Compare current benchmark results against historical baselines to spot performance regressions. Use as an explicit/manual helper for build-to-build degradation review, not for broad optimization strategy or low-level profiling ownership.
This skill hasn't been reviewed yet
ddcaa2a
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.