What problem does it solve? Agent systems are non-deterministic and lack single correct answers, making traditional software testing inadequate. This Skill provides a framework for measuring agent quality across multiple dimensions, catching regressions, and validating context engineering decisions. ## Core Features & Use Cases - Multi-Dimensional Rubric Scoring: Score agent outputs on factual accuracy, completeness, citation accuracy, source quality, and tool efficiency with configurable weights and pass thresholds. - Test Set Management: Build complexity-stratified test sets (simple to very complex) with tag-based filtering and distribution analysis. - Production Monitoring: Sample live agent interactions, track pass rates over time, and trigger alerts at warning (0.85) and critical (0.70) thresholds. - Use Case: Before deploying an updated research agent, run a 50-case stratified test set through the EvaluationRunner, compare per-dimension scores against the baseline, and block deployment if any dimension regresses. ## Quick Start Ask the agent to evaluate a test set of agent outputs using the default five-dimension rubric and report per-dimension scores with an overall pass rate.
