# Powerbi AI Hallucination Guard

> Use when AI/KI answers about Power BI, KPIs, DAX, source systems, reports, or process causes must be checked against metadata, KPI catalogs, tests, source totals, or accepted evidence.

- Skill: `rweisssieker-xp/powerbi-ai-hallucination-guard` (Agent Skill)
- Install (CLI): `npx skillmds@latest add rweisssieker-xp/powerbi-ai-hallucination-guard`
- Raw SKILL.md: https://api.skillmd.com/api/skills/rweisssieker-xp/powerbi-ai-hallucination-guard/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: rweisssieker-xp (https://skillmd.com/u/rweisssieker-xp)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/rweisssieker-xp/powerbi-ai-hallucination-guard

---


# Power BI AI Hallucination Guard

Use this skill before accepting generated AI answers.

## Checks

- Does the answer cite retrieved artifacts or verified metadata?
- Does KPI logic match certified contracts?
- Do DAX/Power Query outputs have tests?
- Are source totals or reconciliation checks available?
- Are assumptions labeled?
- Does the answer overstate causality?

## Output Requirements

- Return accepted, conditional, or rejected.
- Include failed checks, missing evidence, and required remediation.