feat(docs): Diataxis restructure + Astro/Starlight migration (#1263)

* feat(docs): add Diataxis folder structure and update sidebar styling

- Create tutorials, how-to, explanation, reference directories with subdirectories
- Add index.md files for each main Diataxis section
- Update homepage with Diataxis card navigation layout
- Implement clean React Native-inspired sidebar styling
- Convert sidebar to autogenerated for both Diataxis and legacy sections
- Update docusaurus config with dark mode default and navbar changes

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* feat(docs): migrate Phase 1 files to Diataxis structure

Move 21 files to new locations:
- Tutorials: quick-start guides, agent creation guide
- How-To: installation, customization, workflows
- Explanation: core concepts, features, game-dev, builder
- Reference: merged glossary from BMM and BMGD

Also:
- Copy images to new locations
- Update internal links via migration script (73 links updated)
- Build verified successfully

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix(docs): add category labels for sidebar folders

Add _category_.json files to control display labels and position
for autogenerated sidebar categories.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* style(docs): improve welcome page and visual styling

- Rewrite index.md with React Native-inspired welcoming layout
- Add Diataxis section cards with descriptions
- Remove sidebar separator, add spacing instead
- Increase navbar padding with responsive breakpoints
- Add rounded admonitions without left border bar
- Use system font stack for better readability
- Add lighter chevron styling in sidebar
- Constrain max-width to 1600px for wide viewports

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix: use baseUrl in meta tag paths for correct deployment URLs

* feat(docs): complete Phase 2 - split files and fix broken links

Phase 2 of Diataxis migration:
- Split 16 large legacy files into 42+ focused documents
- Created FAQ section with 7 topic-specific files
- Created brownfield how-to guides (3 files)
- Created workflow how-to guides (15+ files)
- Created architecture explanation files (3 files)
- Created TEA/testing explanation files
- Moved remaining legacy module files to proper Diataxis locations

Link fixes:
- Fixed ~50 broken internal links across documentation
- Updated relative paths for new file locations
- Created missing index files for installation, advanced tutorials
- Simplified TOC anchors to fix Docusaurus warnings

Cleanup:
- Removed legacy sidebar entries for deleted folders
- Deleted duplicate and empty placeholder files
- Moved workflow diagram assets to tutorials/images

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix(build): use file glob instead of sidebar parsing for llms-full.txt

Replace brittle sidebar.js regex parsing with recursive file glob.
The old approach captured non-file strings like 'autogenerated' and
category labels, resulting in only 5 files being processed.

Now correctly processes all 86+ markdown files (~95k tokens).

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix(seo): use absolute URLs in AI meta tags for agent discoverability

AI web-browsing agents couldn't follow relative paths in meta tags due to
URL security restrictions. Changed llms-full.txt and llms.txt meta tag
URLs from relative (baseUrl) to absolute (urlParts.origin + baseUrl).

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* refactor(docs): recategorize misplaced files per Diataxis analysis

Phase 2.5 categorization fixes based on post-migration analysis:

Moved to correct Diataxis categories:
- tutorials/installation.md → deleted (duplicate of how-to/install-bmad.md)
- tutorials/brownfield-onboarding.md → how-to/brownfield/index.md
- reference/faq/* (8 files) → explanation/faq/
- reference/agents/barry-quick-flow.md → explanation/agents/
- reference/agents/bmgd-agents.md → explanation/game-dev/agents.md

Created:
- explanation/agents/index.md

Fixed all broken internal links (14 total)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* feat(docs): add Getting Started tutorial and simplify build script

- Add comprehensive Getting Started tutorial with installation as Step 1
- Simplify build-docs.js to read directly from docs/ (no consolidation)
- Remove backup/restore dance that could corrupt docs folder on build failure
- Remove ~150 lines of unused consolidation code

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix(css): use fixed width layout to prevent content shifting

Apply React Native docs approach: set both width and max-width at
largest breakpoint (1400px) so content area maintains consistent
size regardless of content length. Switches to fluid 100% below
1416px breakpoint.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* refactor(docs): restructure tutorials with renamed entry point

- Rename index.md to bmad-tutorial.md for clearer navigation
- Remove redundant tutorials/index.md
- Update sidebar and config references

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* feat(docs): add tutorial style guide and AI agent announcement bar

- Add docs/_contributing/ with tutorial style guide
- Reformat quick-start-bmm.md and bmad-tutorial.md per style guide
- Remove horizontal separators, add strategic admonitions
- Add persistent announcement bar for AI agents directing to llms-full.txt
- Fix footer broken link to tutorials

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* feat(docs): add markdown demo page and UI refinements

- Add comprehensive markdown-demo.md for style testing
- Remove doc category links from navbar (use sidebar instead)
- Remove card buttons from welcome page
- Add dark mode styling for announcement bar
- Clean up index.md card layout

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* feat(docs): apply unified tutorial style and update references

- Reformat create-custom-agent.md to follow tutorial style guide
- Update tutorial-style.md with complete unified structure
- Update all internal references to renamed tutorial files
- Remove obsolete advanced/index.md

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* refactor(docs): migrate from Docusaurus to Astro+Starlight

Replace Docusaurus with Astro and the Starlight documentation theme
for improved performance, better customization, and modern tooling.

