skill-evaluator

Evaluate Claude Code skills across eight dimensions and generate improvement reports.

2|1|Updated Nov 20, 2025
One-click install
npx skills add https://github.com/lhohan/claude-code-plugins --skill skill-evaluator-lhohan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-evaluator
Source: https://github.com/lhohan/claude-code-plugins/tree/main/skill-evaluator/skills/skill-evaluator
Command: npx skills add https://github.com/lhohan/claude-code-plugins --skill skill-evaluator-lhohan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Developing high-quality, effective Claude Skills requires adherence to best practices, but manually reviewing each skill for compliance, structure, and prompt engineering quality is time-consuming and prone to oversight. This Skill automates that rigorous evaluation, ensuring your skills are optimized and perform as expected, so you can focus on building, not debugging.

Core Features & Use Cases

  • Comprehensive Quality Audit: Automatically assesses skills across 8 critical dimensions, including size, scope, structure, examples, and prompt engineering quality.
  • Anti-Pattern Detection: Identifies common pitfalls and red flags that can degrade skill performance or usability, preventing future issues.
  • Actionable Improvement Report: Generates a detailed report with an executive summary, metrics, dimensional analysis, and prioritized, concrete suggestions for improvement.
  • Use Case: Before deploying a new Claude Skill, use this evaluator to get an objective, detailed assessment. This ensures your skill meets internal standards and Anthropic's best practices, saving you significant development and debugging time.

Quick Start

Evaluate the skill named 'my-new-skill' against all best practices and provide a detailed report.

Frequently Asked Questions about skill-evaluator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I evaluate the quality of a Claude Skill before deployment?

Skill evaluation assesses your implementation across eight dimensions—size, scope, structure, examples, and prompt engineering quality—to identify issues and ensure it meets best practices before you deploy, saving debugging time.

What best practices should a well-structured Skill follow?

Best practices for Skills cover dimensional analysis including scope clarity, description quality, anti-pattern avoidance, prompt engineering rigor, and completeness. Automated evaluation reports gaps in each area with actionable remediation steps.

Can I detect anti-patterns and common mistakes in my Skill automatically?

Anti-pattern detection identifies common pitfalls—poor structure, weak examples, inadequate descriptions, suboptimal prompt design—that degrade performance or usability, catching issues before deployment.

What metrics does a Skill quality report include?

Quality reports extract line counts, word counts, and character counts alongside dimensional scores, an executive summary, per-dimension assessments, and a prioritized issues list for structured optimization.

How do I improve my Skill's prompt engineering quality?

Prompt engineering evaluation identifies weaknesses in instruction clarity, context design, and reasoning patterns. The detailed report surfaces concrete suggestions to strengthen how your Skill guides Claude's behavior.

What does a Skill evaluation report tell me about scope and structure?

Scope and structure assessment examines whether your Skill's purpose is clearly defined, components are logically organized, and the implementation covers all required functionality without unnecessary complexity.