What problem does it solve?
Turning a change request into verified, reviewed code normally requires constant human supervision of an AI coding session. This Skill automates one full unattended development loop: it clarifies intent, writes a development-ready spec, implements it via a subagent, and runs multiple independent review layers before committing.
Core Features & Use Cases
- Intent-to-Spec Planning: Resolves the invocation intent (free-form text, story ID, or existing spec file), loads planning artifacts like PRDs and architecture docs, and produces a structured spec with an intent contract, code map, tasks, and acceptance criteria.
- Autonomous Implementation and Verification: Hands the spec to a context-free implementation subagent, stages a unified diff, runs the spec's verification commands, and audits that every I/O edge-case matrix row has a passing test.
- Multi-Layer Automated Review: Launches parallel reviewer subagents (blind hunter, edge-case hunter, verification-gap reviewer, intent-alignment auditor), triages every finding into intent_gap, bad_spec, patch, or defer routes, and loops back to re-derive code when the spec is at fault.
- Use Case: Point it at a story in an epic's stories.yaml file; it compiles epic context, plans, implements, reviews, fixes, and commits the change, halting with a structured status (done, blocked, ready-for-dev) and a full audit trail in the spec file.
Quick Start
Invoke bmad-build-auto with a description of the change you want, such as asking it to implement a specific story or fix, and let it run the full unattended loop to completion.
