菜单
Use when you have a written implementation plan to execute in a separate session with review checkpoints
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
Use when you have a spec or requirements for a multi-step task, before touching code
Use when auditing a Rust codebase, module, or workspace and wanting cross-model consensus on findings, a false-positive-filtered consolidated report, and a reproducible audit trail in git
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
Use after writing or modifying code to simplify and refine it for clarity, consistency, and maintainability without changing functionality. Triggers after any implementation work in the current session.
Dynamic performance measurement for Rust projects — profiling, load testing, benchmarking, and analysis of existing observability data (traces, metrics, logs). Use when you need measured impact, not inference. Requires either a runnable binary + load generator, or existing production telemetry. For static code-level analysis without measurement, use rust-perf.
Static performance audit for Rust projects — analyzes code for allocation, async, database, data-structure, and compile-time anti-patterns without requiring a running system. Use when reviewing code for performance issues before or instead of load testing. For runtime profiling and load-test analysis, use rust-perf-measure.
| name | executing-plans |
| description | Use when you have a written implementation plan to execute in a separate session with review checkpoints |
Load plan, review critically, execute all tasks, report when complete.
Announce at start: "I'm using the executing-plans skill to implement this plan."
Note: Tell your human partner that Superpowers works much better with access to subagents. The quality of its work will be significantly higher if run on a platform with subagent support (such as pi with @tintinweb/pi-subagents, Claude Code, or Codex). If subagents are available, use superpowers:subagent-driven-development instead of this skill.
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.
Required workflow skills:
