schema standardization and bmad ide orchesatrtor can do anything
This commit is contained in:
Brian Madison
@@ -1,137 +1,196 @@
|
||||
# Create Agent Task
|
||||
|
||||
This task helps you create a new BMAD agent for web platforms (Gemini, ChatGPT, etc.).
|
||||
This task guides you through creating a new BMAD agent that conforms to the agent schema and integrates with existing teams and workflows.
|
||||
|
||||
**Note for User-Created Agents**: If you're creating a custom agent for your own use (not part of the core BMAD system), prefix the agent ID with a period (e.g., `.data-analyst`) to ensure it's gitignored and won't conflict with repository updates.
|
||||
**Note for User-Created Agents**: If creating a custom agent for your own use (not part of the core BMAD system), prefix the agent ID with a period (e.g., `.data-analyst`) to ensure it's gitignored and won't conflict with repository updates.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
1. Load and understand the agent schema: `/bmad-core/schemas/agent-schema.yml`
|
||||
2. Review existing agents in `/agents/` to understand naming patterns
|
||||
3. Check existing teams in `/bmad-core/agent-teams/` for integration opportunities
|
||||
4. Review workflows in `/bmad-core/workflows/` to understand where the agent might fit
|
||||
|
||||
## Process
|
||||
|
||||
Follow these steps to create a new agent:
|
||||
### 1. Gather Core Agent Information
|
||||
|
||||
### 1. Gather Basic Information
|
||||
Based on the agent schema's required fields, collect:
|
||||
|
||||
Ask the user for:
|
||||
|
||||
- **Agent ID**: A short, lowercase identifier (e.g., `data-analyst`, `security-expert`)
|
||||
- **Agent Name**: The character name (e.g., "Elena", "Marcus")
|
||||
- **Title**: Professional title (e.g., "Data Analyst", "Security Expert")
|
||||
- **Description**: A brief description of the agent's role and primary focus
|
||||
- **Agent ID**: Following the schema pattern `^[a-z][a-z0-9-]*$` (e.g., `data-analyst`, `security-expert`)
|
||||
- For user agents: prefix with period (`.data-analyst`)
|
||||
- **Character Name**: Following pattern `^[A-Z][a-z]+$` (e.g., "Elena", "Marcus")
|
||||
- **Professional Title**: 5-50 characters (e.g., "Data Analyst", "Security Expert")
|
||||
- **Description**: 20-300 characters describing the agent's main goal and purpose
|
||||
|
||||
### 2. Define Personality and Expertise
|
||||
|
||||
Ask about:
|
||||
Create a comprehensive persona by exploring:
|
||||
|
||||
- **Personality traits**: How should this agent behave? (professional, friendly, detail-oriented, etc.)
|
||||
- **Communication style**: How do they speak? (formal, casual, technical, empathetic)
|
||||
- **Expertise areas**: What are they exceptionally good at?
|
||||
- **Years of experience**: How senior are they in their role?
|
||||
- **Motivations**: What drives them to excel?
|
||||
- **Identity**: Extended description of specialization (20+ characters)
|
||||
- **Focus**: Primary objectives and responsibilities (20+ characters)
|
||||
- **Style**: Communication and approach characteristics (20+ characters)
|
||||
- **Core Principles**: At least 3 principles including the required "Numbered Options Protocol"
|
||||
- **Experience Level**: Years in field and depth of expertise
|
||||
- **Working Approach**: How they solve problems and deliver value
|
||||
|
||||
### 3. Identify Capabilities
|
||||
### 3. Identify Dependencies
|
||||
|
||||
Determine what the agent can do:
|
||||
Analyze what resources the agent needs:
|
||||
|
||||
- **Existing tasks**: Which existing tasks from `/bmad-core/tasks/` should this agent know?
|
||||
- **New tasks needed**: Does this agent need any specialized tasks that don't exist yet?
|
||||
- **Templates used**: Which document templates will this agent work with?
|
||||
- **Checklists**: Which quality checklists apply to this agent's work?
|
||||
#### Tasks (from `/bmad-core/tasks/`)
|
||||
- Review available tasks and identify which apply
|
||||
- Common tasks most agents need:
|
||||
- `advanced-elicitation` (for conversational depth)
|
||||
- `create-doc-from-template` (if they create documents)
|
||||
- `execute-checklist` (if they validate work)
|
||||
- Identify any new specialized tasks needed
|
||||
|
||||
#### Templates (from `/bmad-core/templates/`)
|
||||
- Which document templates will this agent create/use?
|
||||
- Match template pattern: `^[a-z][a-z0-9-]*-tmpl$`
|
||||
|
||||
#### Checklists (from `/bmad-core/checklists/`)
|
||||
- Which quality checklists apply to their work?