Build pipeline changes:
- New build-docs.js orchestrates link checking, artifact generation,
  and Astro build in sequence
- Add check-doc-links.js for validating internal links and anchors
- Generate llms.txt and llms-full.txt for LLM-friendly documentation
- Create downloadable source bundles (bmad-sources.zip, bmad-prompts.zip)
- Suppress MODULE_TYPELESS_PACKAGE_JSON warning in Astro build
- Output directly to build/site for cleaner deployment

Website architecture:
- Add rehype-markdown-links.js plugin to transform .md links to routes
- Add site-url.js helper for GitHub Pages URL resolution with strict
  validation (throws on invalid GITHUB_REPOSITORY format)
- Custom Astro components: Banner, Header, MobileMenuFooter
- Symlink docs/ into website/src/content/docs for Starlight

Documentation cleanup:
- Remove Docusaurus _category_.json files (Starlight uses frontmatter)
- Convert all docs to use YAML frontmatter with title field
- Move downloads.md from website/src/pages to docs/
- Consolidate style guide and workflow diagram docs
- Add 404.md and tutorials/index.md

---------

Co-authored-by: forcetrainer <bryan@inagaki.us>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Alex Verkhovsky
2026-01-07 14:42:15 +08:00
committed by GitHub
co-authored by forcetrainer Claude Opus 4.5
parent dc7a7f8c43
commit 2e16650067
134 changed files with 12848 additions and 20193 deletions
@@ -0,0 +1,171 @@
---
title: "Create a Custom Agent"
---
Build your own AI agent with a unique personality, specialized commands, and optional persistent memory using the BMad Builder workflow.
:::note[BMB Module]
This tutorial uses the **BMad Builder (BMB)** module. Make sure you have BMAD installed with the BMB module enabled.
:::
## What You'll Learn
- How to run the `create-agent` workflow
- Choose between Simple, Expert, and Module agent types
- Define your agent's persona (role, identity, communication style, principles)
- Package and install your custom agent
- Test and iterate on your agent's behavior
:::note[Prerequisites]
- BMAD installed with the BMB module
- An idea for what you want your agent to do
- About 15-30 minutes for your first agent
:::
:::tip[Quick Path]
Run `create-agent` workflow → Follow the guided steps → Install your agent module → Test and iterate.
:::
## Understanding Agent Types
Before creating your agent, understand the three types available:
| Type | Best For | Memory | Complexity |
| ---------- | ------------------------------------- | ---------- | ---------- |
| **Simple** | Focused tasks, quick setup | None | Low |
| **Expert** | Specialized domains, ongoing projects | Persistent | Medium |
| **Module** | Building other agents/workflows | Persistent | High |
**Simple Agent** - Use when your task is well-defined and focused. Perfect for single-purpose assistants like commit message generators or code reviewers.
**Expert Agent** - Use when your domain requires specialized knowledge or you need memory across sessions. Great for roles like Security Architect or Documentation Lead.
**Module Agent** - Use when your agent builds other agents or needs deep integration with the module system.
## Step 1: Start the Workflow
In your IDE (Claude Code, Cursor, etc.), invoke the create-agent workflow with the agent-builder agent.
The workflow guides you through eight steps:
| Step | What You'll Do |
| --------------------------- | -------------------------------------------- |
| **Brainstorm** *(optional)* | Explore ideas with creative techniques |
| **Discovery** | Define the agent's purpose and goals |
| **Type & Metadata** | Choose Simple or Expert, name your agent |
| **Persona** | Craft the agent's personality and principles |
| **Commands** | Define what the agent can do |
| **Activation** | Set up autonomous behaviors *(optional)* |
| **Build** | Generate the agent file |
| **Validation** | Review and verify everything works |
:::tip[Workflow Options]
At each step, the workflow provides options:
- **[A] Advanced** - Get deeper insights and reasoning
- **[P] Party** - Get multiple agent perspectives
- **[C] Continue** - Move to the next step
:::
## Step 2: Define the Persona
Your agent's personality is defined by four fields:
| Field | Purpose | Example |
| ----------------------- | -------------- | ----------------------------------------------------------------- |
| **Role** | What they do | "Senior code reviewer who catches bugs and suggests improvements" |
| **Identity** | Who they are | "Friendly but exacting, believes clean code is a craft" |
| **Communication Style** | How they speak | "Direct, constructive, explains the 'why' behind suggestions" |
| **Principles** | Why they act | "Security first, clarity over cleverness, test what you fix" |
Keep each field focused on its purpose. The role isn't personality; the identity isn't job description.
:::note[Writing Great Principles]
The first principle should "activate" the agent's expertise:
- **Weak:** "Be helpful and accurate"
- **Strong:** "Channel decades of security expertise: threat modeling begins with trust boundaries, never trust client input, defense in depth is non-negotiable"
:::
