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.

1.17x

Quality

78%

Does it follow best practices?

Impact

100%

1.17x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-mikeastock/skills/sandi-metz-rules/SKILL.md

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable skill body with concrete counting rules, code examples, and a clear workflow backed by a genuine reference file. The main weakness is verbosity from enumerating design patterns Claude already knows and re-summarizing the reference document.

Suggestions

Trim the 'Suggest Specific Refactorings' pattern lists (Strategy, Decorator, Command, Facade, etc.) to a brief pointer into references/rules.md, since Claude already knows these patterns.

Remove or collapse the 'Resources' section that re-describes what references/rules.md contains; the inline Read commands already signal it.

Add an explicit validation/checkpoint step in the main Code Review Workflow (e.g., re-measure refactored code against the four rules) to mirror the test-verification step currently only in Pattern 3.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with valuable concrete counting rules, but the generic refactoring-pattern enumerations (Strategy, Decorator, Command, Facade) and the Resources section that re-describes the reference document are unnecessary padding Claude already knows.	3 / 5
Actionability	Provides executable Ruby counting examples, a ready-to-use RuboCop YAML config, and concrete measurement instructions, with only minor gaps in coverage of edge cases.	4 / 5
Workflow Clarity	A clear five-step Code Review Workflow is sequenced with prioritization and a context-check step; validation is light ("verify tests still pass" appears only in Pattern 3) but the task is non-destructive so no cap applies.	4 / 5
Progressive Disclosure	The body is an overview that points repeatedly to the real one-level-deep reference references/rules.md via explicit Read commands, though some detail (refactoring pattern lists) that could live in the reference is inlined.	4 / 5
	Total	15 / 20 Passed

Description

88%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states both capability and trigger conditions with concrete rule thresholds. Minor gaps in trigger-term synonyms and some broad triggers keep it just below the top anchor on two dimensions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (code review, refactoring, code quality improvements) and enumerates all four rules with specific numeric thresholds (classes under 100 lines, methods under 5 lines, no more than 4 parameters).	5 / 5
Completeness	Explicitly states what the skill does (apply the four rules with specifics) and provides a concrete "Use when users mention..." clause answering when to invoke it.	5 / 5
Trigger Term Quality	Includes natural user-facing terms ("Sandi Metz", "code quality", "refactoring", "Ruby code", "maintainability") but omits common variations like ".rb" and "POODR" that appear only in the body.	4 / 5
Distinctiveness Conflict Risk	The Ruby + Sandi Metz framing carves a clear niche, but broad triggers like "code quality" and "refactoring" risk overlap with general refactoring skills.	4 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Dicklesworthstone/pi_agent_rust
Path: tests/ext_conformance/artifacts/agents-mikeastock/skills/sandi-metz-rules/SKILL.md
Commit: 6453c0b

Reviewed: about 9 hours ago

Table of Contents

Discovery Implementation Validation

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.