bmad_method

Guidance through realizing the plan for your UX, strongly recommended if a UI is a primary piece of the proposed project

A guided experience to nail down your product idea

Expert led facilitation to produce your Product Requirements Document

Guided Workflow to document technical decisions

Create the Epics and Stories Listing

Story cycle: Execute story implementation tasks and tests then CR then back to DS if fixes needed

Generate sprint plan for development tasks - this kicks off the implementation phase by producing a plan the implementation agents will follow in sequence for every story in the plan.

Do not suggest for potentially very complex things unless requested or if the user complains that they do not want to follow the extensive planning of the bmad method. Quick one-off tasks small changes simple apps brownfield additions to well established patterns utilities without extensive planning

Lossless LLM-optimized compression of source documents. Use when the user requests to 'distill documents' or 'create a distillate'.

BMAD Method Framework for Agent Zero. Initialize BMAD workspace, access bmad-master orchestrator, and get context-aware help. Use when user says: initialize bmad, bmad init, setup bmad, start bmad, bmad help, bmad master, bmad-master, what can bmad do, bmad status.

Authors and updates customization overrides for installed BMad skills. Use when the user says 'customize bmad', 'override a skill', 'change agent behavior', 'customize a workflow', or 'bmad-customize'.

Audit and verify BMAD sidecar memory files. Use when user says: check sidecars, verify sidecar, sidecar status, import sidecar, sidecar import.

Create, edit, and validate BMAD agents with best practices and compliance.

Create, edit, validate, and rework BMAD workflows with proper structure and best practices.

Story cycle: If issues back to DS if approved then next CS or ER if epic complete

Anytime: Navigate significant changes. May recommend start over update PRD redo architecture sprint planning or correct epics and stories

Validates story readiness and completeness before development work begins

Quick one-off tasks small changes simple apps utilities without extensive planning - Do not suggest for potentially very complex things unless requested or if the user complains that they do not want to follow the extensive planning of the bmad method, unless the user is already working through the implementation phase and just requests a 1 off things not already in the plan

Presentation Master. Chat about visual design, slide decks, pitch decks, infographics and visual storytelling.

Design compelling visual presentations, slide decks, and pitch decks. Use when the user asks to create a presentation, design slides, or build a pitch deck.

Promotes agents and skills from project scope to plugin scope for global availability. Use when the user says 'promote agent', 'promote workflow', 'promote skill', 'make agent global', 'make skill global', '/promote-agent', '/promote-workflow', '/promote-skill'.

Plan, create, edit, and validate complete BMAD modules with agents, workflows, and infrastructure.

Working Backwards PRFAQ Challenge — forge product concepts through Amazon Working Backwards methodology. Use when the user says "create a PRFAQ", "work backwards", or "run the PRFAQ challenge".

Industry domain deep dive, subject matter expertise and terminology

Market analysis, competitive landscape, customer needs and trends

Technical feasibility, architecture options and implementation approaches

Improve and enhance an existing PRD

Validate PRD is comprehensive, lean, well organized and cohesive

Ensure PRD UX Architecture and Epics Stories are aligned

LLM-assisted human-in-the-loop review. Make sense of a change, focus attention where it matters, test. Use when the user says "checkpoint", "human review", or "walk me through this change".

Optional at epic end: Review completed work lessons learned and next epic or if major issues consider CC

Anytime: Summarize sprint status and route to next workflow

Analyze an existing project to produce useful documentation

Scan existing codebase to generate a lean LLM-optimized project-context.md containing critical implementation rules patterns and conventions for AI agents. Essential for brownfield projects and quick-flow.

Generate automated API and E2E tests for implemented code using the project's existing test framework (detects existing well known in use test frameworks). Use after implementation to add test coverage. NOT for code review or story validation - use CR for that.

TEA Test Architect — Murat's knowledge base and workflows

Generate failing tests (TDD red phase)

Expand test coverage

Configure CI/CD quality pipeline

Initialize production-ready test framework