By uucz
Invoke multilingual skills and commands to prevent AI coding agents from over-engineering. Automatically detect and block unrequested changes, new abstractions, docs, deps, rewrites, or excessive diffs, enforcing minimal scoped edits to only specified code/files with simplest solutions first.
Automatically activates when over-engineering patterns are detected: (1) Modifying code or files the user did not explicitly ask to change (2) Creating new abstraction layers (class, interface, factory, wrapper) without being asked (3) Adding comments, documentation, JSDoc, or type annotations without being asked (4) Introducing new dependencies without being asked (5) Rewriting entire files instead of making minimal edits (6) Diff scope significantly exceeding the user's request (7) User signals like "too much", "don't change that", "only change X", "keep it simple", "stop" (8) Adding error handling, validation, or defensive code for scenarios that cannot occur (9) Generating tests, configuration scaffolding, or documentation without being asked
S'active automatiquement lorsque des patterns de sur-ingénierie sont détectés : (1) Modifier du code ou des fichiers que l'utilisateur n'a pas explicitement demandé de changer (2) Créer de nouvelles couches d'abstraction (class, interface, factory, wrapper) sans demande (3) Ajouter des commentaires, de la documentation, JSDoc ou des annotations de type sans demande (4) Introduire de nouvelles dépendances sans demande (5) Réécrire des fichiers entiers au lieu de faire des modifications minimales (6) Le diff dépasse significativement la portée de la demande de l'utilisateur (7) L'utilisateur signale "trop", "ne change pas ça", "change seulement X", "garde ça simple", "arrête" (8) Ajouter de la gestion d'erreurs, de la validation ou du code défensif pour des scénarios impossibles (9) Générer des tests, du scaffolding de configuration ou de la documentation sans demande
過剰エンジニアリングのパターンが検出された場合に自動的に発動します: (1) ユーザーが明示的に変更を求めていないコードやファイルを修正する (2) 要求されていない新しい抽象レイヤー(class、interface、factory、wrapper)を作成する (3) 要求されていないコメント、ドキュメント、JSDoc、型注釈を追加する (4) 要求されていない新しい依存パッケージを導入する (5) 最小限の編集ではなくファイル全体を書き直す (6) diff の範囲がユーザーの要求を明らかに超えている (7) ユーザーが「やりすぎ」「そこは変えないで」「Xだけ変えて」「シンプルに」「やめて」と言う (8) 起こり得ないシナリオに対するエラーハンドリング、バリデーション、防御的コードを追加する (9) 要求されていないテスト、設定のスキャフォールディング、ドキュメントを生成する
과잉 엔지니어링 패턴이 감지되면 자동으로 활성화됩니다: (1) 사용자가 명시적으로 변경을 요청하지 않은 코드나 파일을 수정하는 경우 (2) 요청되지 않은 새로운 추상화 레이어(class, interface, factory, wrapper)를 생성하는 경우 (3) 요청되지 않은 주석, 문서, JSDoc, 타입 어노테이션을 추가하는 경우 (4) 요청되지 않은 새로운 의존성을 도입하는 경우 (5) 최소한의 편집 대신 파일 전체를 다시 작성하는 경우 (6) diff 범위가 사용자의 요청을 명백히 초과하는 경우 (7) 사용자가 "너무 많아", "거기는 건드리지 마", "X만 변경해", "간단하게", "그만" 등의 신호를 보내는 경우 (8) 발생할 수 없는 시나리오에 대한 에러 처리, 유효성 검사, 방어적 코드를 추가하는 경우 (9) 요청되지 않은 테스트, 설정 스캐폴딩, 문서를 생성하는 경우
