iris-interface-field-match

Name: iris-interface-field-match
Availability: InStock
Author: skylercook

Normalize and match semantic fields in IRIS interface JSON data.

Updated Jun 4, 2026

Search Tags:#semantic analysis #candidate matching #data review #field normalization #IRIS interface

Ready to run

npx skills add https://github.com/SkylerCook/imedical.agents --skill iris-interface-field-match

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: iris-interface-field-match
Source: https://github.com/SkylerCook/imedical.agents/tree/main/plugins/iris-interface-dev-plugin/skills/iris-interface-field-match
Command: npx skills add https://github.com/SkylerCook/imedical.agents --skill iris-interface-field-match

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill addresses the need for semantic normalization, candidate matching, and diagnosis of unmatched fields in IRIS interface data, facilitating efficient data processing and review.

Core Features & Use Cases

Semantic Normalization: Standardize field codes, names, types, lengths, and mandatory flags.
Candidate Matching: Provide semantic matches, confidence scores, and evidence.
Unmatched Diagnosis: List reasons for unmatched fields such as missing codes, ambiguous names, type conflicts, and missing local feedback.
Feedback Draft Generation: Create local feedback drafts for manual review and confirmation.
Use Case: Ideal for post-processing iris-interface-doc-ingest outputs to ensure data quality and accuracy before further analysis or integration.

Quick Start

Execute the skill in the project root directory with the command: python .agents/plugins/iris-interface-dev-plugin/scripts/iris-interface-field-match.py --parsed docs/output/iris-interface/<doc-name>/parsed.json --project-root .

Frequently Asked Questions about iris-interface-field-match

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

FAQPage Schema

How do I normalize IRIS interface fields from a parsed JSON file?▼

To normalize IRIS interface fields from a parsed JSON file, execute the provided Python script via command line. The process standardizes field codes, names, types, lengths, and mandatory flags to ensure data consistency before manual review or downstream integration.

What is semantic candidate matching for interface data?▼

Semantic candidate matching for interface data compares parsed fields to provide semantic matches, confidence scores, and evidence. It standardizes varying field definitions and identifies corresponding data points to improve data review efficiency in interface management workflows.

Can I diagnose unmatched fields and missing mandatory flags in IRIS data?▼

Yes, you can diagnose unmatched fields and missing mandatory flags in IRIS data. The script lists specific reasons for unmatched fields, such as missing codes, ambiguous names, type conflicts, and missing local feedback, facilitating targeted manual review.

Do I need Python to run semantic normalization and matching on IRIS interfaces?▼

Yes, you need Python to run semantic normalization and matching on IRIS interfaces. The Skill requires Python script execution for processing. You must run it in your project root directory, specifying the parsed JSON file path and project root.

How do I generate feedback drafts for unmatched IRIS fields?▼

You generate feedback drafts for unmatched IRIS fields by executing the field matching Python script. It automatically creates local feedback drafts for manual review and confirmation, addressing issues like ambiguous names or type conflicts found during the matching process.

What is the best way to post-process parsed JSON outputs for IRIS interface data?▼

The best way to post-process parsed JSON outputs for IRIS interface data is using a dedicated semantic normalization script. It standardizes fields, matches candidates with confidence scores, and diagnoses unmatched entries to ensure data quality before further analysis.