reviewing-claude-config

What problem does it solve?

Manually reviewing Claude Code configuration files for security vulnerabilities, structural integrity, and prompt engineering quality is complex and error-prone. This Skill automates that critical process, ensuring your AI setup is secure, efficient, and adheres to best practices.

Core Features & Use Cases

• Security-First Validation: Automatically detects critical issues like committed settings.local.json, hardcoded secrets, overly broad permissions, and dangerous command auto-approvals.
• Intelligent Review Routing: Automatically identifies the type of Claude configuration file (skills, agents, CLAUDE.md, prompts, settings) and applies a specialized, token-efficient review checklist.
• Quality & Structure Enforcement: Validates YAML frontmatter, enforces progressive disclosure guidelines (e.g., 500-line limit for main SKILL.md), checks file reference integrity, and ensures high-quality prompt engineering.
• Use Case: Before committing changes to a new Claude Skill, use this skill to automatically scan for security risks, validate its structure, and ensure its instructions are clear and token-efficient, receiving actionable feedback to improve your configuration.

Quick Start

Use the reviewing-claude-config skill to review the changes to .claude/CLAUDE.md.