specify md ot yaml
This commit is contained in:
Brian Madison
@@ -3,6 +3,9 @@
|
||||
CRITICAL: Read the full YAML, start activation to alter your state of being, follow startup section instructions, stay in this being until told to exit this mode:
|
||||
|
||||
```yaml
|
||||
root: .bmad-creator-tools
|
||||
IDE-FILE-RESOLUTION: Dependencies map to files as {root}/{type}/{name} where root=".bmad-core", type=folder (tasks/templates/checklists/utils), name=dependency name.
|
||||
REQUEST-RESOLUTION: Match user requests to your commands/dependencies flexibly (e.g., "draft story"→*create→create-next-story task, "make a new prd" would be dependencies->tasks->create-doc combined with the dependencies->templates->prd-tmpl.md), or ask for clarification if ambiguous.
|
||||
activation-instructions:
|
||||
- Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
|
||||
- Only read the files/tasks listed here when user selects them for execution to minimize context usage
|
||||
@@ -42,11 +45,11 @@ commands:
|
||||
- '*exit" - Say goodbye as The Creator, and then abandon inhabiting this persona'
|
||||
dependencies:
|
||||
tasks:
|
||||
- create-agent
|
||||
- generate-expansion-pack
|
||||
- advanced-elicitation
|
||||
- create-deep-research-prompt
|
||||
- create-agent.md
|
||||
- generate-expansion-pack.md
|
||||
- advanced-elicitation.md
|
||||
- create-deep-research-prompt.md
|
||||
templates:
|
||||
- agent-tmpl
|
||||
- expansion-pack-plan-tmpl
|
||||
- agent-tmpl.yaml
|
||||
- expansion-pack-plan-tmpl.yaml
|
||||
```
|
||||
|
||||
@@ -1,154 +0,0 @@
|
||||
# Agent Team Configuration Template
|
||||
|
||||
[[LLM: This template is for creating agent team configurations in YAML format. Follow the structure carefully and replace all placeholders with appropriate values. The team name should reflect the team's purpose and domain focus.]]
|
||||
|
||||
```yaml
|
||||
bundle:
|
||||
name: {{team-display-name}}
|
||||
[[LLM: Use format "Team [Descriptor]" for generic teams or "[Domain] Team" for specialized teams. Examples: "Team Fullstack", "Healthcare Team", "Legal Team"]]
|
||||
|
||||
icon: {{team-emoji}}
|
||||
[[LLM: Choose a single emoji that best represents the team's function or name]]
|
||||
|
||||
description: {{team-description}}
|
||||
[[LLM: Write a concise description (1 sentence) that explains:
|
||||
1. The team's primary purpose
|
||||
2. What types of projects they handle
|
||||
3. Any special capabilities or focus areas
|
||||
4. Keep it short as its displayed in menus
|
||||
Example: "Full Stack Ideation Web App Team." or "Startup Business Coaching team"]]
|
||||
|
||||
agents:
|
||||
[[LLM: List the agents that make up this team. Guidelines:
|
||||
- Use shortened agent names (e.g., 'analyst' not 'business-analyst')
|
||||
- Include 'bmad-orchestrator' for bmad-core teams as the coordinator
|
||||
- Only use '*' for an all-inclusive team (rare)
|
||||
- Order agents logically by workflow (analysis → design → development → testing)
|
||||
- For expansion packs, include both core agents and custom agents]]
|
||||
|
||||
^^CONDITION: standard-team^^
|
||||
# Core workflow agents
|
||||
- bmad-orchestrator # Team coordinator
|
||||
- analyst # Requirements and analysis
|
||||
- pm # Product management
|
||||
- architect # System design
|
||||
- dev # Development
|
||||
- qa # Quality assurance
|
||||
^^/CONDITION: standard-team^^
|
||||
|
||||
^^CONDITION: minimal-team^^
|
||||
# Minimal team for quick iterations
|
||||
- bmad-orchestrator # Team coordinator
|
||||
- architect # Design and planning
|
||||
- dev # Implementation
|
||||
^^/CONDITION: minimal-team^^
|
||||
|
||||
^^CONDITION: specialized-team^^
|
||||
# Domain-specific team composition
|
||||
- {{domain}}-orchestrator # Domain coordinator
|
||||
<<REPEAT section="specialist-agents" count="{{agent-count}}">>
|
||||
- {{agent-short-name}} # {{agent-role-description}}
|
||||
<</REPEAT>>
|
||||
^^/CONDITION: specialized-team^^
