validator

Validate final medical analyses against extracted source data.

Updated Aug 23, 2026

Search Tags:#consistency #data quality #validator #fact verification #medical data #source of truth

Ready to run

npx skills add https://github.com/n1healthcare/easy-chr --skill validator-n1healthcare

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: validator
Source: https://github.com/n1healthcare/easy-chr/tree/main/server/.gemini/skills/validator
Command: npx skills add https://github.com/n1healthcare/easy-chr --skill validator-n1healthcare

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Comprehensive validator that checks ALL facts, claims, numbers, context, and qualitative data against source documents.

Core Features & Use Cases

Numeric Data Completeness: Verify that every numeric value in extracted.md appears in final_analysis.md.
Qualitative Coverage: Ensure symptoms, medical history, medications, and contextual details are represented.
Context & Traceability: Detect inconsistencies, preserve context, and verify recommendation traceability.

Quick Start

Run the validator against extracted.md and final_analysis.md to identify missing data, misinterpretations, and unsupported claims.

Frequently Asked Questions about validator

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

FAQPage Schema

How do I verify that my medical analysis reflects the source documents?▼

To verify medical analysis against source documents, compare the extracted data and synthesized analysis to check numeric values, qualitative items, and context. This validation flags missing data, misinterpretations, and unsupported claims for remediation.

What is the best way to check numeric data completeness in medical reports?▼

Checking numeric data completeness involves verifying that every numeric value in your extracted data appears in the final analysis. This ensures no quantitative medical data is lost during synthesis.

Can I detect unsupported claims and misinterpretations in a synthesized medical summary?▼

Yes, you can detect unsupported claims and misinterpretations by validating the final analysis against extracted data. This process checks qualitative items and context to flag inconsistencies across multiple sections.

How do I ensure qualitative coverage like symptoms and medications are represented in my analysis?▼

To ensure qualitative coverage, validate that symptoms, medical history, medications, and contextual details from extracted data are fully represented in the final analysis, preserving all necessary context.

What are the limitations of automated fact verification for medical context gaps?▼

Automated fact verification for medical context gaps relies on comparing extracted data against final analysis files. It requires both files to be properly formatted, as it cannot verify facts absent from the original source extraction.