reikys-hallucination-guard
Execution-based verification guardrail with 14 check items for AI agent output
Best for AI agent output validationWorks with GitHubLow risk
⌘source
- author
@LeoYeAI- language
- Python
★2kstars
306forks
May 6, 2026
✦overview.md
Key Features
- ·14 execution-based verification items
- ·Path, command, library, numerical checks
- ·Completeness and consistency checks
- ·Structured PASS/FAIL report
Use Cases
- →Verifying AI agent output for file path accuracy
- →Checking if commands and binaries actually exist
- →Ensuring code imports match installed packages
- →Validating numerical facts and claims
- →Confirming task completeness and naming consistency
Best for
- ✓AI agent output validation
- ✓production deployments
- ✓quality assurance teams
Not ideal for
- !real-time interactive checking
- !non-technical content
FAQs
name
hallucination-guard
description
Execution-based verification guardrail with 14 check items for AI agent output
version:1.0.0
author:reikys
tags:["verification","quality","safety","guard","hallucination"]
trigger:hallucination check
🛡️ hallucination-guard
Solving the biggest trust problem with AI agents. Not with "double-check that" prompts, but with 14 execution-based verification items.
🎯 Problem Definition
AI agents carry the following trust issues:
| Problem Type | Example |
|---|---|
| Path hallucination | References non-existent files/directories as if they exist |
| Command hallucination | Describes uninstalled binaries as if they run normally |
| Library hallucination | Writes code that imports packages that don't exist on npm/pip |
| Numerical hallucination | States unsourced statistics/percentages as fact |
| Completeness hallucination | Reports "done" while leaving TODO/PLACEHOLDER behind |
| Consistency hallucination | Uses different names for the same concept within a document |
Limitations of Existing Solutions
- truth-check, verification-before-completion: Just tells the agent "check again" — still hallucination-based
- hallucination-guard: 14 concrete items × executable commands × structured PASS/FAIL report
⚡ Quick Start
1. Trigger Method
$install
1-click copynpx skills add LeoYeAI/openclaw-master-skills --skill reikys-hallucination-guardSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
3/ 5
goodMostly clear, but there are still a few confusing or poorly structured parts.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
3/ 5
mediumPartially actionable with several concrete steps, but still missing important details.