hallucination-risk-reviewer

# Hallucination Risk Reviewer ## What this skill does This skill reviews an LLM-generated response or the output of an AI-powered application feature to assess its hallucination risk. It identifies the specific types of claims that are most likely to be fabricated, flags confidence calibration issues (the model sounds certain about things it may not know), and recommends mitigations. The output is a structured risk assessment that helps you decide whether to use the output as-is, verify specific claims, or redesign the prompt/system. Use this when building AI-powered features where factual accuracy matters, when reviewing generated content before publishing, or when evaluating whether an LLM is suitable for a high-stakes use case. ## How to use ### Claude Code / Cline Copy this file to `.agents/skills/hallucination-risk-reviewer/SKILL.md` in your project root. Then ask: - *"Use the Hallucination Risk Reviewer skill on this AI-generated response: [paste response]."* - *"Review the outputs of our AI support bot for hallucination risk using the Hallucination Risk Reviewer skill."* Provide: - The AI-generated text or a sample of outputs - The original prompt or context given to the model (if known) - The use case (what decision or action will this output inform?) - The model or system used (if known) ### Cursor Add the instructions below to your `.cursorrules` or paste them into the Cursor AI pane. Provide the output to review. ### Codex Paste the AI output and contex...