メニュー
Use when you have authored a plan and want the other AI agent (Claude or Copilot) to review it - copies the active plan to planning/needs-review/ for adversarial review
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Advanced Context Engineering with Frequent Intentional Compaction (ACE-FCA) for complex coding tasks. Use this skill when working on brownfield codebases, large repos (100k+ LOC), complex bugs, multi-file refactors, or features requiring deep codebase understanding. Triggers include requests to fix bugs in unfamiliar code, implement features in large codebases, understand complex code flows, or when the user mentions "research plan implement", "ACE-FCA", or "frequent compaction". This workflow prevents context window exhaustion and produces high-quality, reviewable artifacts.
Use when peeking, draining, snapshotting metrics on, enumerating, or otherwise inspecting/manipulating Azure Service Bus subscriptions, queues, or dead-letter sub-queues — including diagnosing DLQ accumulation, capturing parked messages for forensics before discard, draining stuck alert backlogs, comparing active/dlq counts across multiple subs, enumerating an entire namespace's topology, or clearing a subscription's ForwardTo (which the az CLI cannot do).
Use on a loop interval to check for code slices awaiting review in planning/code-reviews/needs-review/, move to in-progress, dispatch code-reviewer subagent, append findings, and move to reviewed/ - silent when no files found
Use when reviewed code-review slices are ready for triage and the developer wants to walk findings, classify them accept/merge/reject/flag, and apply accepted changes to code — third punch-in command of the code review workflow, after code-review-plan-execute completes
Use when ready to plan a code review of a development branch — walks the branch, discovers existing plan documents, maps commits to plans, Q&As unmapped commits with the user, and writes a meta-plan with a slice table at planning/YYYY-MM-DD-code-review-plan-<slug>.md
Use when a code-review meta-plan is ready and you want to drive the full review pipeline — pre-flight, seed slices, dispatch reviewers per slice, synthesize findings, and notify on completion; defensive and idempotent so repeated runs resume from where the last run stopped
| name | plan-send-review |
| description | Use when you have authored a plan and want the other AI agent (Claude or Copilot) to review it - copies the active plan to planning/needs-review/ for adversarial review |
| metadata | {"category":"review-helpers","order":10} |
Copy the active session's plan file to the project's review queue so the other AI agent can review it.
Find the active plan in one of these locations:
| Agent | Location | Notes |
|---|---|---|
| Claude Code | ~/.claude/plans/<name>.md | Active plan from current session |
| Copilot CLI | ~/.copilot/session-state/<session-id>/plan.md | Session plan file |
| Project | planning/**/*.md (excluding needs-review/) | Any plan in the project tree |
# Claude plans
ls -t ~/.claude/plans/*.md 2>/dev/null | head -5
# Copilot session plans (most recent)
ls -t ~/.copilot/session-state/*/plan.md 2>/dev/null | head -5
# Project plans (excluding the review pipeline)
find planning/ -name "*.md" -not -path "*/needs-review/*" 2>/dev/null
If multiple candidates exist, ask the user which plan to send.
# ...) from the planYYYY-MM-DD-<slug>.mdplanning/needs-review/, append -2, -3, etc.Example: 2026-03-14-streaming-response-architecture.md
cp <source-plan> planning/needs-review/YYYY-MM-DD-slug.md
Copy, not move. The original plan stays in place. The author continues working with their copy.
Report to the user: