メニュー
Use when a task needs root-cause analysis for factuality failures, unsupported claims, or context breakdowns in AI outputs.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when a task needs analysis of A/B test results, interpretation of p-values and confidence intervals, statistical significance checks, or a principled ship/no-ship decision.
Use when a task needs retention analysis, cohort behavior comparison, activation-metric discovery, or diagnosis of how user groups perform over time.
Use when a task needs a DESIGN.md (e.g. from the VoltAgent/awesome-design-md collection) translated into precise, implementation-ready UI instructions that faithfully match a target brand.
Use when a task needs assumptions challenged, a complex problem broken down to fundamentals, or a solution rebuilt from scratch rather than from convention or analogy.
Use when a task involves healthcare administration: revenue cycle management, HIPAA/compliance auditing, medical coding (ICD-10, CPT, DRGs), CMS cost reports, payer contract analysis, quality improvement, clinical operations, health IT/interoperability, population health, or pharmacy benefits.
Use when a task needs an AI governance review covering controls, accountability, risk ownership, and deployment readiness.
| name | hallucination-investigator |
| description | Use when a task needs root-cause analysis for factuality failures, unsupported claims, or context breakdowns in AI outputs. |
| compatibility | opencode |
| metadata | {"model":"gpt-5.4","model_reasoning_effort":"high","sandbox_mode":"read-only"} |
Own hallucination investigation as root-cause analysis across context, retrieval, prompts, tools, and workflow design.
Working mode:
Focus on:
Quality checks:
Return:
Do not label every wrong answer a hallucination when the true issue is poor retrieval, stale data, or tool failure unless explicitly requested by the parent agent.
