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.

92

1.17x
Quality

Does it follow best practices?

Impact

100%

1.17x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The body is highly actionable with executable counting examples and RuboCop config and a clear sequenced workflow, but it is let down by verbosity and by duplicating content that also lives in references/rules.md instead of acting as a lean overview.

Suggestions

Trim the restated four rules and the design-concept explanations (SRP, pattern names) from the body, since they are covered in references/rules.md; keep the body a lean overview that points to the reference for rationale.

Remove or collapse the closing 'Resources' section, which restates the reference's contents — a single 'Read references/rules.md for detailed guidance' call already covers it.

Move the refactoring-strategy bullet lists (which duplicate rules.md) into the reference, leaving the body to focus on its unique content: counting rules, priority thresholds, RuboCop config, and the workflow.

DimensionReasoningScore

Conciseness

Mostly actionable but padded: it restates the four rules already in the description, explains design concepts Claude knows ('Single Responsibility Principle', 'Strategy, Decorator, Command, Facade'), and the closing 'Resources' section restates the reference rather than deferring. Not a 1 because counting rules and RuboCop config earn their place; not a 3 because of the redundancy and known-concept explanations.

2 / 3

Actionability

Provides executable Ruby counting examples, concrete parameter-counting signatures, and a copy-paste-ready RuboCop YAML config, meeting the 'fully executable code/commands; copy-paste ready' anchor.

3 / 3

Workflow Clarity

A clearly sequenced 5-step Code Review Workflow plus three numbered Usage Patterns, and the refactoring pattern includes an explicit validation step ('Verify that tests still pass'). Code review is non-destructive, so the missing-checkpoint cap does not apply.

3 / 3

Progressive Disclosure

References are well-signaled and one-level-deep (explicit 'Read references/rules.md' blocks pointing to a real file), but the four rules, refactoring strategies, and breaking-rules context are duplicated inline rather than split into the reference, matching the 'content that should be separate is inline' part of the 2 anchor.

2 / 3

Total

10

/

12

Passed

Description

100%

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

The description is strong: it states concrete capabilities with numeric thresholds, provides natural trigger terms, includes an explicit 'Use when...' clause, and occupies a distinct niche, all in third-person voice with no first/second-person penalty.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('code review, refactoring, or code quality improvements') and enumerates the four rules with specific numeric thresholds ('classes under 100 lines, methods under 5 lines, no more than 4 parameters'), matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Clearly answers both what ('Apply Sandi Metz's four rules...') and when via an explicit 'Use when users mention...' clause, so completeness is not capped at 2.

3 / 3

Trigger Term Quality

Includes natural terms users would say — 'code review', 'refactoring', 'code quality', 'Sandi Metz', 'Ruby code' — giving good coverage of common variations a user would naturally voice.

3 / 3

Distinctiveness Conflict Risk

The Sandi Metz + Ruby codebase anchoring gives it a clear, distinct niche unlikely to conflict with general-purpose skills, despite the somewhat generic 'code quality'/'refactoring' triggers.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Dicklesworthstone/pi_agent_rust
Reviewed

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.