메뉴
Use when a written plan exists and you are about to build it in the current session, to work it task by task with a checkpoint after each. Keeps execution honest against the plan instead of drifting into a freehand build.
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
Use when several pieces of work are genuinely independent and can run at once, to fan them out across parallel agents instead of doing them in sequence. Cuts wall-clock time and keeps each strand in its own clean context.
Use when work needs its own isolated checkout — parallel strands that would fight over files, or a risky change you want quarantined from the main tree. Gives each strand a real working directory on its own branch without re-cloning.
Use whenever the user says "use slipstream", "use superpowers", or starts any task in a project that has slipstream. A hard, always-on discipline that forces scoped reads over whole-file reads to save tokens, recalls memory before acting, and records what is durable every turn so memory grows constantly.
Use when a site needs to look designed rather than defaulted, before building sections: establish a cohesive design system of type scale, spacing, colour, radius and shadow tokens so every component shares one premium visual language.
Use when building the top of a landing page, to produce a high-impact hero with confident display type, a clear single call to action and balanced composition, the kind of opening a polished marketing site leads with.
Use when filling out a landing page below the hero, to build the polished marketing sections a premium site is made of: a feature grid, a logo or social-proof strip, a testimonial and a closing call to action.
| name | executing-plans |
| description | Use when a written plan exists and you are about to build it in the current session, to work it task by task with a checkpoint after each. Keeps execution honest against the plan instead of drifting into a freehand build. |
| slipstream | {"category":"context","requires":[],"tags":["planning","execution","verification"]} |
A plan is only worth writing if it is followed. The failure mode is opening the plan, reading the goal, and then building from memory — the plan becomes decoration and the checkpoints never happen. This skill is the discipline of executing a plan as written: one task at a time, verify before moving on, and surface any divergence rather than quietly absorbing it.
It is the counterpart to [[write-plan]]: that skill produces the plan; this one spends it. For independent tasks you may hand each to a fresh agent ([[subagent-driven-development]]); this skill is the in-session path where you build the tasks yourself.
Every task was built and verified in plan order, each task boundary is a commit, any divergence was written back into the plan before continuing, and the full acceptance criteria pass at the end.
