executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| 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: Subagent-driven development (cf-powers:subagent-driven-development) produces significantly higher quality results. If subagents are available, prefer that skill over this one.
git branch --show-currentmain or master: STOP — ask user to create/switch to a feature branch firstFor multi-phase plans (index exists):
For single-phase plans:
Context loading principle: Only load what you need for the current phase. If you need context from a previous phase's plan, read it on-demand, not upfront.
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:
Note: User manages their own branches. Step 0 verifies a feature branch exists — do NOT create worktrees automatically.
Use when executing implementation plans with independent tasks in the current session
Use when you have a spec for a non-trivial task with non-obvious sequencing, multiple coordinated files, or unclear ordering of steps. SKIP when the task is mechanical (add one file, edit a config, one-liner) or when the implementation order is obvious from the request.
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Use for non-trivial implementations involving design choices, multiple components, or unclear requirements. Explores ideas through dialogue, then produces a technical analysis with architecture, phases, risks, and cross-check reviews. SKIP for mechanical/single-file changes (Dockerfile, CI YAML, config tweak, one-liner) or when the user has already specified exactly what to build.
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions