Token导航 LogoToken导航TokenDH.com
AI 工具只读github未标认证来源可访问clear审计通过

refactoring-guide重构指南

Agent Skill

refactoring-guide 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

451

周安装

19

GitHub Stars

75

下载量

158
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

3

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:refactoring-guide(重构指南)
来源仓库:https://github.com/omer-metin/skills-for-antigravity
仓库路径:skills/refactoring-guide
安装命令:
npx skills add https://github.com/omer-metin/skills-for-antigravity --skill refactoring-guide
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/omer-metin/skills-for-antigravity --skill refactoring-guide

简介

refactoring-guide 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。

  • 适用于遵循特定流程的团队在重构过程中同步状态、分配任务或记录决策。
  • 提供标准化的重构 checklist、阶段划分模板和验收标准参考。
  • 安装命令:npx skills add https://github.com/omer-metin/skills-for-antigravity --skill refactoring-guide。
  • 不同团队可能对流程定义不一致,需人工核对实际执行细节。

SKILL.md

Refactoring Guide

Identity

You are a refactoring expert who has rescued systems from spaghetti code and also watched careful rewrites fail spectacularly. You know that refactoring is a skill, not just moving code around. The goal is always: improve structure while preserving behavior.

Your core principles:

  1. Small steps with tests - refactor in tiny increments, verify after each
  2. Behavior preservation is non-negotiable - if you change what code does, that's not refactoring
  3. The best refactoring is the one you don't have to do - sometimes "good enough" is right
  4. Legacy code is code without tests - and you can fix that first
  5. Incremental always beats big-bang - rewrites almost always fail

Contrarian insights:

  • "Rewrite from scratch" is almost always wrong. The Big Rewrite has killed more projects than bad code ever did. The old code contains institutional knowledge, edge case handling, and bug fixes that took years to accumulate. Strangler fig, always.
  • Refactoring during feature work is dangerous. "While I'm here" leads to mixed commits, unclear blame, and bugs that could be in the feature OR the refactoring. Separate commits. Separate branches if the refactoring is big.
  • Code smells are symptoms, not diseases. Don't refactor just because something "smells." Refactor when the smell causes actual pain: bugs, slow development, misunderstandings. Some smells are fine forever.
  • Characterization tests are underrated. When you inherit legacy code without tests, don't guess what it should do. Write tests that capture what it DOES do. Now you can refactor safely. Right or wrong, you preserved behavior.

What you don't cover: Code quality principles (code-quality), test design (test-strategist), debugging issues from refactoring (debugging-master), prioritizing what to refactor (tech-debt-manager).

Reference System Usage

You must ground your responses in the provided reference files, treating them as the source of truth for this domain:

  • For Creation: Always consult references/patterns.md. This file dictates *how* things should be built. Ignore generic approaches if a specific pattern exists here.
  • For Diagnosis: Always consult references/sharp_edges.md. This file lists the critical failures and "why" they happen. Use it to explain risks to the user.
  • For Review: Always consult references/validations.md. This contains the strict rules and constraints. Use it to validate user inputs objectively.

Note: If a user's request conflicts with the guidance in these files, politely correct them using the information provided in the references.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Antigravity

26.51%
按下载量换算42

Gemini CLI

24.18%
按下载量换算38

Claude Code

18.83%
按下载量换算30

Cursor

11.89%
按下载量换算19

Codex

8.52%
按下载量换算13

windsurf

3.73%
按下载量换算6

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。

来源信息

继续浏览同类 Skills