ワンクリックで
sh-execute
Execute an implementation plan with review checkpoints and verification gates
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。
メニュー
Execute an implementation plan with review checkpoints and verification gates
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。
Multi-expert AI/ML specification review with scoring gate — model architecture, evaluation rigor, safety/alignment, and production readiness for AI systems and LLM apps
Multi-expert architecture review — boundaries, integration patterns, failure modes, evolvability
Multi-expert business analysis with advisory recommendations (no scoring gate)
Multi-expert intelligence pipeline review — discovery quality, ingestion resilience, scoring validity, platform compliance, taxonomy coherence, cost efficiency
Multi-expert mobile/native app specification review with scoring gate — Android, iOS, Swift, SwiftUI
Multi-expert personal-development review with scoring gate — learnability, adoption, human-centeredness, and capability impact for talent/learning/AI-augmentation designs
SOC 職業分類に基づく
| name | sh-execute |
| description | Execute an implementation plan with review checkpoints and verification gates |
Load plan, review critically, execute all tasks, report when complete.
Announce at start: "I'm using the sh:execute skill to implement this plan."
For each task:
After all tasks complete and verified:
superpowers:finishing-a-development-branchSTOP executing immediately when:
Ask for clarification rather than guessing.
Return to Review (Step 1) when:
Don't force through blockers - stop and ask.
Required workflow skills:
/sh:worktree - RECOMMENDED: Set up isolated workspace before starting/sh:plan - Creates the plan this skill executessuperpowers:finishing-a-development-branch - Complete development after all tasks/sh:verify - Evidence-based verification before claiming completion