agent-introspection-debugging

What problem does it solve? AI agent runs often fail by looping on the same tool calls, burning tokens without progress, or drifting from the intended task. This Skill provides a structured self-debugging workflow so the agent captures the failure, diagnoses the root cause, applies a minimal recovery, and reports the outcome instead of retrying blindly. ## Core Features & Use Cases - Four-Phase Debug Loop: Failure capture, root-cause diagnosis, contained recovery, and a structured introspection report. - Failure Pattern Table: Maps common symptoms like maximum tool calls, context overflow, ECONNREFUSED, 429 quota exhaustion, and 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 after repeating the same command, use this Skill to record the failure state, classify the pattern, run one direct check, and produce a human-readable self-debug report. ## Quick Start Use the agent-introspection-debugging skill to diagnose why this agent run keeps looping on the same tool call and produce a recovery report.