spk-run-next

name: spk-run-next description: "Drive the canonical spec-kitty next control loop and route query, step, blocked, decision_required, and terminal results."

Use this skill when advancing an active mission, asking what to do next, or recovering from a runtime decision.

Query state with spec-kitty next --mission <handle> --json or advance with spec-kitty next --agent <name> --mission <handle> --result <success|failed|blocked>.
Read the returned decision kind.
For query, inspect only; do not execute a prompt or mark a result.
For step, execute the generated prompt file.
For decision_required, answer with --answer, --result, --agent, and --decision-id when multiple decisions are pending.
For blocked, fix guard failures before retrying.
For terminal, route to spk-gate-accept.

For detailed runtime semantics, use spec-kitty-runtime-next when available.