DCL Semantic Drift Guard — Hallucination & Context Drift Detector by @daririnch
Use this skill to detect semantic hallucinations and context drift in LLM outputs. Triggers when an agent or pipeline needs to verify that a generated respon...
⚡ When to Use
Trigger Action |---|---|---|---| | Legal contract summarization | `context` | `strict` | Fabricated clauses = liability | | RAG-based customer support | `kb_query` | `balanced` | Prevent wrong product info | | Medical documentation | `context` | `strict` | Patient safety | | Financial report generation | `context` | `strict` | Regulatory compliance | | EU AI Act compliance auditing | `kb_query` | `strict` | FSTEK / AI Act article mapping | | Internal knowledge assistant | `kb_query` | `lenient` | Lower stakes, exploratory | ---
▸ Show full description clawhub install dcl-semantic-drift-guardCopy
🧪 Use this skill with your agent Most visitors already have an agent. Pick your environment, install or copy the workflow, then run the smoke-test prompt above.
🔍 Can't find the right skill?
Search 60,000+ AI agent skills — free, no login needed.
Search Skills →