Which version of the Claude Code guidelines are supported?

This skill is built to validate against Architecture Guidelines v0.5 and current Plugin Storage Conventions.

What specifically does the Claude Skill Reviewer validate?

It validates three primary areas: metadata/storage (YAML and persistence), implementation (JSON fencing and hooks), and architecture (two-tier separation and naming conventions).

What happens if one of the review agents fails?

The system provides partial results from successful agents and reports specifically on which reviewer failed and why, ensuring you still receive valuable feedback.

Can I review specific files or just entire packages?

You can review specific agents, individual skills, or entire packages by providing the relevant path to the review command.

Does this tool modify my source code?

No, the skill is strictly read-only. It analyzes your files and provides a detailed report with suggested actions for you to implement.

Claude Skill Reviewer

Name: Claude Skill Reviewer
Author: randlee

byrandlee

•

セキュリティとテスト

Validates and audits Claude Code skills and agents against architectural, implementation, and storage standards.

概要

The Claude Skill Reviewer is a specialized validation suite designed for developers building within the Claude Code ecosystem. It utilizes a three-agent orchestration pattern to concurrently analyze metadata persistence, code mechanics (security and hooks), and architectural integrity such as two-tier separation. By providing actionable, structured reports categorized by severity, this skill ensures that custom agents and skills meet the latest v0.5 guidelines, facilitating higher quality standards and seamless deployment for AI-driven workflows.

主な機能

Parallel orchestration of metadata, implementation, and architecture review agents
Architectural compliance checks for two-tier skill/agent design patterns
Security-focused code reviews targeting JSON fencing and hook implementation
1 GitHub stars
Automated YAML frontmatter and registry.yaml consistency validation
Actionable reporting with grouped errors, warnings, and optimization tips

ユースケース

Debugging agent tool-use hooks and dependency declarations during development
Ensuring legacy agent packages comply with modern Plugin Storage Conventions
Auditing new Claude Code skills before production deployment

概要

主な機能

Parallel orchestration of metadata, implementation, and architecture review agents
Architectural compliance checks for two-tier skill/agent design patterns
Security-focused code reviews targeting JSON fencing and hook implementation
1 GitHub stars
Automated YAML frontmatter and registry.yaml consistency validation
Actionable reporting with grouped errors, warnings, and optimization tips

ユースケース

Debugging agent tool-use hooks and dependency declarations during development
Ensuring legacy agent packages comply with modern Plugin Storage Conventions
Auditing new Claude Code skills before production deployment