Token导航 LogoToken导航

Agent Skill · 研究检索

sandi-metz-rules(桑迪梅斯规则)

sandi-metz-rules 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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。

sandi-metz-rules 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证为 MIT,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 60,976。

总安装 360周安装 15GitHub Stars 94下载 120核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

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:sandi-metz-rules(桑迪梅斯规则)
来源仓库:https://github.com/nateberkopec/dotfiles
仓库路径:skills/sandi-metz-rules
安装命令:
npx skills add https://github.com/nateberkopec/dotfiles --skill sandi-metz-rules
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/nateberkopec/dotfiles --skill sandi-metz-rules

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

sandi-metz-rules 用于查找、检索和筛选相关信息。适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词、任务场景或来源线索快速定位候选结果。通过 npx skills add 命令从指定 GitHub 仓库安装,需结合原始 README 确认具体用法。

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。当前分类为研究检索,暂无更多功能说明。

来源仓库内路径:skills/sandi-metz-rules

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/nateberkopec/dotfiles --skill sandi-metz-rules;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

sandi-metz-rules 怎么安装?

在终端执行 npx skills add https://github.com/nateberkopec/dotfiles --skill sandi-metz-rules。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

sandi-metz-rules 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

sandi-metz-rules 需要什么权限?

权限级别是只读。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。

sandi-metz-rules 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

sandi-metz-rules 用的人多吗?

公开数据是累计安装 360 次,近一周安装 15 次,下载 120 次,GitHub 94 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

sandi-metz-rules 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
sandi-metz-rules

桑迪梅斯规则 · 本页

36094只读MIT通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Sandi Metz Rules

Overview

This skill helps apply Sandi Metz's four rules for writing maintainable object-oriented code to Ruby codebases. These rules are heuristics that encourage good design practices, making code easier to understand, test, and maintain.

The Four Rules

  1. Classes can be no longer than 100 lines of code
  2. Methods can be no longer than 5 lines of code
  3. Pass no more than 4 parameters into a method
  4. Controllers can instantiate only one object

When to Use This Skill

Apply this skill when:

  • Users explicitly request applying Sandi Metz's rules
  • Reviewing Ruby code for maintainability and code quality
  • Refactoring existing Ruby code to improve design
  • Users ask about "code smells" or improving object-oriented design
  • Analyzing Ruby code for complexity or maintainability issues
  • Users mention terms like "POODR" or reference Sandi Metz's work

Code Review Workflow

1. Analyze the Code

When reviewing code against Sandi Metz's rules:

Read the reference document: First, load the detailed rules documentation:

Read references/rules.md

Measure accurately:

  • For classes: Count lines of actual code (exclude blank lines, comments, class definition, and end statements)
  • For methods: Count lines of actual code (exclude blank lines, comments, method definition, and end statements)
  • For parameters: Count all explicit parameters including keyword arguments (but not &block)
  • For controllers: Count object instantiations in each action (excluding finding existing objects)

Identify violations: Scan the codebase for violations of each rule. Use grep or file searching to find classes and methods, then analyze them systematically.

2. Prioritize Issues

Not all violations are equal:

High priority:

  • Classes over 200 lines (severe violations)
  • Methods over 10 lines (severe violations)
  • Methods with 6+ parameters
  • Controllers with complex business logic

Medium priority:

  • Classes between 100-200 lines
  • Methods between 5-10 lines
  • Methods with 5 parameters

Low priority:

  • Borderline cases (e.g., 6-line methods)
  • Violations in test files, configuration, or DSLs

3. Suggest Specific Refactorings

For each violation, provide concrete refactoring strategies:

Long classes:

  • Extract related methods into new classes
  • Identify separate responsibilities using Single Responsibility Principle
  • Use composition or modules to share behavior
  • Apply patterns: Strategy, Decorator, Command, Facade

Long methods:

