musmem-homonym

Detect athlete name homonyms in bodybuilding contest data using year-gap clustering.

Updated Mar 1, 2026
One-click install
npx skills add https://github.com/timfogarty1549/musmemSkills --skill musmem-homonym
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: musmem-homonym
Source: https://github.com/timfogarty1549/musmemSkills/tree/main/musmem-homonym
Command: npx skills add https://github.com/timfogarty1549/musmemSkills --skill musmem-homonym

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Scans bodybuilding contest data files to flag athlete name pairs that likely refer to two different individuals, using year-gap analysis to catch reappearing athletes across wide time spans and age-group transitions.

Core Features & Use Cases

  • Gap-based homonym detection: identifies names with large year gaps (≥ 10 years) and classifies confidence levels.
  • Interactive workflow: prompts for file paths at runtime and allows validation of candidates before action.
  • Reports and filtering: outputs candidates with clusters of years and supports saving non-homonym decisions.

Quick Start

Copy the script to a temporary location and run it to begin interactive review.

Frequently Asked Questions about musmem-homonym

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

FAQPage Schema
How do I detect athlete homonyms in contest data with large year gaps?

This skill identifies athlete name homonyms in bodybuilding contest data by detecting year gaps of 10 or more years, evaluating multi-criteria confidence levels, and clustering contest years to flag reappearing names.

What is the best way to clean sports data for athlete name duplicates across age divisions?

The best way is applying year-gap clustering to semicolon-delimited contest data files, which flags names with 10-plus year gaps and supports cross-file analyses to identify age-division transitions generating false duplicate matches.

Can I load multiple .dat files for cross-file homonym analysis?

Yes, the interactive workflow supports loading multiple .dat files to perform cross-file analyses of long-time gaps, allowing you to validate homonym candidates across different contest datasets simultaneously.

Does the homonym detection process support saving exclusion logs for non-homonym decisions?

Yes, the interactive review workflow includes a non-homonym exclusion log feature that saves your validation decisions, allowing you to track reviewed candidates and filter them out of future analyses.

What are the limitations of year-gap clustering for bodybuilding data cleaning?

Year-gap clustering requires semicolon-delimited .dat files with consistent athlete names, years, and contest codes, and may miss homonyms with gaps under 10 years or fail to detect duplicates without open or masters division transitions.