菜单
Use when the user asks to refactor, clean up, simplify, modularize, deduplicate, rename, or improve the structure of existing code WITHOUT changing behavior. If the user wants new behavior, do not use this skill. Enforces small reversible steps and behavior preservation.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when the user asks to fix a bug, investigate an error, debug a crash, explain a stack trace, or make a failing test pass. Enforces reproduce → isolate → smallest fix → verify, instead of guessing a cause and patching code.
Use when the user asks to review a pull request, review a diff, review changes on a branch, or audit code written by a teammate or AI agent. Reviews the diff (not the summary) for unrelated changes, missing verification, behavior risks, and over-engineering.
Use when the user asks to add a new feature, add a new API/endpoint/page/component, implement a new capability, or extend existing functionality with new behavior. Forces a plan-before-code loop, scoping non-goals, and verifying the new behavior end-to-end.
Use when the user asks to understand, explain, trace, audit, or explore code WITHOUT modifying it. Examples — "how does X work", "where is Y called", "why does this branch exist", "trace the request flow". Stays read-only and does not produce a fix.
Use when a request is large, ambiguous, or spans multiple files/components and the user has NOT yet approved an implementation approach. Produces a verifiable plan via Plan Mode and a TodoWrite breakdown, then hands off to a more specific skill (bug-fix, refactor, feature-add) for execution.
Use before releasing, deploying, publishing, cutting a tag, or merging into a production-bound branch. Classifies risk level and audits verification evidence, rollback plan, and operational readiness — not just whether the code compiles.
| name | acp-refactor |
| description | Use when the user asks to refactor, clean up, simplify, modularize, deduplicate, rename, or improve the structure of existing code WITHOUT changing behavior. If the user wants new behavior, do not use this skill. Enforces small reversible steps and behavior preservation. |
| version | 1.0.0 |
Use this skill when the user asks for refactoring, cleanup, simplification, modularization, or architecture improvement.
The goal of refactoring is to improve structure while preserving behavior.
If behavior changes, it is not just refactoring anymore.
Before editing, state the exact goal:
Do not refactor just because code looks old or ugly.
Public behavior must remain unchanged unless the user explicitly asks for a behavior change.
Before editing, identify:
Prefer small, reversible changes. For multi-step refactors, create a TodoWrite list so each step (rename, extract, move, dedupe) is tracked and can be verified independently.
Good steps:
Bad steps:
After each meaningful step, run relevant checks when possible:
If checks are unavailable, explain the risk.
Refactor goal:
- ...
Behavior preserved:
- ...
Changed:
- ...
Verified:
- ...
Risk:
- ...
Stop and ask for confirmation if: