メニュー
Use when you have a written implementation plan to execute
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。
Run a safe Grok Build code review of a branch or explicitly requested local changes. Use when an external Grok review is requested for correctness, architecture, maintainability, regressions, or missing tests; the workflow invokes Grok's native /review skill, preserves durable artifacts, and never edits or publishes changes.
Run Fable, Grok, and Thermo-Nuclear code reviews concurrently against one validated, immutable Git scope, while preserving separate outputs and reporting partial failures. Use when the user explicitly asks for a parallel, three-reviewer, multi-model, or strongest available code review of a PR, branch, commit range, or comparison with main.
Use zmx for durable, long-running processes that must persist beyond the current agent session, such as an app server the user will test later.
Fetch CI build results and diagnose failures. Auto-detects provider from project files or URLs. Supports GitHub Actions, Buildkite, and CircleCI.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when you have a spec or requirements for a multi-step task, before touching code
SOC 職業分類に基づく
| name | executing-plans |
| description | Use when you have a written implementation plan to execute |
| metadata | {"category":"superpowers"} |
Load plan, review critically, execute all tasks, report when complete.
Announce at start: "I'm using the executing-plans skill to implement this plan."
For each task:
After all tasks complete and verified:
STOP executing immediately when:
Ask for clarification rather than guessing.
Return to Review (Step 1) when:
Don't force through blockers - stop and ask.
