executing-plans
Use when implementing an approved written plan with dependent tasks in the current session. Do NOT use when the plan is missing, unapproved, or naturally parallel.
- License 许可
- MIT
- 最近更新
- 2026-10-14
- Stars
- ★ 16
- Forks
- 5
01 前言 Front Matter
- name
- executing-plans
- version
- 6.2.0
- category
- workflow
- description
- Use when implementing an approved written plan with dependent tasks in the current session. Do NOT use when the plan is missing, unapproved, or naturally parallel.
02 资源文件 1
- 参考文档CHANGELOG.md311 B
03 SKILL.md 正文
Executing Plans
Execute the plan in the current agent by default.
Process
- Read the plan and applicable project instructions.
- Confirm the workspace and existing user changes are safe.
- Flag only gaps that block or materially change the outcome.
- Track tasks by useful deliverable, not every command.
- For each task, implement the scoped outcome and run its risk-appropriate verification.
- Update the plan or canonical backlog when reality changes.
- Review the complete diff once at the end.
Read ../using-superpowers/references/risk-policy.md.
Do not switch to subagent-driven development merely because subagents exist. Delegate only when the user requests it or tasks are independent enough to benefit from parallel work.
Stop and Ask
Stop when authority is missing, a destructive action is newly required, a critical requirement is ambiguous, or repeated evidence invalidates the plan. Ordinary implementation details are resolved from the codebase.
When implementation is verified, use
superpowers:finishing-a-development-branch only if an integration decision is
actually needed.
04 同仓库更多 Skills
bad
暂无简介
writing-skills
Use when creating, editing, or validating reusable agent skills and their trigger behavior. Do NOT use for ordinary project documentation or one-off prompts.
writing-plans
Use when an approved change spans multiple dependent outcomes and needs a durable implementation sequence before coding. Do NOT use for small, obvious, reversible edits.
verification-before-completion
Use when about to claim work is complete, fixed, passing, or ready to integrate. Do NOT use to repeat checks without a completion claim or concrete doubt.
using-superpowers
Use when starting a conversation or deciding whether a Superpowers workflow matches the current task. Do NOT use it to auto-invoke skills whose stated triggers do not match.
using-git-worktrees
Use when feature work needs isolation from the current workspace or before executing a risky implementation plan. Do NOT use when the current workspace is already safe and isolated.