bmad-build

Implements user intents as code through a plan, implement, review, and present workflow.

1|Updated Jun 2, 2026
One-click install
npx skills add https://github.com/SevWren/Daily-Motivation-Brain-Helper --skill bmad-build-sevwren
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bmad-build
Source: https://github.com/SevWren/Daily-Motivation-Brain-Helper/tree/main/.claude/skills/bmad-build
Command: npx skills add https://github.com/SevWren/Daily-Motivation-Brain-Helper --skill bmad-build-sevwren

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Turning a feature request, bug fix, or change request into working code often skips planning, review, and verification, producing inconsistent results. This Skill enforces a disciplined multi-step workflow that converts any user intent into a reviewed, tested, and committed code change that follows the project's existing architecture and conventions. ## Core Features & Use Cases - Spec-driven implementation: Clarifies intent, investigates the codebase, and writes a structured spec file with a code map, tasks, and acceptance criteria before any code changes. - Dual routing: Routes zero-blast-radius changes through a fast one-shot path and everything else through a full plan-code-review pipeline with human approval checkpoints. - Adversarial review layers: Runs parallel review subagents (blind hunter, edge-case hunter, verification-gap reviewer) and triages findings into intent gaps, spec fixes, patches, or deferred work. - Use Case: Ask it to add a new API endpoint; it drafts a spec, gets your approval, implements via a subagent, reviews the diff for edge cases and missing tests, then commits with a suggested review order. ## Quick Start Ask the assistant to implement a feature or fix a bug, for example: use bmad-build to add pagination to the project list endpoint.

Frequently Asked Questions about bmad-build

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I implement a feature from a user story with an AI coding workflow?

Provide the story or intent and the workflow clarifies it, investigates the codebase, writes a spec with tasks and acceptance criteria, then implements and reviews the change. Epic stories automatically load compiled epic context and sync sprint status.

What is the difference between the one-shot and plan-code-review routes?

One-shot handles zero-blast-radius changes with clear intent and no architectural decisions, implementing directly with a lighter review. Plan-code-review covers everything else with a full spec, human approval checkpoint, implementation subagent, and multi-layer review.

Does this workflow require subagent support in the AI runtime?

Subagents are used for codebase investigation, implementation, and review layers, but fallbacks exist. Without subagent support, implementation happens directly and review prompts are written to files for the user to run in separate sessions.

How does the review step handle findings it disagrees with?

Findings are deduplicated, assigned severity by consequence, and triaged into intent gaps, spec problems, patches, deferred items, or rejections. Only patches are auto-fixed; intent and spec problems trigger loopbacks, and noise is dropped silently.

What happens when a spec exceeds the recommended token limit?

Specs target 900-1600 tokens. If a spec exceeds 1600 tokens, the workflow halts and asks whether to split secondary goals into deferred-work entries or keep the full spec, since oversized specs risk context rot in implementation agents.