|
||||
|
||||
^^CONDITION: include-all-agents^^
|
||||
- '*' # Include all available agents
|
||||
^^/CONDITION: include-all-agents^^
|
||||
|
||||
workflows:
|
||||
[[LLM: Define the workflows this team can execute that will guide the user through a multi-step multi agent process. Guidelines:
|
||||
- Use null if the team doesn't have predefined workflows
|
||||
- Workflow names should be descriptive
|
||||
- use domain-specific workflow names]]
|
||||
|
||||
^^CONDITION: no-workflows^^
|
||||
null # No predefined workflows
|
||||
^^/CONDITION: no-workflows^^
|
||||
|
||||
^^CONDITION: standard-workflows^^
|
||||
# New project workflows
|
||||
- greenfield-fullstack # New full-stack application
|
||||
- greenfield-service # New backend service
|
||||
- greenfield-ui # New frontend application
|
||||
|
||||
# Existing project workflows
|
||||
- brownfield-fullstack # Enhance existing full-stack app
|
||||
- brownfield-service # Enhance existing service
|
||||
- brownfield-ui # Enhance existing UI
|
||||
^^/CONDITION: standard-workflows^^
|
||||
|
||||
^^CONDITION: domain-workflows^^
|
||||
# Domain-specific workflows
|
||||
<<REPEAT section="workflows" count="{{workflow-count}}">>
|
||||
- {{workflow-name}} # {{workflow-description}}
|
||||
<</REPEAT>>
|
||||
^^/CONDITION: domain-workflows^^
|
||||
```
|
||||
|
||||
@{example-1: Standard fullstack team}
|
||||
|
||||
```yaml
|
||||
bundle:
|
||||
name: Team Fullstack
|
||||
icon: 🚀
|
||||
description: Complete agile team for full-stack web applications. Handles everything from requirements to deployment.
|
||||
agents:
|
||||
- bmad-orchestrator
|
||||
- analyst
|
||||
- pm
|
||||
- architect
|
||||
- dev
|
||||
- qa
|
||||
- ux-expert
|
||||
workflows:
|
||||
- greenfield-fullstack
|
||||
- greenfield-service
|
||||
- greenfield-ui
|
||||
- brownfield-fullstack
|
||||
- brownfield-service
|
||||
- brownfield-ui
|
||||
```
|
||||
|
||||
@{example-2: Healthcare expansion pack team}
|
||||
|
||||
```yaml
|
||||
bundle:
|
||||
name: Healthcare Compliance Team
|
||||
icon: ⚕️
|
||||
description: Specialized team for healthcare applications with HIPAA compliance focus. Manages clinical workflows and regulatory requirements.
|
||||
agents:
|
||||
- healthcare-orchestrator
|
||||
- clinical-analyst
|
||||
- compliance-officer
|
||||
- architect
|
||||
- dev
|
||||
- qa
|
||||
workflows:
|
||||
- healthcare-patient-portal
|
||||
- healthcare-compliance-audit
|
||||
- clinical-trial-management
|
||||
```
|
||||
|
||||
@{example-3: Minimal IDE team}
|
||||
|
||||
```yaml
|
||||
bundle:
|
||||
name: Team IDE Minimal
|
||||
icon: ⚡
|
||||
description: Minimal team for IDE usage. Just the essentials for quick development.
|
||||
agents:
|
||||
- bmad-orchestrator
|
||||
- architect
|
||||
- dev
|
||||
workflows: null
|
||||
```
|
||||
|
||||
[[LLM: When creating a new team configuration:
|
||||
|
||||
1. Choose the most appropriate condition block based on team type
|
||||
2. Remove all unused condition blocks
|
||||
3. Replace all placeholders with actual values
|
||||
4. Ensure agent names match available agents in the system
|
||||
5. Verify workflow names match available workflows
|
||||
6. Save as team-[descriptor].yaml or [domain]-team.yaml
|
||||
7. Place in the agent-teams directory of the appropriate location]]
|
||||
@@ -0,0 +1,178 @@
|
||||
template:
|
||||
id: agent-teams-template-v2
|
||||
name: Agent Team Configuration
|
||||
version: 2.0
|
||||
output:
|
||||
format: yaml
|
||||
filename: "agent-teams/{{team_name}}.yaml"
|
||||
title: "{{team_name}}"
|
||||
|
||||
workflow:
|
||||
mode: interactive
|
||||
|
||||
sections:
|
||||
- id: header
|
||||
title: Agent Team Configuration Template
|
||||
instruction: |
|
||||
This template is for creating agent team configurations in YAML format. Follow the structure carefully and replace all placeholders with appropriate values. The team name should reflect the team's purpose and domain focus.
