Skill Eval

DRANK

Testing Your AI Agent Skills I’ve been working with AI coding agents daily — Gemini CLI, Claude Code, and others. One pattern I keep seeing is teams building skills for these agents: procedural instructions that teach the model how to use internal tools, follow specific workflows, or comply with team conventions. The problem? No one tests them. Why Skills Need Tests When you write a skill, you’re essentially writing documentation that an agent will follow autonomously.