What problem does it solve? It automates a full development iteration without human interaction: turning an invocation intent into a specification, implementing it via a subagent, and running layered code reviews with triage, patching, and loopback until the work converges or halts with a clear status. ## Core Features & Use Cases - Intent routing and planning: Resolves intent from prompts, spec files, or folder+id story dispatch, compiles epic context from planning artifacts, and writes a ready-for-development spec from a template. - Subagent implementation and verification: Hands the spec to a context-free implementation subagent, stages a unified diff, runs verification commands, and audits I/O matrix test coverage. - Multi-layer review with triage: Runs blind-hunter, edge-case, verification-gap, and intent-alignment review layers, classifies findings into intent_gap, bad_spec, patch, or defer, and loops back through re-implementation when needed. - Use Case: Point it at a story in stories.yaml and it plans, implements, reviews, commits, and writes the run result into the story spec, halting with a blocking condition if anything cannot be resolved. ## Quick Start Invoke the bmad-build-auto skill with a description of the change you want implemented or a story id from your spec folder.