Lightweight anti-over-engineering guard. Activates when: (1) Modifying code or files the user did not explicitly ask to change (2) Creating new abstraction layers without being asked (3) Rewriting entire files instead of making minimal edits (4) Diff scope significantly exceeding the user's request (5) User signals like "too much", "only change X", "keep it simple" 轻量级反过度工程守卫。当检测到以下模式时激活: (1) 修改用户未明确要求改动的代码或文件 (2) 创建用户未要求的新抽象层 (3) 重写整个文件而非做最小编辑 (4) diff 范围明显超出用户请求 (5) 用户说"太多了"、"只改 X"、"简单点"
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
English | 中文 | 日本語 | 한국어 | Français
你的 AI 有「讨好型人格」——你让它修个 bug,它给你重构了整个文件。
1460 次控制实验证实:AI 编码助手存在系统性的过度工程倾向。它不是在认真工作,是在讨好你。三行规则就能治好它。
npx moyu-dev
Cursor / VS Code / Windsurf / Cline / Codex / Kiro — 自动检测并安装。Claude Code 用户:
claude skill install --url https://github.com/uucz/moyu --skill moyu
你的 AI 编程助手是不是经常这样:
每一条都不是 AI 的问题——是你的问题。 你得 review 这些代码,理解这些抽象,维护这些依赖。AI 加了 30 分钟的戏,你多加了 2 小时的班。
任务:添加一个
bulk_complete批量完成函数
❌ 普通 AI 的输出(43 行)
def bulk_complete(task_ids):
"""Mark multiple tasks as done in a single operation.
Args:
task_ids: A list of task ID integers to mark as completed.
Returns:
A dict with two keys:
- "completed": list of IDs that were successfully marked done.
- "not_found": list of IDs that did not match any existing task.
Raises:
TypeError: If *task_ids* is not a list.
ValueError: If any element in the list is not an integer.
"""
if not isinstance(task_ids, list):
raise TypeError("task_ids must be a list")
for tid in task_ids:
if not isinstance(tid, int):
raise ValueError(f"Each task ID must be an integer, got {type(tid).__name__}")
tasks = load_tasks()
lookup = {t["id"]: t for t in tasks}
now = str(datetime.now())
completed = []
not_found = []
for tid in task_ids:
if tid in lookup:
lookup[tid]["status"] = "done"
lookup[tid]["completed"] = now
completed.append(tid)
else:
not_found.append(tid)
if completed:
save_tasks(tasks)
return {"completed": completed, "not_found": not_found}
14 行文档注释、类型检查、lookup 字典优化、not_found 追踪、条件保存、结构化返回值——没人要求这些。
✅ 摸鱼 AI 的输出(8 行)
def bulk_complete(ids):
tasks = load_tasks()
for t in tasks:
if t["id"] in ids:
t["status"] = "done"
t["completed"] = str(datetime.now())
save_tasks(tasks)
功能完整,没有多余的东西。减少 81% 代码。
最好的代码是你没写的代码。 最好的 PR 是最小的 PR。 真正的 Staff Engineer 知道什么不该做。
摸鱼不是让 AI 偷懒——是让 AI 不做废活,这样你才能真正摸鱼。
两者叠加 = AI 高效 996,你准时下班。
摸鱼不仅仅是修复 AI 的行为——它是一套工程纪律。即使未来 AI 不再过度工程,"只改被要求改的、用最简方案、不确定就问"依然是好的工程实践。摸鱼的价值不依赖于 AI 的缺陷,而是锚定在工程文化上。
| # | 铁律 | 含义 |
|---|---|---|
| 1 | 只改被要求改的代码 | 修改范围严格限定在用户指定的代码和文件内 |
| 2 | 最简方案优先 | 一行能解决的写一行,能复用就复用 |
| 3 | 不确定就问 | 用户没说要的,就是不需要的 |
npx claudepluginhub uucz/moyuMeta-cognition: refine input through brainstorming, refine output through challenge and condensed communication mode.
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Programming as Theory Building guidelines for coding agents, grounded in Peter Naur's paper and focused on preserving program theory during code work.
Engineering discipline skills: optimization rules, systematic debugging, AI slop cleanup, and implementation guardrails
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls
Removes AI-generated code slop from code changes in the current branch