Data Quality Triage

Route records to done, needs_review, or unsalvageable based on completeness and confidence signals.

Updated Apr 23, 2026
One-click install
npx skills add https://github.com/TrevorMann/AIDataCleansing --skill data-quality-triage
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Data Quality Triage
Source: https://github.com/TrevorMann/AIDataCleansing/tree/main/skills/_common/data_quality_triage
Command: npx skills add https://github.com/TrevorMann/AIDataCleansing --skill data-quality-triage

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates the triage of records based on their completeness and confidence signals, streamlining the decision-making process for record routing.

Core Features & Use Cases

  • Record Triage: Automatically route records to 'done', 'needs_review', or 'unsalvageable' based on completeness and confidence signals.
  • Configuration Flexibility: Configure the required fields and confidence signal keys to adapt to different datasets and use cases.
  • Use Case: Imagine you have a large dataset with various fields, and you want to ensure that the data is complete and accurate before proceeding with further processing. Use this Skill to quickly triage the records and identify any potential issues.

Quick Start

Use the Data Quality Triage skill to triage the records in the dataset and determine their route (done, needs_review, unsalvageable).

Frequently Asked Questions about Data Quality Triage

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate record triage based on data completeness and confidence scoring?

Automate record triage by configuring required fields and confidence signal keys to evaluate datasets. The system uses custom scoring and routing logic to categorize records into done, needs_review, or unsalvageable queues without external dependencies.

What is the best way to route records for administrative workflows requiring high data accuracy?

Route records by applying custom validation logic to completeness and confidence signals. This method categorizes records into done, needs_review, or unsalvageable buckets, streamlining decision-making for administrative workflows where data accuracy is critical.

How does confidence scoring work for identifying incomplete records in a dataset?

Confidence scoring evaluates records against configured required fields and signal keys. It checks data completeness and accuracy, assigning a score that determines whether a record is routed as done, flagged for needs_review, or marked unsalvageable.

Can I configure required fields and confidence signal keys for different datasets?

Yes, you can configure required fields and confidence signal keys to adapt the triage logic to different datasets and use cases. This flexibility ensures the custom scoring accurately reflects the specific completeness requirements of your administrative workflows.

Do I need external dependencies to validate data quality and route records?

No external dependencies are required to validate data quality and route records. The triage system utilizes built-in custom scoring and routing logic to evaluate completeness and confidence signals entirely standalone.