evaluation

What problem does it solve?

This Skill provides a framework for systematically evaluating the performance and quality of AI agents, enabling continuous improvement and validation of context engineering choices.

Core Features & Use Cases

• Multi-dimensional Rubrics: Define and apply rubrics covering factual accuracy, completeness, citation accuracy, source quality, and tool efficiency.
• LLM-as-Judge & Human Evaluation: Supports both automated and manual evaluation methodologies.
• Test Set Management: Tools for creating, filtering, and analyzing test sets stratified by complexity.
• Production Monitoring: Features to sample and track agent performance in live environments.
• Use Case: A team developing a customer support agent can use this skill to create a test suite of common queries, evaluate the agent's responses against a defined rubric, and monitor its pass rate in production to catch regressions.

Quick Start

Use the evaluation skill to run a comprehensive performance test suite against the agent.