What problem does it solve? After an epic finishes, teams lack a structured way to judge what actually shipped: defects that no single story review could catch, unfinished stories, and unverified claims about quality. This Skill reads the evidence an epic left behind — spec, story files, diffs, commits, sprint status — and produces a retrospective where every finding carries a source reference. ## Core Features & Use Cases - Evidence-based analysis: Gathers the epic spec, story files, diff range, per-story commits, and sprint status, then derives aggregate views (architecture delta, duplication map, god-class growth, spec-to-implementation reconciliation) via deterministic scripts. - Acceptance verdict: Judges the epic against declared or profiled acceptance criteria and renders accepted, accepted-with-open-items, or rejected, with unfinished stories forcing a machine verdict of rejected. - Sprint status integration: Updates sprint-status.yaml safely through a comment-preserving, atomic-write script that appends action items and marks the retrospective done. - Use Case: After an unattended multi-story epic run, ask for a retrospective to get a document listing sourced findings, routed action items with owners, follow-through on the previous epic's action items, and an honest acceptance verdict. ## Quick Start Ask the assistant to run a retrospective on the epic you just completed, for example by saying run a retrospective on epic 3.
