Sandi Metz Rules logo

Sandi Metz Rules

CommunityPopular
Dicklesworthstone
sandi-metz-rules

This skill should be used when users request code review, refactoring, or code quality improvements for Ruby codebases. Apply Sandi Metz's four rules for writing maintainable object-oriented code - classes under 100 lines, methods under 5 lines, no more than 4 parameters, and controllers instantiate only one object. Use when users mention "Sandi Metz", "code quality", "refactoring", or when reviewing Ruby code for maintainability.

Overview

PublisherDicklesworthstone
Repositorypi_agent_rust
Skill namesandi-metz-rules
Stars
1.7K
Forks
206
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Dicklesworthstone on GitHub. Read the source before you install it.

Installation

Install the Sandi Metz Rules AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Dicklesworthstone/pi_agent_rust.git /tmp/pi_agent_rust
mkdir -p .claude/skills
cp -r /tmp/pi_agent_rust/tests/ext_conformance/artifacts/agents-mikeastock/skills/sandi-metz-rules .claude/skills/sandi-metz-rules
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sandi Metz Rules in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Sandi Metz Rules on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Sandi Metz Rules is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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:

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

Method lines:

ruby
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:

ruby
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:

yaml
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

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Sandi Metz Rules AI skill do?

This skill should be used when users request code review, refactoring, or code quality improvements for Ruby codebases. Apply Sandi Metz's four rules for writing maintainable object-oriented code - classes under 100 lines, methods under 5 lines, no more than 4 parameters, and controllers instantiate only one object. Use when users mention "Sandi Metz", "code quality", "refactoring", or when reviewing Ruby code for maintainability.

Why use Sandi Metz Rules on TypingMind?

Because you install it once and use it with any model. Sandi Metz Rules is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Sandi Metz Rules in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Dicklesworthstone/pi_agent_rust/tree/main/tests/ext_conformance/artifacts/agents-mikeastock/skills/sandi-metz-rules. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Sandi Metz Rules?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Sandi Metz Rules?

As many as you like. As long as a model supports skills, you can use Sandi Metz Rules with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Sandi Metz Rules AI skill free?

It is published on GitHub by Dicklesworthstone. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