Agentic AI Plugin Evaluator: Score and Audit Repositories

Agentic AI Plugin Evaluator: Score and Audit Repositories

The Agentic AI Plugin Evaluator assists developers and AI teams in auditing, scoring, and comparing repositories containing portable agent plugins. This tool evaluates compliance against the official Agent Plugins specification, providing an evidence-backed scoring system that helps identify release blockers and compare two agent plugins side-by-side.

What this skill does

• Audits repositories for conformance with the Agent Plugins specification using the root plugin.json.
• Assesses bundled skills and MCP servers to ensure they meet established criteria.
• Generates a scorecard on a 0–100 scale to provide a quantifiable evaluation of the plugin.
• Identifies potential release blockers, offering insight into necessary improvements.
• Compares two repositories by evaluating their features, allowing a thorough side-by-side analysis.

Who it is for

This skill is aimed at developers and teams working with AI coding agents such as Claude Code, Cursor, and Codex, who require a robust assessment of their plugin repositories. It is particularly beneficial for those involved in quality assurance and compliance checks.

Use cases

• Validating plugin repositories prior to release to ensure full compliance with the specification.
• Producing detailed and evidence-supported reports for team review or client presentation.
• Comparative analysis of multiple plugins to determine the most compliant or feature-rich option.
• Identifying and addressing deficiencies that could delay or prevent plugin deployment.

Technical details

• Parameters include local repository/plugin path or Git URL, optional second repository for comparison, output destination for scorecards, and the Agent Plugins version to evaluate.
• Maintains a strict safety boundary by performing static audits and avoiding execution of untrusted code unless explicitly authorized.
• Redacts suspected secret values to protect sensitive information, relying on corroborating evidence to confirm potential security issues.

For authorised security testing, defensive research, and educational use only.

Source & Licence

This package is built on open-source work published by fabricioctelles (fabricioctelles/skills) and distributed under Apache-2.0. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted under the Apache License 2.0, which also includes an express patent grant. Attribution and any NOTICE file must be retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.