What kind of reports does it generate?

It produces a structured markdown report that includes automated check results, a detailed score breakdown, and prioritized recommendations for improvements.

Do I need to run the scripts manually?

While the skill uses Python scripts for validation, it is designed to invoke them automatically during the assessment process to perform structure, hook, and routing checks.

What is the PopKit Anthropic Assessment skill?

It is a specialized validation tool that checks if your PopKit plugins follow the official Claude Code patterns and Anthropic's technical requirements using automated scripts.

Is this suitable for professional development workflows?

Yes, because it uses machine-readable standards and objective scripts, it is ideal for maintaining consistency and quality in production-grade AI automation tools.

How does the scoring system work?

The assessment starts with a score of 100 and applies deductions based on the severity of issues found, ranging from critical (-20) to minor warnings (-1).

PopKit Anthropic Compliance Assessment

Name: PopKit Anthropic Compliance Assessment
Author: jrc1883

byjrc1883

•

安全与测试

Validates PopKit plugins against official Claude Code patterns and Anthropic engineering standards through automated script-based checks.

The PopKit Anthropic Assessment skill provides a rigorous, machine-readable validation framework for developers building within the PopKit ecosystem. By executing a series of specialized Python scripts, it audits plugin structure, hook protocol compliance, and agent routing efficiency against predefined JSON schemas. It transforms subjective code reviews into objective, reproducible reports with a standardized scoring system and prioritized recommendations, ensuring that tools built for Claude Code adhere to the highest engineering standards for performance, reliability, and progressive disclosure.

主要功能

01Agent routing coverage analysis to prevent command conflicts

02Automated validation of plugin.json and hooks.json schemas

03Machine-readable checklists based on Anthropic engineering best practices

04Hook protocol verification for consistent stdin/stdout handling

05Objective 0-100 scoring system with prioritized fix recommendations

065 GitHub stars

使用场景

01Pre-release quality assurance for custom PopKit plugins and hooks

02Standardizing engineering practices across distributed AI development teams

03Troubleshooting hook implementation errors within Claude Code workflows

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add jrc1883/popkit-claude pop-assessment-anthropic

For use in Claude.ai and ChatGPT

Download Skill