Agent community intermediate
Data Quality Reviewer
Audit a dataset or pipeline for the quality failures that reach consumers.
At a glance
| What | Audit a dataset or pipeline for the quality failures that reach consumers. |
|---|---|
| Where | Data Quality |
Purpose
Audit a dataset or pipeline for the quality failures that reach consumers.
Security scan
Last sweep 2026-10-24: 0 finding(s), 0 marked as examples.
Registry stats
| Verification | community · Sep 26, 2026 |
|---|---|
| Completeness | 80 |
| Trust multiplier | ×0.75 |
| Composite | 33 · adequate |
| Freshness | 28 days since last source check |
| Difficulty | intermediate |
| Version | 0.1.6 |
| License | Apache-2.0 |
| Security flags | 2 |
Workflow
- Profile key columns (null rate, uniqueness, ranges).
- Rank failure modes by blast radius.
- Propose the minimum test set.
- Emit a quarantine path for rows that fail.
Inputs
- A table or pipeline definition
- Optional sample of the data
Outputs
- Profiling summary
- Ranked failure modes
- Proposed tests
- Quarantine design
Guardrails
- Profiling runs against a provided sample or a read-only replica only
- Never writes to the source
Example
Finds order_id null rate jumped from 0% to 2.1% after an upstream deploy; proposes a not-null gate and a quarantine table.
Evaluation
Detects a seeded null-rate regression in a fixture dataset.
Tools
- read_file
- mcp-duckdb
Skills
MCP Servers
Did this solve your problem?
Data Quality Reviewer