## Step 3: Install Your Agent
Once created, package your agent for installation:
```
my-custom-stuff/
├── module.yaml # Contains: unitary: true
├── agents/
│ └── {agent-name}/
│ ├── {agent-name}.agent.yaml
│ └── _memory/ # Expert agents only
│ └── {sidecar-folder}/
└── workflows/ # Optional: custom workflows
```
Install using the BMAD installer, then invoke your new agent in your IDE.
## What You've Accomplished
You've created a custom AI agent with:
- A defined purpose and role in your workflow
- A unique persona with communication style and principles
- Custom menu commands for your specific tasks
- Optional persistent memory for ongoing context
Your project now includes:
```
_bmad/
├── _config/
│ └── agents/
│ └── {your-agent}/ # Your agent customizations
└── {module}/
└── agents/
└── {your-agent}/
└── {your-agent}.agent.yaml
```
## Quick Reference
| Action | How |
| ------------------- | ---------------------------------------------- |
| Start workflow | `"Run the BMAD Builder create-agent workflow"` |
| Edit agent directly | Modify `{agent-name}.agent.yaml` |
| Edit customization | Modify `_bmad/_config/agents/{agent-name}` |
| Rebuild agent | `npx bmad-method build <agent-name>` |
| Study examples | Check `src/modules/bmb/reference/agents/` |
## Common Questions
**Should I start with Simple or Expert?**
Start with Simple for your first agent. You can always upgrade to Expert later if you need persistent memory.
**How do I add more commands later?**
Edit the agent YAML directly or use the customization file in `_bmad/_config/agents/`. Then rebuild.
**Can I share my agent with others?**
Yes. Package your agent as a standalone module and share it with your team or the community.
**Where can I see example agents?**
Study the reference agents in `src/modules/bmb/reference/agents/`:
- [commit-poet](https://github.com/bmad-code-org/BMAD-METHOD/tree/main/src/modules/bmb/reference/agents/simple-examples/commit-poet.agent.yaml) (Simple)
- [journal-keeper](https://github.com/bmad-code-org/BMAD-METHOD/tree/main/src/modules/bmb/reference/agents/expert-examples/journal-keeper) (Expert)
## Getting Help
- **[Discord Community](https://discord.gg/gk8jAdXWmj)** - Ask in #general-dev or #bugs-issues
- **[GitHub Issues](https://github.com/bmad-code-org/BMAD-METHOD/issues)** - Report bugs or request features
## Further Reading
- **[What Are Agents](../../explanation/core-concepts/what-are-agents.md)** - Deep technical details on agent types
- **[Agent Customization](../../how-to/customization/customize-agents.md)** - Modify agents without editing core files
- **[Custom Content Installation](../../how-to/installation/install-custom-modules.md)** - Package and distribute your agents
:::tip[Key Takeaways]
- **Start small** - Your first agent should solve one problem well
- **Persona matters** - Strong principles activate the agent's expertise
- **Iterate often** - Test your agent and refine based on behavior
- **Learn from examples** - Study reference agents before building your own
:::
@@ -0,0 +1,247 @@
---
title: "Getting Started with BMad v4"
description: Install BMad and create your first planning document
---
Build software faster using AI-powered workflows with specialized agents that guide you through planning, architecture, and implementation.
:::note[Stable Release]
This tutorial covers BMad v4, the current stable release. For the latest features (with potential breaking changes), see the [BMad v6 Alpha tutorial](./getting-started-bmadv6.md).
:::
## What You'll Learn
- Install and configure BMad for your IDE
- Understand how BMad organizes work into phases and agents
- Initialize a project and choose a planning track
- Create your first requirements document
:::note[Prerequisites]
- **Node.js 20+** — Required for the installer
- **Git** — Recommended for version control
- **AI-powered IDE** — Claude Code, Cursor, Windsurf, or similar
- **A project idea** — Even a simple one works for learning
:::
:::tip[Quick Path]
**Install** → `npx bmad-method install`
**Initialize** → Load Analyst agent, run `workflow-init`
**Plan** → PM creates PRD, Architect creates architecture
**Build** → SM manages sprints, DEV implements stories
**Always use fresh chats** for each workflow to avoid context issues.
:::
## Understanding BMad
BMad helps you build software through guided workflows with specialized AI agents. The process follows four phases:
| Phase | Name | What Happens |
|-------|------|--------------|
| 1 | Analysis | Brainstorm, research *(optional)* |
| 2 | Planning | Requirements — PRD or tech-spec *(required)* |
| 3 | Solutioning | Architecture, design decisions *(varies by track)* |
| 4 | Implementation | Build code story by story *(required)* |
Based on your project's complexity, BMad offers three planning tracks:
| Track | Best For | Documents Created |
|-------|----------|-------------------|
| **Quick Flow** | Bug fixes, simple features, clear scope | Tech-spec only |
| **BMad Method** | Products, platforms, complex features | PRD + Architecture + UX |
| **Enterprise** | Compliance, multi-tenant, enterprise needs | PRD + Architecture + Security + DevOps |
## Installation
Open a terminal in your project directory and run:
```bash
