agent-native-audit

Audit codebases for adherence to eight agent-native architecture principles.

5|Updated Oct 22, 2025
One-click install
npx skills add https://github.com/marchatton/agent-skills --skill agent-native-audit-marchatton
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-native-audit
Source: https://github.com/marchatton/agent-skills/tree/main/.agents/skills/10-audit/agent-native-audit
Command: npx skills add https://github.com/marchatton/agent-skills --skill agent-native-audit-marchatton

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the challenge of ensuring software architectures adhere to agent-native principles, providing a structured audit to identify gaps and areas for improvement.

Core Features & Use Cases

  • Comprehensive Principle Audit: Evaluates adherence to 8 core agent-native principles.
  • Scored Assessment: Provides quantitative scores for each principle and an overall system health check.
  • Use Case: A development team can use this Skill to periodically assess their application's architecture, ensuring it remains aligned with best practices for agent integration and responsiveness.

Quick Start

Run a full audit of the agent-native architecture for the current project.

Frequently Asked Questions about agent-native-audit

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

FAQPage Schema
What is an agent-native architecture audit?

An agent-native architecture audit evaluates a codebase against eight core principles including action parity, context injection, and capability discovery. It produces a scored report highlighting compliance gaps and recommendations for system-wide health improvements.

How do I audit my codebase for agent-native compliance?

You audit agent-native compliance by running this skill to analyze your codebase against eight principles including tools as primitives and shared workspace. It generates a scored assessment with actionable recommendations for system health.

What principles are evaluated in an agent-native architecture assessment?

The assessment evaluates eight principles: action parity, tools as primitives, context injection, shared workspace, CRUD completeness, UI integration, capability discovery, and prompt-native features. Each receives a quantitative score for overall system health tracking.

Can I use this audit for periodic system health checks?

Yes, this audit is designed for periodic system health checks. Development teams can run it regularly to assess their application architecture and ensure continuous alignment with agent integration best practices.

Does the audit require specific dependencies or external tools?

No specific dependencies are required to run the agent-native architecture audit. It operates independently using built-in scripts and references to analyze the codebase and generate the scored compliance report.