hallucination-investigator

Diagnose hallucinations in AI outputs through root-cause analysis across context, retrieval, prompts, and tools.

22|2|Updated Mar 24, 2026

Search Tags:#verification #retrieval #prompts #hallucination #root-cause-analysis #factuality #evidence-reconstruction

Ready to run

npx skills add https://github.com/jshsakura/awesome-opencode-skills --skill hallucination-investigator

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: hallucination-investigator
Source: https://github.com/jshsakura/awesome-opencode-skills/tree/main/skills/hallucination-investigator
Command: npx skills add https://github.com/jshsakura/awesome-opencode-skills --skill hallucination-investigator

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Reconstructs failing AI outputs to diagnose root causes of hallucinations and factuality gaps across context, retrieval, prompts, tools, and workflow design.

Core Features & Use Cases

Reconstructs failing examples with available evidence to identify missing context, retrieval gaps, prompts, and tool misuse.
Pinpoints whether failures stem from data limitations, prompt framing, or unsupported inferences, and proposes actionable fixes.
Provides guardrails and verification scenarios to prevent recurrence and validate fixes.

Quick Start

Analyze a failure by providing the failing AI response and relevant context to identify root causes and recommended improvements.

Frequently Asked Questions about hallucination-investigator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I find the root cause of AI hallucinations in my prompts?▼

To find the root cause of AI hallucinations, you reconstruct failing outputs with available evidence to identify missing context, retrieval gaps, prompt framing issues, or tool misuse. This process pinpoints whether failures stem from data limitations or unsupported inferences.

What is factuality failure analysis in AI outputs?▼

Factuality failure analysis diagnoses why AI outputs are inaccurate by comprehensively examining context, retrieval quality, prompts, and tools. It reconstructs the failure with evidence to determine root causes and proposes high-leverage fixes to prevent recurrence.

How do I debug retrieval gaps causing inaccurate AI responses?▼

Debug retrieval gaps by analyzing failing AI responses alongside relevant context to identify missing information. Root-cause analysis determines if inaccurate outputs stem from retrieval quality, prompt framing, or unsupported inferences, enabling targeted fixes.

How do I fix factuality issues and prevent them from recurring?▼

Fix factuality issues by proposing actionable improvements based on identified root causes across context, prompts, and tools. Prevent recurrence by applying guardrails and running verification scenarios that validate the fixes against future failures.

Why does my AI output contain unsupported inferences?▼

Unsupported inferences occur when AI outputs lack sufficient context or retrieval evidence. Root-cause analysis reconstructs the failing example to determine if the failure stems from data limitations, prompt framing, or tool misuse causing the unsupported inference.

Can I use root-cause analysis to diagnose tool misuse in AI workflows?▼

Yes, root-cause analysis diagnoses tool misuse by examining failing examples across your workflow design. It identifies whether inaccurate outputs originate from tool limitations, retrieval gaps, or prompt framing, and proposes high-leverage fixes with verification scenarios.