npx bmad-method install
```
The interactive installer guides you through setup:
- **Choose Installation Location** — Select current directory (recommended), subdirectory, or custom path
- **Select Your AI Tool** — Claude Code, Cursor, Windsurf, or other
- **Choose Modules** — Select **BMM** (BMad Method) for this tutorial
- **Accept Defaults** — Customize later in `_bmad/[module]/config.yaml`
Verify your installation:
```
your-project/
├── _bmad/
│ ├── bmm/ # Method module
│ │ ├── agents/ # Agent files
│ │ ├── workflows/ # Workflow files
│ │ └── config.yaml # Module config
│ └── core/ # Core utilities
├── _bmad-output/ # Generated artifacts (created later)
└── .claude/ # IDE configuration (if using Claude Code)
```
:::tip[Troubleshooting]
Having issues? See [Install BMad](../../how-to/installation/install-bmad.md) for common solutions.
:::
## Step 1: Initialize Your Project
Load the **Analyst agent** in your IDE:
- **Claude Code**: Type `/analyst` or load the agent file directly
- **Cursor/Windsurf**: Open the agent file from `_bmad/bmm/agents/`
Wait for the agent's menu to appear, then run:
```
Run workflow-init
```
Or use the shorthand: `*workflow-init`
The workflow asks you to describe:
- **Your project and goals** — What are you building? What problem does it solve?
- **Existing codebase** — Is this new (greenfield) or existing code (brownfield)?
- **Size and complexity** — Roughly how big is this? (adjustable later)
Based on your description, the workflow suggests a planning track. For this tutorial, choose **BMad Method**.
Once you confirm, the workflow creates `bmm-workflow-status.yaml` to track your progress.
:::caution[Fresh Chats]
Always start a fresh chat for each workflow. This prevents context limitations from causing issues.
:::
## Step 2: Create Your Plan
With your project initialized, work through the planning phases.
### Phase 1: Analysis (Optional)
If you want to brainstorm or research first:
- **brainstorm-project** — Guided ideation with the Analyst
- **research** — Market and technical research
- **product-brief** — Recommended foundation document
### Phase 2: Planning (Required)
**Start a fresh chat** and load the **PM agent**.
```
Run prd
```
Or use shortcuts: `*prd`, select "create-prd" from the menu, or say "Let's create a PRD".
The PM agent guides you through:
1. **Project overview** — Refine your project description
2. **Goals and success metrics** — What does success look like?
3. **User personas** — Who uses this product?
4. **Functional requirements** — What must the system do?
5. **Non-functional requirements** — Performance, security, scalability needs
When complete, you'll have `PRD.md` in your `_bmad-output/` folder.
:::note[UX Design (Optional)]
If your project has a user interface, load the **UX-Designer agent** and run the UX design workflow after creating your PRD.
:::
### Phase 3: Solutioning (Required for BMad Method)
**Start a fresh chat** and load the **Architect agent**.
```
Run create-architecture
```
The architect guides you through technical decisions: tech stack, database design, API patterns, and system structure.
:::tip[Check Your Status]
Unsure what's next? Load any agent and run `workflow-status`. It tells you the next recommended or required workflow.
:::
## Step 3: Build Your Project
Once planning is complete, move to implementation.
### Initialize Sprint Planning
Load the **SM agent** and run `sprint-planning`. This creates `sprint-status.yaml` to track all epics and stories.
### The Build Cycle
For each story, repeat this cycle with fresh chats:
| Step | Agent | Workflow | Purpose |
|------|-------|----------|---------|
| 1 | SM | `create-story` | Create story file from epic |
| 2 | DEV | `dev-story` | Implement the story |
| 3 | DEV | `code-review` | Quality validation *(recommended)* |
After completing all stories in an epic, load the **SM agent** and run `retrospective`.
## What You've Accomplished
You've learned the foundation of building with BMad:
- Installed BMad and configured it for your IDE
- Initialized a project with your chosen planning track
- Created planning documents (PRD, Architecture)
- Understood the build cycle for implementation
Your project now has:
```
your-project/
├── _bmad/ # BMad configuration
├── _bmad-output/
│ ├── PRD.md # Your requirements document
│ ├── architecture.md # Technical decisions
│ └── bmm-workflow-status.yaml # Progress tracking
└── ...
```
## Quick Reference
| Command | Agent | Purpose |
|---------|-------|---------|
| `*workflow-init` | Analyst | Initialize a new project |
| `*workflow-status` | Any | Check progress and next steps |
| `*prd` | PM | Create Product Requirements Document |
| `*create-architecture` | Architect | Create architecture document |
| `*sprint-planning` | SM | Initialize sprint tracking |
| `*create-story` | SM | Create a story file |
| `*dev-story` | DEV | Implement a story |
| `*code-review` | DEV | Review implemented code |
## Common Questions
**Do I need to create a PRD for every project?**
Only for BMad Method and Enterprise tracks. Quick Flow projects use a simpler tech-spec instead.
**Can I skip Phase 1 (Analysis)?**
Yes, Phase 1 is optional. If you already know what you're building, start with Phase 2 (Planning).
