What problem does it solve? Long-running LLM agents silently degrade as context grows: critical instructions get lost in the middle of the prompt, hallucinated claims poison downstream reasoning, and contradictory retrieved documents cause unpredictable outputs. This Skill provides a systematic framework to detect, diagnose, and fix these failures before they cascade. ## Core Features & Use Cases - Five-Pattern Diagnosis: Identify lost-in-middle, context poisoning, distraction, confusion, and clash failures with specific detection signals for each. - Health Analysis Toolkit: Run composite context health checks combining attention distribution, poisoning indicators, and utilization metrics via the included Python scripts. - Mitigation Framework: Apply the Write/Select/Compress/Isolate strategies matched to the active degradation pattern, with recovery procedures like truncation and context resets. - Use Case: An agent that worked well for 10 turns starts citing an incorrect retrieved fact at turn 30. Use this Skill to trace the poisoning entry point, truncate context to before that point, and reload only verified sources. ## Quick Start Ask the AI to analyze your agent's conversation context for degradation symptoms and recommend which mitigation strategy to apply.
