guardian-ai

Community

Prevent destructive operations and enhance security with NEURO-powered safety reviews.

Authorweebcoder101
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill acts as a pre-execution safety net, reviewing every user prompt to prevent accidental destructive operations and catch security issues before they occur.

Core Features & Use Cases

  • NEURO-Powered Safety Reviews: Uses NEURO API for in-depth safety checks on user prompts.
  • Hard-Block Checks: Instantly blocks known dangerous operations like filesystem deletion.
  • Safe Pattern Checks: Automatically approves common, non-risky commands.
  • Integration with Skill Chains: Integrates with existing skill chains for seamless operation.
  • Customizable Risk Levels: Configure risk levels and manual approvals.

Quick Start

Use the guardian-ai skill to review a prompt with 'guardian-ai --prompt "delete all users table"'

Dependency Matrix

Required Modules

neurometric

Components

scriptsreferences

💻 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: guardian-ai
Download link: https://github.com/weebcoder101/dreamcode/archive/main.zip#guardian-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 620,000+ vetted skills library on demand.