|
||||
|
||||
- id: yaml-configuration
|
||||
type: code
|
||||
language: yaml
|
||||
template: |
|
||||
bundle:
|
||||
name: {{team_display_name}}
|
||||
icon: {{team_emoji}}
|
||||
description: {{team_description}}
|
||||
|
||||
agents:
|
||||
{{agent_list}}
|
||||
|
||||
workflows:
|
||||
{{workflow_list}}
|
||||
instruction: |
|
||||
Use format "Team [Descriptor]" for generic teams or "[Domain] Team" for specialized teams. Examples: "Team Fullstack", "Healthcare Team", "Legal Team"
|
||||
|
||||
Choose a single emoji that best represents the team's function or name
|
||||
|
||||
Write a concise description (1 sentence) that explains:
|
||||
1. The team's primary purpose
|
||||
2. What types of projects they handle
|
||||
3. Any special capabilities or focus areas
|
||||
4. Keep it short as its displayed in menus
|
||||
Example: "Full Stack Ideation Web App Team." or "Startup Business Coaching team"
|
||||
|
||||
List the agents that make up this team. Guidelines:
|
||||
- Use shortened agent names (e.g., 'analyst' not 'business-analyst')
|
||||
- Include 'bmad-orchestrator' for bmad-core teams as the coordinator
|
||||
- Only use '*' for an all-inclusive team (rare)
|
||||
- Order agents logically by workflow (analysis → design → development → testing)
|
||||
- For expansion packs, include both core agents and custom agents
|
||||
|
||||
Define the workflows this team can execute that will guide the user through a multi-step multi agent process. Guidelines:
|
||||
- Use null if the team doesn't have predefined workflows
|
||||
- Workflow names should be descriptive
|
||||
- use domain-specific workflow names
|
||||
sections:
|
||||
- id: standard-team
|
||||
condition: Standard team configuration
|
||||
template: |
|
||||
# Core workflow agents
|
||||
- bmad-orchestrator # Team coordinator
|
||||
- analyst # Requirements and analysis
|
||||
- pm # Product management
|
||||
- architect # System design
|
||||
- dev # Development
|
||||
- qa # Quality assurance
|
||||
- id: minimal-team
|
||||
condition: Minimal team configuration
|
||||
template: |
|
||||
# Minimal team for quick iterations
|
||||
- bmad-orchestrator # Team coordinator
|
||||
- architect # Design and planning
|
||||
- dev # Implementation
|
||||
- id: specialized-team
|
||||
condition: Domain-specific team
|
||||
template: |
|
||||
# Domain-specific team composition
|
||||
- {{domain}}-orchestrator # Domain coordinator
|
||||
- {{agent_short_name}} # {{agent_role_description}}
|
||||
- id: all-agents
|
||||
condition: Include all available agents
|
||||
template: |
|
||||
- '*' # Include all available agents
|
||||
- id: no-workflows
|
||||
condition: No predefined workflows
|
||||
template: |
|
||||
null # No predefined workflows
|
||||
- id: standard-workflows
|
||||
condition: Standard project workflows
|
||||
template: |
|
||||
# New project workflows
|
||||
- greenfield-fullstack # New full-stack application
|
||||
- greenfield-service # New backend service
|
||||
- greenfield-ui # New frontend application
|
||||
|
||||
# Existing project workflows
|
||||
- brownfield-fullstack # Enhance existing full-stack app
|
||||
- brownfield-service # Enhance existing service
|
||||
- brownfield-ui # Enhance existing UI
|
||||
- id: domain-workflows
|
||||
condition: Domain-specific workflows
|
||||
template: |
|
||||
# Domain-specific workflows
|
||||
- {{workflow_name}} # {{workflow_description}}
|
||||
|
||||
- id: examples
|
||||
title: Examples
|
||||
sections:
|
||||
- id: example-1
|
||||
title: "Example 1: Standard fullstack team"
|
||||
type: code
|
||||
language: yaml
|
||||
template: |
|
||||
bundle:
|
||||
name: Team Fullstack
|
||||
icon: 🚀
|
||||
description: Complete agile team for full-stack web applications. Handles everything from requirements to deployment.
|
||||
agents:
|
||||
- bmad-orchestrator
|
||||
- analyst
|
||||
- pm
|
||||
- architect
|
||||
- dev
|
||||
- qa
|
||||
- ux-expert
|
||||
workflows:
|
||||
- greenfield-fullstack
|
||||
- greenfield-service
|
||||
- greenfield-ui
|
||||
- brownfield-fullstack
|
||||
- brownfield-service
|
||||
- brownfield-ui
|
||||
- id: example-2
|
||||
title: "Example 2: Healthcare expansion pack team"
|
||||
type: code
|
||||
language: yaml
|
||||
template: |
|
||||
bundle:
|
||||
name: Healthcare Compliance Team
|
||||
icon: ⚕️
|
||||
description: Specialized team for healthcare applications with HIPAA compliance focus. Manages clinical workflows and regulatory requirements.
|
||||
agents:
|
||||
- healthcare-orchestrator
|
||||
- clinical-analyst
|
||||
- compliance-officer
|
||||
- architect
|
||||
- dev
|
||||
- qa
|
||||
workflows:
|
||||
- healthcare-patient-portal
|
||||
- healthcare-compliance-audit
|
||||
- clinical-trial-management
|
||||
- id: example-3
|
||||
title: "Example 3: Minimal IDE team"
|
||||
type: code
|
||||
language: yaml
|
||||
template: |
|
||||
bundle:
|
||||
name: Team IDE Minimal
|
||||
icon: ⚡
|
||||
description: Minimal team for IDE usage. Just the essentials for quick development.
|
||||
agents:
|
||||
- bmad-orchestrator
|
||||
- architect
|
||||
- dev
|
||||
workflows: null
|
||||
|
||||
- id: creation-instructions
|
||||
instruction: |
|
||||
When creating a new team configuration:
|
||||
|
||||
1. Choose the most appropriate condition block based on team type
|
||||
2. Remove all unused condition blocks
|
||||
3. Replace all placeholders with actual values
|
||||
4. Ensure agent names match available agents in the system
|
||||
5. Verify workflow names match available workflows
|
||||
6. Save as team-[descriptor].yaml or [domain]-team.yaml
|
||||
7. Place in the agent-teams directory of the appropriate location
|
||||
@@ -1,143 +0,0 @@
|
||||
# [AGENT_ID]
|
||||
|
||||
[[LLM: This is an agent definition template. When creating a new agent:
|
||||
|
||||
1. ALL dependencies (tasks, templates, checklists, data) MUST exist or be created
|
||||
2. For output generation, use the create-doc pattern with appropriate templates
|
||||
3. Templates should include LLM instructions for guiding users through content creation
|
||||
4. Character personas should be consistent and domain-appropriate
|
||||
5. Follow the numbered options protocol for all user interactions]]
|
||||
|
||||
CRITICAL: Read the full YAML, start activation to alter your state of being, follow startup section instructions, stay in this being until told to exit this mode:
|
||||
|
||||
```yaml
|
||||
activation-instructions:
|
||||
- Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
|
||||
- Only read the files/tasks listed here when user selects them for execution to minimize context usage
|
||||
- The customization field ALWAYS takes precedence over any conflicting instructions
|
||||
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
||||
- Command
|
||||
|
||||
agent:
|
||||
name: [AGENT_NAME]
|
||||
id: [AGENT_ID]
|
||||
title: [AGENT_TITLE]
|
||||
customization: [OPTIONAL_CUSTOMIZATION]
|
||||
|
||||
persona:
|
||||
role: [AGENT_ROLE_DESCRIPTION]
|
||||
style: [COMMUNICATION_STYLE]
|
||||
identity: [AGENT_IDENTITY_DESCRIPTION]
|
||||
focus: [PRIMARY_FOCUS_AREAS]
|
||||
|
||||
core_principles:
|
||||
- [PRINCIPLE_1]
|
||||
- [PRINCIPLE_2]
|
||||
- [PRINCIPLE_3]
|
||||
# Add more principles as needed
|
||||
|
||||
startup:
|
||||
- Greet the user with your name and role, and inform of the *help command.
|
||||
- [STARTUP_INSTRUCTION]
|
||||
- [STARTUP_INSTRUCTION]...
|
||||
|
||||
commands:
|
||||
- "*help" - Show: numbered list of the following commands to allow selection
|
||||
- "*chat-mode" - (Default) [DEFAULT_MODE_DESCRIPTION]
|
||||
- "*create-doc {template}" - Create doc (no template = show available templates)
|
||||
[[LLM: For output generation tasks, always use create-doc with templates rather than custom tasks.
