audit-human-ai

Community

Audit Human-AI boundaries for safe autonomy.

Authormoongci38-oss
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This framework enables teams to quantify and improve the safety of Human-AI collaboration by evaluating autonomy and escalation design.

Core Features & Use Cases

  • Assess 5-Level Autonomy mapping across phases, determine actual operational levels, and verify alignment with design goals.
  • Analyze gate design, escalation triggers, anti-patterns (Rubber Stamping, Quasi-Automation, False Agency), Sterz 4 conditions, and metrics tracking.
  • Use cases: governance reviews, risk assessments, and compliance audits for AI-enabled projects.

Quick Start

Provide an audit target (system or project) and run the audit workflow to generate a structured JSON payload and a Notion-ready report.

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: audit-human-ai
Download link: https://github.com/moongci38-oss/forge/archive/main.zip#audit-human-ai

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 471,000+ vetted skills library on demand.