Menú
Deploy one or more services end-to-end with health verification
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Orient in project state before starting work
Review open issues and PRs across the workspace to decide what needs action
Examine evidence (files, logs, code, output) against user instructions and baseline quality factors. Audit only, no fixes.
Use when executing an implementation plan. Builds in TDD cycles with disciplined commits — one commit per plan step, no unrelated files swept in.
Use before building anything non-trivial — new features, architectural changes, multi-file modifications. Explores intent, requirements, and design before implementation.
Use when diagnosing bugs, test failures, or unexpected behavior. Requires hypotheses before fixes — no jumping to solutions.
| name | deploy |
| description | Deploy one or more services end-to-end with health verification |
Deploy one or more services end-to-end. Follow every step in order — do NOT proceed to the next service until the current one is verified healthy.
For EACH service:
git status in all affected repos — commit or stash any uncommitted changescurl -s against the health endpointOnly move to the next service after the current one is confirmed healthy. If anything fails, diagnose and fix before proceeding.
$ARGUMENTS