Skip to content
Development
Command

/skills-eval

Audit skill quality, frontmatter compliance, token efficiency, and activation reliability. Recommends improvements.

From plugin
claude-night-market
325163 skills59 agents163 commands1 MCP
Install
$ npx -y skills add athola/claude-night-market --agent claude-code

How it fires

How this command gets triggered: by you, by Claude, or both.

  • Fires itselfClaude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/skills-eval

Context preview

What this command does when you run it.

Audit skill quality, frontmatter compliance, token efficiency, and activation reliability. Recommends improvements.

Command definition

skills-eval.md
name: skills-eval
description: Audit skill quality, frontmatter compliance, token efficiency, and activation reliability. Recommends improvements.
usage: /skills-eval [skill-name]

Skills Evaluation Command

When To Use

Use this command when you need to:

  • Auditing skill ecosystem quality
  • Discovering implementation patterns
  • Planning skill improvements
  • Checking compliance with standards
  • Generating improvement recommendations

When NOT To Use

Avoid this command if:

  • Evaluating hooks - use /hooks-eval instead
  • Validating plugin structure - use /validate-plugin instead
  • Creating new skills - use /create-skill instead

Usage

Evaluates all Claude Skills in your ~/.claude/ ecosystem for quality, compliance, and potential improvements.

Basic Usage

/prompt:skills-eval

Evaluates all discovered skills and generates improvement recommendations.

Specific Skill Evaluation

/prompt:skills-eval <skill-name>

Evaluates a specific skill (e.g., `/prompt:skills-eval modular-skills`).

What It Does

1. **Discovers Skills**: Finds all SKILL.md files in ~/.claude/ hierarchy 2. **Quality Analysis**: Evaluates structure, content, token efficiency, and activation reliability 3. **Compliance Checking**: Validates against Claude Skills standards and security guidelines 4. **Improvement Generation**: Provides specific improvement suggestions 5. **Prioritization**: Ranks improvements by impact and effort

Evaluation Criteria

  • **Structure Compliance**: YAML frontmatter, progressive disclosure, organization
  • **Content Quality**: Clarity, completeness, practical value
  • **Token Efficiency**: Content density, loading optimization
  • **Activation Reliability**: Naming, tags, trigger patterns
  • **Tool Integration**: Executable components, automation value
  • **Security Compliance**: Safe practices, dependency validation

Output Format

For each skill, provides:

  • Overall quality score (0-100)
  • Detailed breakdown by category
  • Specific improvement recommendations
  • Priority ranking and estimated effort
  • Implementation roadmap

Examples

/prompt:skills-eval
# Evaluates all 50+ skills, identifies 5 critical issues and 20+ improvements

/prompt:skills-eval modular-skills
# Deep dive on specific skill with detailed improvement plan

Integration with Tools

This command uses the skills-eval skill's specialized tools:

  • `skills-auditor`: Quality analysis
  • `improvement-suggester`: Actionable recommendation generation
  • `compliance-checker`: Standards and security validation

This evaluation validates an efficient skills ecosystem that follows Claude Skills best practices.

Read more
Ships withclaude-night-market

A plugin marketplace for Claude Code. Install only the plugins you need to run git workflows, code review, spec-driven development, and autonomous agents from inside your Claude Code session.

Get the whole plugin, auto-invoked
Stats
325
Stars
0
Views
35
Forks
Active
Maintenance
Python
Language
MIT
License
1d ago
Last commit
8mo ago
Created

Repo: athola/claude-night-market