The BMAD Method skill integrates auto-detection, memory, and slash commands into Claude Code. It enables developers to use agile development methodologies with AI assistance. The skill connects to Claude Code and enhances development workflows.
git clone https://github.com/aj-geddes/claude-code-bmad-skills.gitBMAD Method v6 transforms Claude Code into a complete agile development environment by integrating nine specialized skills—including Business Analyst, Product Manager, System Architect, and Developer agents—with fifteen structured workflow commands. The methodology optimizes token usage by 70-85% through a helper pattern approach while providing native Claude Code integration without external dependencies. It guides development through five phases: product discovery, requirements planning, system architecture, sprint planning, and implementation, with additional modules for custom agent creation, creative intelligence, and UX design. Teams benefit from reduced context switching, standardized agile processes, and AI-assisted workflows that maintain consistency across projects. The skill works cross-platform on Windows, Linux, macOS, and WSL with automatic platform detection during installation.
["Install the BMAD skill in your Claude Code environment by running `claude plugins install bmad` in your terminal.","Navigate to your project root and run `/detect` to scan the repository structure. Review the output to identify key areas needing attention.","Use `/memory` to load relevant context files (e.g., `README.md`, `package.json`, or custom config files). Specify files with `/memory load [file_path]` or load all with `/memory load-all`.","Execute `/agile` followed by your specific task (e.g., `/agile refactor [component]`). Use `/agile metrics [metric]` to track progress against goals.","Review the generated artifacts (code changes, documentation, test files) and commit them to your version control system. Use `/agile log` to generate a summary report for your team."]
Initialize new projects with structured product discovery and requirements gathering using /product-brief and /prd commands
Plan and execute development sprints with /sprint-planning and /create-story for user story generation
Design system architecture using the System Architect agent before implementation begins
Create custom agents and workflows for team-specific processes with the Builder module
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/aj-geddes/claude-code-bmad-skillsCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Use the BMAD Method with Claude Code to [TASK]. Start with `/detect` to analyze the repository structure and identify [FOCUS_AREAS]. Then use `/memory` to load relevant context from [CONTEXT_FILES]. Finally, execute `/agile` to generate and implement [DELIVERABLE] while maintaining [METRICS]. Document all steps in [LOG_FILE].
### BMAD Method Execution Report **Project:** Acme Corp E-commerce Platform **Task:** Refactor legacy checkout flow to reduce latency by 30% **Step 1: Repository Detection (/detect)** Analyzed 47 files across `/src`, `/tests`, and `/config`. Identified 12 files in `/src/checkout` with average complexity score of 7.2/10. Highlighted `PaymentProcessor.js` (1500 lines) and `CartService.js` (800 lines) as primary bottlenecks. **Step 2: Context Loading (/memory)** Loaded: - `checkout_architecture.md` (last updated 2 weeks ago) - `performance_metrics.json` (showing 4.2s avg checkout time) - `tech_debt_report.csv` (flagging 8 critical issues) **Step 3: Agile Execution (/agile)** Generated 3 sprint tasks: 1. Split `PaymentProcessor.js` into `PaymentGateway.js` and `FraudDetection.js` (estimated 2 days) 2. Implement Redis caching for cart sessions (estimated 1 day) 3. Add load testing with k6 (estimated 0.5 days) **Metrics Tracked:** - Code coverage: 85% → 92% (+7%) - Latency: 4.2s → 2.9s (-31%) - Cyclomatic complexity: 7.2 → 4.1 (-43%) **Deliverables:** - `/src/checkout/services/` (new directory) - `checkout_refactor.md` (documentation) - `performance_after_refactor.json` (validation data) All changes committed to `feature/checkout-refactor` branch with PR #1245 ready for review.
AI assistant built for thoughtful, nuanced conversation
Get more done every day with Microsoft Teams – powered by AI
Automate security compliance and monitor real-time security posture seamlessly.
Automate your spreadsheet tasks with AI power
Agentic AI Workflow platform
Connected workspace for docs, wikis, and projects
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan