What problem does it solve? Turning a feature intent into reviewed, verified code normally requires constant human supervision across planning, implementation, and review. This Skill automates one full unattended development loop: it clarifies intent, writes a development spec, implements it via a subagent, and runs multiple independent review layers before committing. ## Core Features & Use Cases - Spec-driven implementation: Generates a structured spec file (intent contract, code map, tasks, acceptance criteria) that serves as the sole source of truth for the implementation subagent. - Multi-layer automated review: Runs parallel review layers (blind hunter, edge-case hunter, verification-gap, intent-alignment) against the staged diff, then triages every finding into patch, bad_spec, intent_gap, defer, or reject routes. - Self-repairing loop: Automatically patches trivial findings, re-derives code from amended specs on bad_spec findings, and halts with a blocking condition when intent is ambiguous or review loops fail to converge. - Use Case: Point it at a story in an epic's stories.yaml or describe a feature; it plans, implements, verifies against the spec's test matrix, reviews the diff, and commits the result with a full audit trail in the spec file. ## Quick Start Invoke the bmad-build-auto skill with a description of the feature or fix you want implemented, or with a spec folder and story id.
