What problem does it solve? After an epic ships, no single coding session saw the whole change, so cross-story defects, god-class growth, and spec drift go unnoticed. This Skill reads the evidence an epic left behind — specs, story files, diffs, commits, sprint status — and produces a sourced retrospective with an honest acceptance verdict. ## Core Features & Use Cases - Evidence-based analysis: Gathers the epic spec, story files, diff range, and per-story commits via deterministic scripts, then derives aggregate views like architecture delta, duplication maps, and spec-to-implementation reconciliation. - Acceptance verdict: Judges the epic against declared or profiled acceptance criteria as accepted, accepted-with-open-items, or rejected, with unfinished stories forcing a machine verdict of rejected. - Sprint-status integration: Updates sprint-status.yaml atomically with comment preservation, appending owned action items and validating every write with rollback on failure. - Use Case: After an unattended multi-story epic run finishes, ask for a retrospective to get a document listing every finding with its file, line, or commit source, plus routed action items and a verdict an orchestrator can gate the next epic on. ## Quick Start Run a retrospective on epic 3 and tell me whether it passed its acceptance criteria.
