Agent skills
SubjectAn agent driving kapi: the shipped Agent Skill, and the MCP tools an assistant calls.EvidenceScenario-scored. A prompt and a workspace go in, and what the agent did comes out: which tool it reached for, whether it finished at a green gate. No model grades anything. Triggering is stochastic, so a scenario means little until it is repeated.Gates CINo, and these never run in CI. They drive an interactive agent on a maintainer's machine, so the committed dataset is all CI sees and the date on it is the real currency of the numbers.
1 measured2 partial
How kapi is reached: the CLI, the desktop app, the shipped Agent Skill, and the MCP tools an assistant calls. Rests on every layer below, since a surface is how a person or an agent gets at them.