skills.rest
fukukei23
fukukei23COMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-test

Validate AI skill definitions for workflow inconsistencies and operational defects.

Updated Mar 26, 2026
Search Tags:#static analysis#prompt engineering#claude code#skill validation#skill audit#workflow testing
One-click install
npx skills add https://github.com/fukukei23/claude-config --skill skill-test-fukukei23
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-test
Source: https://github.com/fukukei23/claude-config/tree/main/.claude/worktrees/make-song-analyze-song-bridge/skills/skill-test
Command: npx skills add https://github.com/fukukei23/claude-config --skill skill-test-fukukei23

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps maintain reliable AI skills by detecting specification errors, trigger conflicts, workflow gaps, and potential operational issues before they affect users.

Core Features & Use Cases

  • Static Skill Inspection: Reviews SKILL.md definitions for inconsistent instructions, missing logic, environment dependencies, and security concerns.
  • Dry-Run Validation: Traces skill workflows through normal, error, and boundary scenarios to identify execution risks without modifying files.
  • Batch Health Audits: Audits multiple skills at once, ranks issues by severity, and produces actionable remediation drafts for skill maintenance.

Quick Start

Use the skill-test skill to inspect the target skill definition and generate a validation report with detected issues and improvement suggestions.

Frequently Asked Questions about skill-test

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

FAQPage Schema
How do I validate AI skill definitions for workflow inconsistencies?▼

Static analysis of skill definitions detects workflow inconsistencies, missing safeguards, and operational defects. It applies to individual SKILL.md reviews, batch health audits, trigger analysis, and workflow verification.

What is a dry-run validation for prompt engineering workflows?▼

Dry-run validation traces skill workflows through normal, error, and boundary scenarios to identify execution risks without modifying files. It ensures operational safety during prompt engineering testing.

Can I perform a batch health audit on multiple Claude Code skills?▼

Yes, batch health audits evaluate multiple Claude Code skills simultaneously. The audit ranks detected issues by severity and produces actionable remediation drafts for skill maintenance.

Does skill validation require external dependencies or components?▼

Skill validation requires no external dependencies or components. It relies on structured skill metadata inspection and scenario-based dry runs to generate severity ranking and remediation reporting.

What is the best way to uncover design flaws in SKILL.md files?▼

The best way to uncover design flaws in SKILL.md files is through static skill inspection. This reviews definitions for inconsistent instructions, missing logic, environment dependencies, and security concerns early.

When should I not use static analysis for skill validation?▼

You should not use static analysis for skill validation when you need to execute the skill in a live environment to test runtime behavior. Static analysis only detects specification errors and trigger conflicts without actual execution.

Related Skills

Explore More Software Engineering Skills→
WaterplanAIWaterplanAI
31

dr

Forward all arguments from /dr to /dry-run for command validation.

Official
Basic
majiayu000majiayu000
12

skill

Route user requests to registered skill modules and execute them in context.

Community
Basic
kanade0404kanade0404

empirical-prompt-tuning

Diagnose and improve prompt trigger reliability through empirical evaluation.

Community
Advanced
sohei56sohei56
15

cross-review

Audit a repository for specification conflicts, logic defects, and security issues.

Community
Advanced