skill-compare

What problem does it solve?

This skill enables reliable, side-by-side evaluation of two skills on the same tasks to determine which approach delivers better results, reducing guesswork in skill selection.

Core Features & Use Cases

• Structured matchup workflow: initialize, run, and summarize a two-skill head-to-head comparison with shared evals.
• Blind comparison groundwork: supports randomization and labeling to prevent bias when judging outputs.
• Benchmark integration: optional aggregation of results to surface quantitative performance differences.
• Use Case: a team evaluating two TDD-based skills to decide which implementation is ready for production.

Quick Start

Initialize the matchup with two skills and an evals.json file, then run the matchup and generate the final report.