doc updates

This commit is contained in:
Brian Madison
2025-10-26 23:25:48 -05:00
parent b753fb293b
commit 334e24823a
19 changed files with 2707 additions and 792 deletions

View File

@@ -361,6 +361,13 @@ When building agents:
- Workflows can be incomplete (marked "todo")
- Workflow paths must be valid or "todo"
**Workflow Interaction Styles** (BMAD v6 default):
- **Intent-based + Interactive**: Workflows adapt to user context and skill level
- Workflows collaborate with users, not just extract data
- See workflow-creation-guide.md "Instruction Styles" section for details
- When creating workflows for your agent, default to intent-based unless you need prescriptive control
### With Tasks
- Tasks are single operations

View File

@@ -128,10 +128,51 @@
<action>Transform their natural language capabilities into technical YAML command structure, explaining the implementation approach as you structure each capability into workflows, actions, or prompts</action>
<check if="agent will invoke workflows or have significant user interaction">
<action>Discuss interaction style for this agent:
Since this agent will {{invoke_workflows/interact_significantly}}, consider how it should interact with users:
**For Full/Module Agents with workflows:**
**Interaction Style** (for workflows this agent invokes):
- **Intent-based (Recommended)**: Workflows adapt conversation to user context, skill level, needs
- **Prescriptive**: Workflows use structured questions with specific options
- **Mixed**: Strategic use of both (most workflows will be mixed)
**Interactivity Level** (for workflows this agent invokes):
- **High (Collaborative)**: Constant user collaboration, iterative refinement
- **Medium (Guided)**: Key decision points with validation
- **Low (Autonomous)**: Minimal input, final review
Explain: "Most BMAD v6 workflows default to **intent-based + medium/high interactivity**
for better user experience. Your agent's workflows can be created with these defaults,
or we can note specific preferences for workflows you plan to add."
**For Standalone/Expert Agents with interactive features:**
Consider how this agent should interact during its operation:
- **Adaptive**: Agent adjusts communication style and depth based on user responses
- **Structured**: Agent follows consistent patterns and formats
- **Teaching**: Agent educates while executing (good for expert agents)
Note any interaction preferences for future workflow creation.
</action>
</check>
<action>If they seem engaged, explore whether they'd like to add special prompts for complex analyses or critical setup steps for agent activation</action>
<action>Build the YAML menu structure naturally from the conversation, ensuring each command has proper trigger, workflow/action reference, and description</action>
<action>For commands that will invoke workflows, note whether those workflows exist or need to be created:
- Existing workflows: Verify paths are correct
- New workflows needed: Note that they'll be created with intent-based + interactive defaults unless specified
</action>
<example>
```yaml
menu: