critical-validation

Validate contract analysis findings against data artifacts and innocent explanations.

3|1|Updated Mar 6, 2026

Search Tags:#investigation #validation #data quality #risk assessment #contract analysis #anomaly detection

Ready to run

npx skills add https://github.com/zltastopa/zmluvy --skill critical-validation

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: critical-validation
Source: https://github.com/zltastopa/zmluvy/tree/main/skills/critical-validation
Command: npx skills add https://github.com/zltastopa/zmluvy --skill critical-validation

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill prevents the reporting of false positives or misleading anomalies in data analysis by rigorously validating each finding against potential data artifacts and innocent explanations.

Core Features & Use Cases

Data Artifact Check: Identifies and filters out issues caused by data quality problems like NULL ICOs, duplicate entries, or nonsensical dates.
Innocent Explanation Validation: Cross-references findings with common, non-suspicious patterns (e.g., grants, large infrastructure projects, freelancer payments) to dismiss false alarms.
Classification: Assigns a definitive status (CONFIRMED, DISMISSED, INCONCLUSIVE) to each finding, ensuring only verified anomalies are escalated.
Use Case: After an SQL query flags potential contract splitting, this Skill would first check if the ICOs are missing or if it's a legitimate grouping of freelancers before concluding it's a confirmed issue.

Quick Start

Use the critical-validation skill to check the finding about potential contract splitting for supplier XYZ.

Frequently Asked Questions about critical-validation

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

FAQPage Schema

How do I validate contract analysis anomalies before reporting them?▼

To validate contract analysis anomalies before reporting, you must check each finding for data artifacts like NULL ICOs or duplicate entries and cross-reference against innocent explanations like legitimate freelancer payments, assigning a status of CONFIRMED, DISMISSED, or INCONCLUSIVE.

What is the process for dismissing false positives in risk assessment workflows?▼

Dismissing false positives in risk assessment workflows involves a multi-step validation process that identifies data quality problems such as nonsensical dates and checks for non-suspicious patterns like grants or large infrastructure projects before classifying the finding.

How do I check if a flagged contract splitting anomaly is a data artifact?▼

To check if a flagged contract splitting anomaly is a data artifact, verify whether the data contains missing ICOs, duplicate entries, or if it represents a legitimate grouping of freelancers rather than a confirmed suspicious issue.

Can I use anomaly detection validation for post-query data quality issues?▼

Yes, anomaly detection validation applies to post-query workflows by filtering out issues caused by data quality problems like NULL ICOs, ensuring that only verified anomalies with no innocent explanations are escalated as confirmed findings.

What are the limitations of validating investigative findings without checking innocent explanations?▼

Without checking innocent explanations, validating investigative findings risks reporting false positives, as legitimate patterns such as grants, large infrastructure projects, or freelancer payments may be incorrectly classified as confirmed anomalies.

Why does my risk assessment flag legitimate infrastructure projects as anomalies?▼

Your risk assessment flags legitimate infrastructure projects as anomalies because the data lacks initial innocent explanation validation, which is required to cross-reference findings with common non-suspicious patterns before assigning a confirmed status.