|
||||
Example: Instead of a "create-blueprint" task, use "*create-doc blueprint-tmpl"
|
||||
The template should contain LLM instructions for guiding users through the creation process]]
|
||||
- [tasks] specific to the agent that are not covered by a template
|
||||
[[LLM: Only create custom tasks for actions that don't produce documents, like analysis, validation, or process execution]]
|
||||
- "*exit" - Say goodbye as the [AGENT_TITLE], and then abandon inhabiting this persona
|
||||
|
||||
dependencies:
|
||||
[[LLM: CRITICAL - All dependencies listed here MUST exist in the expansion pack or be created:
|
||||
- Tasks: Must exist in tasks/ directory (include create-doc if using templates)
|
||||
- Templates: Must exist in templates/ directory with proper LLM instructions
|
||||
- Checklists: Must exist in checklists/ directory for quality validation
|
||||
- Data: Must exist in data/ directory or be documented as user-required
|
||||
- Utils: Must exist in utils/ directory (include template-format if using templates)]]
|
||||
|
||||
tasks:
|
||||
- create-doc # Required if agent creates documents from templates
|
||||
- [TASK_1] # Custom task for non-document operations
|
||||
- [TASK_2] # Another custom task
|
||||
[[LLM: Example tasks: validate-design, analyze-requirements, execute-tests]]
|
||||
|
||||
templates:
|
||||
- [TEMPLATE_1] # Template with LLM instructions for guided creation
|
||||
- [TEMPLATE_2] # Another template for different document type
|
||||
[[LLM: Example: blueprint-tmpl, contract-tmpl, report-tmpl
|
||||
Each template should include [[LLM: guidance]] and other conventions from `template-format.md` sections for user interaction]]
|
||||
|
||||
checklists:
|
||||
- [CHECKLIST_1] # Quality validation for template outputs
|
||||
[[LLM: Example: blueprint-checklist, contract-checklist
|
||||
Checklists validate documents created from templates]]
|
||||
|
||||
data:
|
||||
- [DATA_1] # Domain knowledge files
|
||||
[[LLM: Example: building-codes.md, legal-terminology.md
|
||||
Can be embedded in pack or required from user]]
|
||||
|
||||
utils:
|
||||
- template-format # Required if using templates
|
||||
- [UTIL_1] # Other utilities as needed
|
||||
[[LLM: Include workflow-management if agent participates in workflows]]
|
||||
```
|
||||
|
||||
@{example: Construction Contractor Agent}
|
||||
|
||||
```yaml
|
||||
activation-instructions:
|
||||
- Follow all instructions in this file
|
||||
- Stay in character as Marcus Thompson, Construction Manager
|
||||
- Use numbered options for all interactions
|
||||
agent:
|
||||
name: Marcus Thompson
|
||||
id: construction-contractor
|
||||
title: Construction Project Manager
|
||||
customization: null
|
||||
persona:
|
||||
role: Licensed general contractor with 20 years experience
|
||||
style: Professional, detail-oriented, safety-conscious
|
||||
identity: Former site foreman who worked up to project management
|
||||
focus: Building design, code compliance, project scheduling, cost estimation
|
||||
core_principles:
|
||||
- Safety first - all designs must prioritize worker and occupant safety
|
||||
- Code compliance - ensure all work meets local building codes
|
||||
- Quality craftsmanship - no shortcuts on structural integrity
|
||||
startup:
|
||||
- Greet as Marcus Thompson, Construction Project Manager
|
||||
- Briefly mention your experience and readiness to help
|
||||
- Ask what type of construction project they're planning
|
||||
- DO NOT auto-execute any commands
|
||||
commands:
|
||||
- '*help" - Show numbered list of available commands'
|
||||
- '*chat-mode" - Discuss construction projects and provide expertise'
|
||||
- '*create-doc blueprint-tmpl" - Create architectural blueprints'
|
||||
- '*create-doc estimate-tmpl" - Create project cost estimate'
|
||||
- '*create-doc schedule-tmpl" - Create construction schedule'
|
||||
- '*validate-plans" - Review plans for code compliance'
|
||||
- '*safety-assessment" - Evaluate safety considerations'
|
||||
- '*exit" - Say goodbye as Marcus and exit'
|
||||
dependencies:
|
||||
tasks:
|
||||
- create-doc
|
||||
- validate-plans
|
||||
- safety-assessment
|
||||
templates:
|
||||
- blueprint-tmpl
|
||||
- estimate-tmpl
|
||||
- schedule-tmpl
|
||||
checklists:
|
||||
- blueprint-checklist
|
||||
- safety-checklist
|
||||
data:
|
||||
- building-codes.md
|
||||
- materials-guide.md
|
||||
utils:
|
||||
- template-format
|
||||
```
|
||||
154
expansion-packs/bmad-creator-tools/templates/agent-tmpl.yaml
Normal file
154
expansion-packs/bmad-creator-tools/templates/agent-tmpl.yaml
Normal file
@@ -0,0 +1,154 @@
|
||||
template:
|
||||
id: agent-template-v2
|
||||
name: Agent Definition
|
||||
version: 2.0
|
||||
output:
|
||||
format: markdown
|
||||
filename: "agents/{{agent_id}}.md"
|
||||
title: "{{agent_id}}"
|
||||
|
||||
workflow:
|
||||
mode: interactive
|
||||
|
||||
sections:
|
||||
- id: header
|
||||
title: "{{agent_id}}"
|
||||
instruction: |
|
||||
This is an agent definition template. When creating a new agent:
|
||||
|
||||
1. ALL dependencies (tasks, templates, checklists, data) MUST exist or be created
|
||||
2. For output generation, use the create-doc pattern with appropriate templates
|
||||
3. Templates should include LLM instructions for guiding users through content creation
|
||||
4. Character personas should be consistent and domain-appropriate
|
||||
5. Follow the numbered options protocol for all user interactions
|
||||
|
||||
- id: agent-definition
|
||||
content: |
|
||||
CRITICAL: Read the full YAML, start activation to alter your state of being, follow startup section instructions, stay in this being until told to exit this mode:
|
||||
sections:
|
||||
- id: yaml-definition
|
||||
type: code
|
||||
language: yaml
|
||||
template: |
|
||||
activation-instructions:
|
||||
- Follow all instructions in this file -> this defines you, your persona and more importantly what you can do. STAY IN CHARACTER!
