CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

Install with Tessl CLI

npx tessl i github:Dicklesworthstone/pi_agent_rust --skill sandi-metz-rules
What are skills?

89

Does it follow best practices?

Validation for skill structure

SKILL.md
Review
Evals

Evaluation results

100%

14%

Ruby Code Quality Audit

Precise code measurement rules

Criteria
Without context
With context

Method line counting

100%

100%

Blank lines excluded from methods

100%

100%

Block param excluded

100%

100%

Keyword args counted as params

100%

100%

Default params counted

50%

100%

Class line counting

100%

100%

Violation prioritization

100%

100%

Routes DSL acceptable

100%

100%

Specific line numbers

100%

100%

Method extraction suggestion

100%

100%

Parameter object suggestion

0%

100%

Without context: $0.8927 · 4m 28s · 20 turns · 27 in / 19,061 out tokens

With context: $0.8053 · 3m 1s · 24 turns · 2,651 in / 13,314 out tokens

100%

11%

Ruby Codebase Health Review

Full codebase review with refactoring examples

Criteria
Without context
With context

File locations and line numbers

100%

100%

Largest violations identified first

100%

100%

Parameter violation flagged

100%

100%

Method length violation flagged

25%

100%

Prioritized severity list

100%

100%

Named pattern for long method

70%

100%

Named pattern for too many params

100%

100%

Before/after for parameter violation

100%

100%

Before/after for method length

80%

100%

Refactoring benefit explained

100%

100%

Summary statistics

100%

100%

Without context: $0.3402 · 1m 51s · 13 turns · 18 in / 6,639 out tokens

With context: $0.8515 · 3m 22s · 23 turns · 2,651 in / 14,149 out tokens

100%

20%

Rails Controller Cleanup and Enforcement Setup

Fat controller refactoring and automation

Criteria
Without context
With context

Single object instantiation

100%

100%

Finder calls not counted

0%

100%

Named extraction pattern

100%

100%

Before/after controller comparison

100%

100%

RuboCop ClassLength limit

100%

100%

RuboCop MethodLength limit

0%

100%

RuboCop ParameterLists limit

100%

100%

Additional tools mentioned

100%

100%

Violation counts identified

100%

100%

Service object handles full flow

100%

100%

Without context: $0.3118 · 1m 32s · 16 turns · 23 in / 5,179 out tokens

With context: $0.6204 · 1m 59s · 27 turns · 2,907 in / 7,553 out tokens

Evaluated
Agent
Claude Code

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.