**What if I want to brainstorm first?**
Load the Analyst agent and run `*brainstorm-project` before `workflow-init`.
**Why start fresh chats for each workflow?**
Workflows are context-intensive. Reusing chats can cause the AI to hallucinate or lose track of details. Fresh chats ensure maximum context capacity.
## Getting Help
- **During workflows** — Agents guide you with questions and explanations
- **Check status** — Run `workflow-status` with any agent
- **Community** — [Discord](https://discord.gg/gk8jAdXWmj) (#general-dev, #bugs-issues)
- **Video tutorials** — [BMad Code YouTube](https://www.youtube.com/@BMadCode)
## Key Takeaways
:::tip[Remember These]
- **Always use fresh chats** — Load agents in new chats for each workflow
- **Let workflow-status guide you** — Ask any agent for status when unsure
- **Track matters** — Quick Flow uses tech-spec; Method/Enterprise need PRD and architecture
- **Tracking is automatic** — Status files update themselves
- **Agents are flexible** — Use menu numbers, shortcuts (`*prd`), or natural language
:::
Ready to start? Install BMad, load the Analyst, run `workflow-init`, and let the agents guide you.
@@ -0,0 +1,247 @@
---
title: "Getting Started with BMad v6 Alpha"
description: Install BMad v6 Alpha and build your first project
---
Build software faster using AI-powered workflows with specialized agents that guide you through planning, architecture, and implementation.
:::caution[Alpha Software]
BMad v6 is currently in **alpha**. Expect breaking changes, incomplete features, and evolving documentation. For a stable experience, use the [BMad v4 tutorial](./getting-started-bmadv4.md) instead.
:::
## What You'll Learn
- Install and initialize BMad Method for a new project
- Choose the right planning track for your project size
- Progress through phases from requirements to working code
- Use agents and workflows effectively
:::note[Prerequisites]
- **Node.js 20+** — Required for the installer
- **Git** — Recommended for version control
- **AI-powered IDE** — Claude Code, Cursor, Windsurf, or similar
- **A project idea** — Even a simple one works for learning
:::
:::tip[Quick Path]
**Install** → `npx bmad-method@alpha install`
**Initialize** → Load Analyst agent, run `workflow-init`
**Plan** → PM creates PRD, Architect creates architecture
**Build** → SM manages sprints, DEV implements stories
**Always use fresh chats** for each workflow to avoid context issues.
:::
## Understanding BMad
BMad helps you build software through guided workflows with specialized AI agents. The process follows four phases:
| Phase | Name | What Happens |
|-------|------|--------------|
| 1 | Analysis | Brainstorming, research, product brief *(optional)* |
| 2 | Planning | Create requirements (PRD or tech-spec) |
| 3 | Solutioning | Design architecture *(BMad Method/Enterprise only)* |
| 4 | Implementation | Build epic by epic, story by story |
![BMad Method Workflow - Standard Greenfield](./images/workflow-method-greenfield.svg)
*Complete visual flowchart showing all phases, workflows, and agents for the standard greenfield track.*
Based on your project's complexity, BMad offers three planning tracks:
| Track | Best For | Documents Created |
|-------|----------|-------------------|
| **Quick Flow** | Bug fixes, simple features, clear scope (1-15 stories) | Tech-spec only |
| **BMad Method** | Products, platforms, complex features (10-50+ stories) | PRD + Architecture + UX |
| **Enterprise** | Compliance, multi-tenant systems (30+ stories) | PRD + Architecture + Security + DevOps |
:::note
Story counts are guidance, not definitions. Choose your track based on planning needs, not story math.
:::
## Installation
Open a terminal in your project directory and run:
```bash
npx bmad-method@alpha install
```
The interactive installer guides you through setup and creates a `_bmad/` folder with all agents and workflows.
Verify your installation:
```
your-project/
├── _bmad/
│ ├── bmm/ # Method module
│ │ ├── agents/ # Agent files
│ │ ├── workflows/ # Workflow files
│ │ └── config.yaml # Module config
│ └── core/ # Core utilities
├── _bmad-output/ # Generated artifacts (created later)
└── .claude/ # IDE configuration (if using Claude Code)
```
:::tip[Troubleshooting]
Having issues? See [Install BMad](../../how-to/installation/install-bmad.md) for common solutions.
:::
## Step 1: Initialize Your Project
Load the **Analyst agent** in your IDE, wait for the menu, then run `workflow-init`.
:::note[How to Load Agents]
Type `/<agent-name>` in your IDE and use autocomplete. Not sure what's available? Start with `/bmad` to see all agents and workflows.
:::
The workflow asks you to describe your project, whether it's new or existing, and the general complexity. Based on your description, it recommends a planning track.
Once you confirm, the workflow creates `bmm-workflow-status.yaml` to track your progress through all phases.
:::caution[Fresh Chats]
Always start a fresh chat for each workflow. This prevents context limitations from causing issues.
:::
## Step 2: Create Your Plan
After initialization, work through phases 1-3. **Use fresh chats for each workflow.**
