Skill1.3k repo starsupdated today

spk-run-implement-review

This skill coordinates the implementation and review cycle for Spec Kitty work packages by identifying active tasks, dispatching implementations from runtime context, conducting independent reviews of each package, and feeding reviewer feedback into subsequent implementation attempts. Use it when work packages are in implementation or review lanes and agent coordination of implementers and reviewers is required.

View source Repository: spec-kitty

Install in Claude Code

Copy

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

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

Definition

SKILL.md

# spk-run-implement-review

Use this skill when a mission is in implementation/review lanes or the user
wants the agent to coordinate implementers and reviewers.

## Flow

1. Use `spk-run-next` to identify the active WP and lane.
2. Dispatch implementation only from runtime-provided prompt context.
3. Review each WP independently with `spk-run-review-wp`.
4. On rejection, feed structured reviewer feedback back into the next
   implementation attempt.
5. Continue until runtime returns terminal or a blocker.

## Legacy Alias

For detailed orchestration mechanics, use `spec-kitty-implement-review` when
available.