  • Extract sub-methods with descriptive names
  • Replace conditionals with polymorphism
  • Use guard clauses to reduce nesting
  • Apply Composed Method pattern (keep methods at one level of abstraction)
  • Extract complex expressions into well-named methods

Too many parameters:

  • Introduce Parameter Object for related parameters
  • Use Builder pattern for complex construction
  • Replace parameters with method calls (use instance variables)
  • Consider if the method belongs in a different class

Fat controllers:

  • Extract service objects or use cases
  • Apply Command or Interactor patterns
  • Create Facade objects for complex orchestration
  • Move business logic to domain layer

4. Provide Code Examples

When suggesting refactorings:

  • Show before and after code examples
  • Explain why the refactored version is better
  • Name any patterns used
  • Highlight how the change improves testability and clarity

5. Consider Context

Remember that rules can be broken with good reason:

  • Configuration files (e.g., routes.rb)
  • Test files (though they should still be readable)
  • DSL definitions
  • Generated code or database migrations
  • When following the rule would make code less clear

Always note when a violation might be acceptable and explain why.

Usage Patterns

Pattern 1: Full Codebase Review

When reviewing an entire codebase:

  1. Search for Ruby files using glob patterns
  2. Identify the largest classes and methods first
  3. Check controllers for business logic
  4. Prioritize violations by severity
  5. Provide a summary of findings with specific file locations and line numbers
  6. Suggest refactorings for the most critical issues

Pattern 2: Specific File or Class Review

When reviewing a specific file:

  1. Load the file
  2. Measure each class and method
  3. Identify all rule violations
  4. Provide specific refactoring suggestions with code examples
  5. Explain the benefits of each suggested change

Pattern 3: Refactoring Assistance

When actively refactoring code:

  1. Load references/rules.md for detailed guidance
  2. Apply the specific refactoring patterns from the reference
  3. Ensure refactored code follows all four rules
  4. Verify that tests still pass
  5. Explain the design improvements made

Code Counting Rules

Use these precise counting rules to ensure consistency:

Class lines:

class MyClass  # Don't count
  def method   # Count: 1
    body       # Count: 2
  end          # Don't count
end            # Don't count

Method lines:

def my_method        # Don't count
  line_1             # Count: 1
  line_2             # Count: 2
                     # Don't count (blank line)
  # comment          # Don't count
  line_3             # Count: 3
end                  # Don't count

Parameters:

def method(a, b, c, d)              # 4 parameters - OK
def method(a, b, c, d, e)           # 5 parameters - Violation
def method(a:, b:, c:, d:)          # 4 parameters - OK
def method(a, b = nil, c = {})      # 3 parameters - OK (defaults still count)
def method(a, *rest)                # 2 parameters - OK
def method(a, &block)               # 1 parameter (blocks don't count)

Automation

Suggest using static analysis tools to enforce these rules:

  • RuboCop: Configure Metrics/MethodLength, Metrics/ClassLength, Metrics/ParameterLists
  • Reek: Detects code smells including LongMethod, LargeClass, LongParameterList
  • flog: Measures method complexity
  • flay: Detects code duplication

Example RuboCop configuration:

Metrics/ClassLength:
  Max: 100

Metrics/MethodLength:
  Max: 5

Metrics/ParameterLists:
  Max: 4
  MaxOptionalParameters: 3

Resources

This skill includes a comprehensive reference document with:

  • Detailed explanation of each rule
  • Rationale and benefits
  • Common violations and their causes
  • Specific refactoring strategies with examples
  • Guidance on when to break the rules
  • Related design principles and patterns

Load this reference when doing detailed code analysis or explaining refactoring approaches:

Read references/rules.md

平台分布

Claude Code

27.7%
按下载量换算33

OpenCode

23.4%
按下载量换算28

windsurf

20.45%
按下载量换算25

Codex

14.66%
按下载量换算18

Antigravity

8.19%
按下载量换算10

Gemini CLI

4.03%
按下载量换算5

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。

继续浏览同类 Skills