:::tip[Check Your Status]
Unsure what's next? Load any agent and ask for `workflow-status`. It tells you the next recommended or required workflow.
:::
### Phase 1: Analysis (Optional)
All workflows in this phase are optional:
- **brainstorm-project** — Guided ideation
- **research** — Market and technical research
- **product-brief** — Recommended foundation document
### Phase 2: Planning (Required)
**For BMad Method and Enterprise tracks:**
1. Load the **PM agent** in a new chat
2. Run the PRD workflow: `*prd`
3. Output: `PRD.md`
**For Quick Flow track:**
- Use `tech-spec` instead of PRD, then skip to implementation
:::note[UX Design (Optional)]
If your project has a user interface, load the **UX-Designer agent** and run the UX design workflow after creating your PRD.
:::
### Phase 3: Solutioning (BMad Method/Enterprise)
**Create Architecture**
1. Load the **Architect agent** in a new chat
2. Run `create-architecture`
3. Output: Architecture document with technical decisions
**Create Epics and Stories**
:::tip[V6 Improvement]
Epics and stories are now created *after* architecture. This produces better quality stories because architecture decisions (database, API patterns, tech stack) directly affect how work should be broken down.
:::
1. Load the **PM agent** in a new chat
2. Run `create-epics-and-stories`
3. The workflow uses both PRD and Architecture to create technically-informed stories
**Implementation Readiness Check** *(Highly Recommended)*
1. Load the **Architect agent** in a new chat
2. Run `implementation-readiness`
3. Validates cohesion across all planning documents
## Step 3: Build Your Project
Once planning is complete, move to implementation. **Each workflow should run in a fresh chat.**
### Initialize Sprint Planning
Load the **SM agent** and run `sprint-planning`. This creates `sprint-status.yaml` to track all epics and stories.
### The Build Cycle
For each story, repeat this cycle with fresh chats:
| Step | Agent | Workflow | Purpose |
|------|-------|----------|---------|
| 1 | SM | `create-story` | Create story file from epic |
| 2 | DEV | `dev-story` | Implement the story |
| 3 | TEA | `automate` | Generate guardrail tests *(optional)* |
| 4 | DEV | `code-review` | Quality validation *(recommended)* |
After completing all stories in an epic, load the **SM agent** and run `retrospective`.
## What You've Accomplished
You've learned the foundation of building with BMad:
- Installed BMad and configured it for your IDE
- Initialized a project with your chosen planning track
- Created planning documents (PRD, Architecture, Epics & Stories)
- Understood the build cycle for implementation
Your project now has:
```
your-project/
├── _bmad/ # BMad configuration
├── _bmad-output/
│ ├── PRD.md # Your requirements document
│ ├── architecture.md # Technical decisions
│ ├── epics/ # Epic and story files
│ ├── bmm-workflow-status.yaml # Phase progress tracking
│ └── sprint-status.yaml # Sprint tracking
└── ...
```
## Quick Reference
| Command | Agent | Purpose |
|---------|-------|---------|
| `*workflow-init` | Analyst | Initialize a new project |
| `*workflow-status` | Any | Check progress and next steps |
| `*prd` | PM | Create Product Requirements Document |
| `*create-architecture` | Architect | Create architecture document |
| `*create-epics-and-stories` | PM | Break down PRD into epics |
| `*implementation-readiness` | Architect | Validate planning cohesion |
| `*sprint-planning` | SM | Initialize sprint tracking |
| `*create-story` | SM | Create a story file |
| `*dev-story` | DEV | Implement a story |
| `*code-review` | DEV | Review implemented code |
## Common Questions
**Do I always need architecture?**
Only for BMad Method and Enterprise tracks. Quick Flow skips from tech-spec to implementation.
**Can I change my plan later?**
Yes. The SM agent has a `correct-course` workflow for handling scope changes.
**What if I want to brainstorm first?**
Load the Analyst agent and run `brainstorm-project` before `workflow-init`.
**Can I skip workflow-init and workflow-status?**
Yes, once you learn the flow. Use the Quick Reference to go directly to needed workflows.
## Getting Help
- **During workflows** — Agents guide you with questions and explanations
- **Community** — [Discord](https://discord.gg/gk8jAdXWmj) (#general-dev, #bugs-issues)
- **Documentation** — [BMM Workflow Reference](../../reference/workflows/index.md)
- **Video tutorials** — [BMad Code YouTube](https://www.youtube.com/@BMadCode)
## Key Takeaways
:::tip[Remember These]
- **Always use fresh chats** — Load agents in new chats for each workflow
- **Let workflow-status guide you** — Ask any agent for status when unsure
- **Track matters** — Quick Flow uses tech-spec; Method/Enterprise need PRD and architecture
- **Tracking is automatic** — Status files update themselves
- **Agents are flexible** — Use menu numbers, shortcuts (`*prd`), or natural language
:::
Ready to start? Install BMad, load the Analyst, run `workflow-init`, and let the agents guide you.
File diff suppressed because it is too large Load Diff
File diff suppressed because one or more lines are too long

