skills.rest
riddopic
riddopicCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

skill-audit

Audit AI skills against evidence-based criteria using Quick Scan and Full Audit modes.

Updated Feb 18, 2026
Search Tags:#code quality#quality assurance#best practices#ai development#skill audit#skills bench
One-click install
npx skills add https://github.com/riddopic/cc-tools --skill skill-audit-riddopic
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-audit
Source: https://github.com/riddopic/cc-tools/tree/main/.claude/skills/skill-audit
Command: npx skills add https://github.com/riddopic/cc-tools --skill skill-audit-riddopic

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill ensures your AI skills meet rigorous quality standards, are appropriately sized, and align with best practices derived from extensive research, preventing the proliferation of low-quality or redundant skills.

Core Features & Use Cases

  • Evidence-Based Auditing: Evaluates skills against empirical criteria from SkillsBench research (procedural quality, length, pretraining gap coverage).
  • Mode Flexibility: Supports 'Quick Scan' for changed skills or 'Full Audit' for a comprehensive review.
  • Use Case: Before deploying new skills or after significant updates, run a 'Full Audit' to identify any skills that are too long, encyclopedic, or overlap with existing ones, ensuring maintainability and effectiveness.

Quick Start

Run a full audit of all your skills.

Frequently Asked Questions about skill-audit

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

FAQPage Schema
How do I audit AI skills for quality and compliance?▼

You can audit AI skills for quality and compliance by evaluating them against evidence-based criteria for procedural quality, length discipline, and pretraining gap coverage using Quick Scan or Full Audit modes.

What are the best practices for preventing redundant skills in a project?▼

To prevent redundant skills, analyze skill co-loading to maintain an optimal skill budget, ensuring your skills are appropriately sized and do not overlap with existing ones in the .claude/skills directory.

How do I check if my AI skills are too long or encyclopedic?▼

You can check if AI skills are too long or encyclopedic by running a Full Audit, which reviews skills against empirical length discipline criteria derived from SkillsBench research.

When should I run a Quick Scan versus a Full Audit on my skills?▼

Run a Quick Scan to audit recently changed skills for fast checks, or run a Full Audit before deploying new skills and after significant updates for a comprehensive quality and compliance review.

Does the skill audit work on both global and project-level skills?▼

Yes, the skill audit operates on both global and project-level skills located within the .claude/skills directory to evaluate procedural quality and pretraining gap coverage.

Related Skills

Explore More Software Engineering Skills→
kdpa-llckdpa-llc
34

local-skills-mcp-usage

Resolve skill placement across personal, project, and custom directories for Local Skills MCP.

Official
Basic
Exploration-labsExploration-labs
49

skill-gap-analyzer

Analyze skill libraries to identify coverage gaps, redundancies, and optimization opportunities.

Official
Basic
aist-ai-sastaist-ai-sast

aist-security-check

Audit changed files for security risks and produce remediation findings.

Official
Advanced
nicolanoviellnicolanoviell
2

code-review

Review code changes for bugs, style issues, and best practices.

Community
Intermediate