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

more clarity in the instructions for new users

Browse Source
This commit is contained in:
Brian Madison
2025-05-03 18:44:43 -05:00
parent e836336fef
commit 8c06be3fb0
2 changed files with 23 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
CURRENT-V2/gems-and-gpts/instruction.md
View File

@@ -29,6 +29,7 @@
### PO + SM
- Instructions: 4-po-sm-gem.md pasted into instructions
- Knowledge: story-template.txt
- This is optional as a Gem - unlike the workflow within the IDE, using this will generate all remaining stories as one output, instead generating each story when its ready to be worked on through completion. There is ONE main use case for this beyond the obvious generating the artifacts to work on one at a time.
- The output of this can easily be passed to a new chat with this PO + SM gem or custom GPT and asked to deeply think or analyze through all of the extensive details to spot potential issues gaps, or inconsistences. I have not done this as I prefer to just generate and build 1 story at a time - so the utility of this I have not fully exhausted - but its an interesting idea.
- Knowledge: story-template.txt

35
README.md
View File

@@ -60,15 +60,24 @@ Join the [Community Discussion Forum](https://github.com/bmadcode/BMAD-METHOD/di
2. The BA will help analyze market conditions and competitors
3. Output is a **Project Brief** used as input for the Product Manager
If you are unsure, start by saying something like the following to brainstorm with the BA with this simple goal eliciting prompt:
- I have an idea for an app I want to brainstorm with you,
- it can do (X)
- so that (y)
- for (Z) user(s)
**Example:** 'I have an idea for an app I want to brainstorm with you, it can **help small business owners automatically** generate professional social media content, so that they can **maintain consistent online presence without hiring expensive marketing agencies**, for **time-starved entrepreneurs** who know social media is important but don't have the skills or time to create quality content daily'
### Phase 1: Product Definition
1. The **Product Manager (PM)** agent takes the project brief or your idea
2. PM creates a comprehensive Product Requirements Document (PRD)
2. PM creates a comprehensive Product Requirements Document (PRD) along with high level epic / story flow docs. (Separate files reduce overall context for future agents - this is in the V2+ version)
3. Initial epic breakdowns are drafted
### Phase 2: Technical Design
1. The **Architect** agent reviews the PRD and creates an architecture document
1. The **Architect** agent reviews the PRD and creates an architecture document and in V2 granular artifacts that optimize for LLM context space of chosen future agents!
2. Architect identifies technical dependencies and reference files
3. Optional: Use Deep Research mode for more in-depth technical exploration
@@ -80,8 +89,7 @@ Join the [Community Discussion Forum](https://github.com/bmadcode/BMAD-METHOD/di
### Phase 4: Story Generation
1. **Technical Scrum Master** generates stories using the story template
2. Each story has clear acceptance criteria and technical details
1. **Technical Scrum Master** generates each story 1 at a time for the dev to complete, (OR in Gem/GPT mode it will do all remaining stories). The output story or stories are highly detailed stories with all technical details the agent will need to keep instructional context lean - not having to search all of the larger documents bloating its context with unnecessary information.
### Phase 5: Development
@@ -91,10 +99,16 @@ Join the [Community Discussion Forum](https://github.com/bmadcode/BMAD-METHOD/di
### Phase 6: Review and Acceptance
1. Code reviews by Tech SM/Architect
1. Code reviews by a new Dev Agent or Architect
2. Functionality reviews by User/QA
3. Story marked as Done when approved
### Phase 6.5: Refactor (Optional Step)
1. Architect or Dev Agent in a new Content, or the User, refactor as needed and ensure if refactor changes structure that source tree diagrams and future implementation documents are updated as needed.
2. This is not required after most stories with properly following the phases before #5 producing a solid plan and architecture - but even the best plans can lead to the emergence of an idea for beautiful restructuring. Also, best laid plans can still lead to an agent doing less than ideal things that are better to correct.
3. Remember, the main key with refactoring at this stage is ensure all was working first, the full app and new functionality has passing tests and linting, has been committed, and pushed to the remote branch. Only then would I take on a major (or even minor refactor) in most cases. If I am doing the refactor myself, I have more trust and might do it before pushing and calling the story done. But with the agent, always lock down your working changes so you have an escape hatch to revert to!
### Phase 7: Deployment
1. Developer Agent handles deployments
@@ -109,20 +123,15 @@ Join the [Community Discussion Forum](https://github.com/bmadcode/BMAD-METHOD/di
- `story-template.md`
- `prd.md`
- `project-brief.md`
- And more specific templates for various document types
- etc... (all of the template files)
## Custom GEMs and GPTs
## Custom GEMs and GPTs (Highly Recommended)
**Using Agents with Web-Based AI Interfaces (Highly recommended, save lots of money, larger context windows, deep research is a game changer)**
The [gems folder](./CURRENT-V2/gems-and-gpts/) contains agent instructions embedded with optimized web use instructions - streamlined for usage within the [Gemini Gems](https://gemini.google.com/gems/create), or [OpenAIs custom GPT's](https://chatgpt.com/gpts/editor). With both custom GPTs and Gemini Gems, you will attach the templates now instead of embedding them (as was the case with V1 of this system, that was not as easy to modify). This way, as you modify templates from the templates folder, if you want to change it in the web version just save it as a .txt extension and attach to the custom GEM or GPT.
## Getting Started
1. Clone this repository
2. Set up your AI assistant custom agents in your IDE OR (recommended) some of them in Gemini
3. Start with the BA or PM agent depending on how well-defined your idea is
4. Follow the workflow phases sequentially until you have your epics all lined up and you (and the PO) are happy with the proposed epic sequence.
[Detailed set up and usage instructions](./CURRENT-V2/gems-and-gpts/instruction.md) are available in the folder also.
## IDE Integration