agent-native-audit

Community

Score agent-native architecture maturity

AuthorAndreicr1
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill automates a comprehensive, principle-driven audit of an agent-native codebase to remove ad-hoc reviews and surface consistent, scored findings and prioritized recommendations for engineering and product teams.

Core Features & Use Cases

  • Parallel principle audits: Launches parallel sub-agents to evaluate eight core agent-native principles including action parity, tools-as-primitives, context injection, shared workspace, CRUD completeness, UI integration, capability discovery, and prompt-native features.
  • Scored findings & gaps: Produces per-principle numeric scores, enumerates specific gaps, and provides prioritized remediation recommendations.
  • Single-principle mode: Supports focused audits for one principle when an argument is supplied to expedite targeted reviews.
  • Use Case: Use this Skill for pre-release architecture reviews, design retrospectives, security/compliance checks, and roadmap prioritization for AI agent features.

Quick Start

Run the agent-native-audit skill to generate a scored, actionable agent-native architecture report for the repository.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: agent-native-audit
Download link: https://github.com/Andreicr1/Netz-Private-Credit-OS/archive/main.zip#agent-native-audit

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.