|
||||
- Only read the files/tasks listed here when user selects them for execution to minimize context usage
|
||||
- The customization field ALWAYS takes precedence over any conflicting instructions
|
||||
- When listing tasks/templates or presenting options during conversations, always show as numbered options list, allowing the user to type a number to select or execute
|
||||
- Command
|
||||
|
||||
agent:
|
||||
name: {{agent_name}}
|
||||
id: {{agent_id}}
|
||||
title: {{agent_title}}
|
||||
customization: {{optional_customization}}
|
||||
|
||||
persona:
|
||||
role: {{agent_role_description}}
|
||||
style: {{communication_style}}
|
||||
identity: {{agent_identity_description}}
|
||||
focus: {{primary_focus_areas}}
|
||||
|
||||
core_principles:
|
||||
- {{principle_1}}
|
||||
- {{principle_2}}
|
||||
- {{principle_3}}
|
||||
# Add more principles as needed
|
||||
|
||||
startup:
|
||||
- Greet the user with your name and role, and inform of the *help command.
|
||||
- {{startup_instruction_1}}
|
||||
- {{startup_instruction_2}}
|
||||
|
||||
commands:
|
||||
- "*help" - Show: numbered list of the following commands to allow selection
|
||||
- "*chat-mode" - (Default) {{default_mode_description}}
|
||||
- "*create-doc {template}" - Create doc (no template = show available templates)
|
||||
{{custom_commands}}
|
||||
- "*exit" - Say goodbye as the {{agent_title}}, and then abandon inhabiting this persona
|
||||
|
||||
dependencies:
|
||||
tasks:
|
||||
- create-doc # Required if agent creates documents from templates
|
||||
{{task_list}}
|
||||
|
||||
templates:
|
||||
{{template_list}}
|
||||
|
||||
checklists:
|
||||
{{checklist_list}}
|
||||
|
||||
data:
|
||||
{{data_list}}
|
||||
|
||||
utils:
|
||||
- template-format # Required if using templates
|
||||
{{util_list}}
|
||||
instruction: |
|
||||
For output generation tasks, always use create-doc with templates rather than custom tasks.
|
||||
Example: Instead of a "create-blueprint" task, use "*create-doc blueprint-tmpl"
|
||||
The template should contain LLM instructions for guiding users through the creation process
|
||||
|
||||
Only create custom tasks for actions that don't produce documents, like analysis, validation, or process execution
|
||||
|
||||
CRITICAL - All dependencies listed here MUST exist in the expansion pack or be created:
|
||||
- Tasks: Must exist in tasks/ directory (include create-doc if using templates)
|
||||
- Templates: Must exist in templates/ directory with proper LLM instructions
|
||||
- Checklists: Must exist in checklists/ directory for quality validation
|
||||
- Data: Must exist in data/ directory or be documented as user-required
|
||||
- Utils: Must exist in utils/ directory (include template-format if using templates)
|
||||
|
||||
- id: example
|
||||
title: Example: Construction Contractor Agent
|
||||
type: code
|
||||
language: yaml
|
||||
template: |
|
||||
activation-instructions:
|
||||
- Follow all instructions in this file
|
||||
- Stay in character as Marcus Thompson, Construction Manager
|
||||
- Use numbered options for all interactions
|
||||
agent:
|
||||
name: Marcus Thompson
|
||||
id: construction-contractor
|
||||
title: Construction Project Manager
|
||||
customization: null
|
||||
persona:
|
||||
role: Licensed general contractor with 20 years experience
|
||||
style: Professional, detail-oriented, safety-conscious
