メニュー
Close a session cleanly by resolving session-owned loose ends and reporting the final state. Use when the session is ending or the user asks to wrap up or audit its end.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use this skill whenever code-review feedback already exists and may affect a code decision or change. This includes PR comments, findings returned by invoke or any external model or review tool, and delegated-review results—even when the user simply says to fix, address, apply, or resolve them. Do not use to perform a new review, diagnose an unrelated bug, implement a new requirement, or merely summarize or explain feedback without deciding about code.
Interview the user to resolve material branches of a decision tree and converge on a shared plan before acting. Use when multiple reasonable choices would materially change scope, cost, reversibility, or outcome, or when the user asks to brainstorm, shape, or grill an idea. Do not use when facts can resolve the ambiguity or a reversible assumption would not materially affect the result.
Draft or review minimal, testable goals. Use only when the user explicitly asks to write, revise, or review a goal.
Create or improve agent skills from concrete behavior and evidence. Use when building or revising SKILL.md, or testing whether a skill earns its context. Do not use for ordinary documentation or one-off prompts.
Diagnose and fix bugs, failures, and performance regressions. Read this skill BEFORE touching any code whenever the user reports a bug, broken behavior, a crash, wrong output, or a regression — even when the cause looks obvious and the user only asked for a fix. Do not use for a simple explanation of a known error when no diagnosis is requested.
Research with parallel agents, independent evidence angles, and cross-validation. Use when the user explicitly asks for parallel or delegated research, or when a high-cost question materially benefits from independent evidence.
| name | wrap-up |
| description | Close a session cleanly by resolving session-owned loose ends and reporting the final state. Use when the session is ending or the user asks to wrap up or audit its end. |
Finish the current workstream without opening another. Resolve session-owned loose ends before summarizing.
Use the conversation and known artifacts to identify promised outcomes, repositories touched in this session, changed files, worktrees, verification, commits or PRs, background processes or servers, browser sessions, and temporary artifacts. Inspect only what is needed to establish their final state. Do not sweep unrelated repositories, project history, documentation, or memory.
git status in every touched repository. Separate work this session does not own from session-owned changes. Finish, verify, and commit session-owned changes when the request and project rules call for it; never stage or alter unrelated work.Run final verification after cleanup: re-run the smallest checks that prove the delivered result, then confirm the touched repositories contain no unexplained session-owned residue. If something cannot be resolved safely, state exactly what remains and why.
State what was completed, the important decisions, and the strongest verification evidence.
Include only actions taken or unresolved state that matters: commits, stopped processes, removed artifacts or worktrees, documentation fixes, and remaining dirty files with their ownership. Omit this section when there is nothing to report.
Include only concrete unfinished actions, blockers, or decisions. Omit this section when nothing remains.
Suggest exactly one short, natural, searchable title for the dominant workstream. Follow active project naming rules and prefer a PR or issue anchor when one exists.
Keep the whole wrap-up proportional to the session. Use handoff instead when the user needs a portable continuation document.