data before analysis or model training.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

82%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.

A well-structured, highly actionable skill body with clear modes, executable commands, and a sensible bundle layout. Minor conciseness and progressive-disclosure refinements would push it to the top of the scale.

Suggestions

Trim the persona fluff in the opening paragraph ('You move fast, think in impact, and never let...') to save tokens without losing operational value.

Link the references file contextually — e.g., add 'See references/data-quality-concepts.md for MCAR/MAR/MNAR theory' where missingness mechanisms are first discussed in Mode 1, rather than only in the trailing References list.

Add an explicit verify/checkpoint note between audit steps in Mode 1 (e.g., confirm profiler output before running downstream analyzers) to strengthen the workflow feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is largely lean — tables, copy-paste commands, and no padding explaining basic concepts — but the persona intro ('You move fast, think in impact...') and a few stylistic lines could be trimmed.	4 / 5
Actionability	Copy-paste-ready bash invocations for all three scripts cover the common cases (profile, columns, JSON output, monitor, method/threshold flags), and the remediation playbook gives specific thresholded actions.	5 / 5
Workflow Clarity	Three numbered modes are clearly sequenced, and destructive remediation steps carry explicit safeguards ('Confirm uniqueness key with data owner before deduplication', 'Never auto-remediate 🔴 findings without human confirmation'); minor gap is the lack of explicit verify-checkpoints between read-only audit steps.	4 / 5
Progressive Disclosure	The body is a well-organized overview with one-level-deep references to three real scripts and a real concepts file (verified present in scripts/ and references/); the single reference is signaled only in a trailing list rather than linked contextually where MCAR/MNAR theory is first invoked.	4 / 5
	Total	17 / 20 Passed

Description

96%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.

A strong description that clearly states concrete capabilities and provides natural, varied trigger phrases with an explicit 'Use when' clause. Only minor overlap risk with adjacent analytics skills keeps it just short of a perfect distinctiveness score.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Audit datasets for completeness, consistency, accuracy, and validity', 'Profile data distributions', 'detect anomalies and outliers', 'surface structural issues', 'produce an actionable remediation plan' — giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both what (audit/profile/detect/remediate) and when (a 'Use when...' clause with concrete trigger phrases), satisfying both halves of the dimension.	5 / 5
Trigger Term Quality	Natural user phrasing with synonyms — 'check data quality', 'profile a dataset', 'hunt outliers or missing values', 'validate data before analysis or model training' — matches how a user would actually phrase the need.	5 / 5
Distinctiveness Conflict Risk	The data-quality-audit framing with DQS and remediation is a clear niche, but 'validate data before analysis' and 'profile a dataset' carry minor overlap risk with general analytics/profiling skills.	4 / 5
	Total	19 / 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: alirezarezvani/claude-skills
Path: engineering/data-quality-auditor/skills/data-quality-auditor/SKILL.md
Commit: 19392f7

Reviewed: ~6 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.