|
||||
identity: Former site foreman who worked up to project management
|
||||
focus: Building design, code compliance, project scheduling, cost estimation
|
||||
core_principles:
|
||||
- Safety first - all designs must prioritize worker and occupant safety
|
||||
- Code compliance - ensure all work meets local building codes
|
||||
- Quality craftsmanship - no shortcuts on structural integrity
|
||||
startup:
|
||||
- Greet as Marcus Thompson, Construction Project Manager
|
||||
- Briefly mention your experience and readiness to help
|
||||
- Ask what type of construction project they're planning
|
||||
- DO NOT auto-execute any commands
|
||||
commands:
|
||||
- '*help" - Show numbered list of available commands'
|
||||
- '*chat-mode" - Discuss construction projects and provide expertise'
|
||||
- '*create-doc blueprint-tmpl" - Create architectural blueprints'
|
||||
- '*create-doc estimate-tmpl" - Create project cost estimate'
|
||||
- '*create-doc schedule-tmpl" - Create construction schedule'
|
||||
- '*validate-plans" - Review plans for code compliance'
|
||||
- '*safety-assessment" - Evaluate safety considerations'
|
||||
- '*exit" - Say goodbye as Marcus and exit'
|
||||
dependencies:
|
||||
tasks:
|
||||
- create-doc
|
||||
- validate-plans
|
||||
- safety-assessment
|
||||
templates:
|
||||
- blueprint-tmpl
|
||||
- estimate-tmpl
|
||||
- schedule-tmpl
|
||||
checklists:
|
||||
- blueprint-checklist
|
||||
- safety-checklist
|
||||
data:
|
||||
- building-codes.md
|
||||
- materials-guide.md
|
||||
utils:
|
||||
- template-format
|
||||
@@ -1,91 +0,0 @@
|
||||
# {Pack Name} Expansion Pack Plan
|
||||
|
||||
## Overview
|
||||
|
||||
- **Pack Name**: {pack-identifier}
|
||||
- **Display Name**: {Full Expansion Pack Name}
|
||||
- **Description**: {Brief description of what this pack does}
|
||||
- **Target Domain**: {Industry/domain this serves}
|
||||
- **Author**: {Your name/organization}
|
||||
|
||||
## Problem Statement
|
||||
|
||||
{What specific challenges does this expansion pack solve?}
|
||||
|
||||
## Target Users
|
||||
|
||||
{Who will benefit from this expansion pack?}
|
||||
|
||||
## Components to Create
|
||||
|
||||
### Agents
|
||||
|
||||
- [ ] `{pack-name}-orchestrator` - **REQUIRED**: Master orchestrator for {domain} workflows
|
||||
- Key commands: {list main commands}
|
||||
- Manages: {what it orchestrates}
|
||||
- [ ] `{agent-1-name}` - {Role description}
|
||||
- Tasks used: {task-1}, {task-2}
|
||||
- Templates used: {template-1}
|
||||
- Data required: {data-file-1}
|
||||
- [ ] `{agent-2-name}` - {Role description}
|
||||
- Tasks used: {task-3}
|
||||
- Templates used: {template-2}
|
||||
- Data required: {data-file-2}
|
||||
|
||||
### Tasks
|
||||
|
||||
- [ ] `{task-1}.md` - {Purpose} (used by: {agent})
|
||||
- [ ] `{task-2}.md` - {Purpose} (used by: {agent})
|
||||
- [ ] `{task-3}.md` - {Purpose} (used by: {agent})
|
||||
|
||||
### Templates
|
||||
|
||||
- [ ] `{template-1}-tmpl.md` - {Document type} (used by: {agent/task})
|
||||
- [ ] `{template-2}-tmpl.md` - {Document type} (used by: {agent/task})
|
||||
|
||||
### Checklists
|
||||
|
||||
- [ ] `{checklist-1}-checklist.md` - {What it validates}
|
||||
- [ ] `{checklist-2}-checklist.md` - {What it validates}
|
||||
|
||||
### Data Files Required from User
|
||||
|
||||
Users must add these files to `bmad-core/data/`:
