Profile a dataset, identify quality problems and anomalies, and deliver a concise review with a chart.
The Data Quality Review Agent Skill gives an agent a repeatable process for assessing CSV, Excel, JSON, JSONL, and Parquet data. It profiles structure and completeness, tests suspicious patterns, separates data-quality defects from unusual but valid observations, and produces a short evidence-led assessment with an appropriate visualization.
Product behaviour reviewed against VDF AI Cloud · 2026-09-04Match the Skill to the job, provide the required context, and decide what a useful output must contain before the agent begins.
The Skill supplies structured judgement and sequencing. VDF AI supplies the separately governed capabilities used during each step.
Confirm the file can be read and establish row, column, type, and missing-value coverage.
Measure distributions, uniqueness, consistency, and structural signals before drawing conclusions.
Investigate anomalies in context so rare but legitimate values are not automatically labelled defects.
Prioritise issues by decision impact and use one clear chart to make the central finding legible.
Data Quality Review can call these capabilities only when they are assigned to the agent and authorised for the user. The Skill itself never expands access.
“Review this customer export before migration and show which quality problems could corrupt matching or reporting.”
A prioritised quality report with profile statistics, anomaly evidence, one chart, and remediation recommendations.
Data Quality Review gives the agent a repeatable method. Tool permissions stay separate, and the capability can run inside a governed multi-agent Network.
Use these relationships as starting points, then narrow the agent’s access and workflow to the actual business context.
A reliable Agent Skill states its boundaries as clearly as its capabilities, especially when the workflow can influence decisions or external systems.
The reviewed skill is designed for CSV, Excel, JSON, JSONL, and Parquet sources when the configured data tools can access the file.
No. It profiles, tests, and explains quality problems. Remediation should be a separate controlled workflow with explicit transformation rules and review.
No. The process distinguishes unusual observations from confirmed defects and uses business context before recommending action.
Assign the Skill, grant only the tools the agent needs, and test the workflow with your own controlled context.