After

Width:  |  Height:  |  Size: 87 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 200 KiB

@@ -0,0 +1,260 @@
---
title: "Getting Started with BMad Game Development"
description: Build games with BMad's Game Development Module
---
Build games faster using AI-powered workflows with specialized game development agents that guide you through preproduction, design, architecture, and implementation.
:::note[Module Extension]
BMGD (BMad Game Development) is a module that extends BMad Method. You'll need BMad installed first—see the [BMad v4 tutorial](./getting-started-bmadv4.md) or [BMad v6 tutorial](./getting-started-bmadv6.md) if you haven't installed it yet.
:::
## What You'll Learn
- Install and configure the BMGD module
- Understand game development phases and specialized agents
- Create a Game Brief and Game Design Document (GDD)
- Progress from concept to working game code
:::note[Prerequisites]
- **BMad Method installed** — Follow the main installation guide first
- **A game idea** — Even a rough concept is enough to start
- **AI-powered IDE** — Claude Code, Cursor, Windsurf, or similar
:::
:::tip[Quick Path]
**Install** → `npx bmad-method install` (select BMGD module)
**Preproduction** → Game Designer creates Game Brief
**Design** → Game Designer creates GDD (and Narrative if story-driven)
**Technical** → Game Architect creates Architecture
**Production** → Game SM manages sprints, Game Dev implements
**Always use fresh chats** for each workflow to avoid context issues.
:::
## Understanding BMGD
BMGD follows four game development phases with specialized agents for each:
| Phase | Name | What Happens |
|-------|------|--------------|
| 1 | Preproduction | Capture game vision, create Game Brief *(optional brainstorming)* |
| 2 | Design | Detail mechanics, systems, narrative in GDD |
| 3 | Technical | Plan engine, architecture, technical decisions |
| 4 | Production | Build game in sprints, story by story |
![BMGD Workflow Overview](./images/workflow-overview.jpg)
*Complete visual flowchart showing all phases, workflows, and agents for game development.*
### Game Development Agents
| Agent | When to Use |
|-------|-------------|
| **Game Designer** | Brainstorming, Game Brief, GDD, Narrative |
| **Game Architect** | Architecture, technical decisions |
| **Game Developer** | Implementation, code reviews |
| **Game Scrum Master** | Sprint planning, story management |
| **Game QA** | Test framework, test design, automation |
| **Game Solo Dev** | Quick prototyping, indie development |
## Installation
If you haven't installed BMad yet:
```bash
npx bmad-method install
```
Or add BMGD to an existing installation:
```bash
npx bmad-method install --add-module bmgd
```
Verify your installation:
```
your-project/
├── _bmad/
│ ├── bmgd/ # Game development module
│ │ ├── agents/ # Game-specific agents
│ │ ├── workflows/ # Game-specific workflows
│ │ └── config.yaml # Module config
│ ├── bmm/ # Core method module
│ └── core/ # Core utilities
├── _bmad-output/ # Generated artifacts (created later)
└── .claude/ # IDE configuration (if using Claude Code)
```
## Step 1: Create Your Game Brief (Preproduction)
Load the **Game Designer** agent in your IDE, wait for the menu, then start with your game concept.
### Optional: Brainstorm First
If you have a vague idea and want help developing it:
```
Run brainstorm-game
```
The agent guides you through game-specific ideation techniques to refine your concept.
### Create the Game Brief
```
Run create-game-brief
```
The Game Designer walks you through:
- **Game concept** — Core idea and unique selling points
- **Design pillars** — The 3-5 principles that guide all decisions
- **Target market** — Who plays this game?
- **Fundamentals** — Platform, genre, scope, team size
When complete, you'll have `game-brief.md` in your `_bmad-output/` folder.
:::caution[Fresh Chats]
Always start a fresh chat for each workflow. This prevents context limitations from causing issues.
:::
## Step 2: Design Your Game
With your Game Brief complete, detail your game's design.
### Create the GDD
**Start a fresh chat** with the **Game Designer** agent.
```
Run create-gdd
```
The agent guides you through mechanics, systems, and game-type-specific sections. BMGD offers 24 game type templates that provide genre-specific structure.
When complete, you'll have `gdd.md` (or sharded into `gdd/` for large documents).
:::note[Narrative Design (Optional)]
For story-driven games, start a fresh chat and run `narrative` to create a Narrative Design Document covering story, characters, world, and dialogue.
:::
:::tip[Check Your Status]
Unsure what's next? Load any agent and run `workflow-status`. It tells you the next recommended workflow.
:::
## Step 3: Plan Your Architecture
**Start a fresh chat** with the **Game Architect** agent.
```
Run create-architecture
```