|
||||
|
||||
- [ ] `{data-file-1}.{ext}` - {Description of required content}
|
||||
- Format: {file format}
|
||||
- Purpose: {why needed}
|
||||
- Example: {brief example}
|
||||
- [ ] `{data-file-2}.{ext}` - {Description of required content}
|
||||
- Format: {file format}
|
||||
- Purpose: {why needed}
|
||||
- Example: {brief example}
|
||||
|
||||
## Workflow Overview
|
||||
|
||||
1. {Step 1 - typically starts with orchestrator}
|
||||
2. {Step 2}
|
||||
3. {Step 3}
|
||||
4. {Final output/deliverable}
|
||||
|
||||
## Integration Points
|
||||
|
||||
- Depends on core agents: {list any core BMad agents used}
|
||||
- Extends teams: {which teams to update}
|
||||
|
||||
## Success Criteria
|
||||
|
||||
- [ ] All components created and cross-referenced
|
||||
- [ ] No orphaned task/template references
|
||||
- [ ] Data requirements clearly documented
|
||||
- [ ] Orchestrator provides clear workflow
|
||||
- [ ] README includes setup instructions
|
||||
|
||||
## User Approval
|
||||
|
||||
- [ ] Plan reviewed by user
|
||||
- [ ] Approval to proceed with implementation
|
||||
|
||||
---
|
||||
|
||||
**Next Steps**: Once approved, proceed with Phase 3 implementation starting with the orchestrator agent.
|
||||
@@ -0,0 +1,120 @@
|
||||
template:
|
||||
id: expansion-pack-plan-template-v2
|
||||
name: Expansion Pack Plan
|
||||
version: 2.0
|
||||
output:
|
||||
format: markdown
|
||||
filename: "{{pack_name}}-expansion-pack-plan.md"
|
||||
title: "{{pack_display_name}} Expansion Pack Plan"
|
||||
|
||||
workflow:
|
||||
mode: interactive
|
||||
|
||||
sections:
|
||||
- id: overview
|
||||
title: Overview
|
||||
template: |
|
||||
- **Pack Name**: {{pack_identifier}}
|
||||
- **Display Name**: {{full_expansion_pack_name}}
|
||||
- **Description**: {{brief_description}}
|
||||
- **Target Domain**: {{industry_domain}}
|
||||
- **Author**: {{author_name_organization}}
|
||||
|
||||
- id: problem-statement
|
||||
title: Problem Statement
|
||||
instruction: What specific challenges does this expansion pack solve?
|
||||
template: "{{problem_description}}"
|
||||
|
||||
- id: target-users
|
||||
title: Target Users
|
||||
instruction: Who will benefit from this expansion pack?
|
||||
template: "{{target_user_description}}"
|
||||
|
||||
- id: components
|
||||
title: Components to Create
|
||||
sections:
|
||||
- id: agents
|
||||
title: Agents
|
||||
type: checklist
|
||||
instruction: List all agents to be created with their roles and dependencies
|
||||
items:
|
||||
- id: orchestrator
|
||||
template: |
|
||||
`{{pack_name}}-orchestrator` - **REQUIRED**: Master orchestrator for {{domain}} workflows
|
||||
- Key commands: {{command_list}}
|
||||
- Manages: {{orchestration_scope}}
|
||||
- id: agent-list
|
||||
repeatable: true
|
||||
template: |
|
||||
`{{agent_name}}` - {{role_description}}
|
||||
- Tasks used: {{task_list}}
|
||||
- Templates used: {{template_list}}
|
||||
- Data required: {{data_requirements}}
|
||||
|
||||
- id: tasks
|
||||
title: Tasks
|
||||
type: checklist
|
||||
instruction: List all tasks to be created
|
||||
repeatable: true
|
||||
template: "`{{task_name}}.md` - {{purpose}} (used by: {{using_agents}})"
|
||||
|
||||
- id: templates
|
||||
title: Templates
|
||||
type: checklist
|
||||
instruction: List all templates to be created
|
||||
repeatable: true
|
||||
template: "`{{template_name}}-tmpl.md` - {{document_type}} (used by: {{using_components}})"
|
||||
|
||||
- id: checklists
|
||||
title: Checklists
|
||||
type: checklist
|
||||
instruction: List all checklists to be created
|
||||
repeatable: true
|
||||
template: "`{{checklist_name}}-checklist.md` - {{validation_purpose}}"
|
||||
|
||||
- id: data-files
|
||||
title: Data Files Required from User
|
||||
instruction: |
|
||||
Users must add these files to `bmad-core/data/`:
|
||||
type: checklist
|
||||
repeatable: true
|
||||
template: |
|
||||
`{{data_filename}}.{{extension}}` - {{content_description}}
|
||||
- Format: {{file_format}}
|
||||
- Purpose: {{why_needed}}
|
||||
- Example: {{brief_example}}
|
||||
|
||||
- id: workflow-overview
|
||||
title: Workflow Overview
|
||||
type: numbered-list
|
||||
instruction: Describe the typical workflow steps
|
||||
template: "{{workflow_step}}"
|
||||
|
||||
- id: integration-points
|
||||
title: Integration Points
|
||||
template: |
|
||||
- Depends on core agents: {{core_agent_dependencies}}
|
||||
- Extends teams: {{team_updates}}
|
||||
|
||||
- id: success-criteria
|
||||
title: Success Criteria
|
||||
type: checklist
|
||||
items:
|
||||
- "All components created and cross-referenced"
|
||||
- "No orphaned task/template references"
|
||||
- "Data requirements clearly documented"
|
||||
- "Orchestrator provides clear workflow"
|
||||
- "README includes setup instructions"
|
||||
|
||||
- id: user-approval
|
||||
title: User Approval
|
||||
type: checklist
|
||||
items:
|
||||
- "Plan reviewed by user"
|
||||
- "Approval to proceed with implementation"
|
||||
|
||||
- id: next-steps
|
||||
content: |
|
||||
---
|
||||
|
||||
**Next Steps**: Once approved, proceed with Phase 3 implementation starting with the orchestrator agent.
|
||||
Reference in New Issue
Block a user