Skills
.Work. You
Rest

grounding-guard

Official

Ensure response accuracy with source document verification.

#fact-checking#grounding#faithfulness#nli#response verification
Authorframerslab
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill prevents misinformation by verifying the faithfulness of AI-generated responses against source documents using NLI entailment and LLM assessment.

Core Features & Use Cases

  • Response Faithfulness: Checks AI-generated responses against source documents.
  • NLI Entailment: Uses NLI to ensure claims are supported by sources.
  • LLM-as-judge: Provides an additional layer of verification by the AI itself.
  • Use Case: Before sharing a synthesized answer from multiple sources, use Grounding Guard to ensure the information is accurate and grounded.

Quick Start

Run the grounding-guard skill to verify the accuracy of the AI's response to the question "What are the main findings of the recent study on climate change?"

Dependency Matrix

Required Modules

None required

Components

scripts

💻 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: grounding-guard
Download link: https://github.com/framerslab/agentos-skills/archive/main.zip#grounding-guard

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.