Can it help reduce token usage?

Yes, the skill analyzes body length and content to ensure every line justifies its token cost, suggesting ways to trim unnecessary prose.

When is the best time to use this skill?

Use it when creating new skills, editing existing ones, or performing a bulk audit of your skill repository to maintain high quality standards.

How does Skill Review improve my Claude skills?

It identifies structural errors, improves trigger phrases for better activation, and ensures your code is token-efficient for better model performance.

What specific checks does the tool perform?

It audits directory structure, validates YAML frontmatter, checks for anti-patterns, and evaluates description quality to ensure reliable triggering.

Does it support Windows file paths?

The skill identifies Windows-style backslashes as anti-patterns and recommends using forward slashes to ensure cross-platform compatibility.

Skill Reviewer

Name: Skill Reviewer
Author: richtabor

byrichtabor

•

Developer Tools

Validates and optimizes agent skills against established best practices and structural standards.

About

Skill Reviewer is a specialized utility designed to ensure Claude Code skills are high-quality, token-efficient, and correctly structured. It performs a comprehensive eight-phase audit—covering everything from directory organization and YAML frontmatter to description quality and the identification of common anti-patterns—providing actionable recommendations to improve skill discoverability and performance.

Key Features

Token efficiency and progressive disclosure analysis
Comprehensive reporting with specific scores and suggested rewrites
YAML frontmatter validation for name and description standards
Detection of common anti-patterns like Windows paths and nested references
41 GitHub stars
Automated structural auditing of skill directories and files

Use Cases

Improving trigger phrase accuracy to ensure skills activate correctly
Validating a new skill before publishing to a repository
Auditing an existing library of skills for consistency and performance

About

Key Features

Token efficiency and progressive disclosure analysis
Comprehensive reporting with specific scores and suggested rewrites
YAML frontmatter validation for name and description standards
Detection of common anti-patterns like Windows paths and nested references
41 GitHub stars
Automated structural auditing of skill directories and files

Use Cases

Improving trigger phrase accuracy to ensure skills activate correctly
Validating a new skill before publishing to a repository
Auditing an existing library of skills for consistency and performance