BMad Method for Claude Cowork — AI-driven agile development with specialized agents, structured workflows, and test architecture. Includes BMM (core dev lifecycle), BMB (agent/workflow builder), and TEA (test engineering architect) modules.
npx claudepluginhub bspann/bmad-cowork --plugin bmad-coworkQuick Flow: streamlined spec-build-review for bug fixes and small features.
Create system architecture from an approved PRD. Phase 3 (Solutioning).
Create a project brief from a product idea. Phase 1 (Analysis).
Implement a story using red-green-refactor TDD. Phase 4.
Break architecture into epics and stories with acceptance criteria. Phase 3.
Get guidance on what to do next in the BMad workflow.
Initialize a new project for BMad workflows. Creates _bmad/ directory, config, and status tracking.
Create a Product Requirements Document from an approved project brief. Phase 2 (Planning).
Run implementation readiness check. GO/NO-GO gate between planning and building.
Run sprint retrospective. Phase 4.
Run adversarial code review on a completed story. Phase 4.
Create sprint plan and sprint-status.yaml. Transitions to Phase 4.
Show current project and sprint status.
Create UX design specifications. Optional Phase 3 workflow.
Use when exploring a product idea, creating a project brief, or conducting discovery research. Specializes in market analysis, problem-space exploration, and translating vague ideas into structured briefs. Trigger with: "analyze my idea", "create a project brief", "explore this concept", "discovery research"
Use when designing system architecture, selecting tech stack, defining data models, or creating API contracts. Specializes in translating PRDs into technical architecture documents. Trigger with: "create architecture", "design system", "tech stack", "data model", "API design"
Use when creating custom BMad agents, workflows, or modules. The meta-agent that extends the BMad ecosystem. Trigger with: "create agent", "create workflow", "build module", "extend BMad", "custom agent"
Use when reviewing code for quality, correctness, security, and adherence to architecture. Adversarial reviewer that finds 3-10 issues minimum per review. Trigger with: "code review", "review code", "review story", "review PR"
Use when implementing stories, writing code, creating tests, or fixing bugs. Follows red-green-refactor TDD methodology with task-by-task verification. Trigger with: "implement story", "dev story", "write code", "implement feature", "fix bug"
Use when creating a PRD, defining requirements, user journeys, or functional specifications. Specializes in translating project briefs into detailed product requirements documents. Trigger with: "create PRD", "define requirements", "product requirements", "user journeys"
Use for bug fixes, small features, rapid prototyping, or well-understood work that doesn't need full planning phases. Combines tech spec + implementation + review in a single streamlined workflow. Trigger with: "quick fix", "small feature", "bug fix", "rapid prototype", "quick dev", "quick flow"
Use when creating epics, stories, sprint plans, or tracking implementation progress. Specializes in breaking architecture into implementable work units with acceptance criteria. Trigger with: "create epics", "create stories", "sprint planning", "story status", "sprint status"
Use when creating test strategies, designing test architectures, setting up test frameworks, writing ATDD specs, automating tests, assessing NFRs, configuring CI pipelines, or making release gate decisions. TEA spans Phase 3 (solutioning) and Phase 4 (implementation). Trigger with: "test strategy", "test design", "test automation", "ATDD", "release gate", "test review", "CI pipeline", "NFR assessment"
Use when creating or updating project documentation, API docs, user guides, or README files. Trigger with: "write docs", "document project", "API documentation", "user guide", "README"
Use when creating UX designs, screen layouts, user flows, component specifications, or design systems. Trigger with: "UX design", "wireframe", "user flow", "design spec", "screen layout", "component design"
Design system architecture from an approved PRD. Phase 3 (Solutioning).
Create a project brief from a product idea. Phase 1 (Analysis) of the BMad Method.
Design and create a new custom BMad agent with persona, expertise, and workflows.
Create a complete BMad module packaging agents, workflows, and knowledge together.
Design and create a new BMad workflow with steps, templates, and checklists.
Handle mid-implementation changes: scope shifts, architecture issues, or requirement changes.
Prepare a detailed story file for implementation with tasks and acceptance criteria.
Implement a story using red-green-refactor TDD. Task-by-task with test verification.
Break architecture into implementable epics and stories with acceptance criteria. Phase 3.
Interactive BMad guide. Shows current project status and recommends the next workflow to run.
Initialize a project for BMad workflows. Creates _bmad/ directory, config, and status tracking.
Create a Product Requirements Document from an approved project brief. Phase 2 (Planning).
Quick flow for bug fixes and small features. Combines spec, build, and review in one workflow.
GO/NO-GO readiness check before starting implementation. Gate between planning and building.
Sprint retrospective. Reflect on what went well, what didn't, and plan improvements.
Adversarial code review that finds 3-10 issues minimum. APPROVE or REQUEST_CHANGES.
Create sprint-status.yaml and plan the first sprint. Transition from planning to implementation.
Check current project status across all phases. Shows completed work and next actions.
Write Acceptance Test-Driven Development specifications before implementation.
Implement test automation for features. The most commonly used TEA workflow.
Configure CI/CD pipeline testing stages, quality gates, and artifact collection.
Set up test framework and infrastructure. Run once in Phase 3 after architecture.
Assess non-functional requirements: performance, security, accessibility, reliability.
TEA Academy - interactive testing education across 7 progressive sessions.
Create risk-based test designs at system level (Phase 3) or per-epic (Phase 4).
Audit test quality and identify coverage gaps. Optional Phase 4 workflow.
Traceability matrix and evidence-backed release gate GO/NO-GO decisions.
Create UX design specifications including screens, flows, and components. Phase 3 (optional).
Battle-tested Claude Code plugin for engineering teams — 38 agents, 156 skills, 72 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.