$ show bmad-code-org/BMAD-METHOD
The BMAD Method is an AI-assisted software development framework that provides a modular set of skills (workflows) to guide AI agents and humans through the entire development lifecycle. Each skill is a self-contained unit that can be invoked to perform specific tasks such as brainstorming, creating product requirements, designing architecture, implementing features, reviewing code, and conducting retrospectives. The framework maintains project context in `AGENTS.md` to ensure AI alignment with project-specific rules and supports deep customization via layered TOML configuration. Built for integration with AI-powered IDEs (like Claude Code, Cursor), the system emphasizes evidence-based practices, including validation lenses, memlog-based session tracking, and ticketing integration for work tracking. It also offers web bundle exports for deploying skills as Gemini Gems or ChatGPT Custom GPTs. The architecture features a clean separation of concerns, with skills encapsulating their own documentation, scripts, assets, and tests, while shared utilities handle configuration resolution, memlog logging, and validation. The project demonstrates strong engineering practices through automated validation tools, multi-language documentation, and a structured release process. While it manages complexity through modularity, users should be aware of maintenance risks such as duplicated validation text across skills and the need to place customizations in override directories to prevent loss during updates. Overall, the BMAD Method provides a robust, reusable toolkit for teams seeking to institutionalize AI-assisted development workflows.
The LLM identified 4 files worth highlighting for reuse:
An append-only log for recording session data (ideas, techniques, insights, outcomes, callbacks, moments) used by multiple skills to persist data across runs. It is self-contained, depends only on the filesystem and config utilities, and demonstrates non-obvious skill in structuring entries and providing a distillation step to produce artifacts. This pattern can be extracted for any project needing structured, chronological logging for AI-assisted workflows.
Handles layered TOML merging (skill defaults → team → user → skill-specific overrides) with support for scalar overrides, table deep merges, and keyed array-of-tables. This utility is isolated, reusable in any project needing hierarchical configuration, and demonstrates non-obvious skill in managing complex merge strategies while maintaining type safety and clarity.
Core logic for loading, resolving, and managing a ticket tree from TOML breakdowns and markdown files. It includes dependency resolution (sibling, epic, file, tracker IDs), cycle detection, state computation, and CLI commands. While tied to BMAD ticketing structure, the patterns for reference resolution, dependency graph building, and state determination are reusable in other ticketing or workflow systems.
Validates skill directories against 10 deterministic rules (existence of required files, manifest validity, content quality, etc.). This tool is self-contained, could be applied to any modular system to ensure component quality, and demonstrates non-obvious skill in automating comprehensive checks while providing clear, actionable feedback.