Skills
.Work. You
Rest

ai-verification-guardrails

Community

Ensure AI output integrity.

Software Engineering#data quality#verification#ai#hallucination detection#guardrails#financial advice
Authorroaming-rockenfels
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill ensures the quality, safety, and reliability of AI-generated outputs by implementing a robust 3-tier verification system, preventing financial advice misinterpretations and hallucinations.

Core Features & Use Cases

  • Tier 1 (Data Freshness): Verifies that input data is up-to-date, checking trading day staleness and FX freshness.
  • Tier 2 (Calculation Integrity): Validates the accuracy of financial calculations, including portfolio consistency and performance bounds.
  • Tier 3 (AI Output Guardrails): Detects and mitigates risks in AI responses, such as financial advice, hallucinations, and incomplete answers.
  • Use Case: When an AI assistant provides portfolio performance analysis, this Skill first checks if the underlying market data is current (Tier 1), then verifies the calculation of the performance metrics (Tier 2), and finally ensures the AI's advice is safe and factually grounded (Tier 3).

Quick Start

Use the ai-verification-guardrails skill to add new verification checks for Tier 2 calculation integrity.

Dependency Matrix

Required Modules

None required

Components

referencesscripts

💻 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: ai-verification-guardrails
Download link: https://github.com/roaming-rockenfels/ghostfolio/archive/main.zip#ai-verification-guardrails

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.