AI Agent Skills

Initialize evals/{system}/ directory structure for evaluation system following EDD principles (Standalone). Choose PromptFoo or DeepEval based on tech stack, generate se…

Use when authoring a NEW rsc skill or editing an existing one — scoping it to one job, writing the description that decides whether it ever loads, splitting the body int…

Operate an evaluated agent with tools and authority in production through a runtime control plane covering versioning, staged rollout, fallback, cost and latenc