The architect guides you through:
- **Engine selection** — Unity, Unreal, Godot, custom, etc.
- **System design** — Core game systems and how they interact
- **Technical patterns** — Architecture patterns suited to your game
- **Structure** — Project organization and conventions
When complete, you'll have `game-architecture.md`.
## Step 4: Build Your Game
Once planning is complete, move to production. **Each workflow should run in a fresh chat.**
### Initialize Sprint Planning
Load the **Game Scrum Master** agent and run `sprint-planning`. This creates `sprint-status.yaml` to track all epics and stories.
### The Build Cycle
For each story, repeat this cycle with fresh chats:
| Step | Agent | Workflow | Purpose |
|------|-------|----------|---------|
| 1 | Game SM | `create-story` | Create story file from epic |
| 2 | Game Dev | `dev-story` | Implement the story |
| 3 | Game QA | `automate` | Generate tests *(optional)* |
| 4 | Game Dev | `code-review` | Quality validation *(recommended)* |
After completing all stories in an epic, load the **Game SM** and run `retrospective`.
### Quick Prototyping Alternative
For rapid iteration or indie development, load the **Game Solo Dev** agent:
- `quick-prototype` — Rapid prototyping
- `quick-dev` — Flexible development without full sprint structure
## What You've Accomplished
You've learned the foundation of building games with BMad:
- Installed the BMGD module
- Created a Game Brief capturing your vision
- Detailed your design in a GDD
- Planned your technical architecture
- Understood the build cycle for implementation
Your project now has:
```
your-project/
├── _bmad/ # BMad configuration
├── _bmad-output/
│ ├── game-brief.md # Your game vision
│ ├── gdd.md # Game Design Document
│ ├── narrative-design.md # Story design (if applicable)
│ ├── game-architecture.md # Technical decisions
│ ├── epics/ # Epic and story files
│ └── sprint-status.yaml # Sprint tracking
└── ...
```
## Quick Reference
| Command | Agent | Purpose |
|---------|-------|---------|
| `*brainstorm-game` | Game Designer | Guided game ideation |
| `*create-game-brief` | Game Designer | Create Game Brief |
| `*create-gdd` | Game Designer | Create Game Design Document |
| `*narrative` | Game Designer | Create Narrative Design |
| `*create-architecture` | Game Architect | Create game architecture |
| `*sprint-planning` | Game SM | Initialize sprint tracking |
| `*create-story` | Game SM | Create a story file |
| `*dev-story` | Game Dev | Implement a story |
| `*code-review` | Game Dev | Review implemented code |
| `*workflow-status` | Any | Check progress and next steps |
## Common Questions
**Do I need to create all documents?**
At minimum, create a Game Brief and GDD. Architecture is highly recommended. Narrative Design is only needed for story-driven games.
**Can I use the Game Solo Dev for everything?**
Yes, for smaller projects or rapid prototyping. For larger games, the specialized agents provide more thorough guidance.
**What game types are supported?**
BMGD includes 24 game type templates (RPG, platformer, puzzle, strategy, etc.) that provide genre-specific GDD sections.
**Can I change my design later?**
Yes. Documents are living artifacts—return to update them as your vision evolves. The SM agent has `correct-course` for scope changes.
## Getting Help
- **During workflows** — Agents guide you with questions and explanations
- **Community** — [Discord](https://discord.gg/gk8jAdXWmj) (#general-dev, #bugs-issues)
- **Documentation** — [BMGD Workflow Reference](../../reference/workflows/bmgd-workflows.md)
- **Video tutorials** — [BMad Code YouTube](https://www.youtube.com/@BMadCode)
## Key Takeaways
:::tip[Remember These]
- **Always use fresh chats** — Load agents in new chats for each workflow
- **Game Brief first** — It informs everything that follows
- **Use game type templates** — 24 templates provide genre-specific GDD structure
- **Documents evolve** — Return to update them as your vision grows
- **Solo Dev for speed** — Use Game Solo Dev for rapid prototyping
:::
Ready to start? Load the **Game Designer** agent and run `create-game-brief` to capture your game vision.
Binary file not shown.

After

Width:  |  Height:  |  Size: 200 KiB

+21
View File
@@ -0,0 +1,21 @@
---
title: "Tutorials"
---
Learning-oriented guides that walk you through building something real with BMad. Perfect for getting hands-on experience.
## Getting Started
Start your journey with BMad by choosing a version that fits your needs:
- [Get Started with v4 (Stable)](./getting-started/getting-started-bmadv4.md) — Production-ready version with battle-tested workflows
- [Try v6 (Alpha)](./getting-started/getting-started-bmadv6.md) — Latest features, still in active development
## First Project
Your first end-to-end project with BMad.
## Advanced
More complex scenarios and advanced patterns.