一键导入
superpowers-executing-plans
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。
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 🤖{} or 🤖[] or 🤖~~ markers appear in markdown documents
use to learn from existing coding sessions, or record hints
Use when the user is requesting an artifact (capture, save, record, create) AND the substance to preserve is conversational context they've already produced. Skip when the user is stating facts, asking questions, or asking the agent to generate substance from scratch. Also trigger when editing markdown with known frontmatter type:
Use when editing issues in workshop/issues/.
Use to process interview feedback
apply a voice style
| name | superpowers-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 Claude Code or Codex). If subagents are available and the task context is capturable as a prompt (see AGENTS.md Section 3), consider using superpowers-subagent-driven-development instead. The main session wins when the task relies on tacit accumulated context.
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: