AI Plugin Index
dataset-quality-audit
Skill by zebbern · updated · ★ 4.7k
Runs 12-dimension quality checks on CSV, Excel, TSV and JSON data. It returns per-dimension scores, an overall grade and fix suggestions for people who need to clean or validate tables. dataset-quality-audit is published by zebbern on GitHub.
Install dataset-quality-audit
Built from the published package, never by AIgit clone --depth 1 https://github.com/zebbern/claude-code-guide /tmp/claude-code-guide && mkdir -p ~/.claude/skills && cp -r /tmp/claude-code-guide/skills/dataset-quality-audit ~/.claude/skills/dataset-quality-auditRun in your terminal. Claude Code loads skills from ~/.claude/skills automatically.
git clone --depth 1 https://github.com/zebbern/claude-code-guide /tmp/claude-code-guide && mkdir -p ~/.gemini/antigravity-cli/skills && cp -r /tmp/claude-code-guide/skills/dataset-quality-audit ~/.gemini/antigravity-cli/skills/dataset-quality-auditAntigravity CLI loads skills from ~/.gemini/antigravity-cli/skills, or .agents/skills for one project.
Step-by-step: install dataset-quality-audit in Antigravity CLI
Skills can run scripts on your machine. Some need an API key: check the README.
Last commit in the past day
MIT: permissive, fine for commercial use
Clear description, installs from GitHub, 4,677 stars, original repository
No risky patterns in the files we checked
About dataset-quality-audit
dataset-quality-audit runs 12-dimension quality checks on tabular data in CSV, TSV, Excel and JSON files. The checks cover missing values, duplicate rows, mixed types within a column, IQR-based outliers, date and email format compliance, uniqueness of ID columns, whitespace issues, constant columns, skewness, column naming, cardinality and cross-column logic. Each dimension gets a score from 0 to 100.
The bundled Python script, scripts/data_quality_checker.py, writes a JSON report with an overall score, a letter grade from A+ to F and top suggestions for fixes. Users can name ID and date columns, sample large files and set the file encoding. It requires Python 3.8 or later with pandas and numpy. It suits anyone who needs to check, profile or clean a dataset before using it.
Written from the project's SKILL.md and checked against it.
What dataset-quality-audit can do
- Missing value checkCounts and reports the percentage of null or NaN values per column.
- Duplicate row checkFinds fully duplicated rows and reports their number and percentage.
- Outlier detectionFlags outliers in numeric columns using the IQR method.
- Format complianceChecks consistency of date, email, phone and other formatted fields.
- Type consistencyDetects columns that mix numbers and text or other types.
- Uniqueness constraintsChecks whether ID-type columns contain duplicate values.
- Whitespace and naming checksFlags stray whitespace, empty strings and inconsistent column names.
- Graded reportProduces an overall score, a letter grade and actionable fix suggestions.
What you need
- Python 3.8+
- pandas
- numpy
Weekly newsletter
Like dataset-quality-audit? Get the best new skills every week
The best new tools, security warnings before you install something risky, and one practical tip. Free, three minute read.
Try asking
- Check data.csv for missing values and duplicate rows
- Find outliers in the sales columns of orders.csv
- Run a data quality audit on users.csv and suggest fixes
Security check
ANo download-and-run commands, hidden instructions or signs of sending keys out were found.
Checked automatically: skills/dataset-quality-audit/SKILL.md, skills/dataset-quality-audit/scripts/data_quality_checker.py. This looks for known risky patterns and is not a full audit. How grades work
Inside the skill
-
LICENSE1 KB -
SKILL.md4 KB -
scripts/data_quality_checker.py25 KB
Alternatives to dataset-quality-audit
All alternatives →
Route broad Data Analytics requests to the appropriate quantitative analysis, visualization, dashboard, report, notebook, KPI, market-sizing, validation, or semantic-layer workflow.
Identifies outdated elements in provided content and suggests updates to maintain freshness. Finds statistics, dates, and examples that need updating. Use PROACTIVELY for older content.
Create a go-to-market strategy covering marketing channels, messaging, success metrics, and launch timeline. Use when planning a product launch, creating a GTM plan from scratch, or defining a launch strategy for a new market.
Analyze auto-memory for promotion candidates, stale entries, consolidation opportunities, and health metrics. Use when the user runs /si:memory-review or asks what has been learned and what should be promoted or pruned.
Create a comprehensive product strategy using the 9-section Product Strategy Canvas — vision, segments, costs, value propositions, trade-offs, metrics, growth, capabilities, and defensibility. Use when building a product strategy, creating a strategic plan, or defining product direction.
Initialize the productivity system and open the dashboard. Use when setting up the plugin for the first time, bootstrapping working memory from your existing task list, or decoding the shorthand (nicknames, acronyms, project codenames) you use in your todos.
dataset-quality-audit: common questions
What file formats does dataset-quality-audit accept?
It accepts CSV, TSV, Excel and JSON tabular files. The input path and file encoding are set with command options.
How is the quality grade calculated?
The report gives an overall score from 0 to 100 and maps it to a grade from A+ to F. A score of 95 to 100 is A+, and below 40 is F.
Can it check large files?
Yes. The --sample option limits the check to a set number of rows, which the source describes as useful for large files.
How do I install dataset-quality-audit?
Run the command above to copy the skill into ~/.claude/skills/. Claude Code picks it up automatically.
Is dataset-quality-audit free?
The code is published under the MIT licence. The service it connects to may have its own pricing.
Is dataset-quality-audit safe to use?
It scores 90 of 100. Grades: maintenance A, licence A, quality A. Security check: grade A, no risky patterns found in the files checked. Review the code before you install. How grades work.
What are alternatives to dataset-quality-audit?
Similar skills: index, seo-content-refresher, gtm-strategy, memory-review.