Skill1.3k repo starsupdated today

spk-run-next

spk-run-next executes the spec-kitty control loop to advance an active mission by calling the next command, then routes the result (step, decision_required, blocked, or terminal) to the appropriate handler for execution, decision-making, guard repair, or final acceptance.

View source Repository: spec-kitty

Install in Claude Code

Copy

git clone --depth 1 https://github.com/Priivacy-ai/spec-kitty /tmp/spk-run-next && cp -r /tmp/spk-run-next/src/doctrine/skills/spk-run-next ~/.claude/skills/spk-run-next

Then start a new Claude Code session; the skill loads automatically.

Definition

SKILL.md

# spk-run-next

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

## Flow

1. Run `spec-kitty next --agent <name>` or use the host's equivalent action.
2. Read the returned decision kind.
3. For `step`, execute the generated prompt file.
4. For `decision_required`, answer the decision explicitly.
5. For `blocked`, fix guard failures before retrying.
6. For `terminal`, route to `spk-gate-accept`.

## Legacy Alias

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