dataset-quality-audit

Run comprehensive quality checks on tabular data (CSV/Excel/TSV/JSON), detecting missing values, duplicates, outliers, format issues, and type inconsistencies to produce an overall score, grade, and actionable suggestions. Triggered when users ask to check data quality, find missing or duplicate values, detect outliers, validate formats, profile data, or clean data.

Quality

86%

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

72%

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 body with concrete commands and a real bundled script. Its main weaknesses are mild verbosity in the opening/tables and the absence of a validation checkpoint for batch data-auditing operations.

Suggestions

Remove or shorten the intro sentence that restates the description, since the capabilities table already conveys the same information.

Add an explicit verification step after running the checker (e.g. 'Review the overall grade and top_suggestions before fixing issues; re-run after cleaning to confirm the score improved') to add a feedback loop for batch operations.

Consider trimming the capabilities table or moving per-dimension detail into a reference file so the overview stays lean while preserving the actionable Quick Start.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable commands, a parameter table, and an output example, but the opening sentence ('A data quality auditing tool that runs 12-dimension quality checks...') restates the description and the capabilities table repeats concepts, so it could be tightened.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands (e.g. 'python3 scripts/data_quality_checker.py users.csv --id-columns "user_id,email"'), a complete parameter table with defaults, and a concrete JSON output example referencing a real bundled script.	3 / 3
Workflow Clarity	The single-command workflow is unambiguous, but for a batch/data-auditing operation there is no validation or verification checkpoint (e.g. inspecting the grade before acting on suggestions), which caps workflow clarity at 2 per the batch-operations guideline.	2 / 3
Progressive Disclosure	Content is organized into clear sections (Capabilities, Quick Start, Detailed Usage, Output Format) and the single bundled script (scripts/data_quality_checker.py) is referenced correctly at one level deep with no nested references, fitting the simple single-script structure.	3 / 3
	Total	10 / 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.

A strong, well-scoped description that clearly states concrete capabilities and provides explicit, natural-language trigger guidance in third person. It avoids over-claiming and is unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('detecting missing values, duplicates, outliers, format issues, and type inconsistencies' and producing 'an overall score, grade, and actionable suggestions'), matching the comprehensive multi-action anchor.	3 / 3
Completeness	Explicitly answers both what it does (quality checks producing score/grade/suggestions) and when to use it via the explicit 'Triggered when users ask to...' clause.	3 / 3
Trigger Term Quality	Includes natural phrases users would actually say ('check data quality', 'find missing or duplicate values', 'detect outliers', 'validate formats', 'profile data', 'clean data'), giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Scopes to 'tabular data (CSV/Excel/TSV/JSON)' with a distinct data-quality/profiling niche and specific triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: zebbern/claude-code-guide
Path: skills/dataset-quality-audit/SKILL.md
Commit: af7d491

Reviewed: about 8 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.