What problem does it solve? Turning a feature request or bug report into verified, reviewed code usually requires juggling planning, implementation, and review by hand. This Skill structures that entire cycle: it clarifies intent, writes a bounded specification, delegates implementation, and runs multi-layer code review before committing. ## Core Features & Use Cases - Spec-driven implementation: Converts user intent into a token-bounded spec file with intent, boundaries, I/O edge-case matrices, tasks, and acceptance criteria, then implements from that spec as the sole source of truth. - Multi-layer automated review: Runs parallel review layers (blind hunter, edge-case hunter, verification-gap) over the staged diff, triages every finding with verdicts, and routes fixes through patch, spec amendment, or deferral. - Epic story support: Compiles focused epic context from planning artifacts (PRD, architecture, UX) and syncs sprint status for story-based work. - Use Case: Hand the Skill a story like "implement story 3-2 digest delivery" and it loads the epic context, drafts a spec for your approval, implements via a subagent, reviews the diff with three reviewer passes, and commits the verified result. ## Quick Start Ask the assistant to use the bmad-build skill to implement your feature request, story, or bug fix and let it guide you through spec approval and review.