|
||||
- Match checklist pattern: `^[a-z][a-z0-9-]*-checklist$`
|
||||
|
||||
#### Data Files (from `/bmad-core/data/`)
|
||||
- `bmad-kb` (if they need BMAD methodology knowledge)
|
||||
- `technical-preferences` (if they make technical decisions)
|
||||
- Other specialized data files
|
||||
|
||||
### 4. Create the Persona File
|
||||
|
||||
Create `/bmad-core/personas/{agent-id}.md` with this structure:
|
||||
(For user-created agents, use `/bmad-core/personas/.{agent-id}.md`)
|
||||
Create `/bmad-core/personas/{agent-id}.md` following the schema-required structure:
|
||||
(For user agents: `/bmad-core/personas/.{agent-id}.md`)
|
||||
|
||||
```markdown
|
||||
# {Agent Name} - {Title}
|
||||
# Role: {Title} Agent
|
||||
|
||||
## Character Profile
|
||||
## Persona
|
||||
|
||||
**Name:** {Agent Name}
|
||||
**Title:** {Title}
|
||||
**Experience:** {Years} years in {field}
|
||||
- Role: {Descriptive Role Statement}
|
||||
- Style: {Communication style and approach}
|
||||
|
||||
## Personality
|
||||
## Core {Title} Principles (Always Active)
|
||||
|
||||
{Describe personality traits, communication style, and approach to work}
|
||||
- **{Principle Name}:** {Detailed explanation}
|
||||
- **{Principle Name}:** {Detailed explanation}
|
||||
- **Numbered Options Protocol:** When presenting multiple options, always use numbered lists for easy selection
|
||||
[Add more principles as needed]
|
||||
|
||||
## Core Expertise
|
||||
## Critical Start Up Operating Instructions
|
||||
|
||||
{List main areas of expertise and specialization}
|
||||
- Let the User Know what Tasks you can perform in a numbered list for user selection.
|
||||
- Execute the Full Tasks as Selected. If no task selected you will just stay in this persona and help the user as needed.
|
||||
- When conversing with the user and providing advice or multiple options, always present them as numbered lists for easy selection. When appropriate, also offer `advanced-elicitation` options during conversations.
|
||||
|
||||
## Responsibilities
|
||||
|
||||
{List key responsibilities in bullet points}
|
||||
|
||||
## Working Style
|
||||
|
||||
{Describe how they approach problems, collaborate, and deliver results}
|
||||
|
||||
## Motivations
|
||||
|
||||
{What drives them to excel in their role}
|
||||
|
||||
## Catchphrases
|
||||
|
||||
{Optional: Any signature phrases or ways of speaking}
|
||||
[Add any agent-specific sections like Expertise, Workflow, etc.]
|
||||
```
|
||||
|
||||
### 5. Create the Agent Configuration
|
||||
|
||||
Create `/agents/{agent-id}.yml` with this structure:
|
||||
(For user-created agents, use `/agents/.{agent-id}.yml`)
|
||||
Create `/agents/{agent-id}.yml` conforming to the schema:
|
||||
(For user agents: `/agents/.{agent-id}.yml`)
|
||||
|
||||
```yaml
|
||||
agent:
|
||||
id: { agent-id }
|
||||
name: { Agent Name }
|
||||
title: { Title }
|
||||
description: >-
|
||||
{Full description of the agent's role and value}
|
||||
persona: { agent-id }
|
||||
customize: >-
|
||||
{Any specific behavioral customizations}
|
||||
name: {Character Name}
|
||||
id: {agent-id}
|
||||
title: {Professional Title}
|
||||
description: {20-300 character description}
|
||||
persona: bmad-core/personas/{agent-id}.md
|
||||
customize: "" # or specific customizations
|
||||
|
||||
dependencies:
|
||||
tasks:
|
||||
- { list of task IDs }
|
||||
- {task-id} # from identified tasks
|
||||
templates:
|
||||
- { list of template IDs }
|
||||
- {template-id} # from identified templates
|
||||
checklists:
|
||||
- { list of checklist IDs }
|
||||
- {checklist-id} # from identified checklists
|
||||
data:
|
||||
- { list of data file IDs }
|
||||
- {data-id} # from identified data files
|
||||
utils:
|
||||
- template-format
|
||||
- {util-id} # typically empty or specific utils
|
||||
```
|
||||
|
||||
### 6. Create Any New Tasks
|
||||
### 6. Team Integration Analysis
|
||||
|
||||
If new tasks were identified, create them in `/bmad-core/tasks/{task-name}.md`
|
||||
(For user-created tasks, use `/bmad-core/tasks/.{task-name}.md`)
|
||||
Review existing teams and suggest integration:
|
||||
|
||||
### 7. Test and Validate
|
||||
1. **Load team configurations** from `/bmad-core/agent-teams/`
|
||||
2. **Analyze fit** based on:
|
||||
- Agent's role and expertise
|
||||
- Team's description and purpose
|
||||
- Existing agents in the team
|
||||
- Workflows the team supports
|
||||
|
||||
1. Run `npm run validate` to check configuration
|
||||
2. Run `npm run build:agent -a {agent-id}` to build the agent
|
||||
3. Review the generated output in `/dist/agents/{agent-id}.txt`
|
||||
3. **Suggest teams** where this agent would add value:
|
||||
- For technical agents → suggest technical teams
|
||||
- For UX/design agents → suggest teams with UI workflows
|
||||
- For planning agents → suggest all teams
|
||||
|
||||
## Example Questions to Ask
|
||||
4. **Offer to update** team configurations:
|
||||
```yaml
|
||||
agents:
|
||||
- bmad
|
||||
- {existing-agents}
|
||||
- {new-agent-id} # Add here
|
||||
```
|
||||
|
||||
1. "What will this agent be called? (ID like 'data-analyst')"
|
||||
2. "What's their character name? (like 'Elena')"
|
||||
3. "What's their professional title?"
