Skip to content
Agent Orchestration
Skill

/spk-run-implement-review

Orchestrate Spec Kitty work-package implementation and review loops until all packages are done, approved, or correctly rejected.

BOOST
From plugin
spec-kitty
1.7k50 skills1 command
Install
$ npx -y skills add spec-kitty/spec-kitty --skill spk-run-implement-review --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/spk-run-implement-review

Context preview

The summary Claude sees to decide when to auto-load this skill.

Orchestrate Spec Kitty work-package implementation and review loops until all packages are done, approved, or correctly rejected.

SKILL.md

spk-run-implement-review.SKILL.md
name: spk-run-implement-review
description: "Orchestrate Spec Kitty work-package implementation and review loops until all packages are done, approved, or correctly rejected."

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.

Sub-Agent Long-Gate Contract

`move-task --to for_review` runs the pre-review regression gate synchronously as part of the transition (#2570/#2493/#2555): it derives the affected test scope for the Mission's changed files and runs it at head before the command returns. That scoped run is a real subprocess and can take from seconds to a few minutes depending on scope size.

  • A dispatched implement/review sub-agent MUST **poll the gate invocation to

completion** — treat the `move-task --to for_review` command as still in flight until it exits, not as a fire-and-forget hand-back. Do not assume control returns immediately, and do not kill or retry the command while it is still running.

  • To skip the gate for a single invocation, pass `--skip-pre-review-gate`.

To disable it process-wide, set `SPEC_KITTY_SKIP_PRE_REVIEW_GATE` — the gate's own opt-out name; it no longer reads the sync-disable vocabulary (#3980). Either opt-out skips the gate before it resolves a workspace or spawns the subprocess.

  • Absent an opt-out, the gate always enforces by default. An orchestrator

observing a sub-agent that appears to hang on a `for_review` transition should first check whether the gate's scoped test subprocess is still running before treating the sub-agent as stuck.

Legacy Alias

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

Read more
Ships withspec-kitty

Spec-Driven Development with organizational governance. Specs tell AI agents what to build; Charter governs how they build it. Git-native missions, enforceable workflows, and consistent engineering standards across AI coding agents and harnesses.

Get the whole plugin
Stats
1,678
Stars
178
Forks
Active
Maintenance
Python
Language
MIT
License
just now
Last commit
0y ago
Created
14h ago
Added

Repo: spec-kitty/spec-kitty

Other skills on spec-kitty.