一键导入
sh-execute
Execute an implementation plan with review checkpoints and verification gates
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Execute an implementation plan with review checkpoints and verification gates
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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
| 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