theory-grounding-reflector

Extract lessons from task failures by analyzing root causes and formulating actionable insights. The theory-grounding-reflector applies failure analysis to identify what went wrong, determine why, and document specific lessons that prevent recurrence, leading to measurable accuracy gains without context bloat.

Root cause analysis identifies the underlying reason a task failed, not just the symptom. This Skill structures failure analysis to classify errors, trace their origin, and extract lessons that apply to future similar tasks, enabling systematic self-improvement across your AI pipeline.

Yes. Failure analysis on data pipelines classifies errors, extracts root causes, and documents lessons as delta items. This prevents context collapse while building resilience—each failure becomes a learning event that strengthens the pipeline against similar future failures.

Document lessons from each failure using failure classification and root-cause extraction. The Skill merges new insights efficiently without context overflow, so each lesson learned persists and applies automatically to future tasks, stopping repeat errors.

Failure analysis goes beyond logging by extracting root causes and formulating actionable lessons stored as bounded delta items. Error logging records what happened; failure analysis explains why and captures the corrective insight, enabling active learning and resilience-building.