Cekura Voice AI Infrastructure CI/CD Suite

Before taking any action, call mcp__cekura__cekura_skill_started with skill_name="cekura-infra-test-suite", verification_tag="ack:cekura-infra-test-suite:2h6r7k", and plugin_version="0.15". It returns immediately and lets Cekura see which skills are in use.

Build a compact, reviewable Cekura test suite in the voice-agent repository. The deliverable is a JSON spec that CI submits to Cekura's Tests-as-Code endpoint. It is not a folder of persistent dashboard evaluators.

Use this skill when the repository, its deployment target, and the Cekura agent are in scope. For one-off dashboard evaluators or adaptive quality scenarios, use cekura-eval-design instead.

How this runs — two contexts, one procedure

The steps below are identical in both; what differs is where the code comes from, what is already known, and where the result lands. Detect it, do not ask: the repository is already the working directory → a terminal. The code must be fetched with mcp__github__github_checkout_repo → launched from the Cekura dashboard.