ros/BMAD-METHOD
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

massive update and guidance.

Browse Source
This commit is contained in:
Brian Madison
2025-04-16 22:13:31 -05:00
parent cb602a3fe5
commit 64f9a9c3f8
12 changed files with 329 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
README.md
View File

@@ -6,15 +6,15 @@ Join in on the [Community Discussion Forum](https://github.com/bmadcode/BMAD-MET
Also check out [Part 1 on the BMad Code YouTube channel](https://youtu.be/JbhiLUY_V2U) - feel free to comment, like, and subscribe also for future videos and updates.
**Super Quick TLDR:** These are [the prompts](./ai-pm/prompts/) you have been searching for!
**Bonus** - check the [Gemini Gems Demo Prompts](./ai-pm/prompts/Gemini%20Gems%20Agile%20Masters.md) for a set of Google Gemini Gems to use with this workflow! Optional and a totally different fun experience. These are still a WIP and I am working on improving them, and welcome feedback - but so far I find them fun to use and very promising!
Note: Depending on which tool you use - the [[prompts folder]](./ai-pm/prompts/) should be set to be ignored my your LLM codebase indexing (ie with cursor add them to .cursorindexingignore - cline and roo may differ).
## Overview
The BMad Method is a (not so) revolutionary approach to software development that leverages AI-driven processes to accelerate and enhance the entire product development lifecycle. This template provides a structured framework that guides you through generating all necessary artifacts to build a complete application with AI assistance.
The BMad Method is a (not so) revolutionary approach to software development that leverages AI-driven processes to accelerate and enhance the entire product development lifecycle from ideation and market fit, through agentic code implementation.
The method is meant to be tool agnostic including a workflow built into the role-prompts. It is a somewhat manual workflow that can be used in multiple ways.
It can easily be adapted to specifics of any agentic coding toolset, ide and platform.
## What is the BMad Method?
@@ -47,8 +47,8 @@ The BMad Method follows a structured workflow:
## Prompt Sequence
The `ai-pm/prompts` folder contains carefully crafted prompts for each phase of development.
This is for the most broadly ambitious project MVP - see the simplified prompts
The `prompts` folder contains carefully crafted prompts for each phase of development.
This is for the most broadly ambitious project MVP
1. **Research Assistant: Analysis** (`0-research-assistant.md`): Optional deep research on your product concept
2. **Business Analyst: Project Brief** (`1-business-analyst.md`): Define your product idea and MVP scope
@@ -57,9 +57,7 @@ This is for the most broadly ambitious project MVP - see the simplified prompts
5. **Architecture Deep Research: PRD Updates** (`4-Arch-Deep.md`): Optional deep research step for Up tp date best practice and rules generation
6. **Architect: Arch Doc** (`5-Arch.md`): Create a detailed architectural blueprint
7. **Technical Product Owner: Epic Story List** (`6-PO.md`): Break down requirements into implementable stories
8. **Technical Scrum Master: Agent Story Files** (`7-SM.md`): Transform stories into Dev Agent ready super detailed stories
There is a OPTIONAL final prompt (`8-SM-IDE.md`) - use this in your IDE with the selected agent to split up item 7 into the individual files for the ToDo folder (assuming you did not modify prompt 7 to generate the files individually within the IDE or external tool.)
8. **Technical Scrum Master: Agent Story Files** (`7-SM.md`): Transform stories into Dev Agent ready super detailed stories (it is not recommended to generate all stories with this up front - instead favor using the /role-prompts/dev.md agent with builtin workflow to craft story 1 by 1 as needed to implement.)
## Key Benefits
@@ -69,27 +67,32 @@ There is a OPTIONAL final prompt (`8-SM-IDE.md`) - use this in your IDE with the
- **Reduced Technical Debt**: Ensure architectural consistency from the start
- **Simplified Collaboration**: Clear artifacts for all stakeholders, Human and AI
## Quick How To
## How To
Recommend checking out this video series starting with [Part 1 on the BMad Code YouTube channel](https://youtu.be/JbhiLUY_V2U) and also checking the [Discussion Forum](https://github.com/bmadcode/BMAD-METHOD/discussions) in the coming days where BMad and the community hopefully will share and collaborate and give further tweaks tips and tricks!
But the **Quick and Dirt**y is:
1. Clone this project
2. Start with the first prompt in `ai-pm/prompts/0-research-assistant.md` (or skip to 1 if research isn't needed)
2. Start with the first prompt in `prompts/0-research-assistant.md` (or skip to 1 if research isn't needed) to do market research with an LLM's deep research capabilities
3. Follow each prompt in sequence, providing output from previous steps as context to the new prompt when indicated in the current prompt
4. Once all stories are drafted by the final prompts of the SM, move generated stories through the Kanban folders as they are implemented - meaning drag the first story to InProgress, start a Agent chat and direct it to that story. Optionally, use the sample workflow (coming soon) to automate (I prefer the manual nature of dragging each item).
5. Track progress until all stories are in the `3-Done` folder
4. One the PO generates the final story list, paste it back into the PRD.
5. Generate each detailed user story and implement it 1 by 1. The stories serve as the memory system and history of incremental agile development.
6. Track progress until all stories are completed to realize the MVP.
My recommendation is to take advantage of Google Gemini or ChatGPT apps, it is very economical and better in some regards.
My recommendation is to take advantage of Google Gemini or ChatGPT web apps for generation of deep research brain storming, PRD, and deep research for the architecture if needed. Beyond that, its easy enough to take the pieces of artifacts needed to put the markdown into the project ai folder, and then use prompts from within the IDE to generate the file architecture, story list updates to the PRD from the PO, and eventual story generation.
For example with Gemini its easy to group and also create google docs from the canvas feature. I like their web interface. And it gives access to its amazing Deep Research platform, expanded NotebookLM capabilities etc.. But you can also use OpenAI, Claude, Grok or do it all also within the IDE.
## Modifications
If you have a subscription to one of those or even free tier access to the best models like Gemini 2.5 or OpenAIs deep research web ui - might as well take advantage of it - it can save you lots of LLM credits, and produce IMO better results for the artifacts.
This is just an idea of what works for me to increamentally build up complex applications from idea to inception. But I use variants of this to work in existing code bases, where I will lay out a PRD with task lists and use the architecture document to put in place guardrails and further details the LLM needs to understand if it is not already in place.
Similar idea if you use the optional UX prompt, take advantage of free tier V0 or similar products to past in the produce prompt to quick start complex UI's.
The sharing of all these prompts are just suggestions - I HIGHLY recommend you use these ideas to tweak and refine what works for you! Experiment with different models, and over time they will improve.
Either way, ensure you are adding all of the artifacts to the ai-pm folder (or another folder of your choice) for your new project.
For small projects, just a PRD and the story files can be more than sufficient. And for more ambitious or unknowns, use the brainstorming step and deep research to help you out.
Valid produce artifacts for the application such as source trees, rules, architecture documentation can provide value beyond the initial implementation of the task at hand can can live with the project, usually moved into the docs folder, and also rules can be added to CONTRIBUTING.md. By putting rules in this file, it can be used by humans and ai tools.
For example in cursor, with a good contributing file, you can have an always rule to always reference the contributing.md file for its core rule set. And then if you use Cline or CoPilot, you can do similar with their rule systems or agent custom instructions.
## Future Enhancements