Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/Morrison-Lab/ai-config --skill done명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SKILL.md 표시 중
| name | done |
| description | → wrap-up. |
| user-invocable | true |
| allowed-tools | ["Bash","Read","Edit","Write"] |
wrap-up)This is a synonym for wrap-up — invoking /done
runs the wrap-up procedure unchanged. The two are interchangeable for dispatch:
any phrasing that fires wrap-up ("wrap up", "finish up", "are we done?") fires
done too, and both run the same procedure. That is why this skill's
description repeats those triggers.
Do this: read wrap-up and follow its instructions exactly. Everything that skill says — verify the real state of every PR/issue/branch/working tree, report a linked final summary that surfaces anything still open, then run a UMS review to persist what was learned — applies unchanged.
Keep the logic only in wrap-up; this file is just the /done entry point so
the names stay in sync.
/doneroutes towrap-up, the session-level wrap-up.mergedis the sibling alias that also lets you anchor the summary on a just-merged PR (/merged #74);post-mergeis the different skill that wraps up a single just-merged PR rather than the whole session.