skills.rest
sorawit-w
sorawit-wCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-evaluator

Audits SKILL.md-defined rules and generates a failure classification and correction report.

1|Updated Apr 17, 2026
Search Tags:#quality assurance#audit#skill#behavior verification#rule adherence
One-click install
npx skills add https://github.com/sorawit-w/agent-skills --skill skill-evaluator-sorawit-w
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-evaluator
Source: https://github.com/sorawit-w/agent-skills/tree/main/skills/skill-evaluator
Command: npx skills add https://github.com/sorawit-w/agent-skills --skill skill-evaluator-sorawit-w

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It helps assess whether a given skill’s instructions and rules are effectively followed and enforced when Claude executes it, identifying gaps or failures in rule adherence.

Core Features & Use Cases

  • Behavioral Validation: Runs pre-designed tests against the skill to verify if the actual outputs conform to its rules.
  • Failure Analysis: Classifies failures by root cause, distinguishing between skill text issues and test-quality problems.
  • Quality Assurance: Ensures that skills behave as documented, reducing risk before deploying or shipping updates.

Quick Start

Use the skill-evaluator to analyze an existing SKILL.md by uploading it and selecting "audit skill". It will generate a report highlighting rule adherence issues and suggested fixes.

Frequently Asked Questions about skill-evaluator

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

FAQPage Schema
How do I verify if Claude skill rules are being followed during execution?▼

To verify skill rule adherence, you can audit the existing skill to determine whether its instructions are consistently enforced when executed, producing a report with failure classification and rule corrections.

What is the best way to audit a SKILL.md file for behavior verification?▼

Auditing a SKILL.md involves running pre-designed behavioral validation tests against the skill, checking if actual outputs conform to documented rules, and generating a detailed report highlighting any adherence issues.

Can I classify why my Claude skill instructions fail to land in practice?▼

You can classify skill instruction failures by root cause through behavioral validation, which distinguishes between issues originating from the skill text itself and problems caused by test-quality.

How do I ensure quality assurance before deploying or shipping skill updates?▼

Quality assurance before deploying skill updates is achieved by running behavioral validation tests to ensure the skill behaves as documented, reducing deployment risk by identifying rule adherence gaps.

Does the skill-evaluator require any dependencies to audit skill behavior?▼

The skill-evaluator does not require any dependencies to audit skill behavior; you simply upload the existing SKILL.md and select the audit option to generate the rule adherence report.

When should I not use a skill audit for rule compliance?▼

A skill audit for rule compliance is not suitable for evaluating external factors outside the skill's text, as its failure analysis strictly targets rule adherence issues and test-quality problems within the skill itself.

Related Skills

Explore More Software Engineering Skills→
yeeehaoooyeeehaooo

template-skill

Standardize Claude skill definitions with SKILL.md frontmatter validation.

Community
Basic
lucaswalllucaswall

code-audit

Coordinate parallel security, reliability, and quality code audits into Linear issues.

Community
Advanced
X-School-AcademyX-School-Academy
9

dev-swarm-refine-mcp-skill-descriptions

Evaluate and rewrite MCP skill descriptions against the agent skill specification.

Official
Intermediate
jnPiyushjnPiyush

code-review-and-audit

Automate code review, security audits, and compliance verification in CI/CD pipelines.

Community
Advanced