agent-introspection-debugging

What problem does it solve? AI agents often fail silently by looping on the same tools, burning tokens without progress, or drifting from the original task. This Skill provides a structured self-debugging workflow so the agent captures failure state, diagnoses root causes, applies contained recovery, and reports results instead of blindly retrying. ## Core Features & Use Cases - Four-Phase Loop: Failure capture, root-cause diagnosis, contained recovery, and a structured introspection report. - Failure Pattern Library: Maps common symptoms (max tool calls, context overflow, ECONNREFUSED, 429 quota exhaustion, stale file state) to likely causes and checks. - Recovery Heuristics: Prioritizes restating the objective, verifying world state, shrinking scope, and running one discriminating check before retrying. - Use Case: When an agent hits a loop-limit failure while fixing a test, activate this Skill to capture the failure, classify the pattern, run one direct check, and produce a human-readable self-debug report. ## Quick Start Ask the agent to use the agent-introspection-debugging skill to diagnose why its current task is stuck in a retry loop and produce a self-debug report.