Improve System — the measured improvement loop Mine the system's own correction history for recurring failure patterns, trend the rejection-rate metric, and propose targeted edits. Propose, never auto-apply. This is the auto-research loop adapted for non-measurable work: chat-history corrections are the proxy signal, qa-rejection rate is the trend metric (video-insights improvement #5, 2026-06-12). Scope boundary - finds specific bugs and drift to fix once. finds recurring behavioural patterns across runs and turns them into standing rules. - consolidates agent overlays into skill diffs (3+ r…