|
||||
4. "Describe their main role in 2-3 sentences."
|
||||
5. "What personality traits should they have?"
|
||||
6. "How many years of experience do they have?"
|
||||
7. "What existing tasks should they know? (e.g., create-doc-from-template, execute-checklist)"
|
||||
8. "Do they need any specialized tasks that don't exist yet?"
|
||||
9. "Which document templates will they use?"
|
||||
10. "What motivates them in their work?"
|
||||
### 7. Workflow Integration Analysis
|
||||
|
||||
## Important Notes
|
||||
Review workflows and suggest where the agent fits:
|
||||
|
||||
- Keep personas engaging but professional
|
||||
- Ensure all referenced tasks, templates, and checklists exist
|
||||
- Web agents can be more detailed than IDE agents (no size constraints)
|
||||
- Consider how this agent will collaborate with existing team members
|
||||
- Run validation after creating to catch any issues
|
||||
1. **Load workflow definitions** from `/bmad-core/workflows/`
|
||||
2. **Analyze workflow stages** to identify where this agent would contribute
|
||||
3. **Suggest integration points**:
|
||||
- Planning phases → analysts, PMs
|
||||
- Design phases → UX experts, architects
|
||||
- Implementation phases → developers
|
||||
- Validation phases → QA, PO
|
||||
|
||||
4. **Document recommendations** for workflow updates if needed
|
||||
|
||||
### 8. Create IDE Agent (Optional)
|
||||
|
||||
If the agent should also work in IDE environments:
|
||||
|
||||
1. Create `/bmad-core/ide-agents/{agent-id}.ide.md`
|
||||
2. Follow the IDE agent schema from `/bmad-core/schemas/ide-agent-schema.yml`
|
||||
3. Include required commands (*help, *chat-mode) and startup instructions
|
||||
|
||||
### 9. Validation and Testing
|
||||
|
||||
1. **Validate against schema**: Ensure configuration matches agent-schema.yml
|
||||
2. **Run build validation**: `npm run validate`
|
||||
3. **Build the agent**: `npm run build:agent -a {agent-id}`
|
||||
4. **Test in teams**: Build teams that include this agent
|
||||
5. **Review output**: Check `/dist/agents/{agent-id}.txt`
|
||||
|
||||
## Integration Checklist
|
||||
|
||||
After creating the agent, verify:
|
||||
|
||||
- [ ] Agent configuration validates against schema
|
||||
- [ ] Persona file includes all required sections
|
||||
- [ ] All referenced dependencies exist
|
||||
- [ ] Team integration suggestions documented
|
||||
- [ ] Workflow integration points identified
|
||||
- [ ] Build completes without errors
|
||||
- [ ] Agent output is under size limits (if applicable)
|
||||
|
||||
## Example Integration Analysis
|
||||
|
||||
When creating a "Security Expert" agent:
|
||||
|
||||
**Team Integration:**
|
||||
- `team-fullstack`: Add for security reviews in full-stack projects
|
||||
- `team-no-ui`: Add for backend service security assessments
|
||||
|
||||
**Workflow Integration:**
|
||||
- `greenfield-*`: Security review after architecture phase
|
||||
- `brownfield-*`: Security assessment before implementation
|
||||
|
||||
This ensures the new agent enhances existing capabilities rather than working in isolation.
|
||||
|
||||
Reference in New Issue
Block a user