Normalize bodybuilding athlete name variants across two dat files.
npx skills add https://github.com/timfogarty1549/musmemSkills --skill musmem-normalize
Please help me install this Agent Skill. Skill: musmem-normalize Source: https://github.com/timfogarty1549/musmemSkills/tree/main/musmem-normalize Command: npx skills add https://github.com/timfogarty1549/musmemSkills --skill musmem-normalize
Interactive tool to review and reconcile bodybuilding athlete name variant groups, correcting spelling errors and formatting mismatches across bb_male.dat and covid-male.dat.
Run musmemNormalize to start reviewing and reconciling name variants across the two dat files.
High-intent search queries and answers about installing and using this skill.
You normalize name variants by running the interactive workflow to fetch variant groups, apply spelling and formatting corrections, detect conflicts, and stamp approved changes back to bb_male.dat and covid-male.dat.
Reconciling bodybuilding names uses an interactive review process where you browse candidate variants, inspect related records, and apply consistent cross-file corrections to resolve duplicates before downstream analytics.
Yes, the workflow implements Python modules to fetch variant groups and detect conflicts interactively, letting you decide each reconciliation before stamping updates directly into the source .dat files.
No external dependencies are required. The workflow runs entirely with built-in Python modules to fetch groups, apply corrections, detect conflicts, and write changes back to the original data files.
Spelling mismatches persist because the two data sources capture athlete names independently. The cross-file normalization workflow resolves these by applying consistent formatting fixes and stamping corrections back to both files simultaneously.
aayushsoamExecute Python code incrementally in a stateful Jupyter kernel.
xcrrrClean raw datasets by fixing missing values, duplicates, and formats.
AlexiosBluffMaraCurate multi-modal LLM training data with GPU-accelerated deduplication and filtering.
puyanguvicMatch non-identical strings using Levenshtein distance and similarity metrics.
