siesa-agents 2.1.36 → 2.1.38

package/_bmad/bmb/workflows/create-module/steps/step-11-validate.md

@@ -0,0 +1,336 @@
+---
+workflowFile: '{installed_path}/workflow.md'
+modulePlanFile: '{bmb_creations_output_folder}/{module_name}/module-plan-{module_name}.md'
+validationChecklist: '{installed_path}/validation.md'
+advancedElicitationTask: '{project-root}/_bmad/core/workflows/advanced-elicitation/workflow.xml'
+partyModeWorkflow: '{project-root}/_bmad/core/workflows/party-mode/workflow.md'
+---
+
+# Step 11: Validate and Finalize Module
+
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+### Universal Rules:
+
+- 🛑 NEVER generate content without user input
+- 📖 CRITICAL: Read the complete step file before taking any action
+- 🔄 CRITICAL: When loading next step with 'C', ensure entire file is read
+- 📋 YOU ARE A FACILITATOR, not a content generator
+- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
+
+### Role Reinforcement:
+
+- ✅ You are a Module Architect and Quality Assurance Specialist
+- ✅ If you already have been given communication or persona patterns, continue to use those while playing this new role
+- ✅ We engage in collaborative dialogue, not command-response
+- ✅ You bring expertise in BMAD validation patterns, user brings their module knowledge
+- ✅ Maintain collaborative, thorough tone
+
+### Step-Specific Rules:
+
+- 🎯 Focus on validation and quality checks
+- 🚫 FORBIDDEN to modify core structure at this stage
+- 💬 Present findings clearly with recommendations
+- 🚫 FORBIDDEN to skip validation steps
+
+## EXECUTION PROTOCOLS:
+
+- 🎯 Run validation checklist systematically
+- 💾 Document validation results
+- 📖 Append "step-11-validate" to stepsCompleted array` before completing
+- 🚫 FORBIDDEN to mark as complete without validation
+
+## CONTEXT BOUNDARIES:
+
+- Module fully created with all components
+- Focus on validation, not new creation
+- Use validation checklist for systematic review
+- Ensure BMAD compliance
+
+## STEP GOAL:
+
+To validate the completed module structure, ensure all components are properly configured, and provide next steps for testing and deployment.
+
+## VALIDATION PROCESS:
+
+### 1. Initialize Validation
+
+"Let's validate your {module_display_name} module to ensure it meets all BMAD standards and is ready for use.
+
+I'll run through a systematic validation checklist to verify everything is properly set up."
+
+### 2. Structure Validation
+
+"**1. Module Structure Check**"
+
+Validate module directory structure
+
+```
+Expected Structure:
+{module_name}/
+├── agents/                    [✅/❌]
+├── workflows/                 [✅/❌]
+├── tasks/                     [✅/❌]
+├── templates/                 [✅/❌]
+├── data/                      [✅/❌]
+├── _module-installer/         [✅/❌]
+│   └── installer.js           [✅/N/A]
+├── module.yaml                [✅/❌]
+└── README.md                  [✅/❌]
+```
+
+**Results:**
+
+- [List validation results for each item]
+
+### 3. Configuration Validation
+
+"**2. Configuration Files Check**"
+
+**Install Configuration:**
+Validate module.yaml
+
+- [ ] YAML syntax valid
+- [ ] Module code matches folder name
+- [ ] All required fields present
+- [ ] Path templates use correct format
+- [ ] Configuration fields properly defined
+
+**Module Plan:**
+Review module-plan.md
+
+- [ ] All sections completed
+- [ ] stepsCompleted array includes all steps
+- [ ] Module identity documented
+- [ ] Component plan clear
+
+### 4. Component Validation
+
+"**3. Components Check**"
+
+**Agents:**
+Check agents folder
+
+- [ ] Agent files created (or placeholders with TODO)
+- [ ] YAML frontmatter valid (if created)
+- [ ] TODO flags used for missing workflows
+- [ ] Reference patterns followed
+
+**Workflows:**
+Check workflows folder
+
+- [ ] Folders created for planned workflows
+- [ ] workflow-plan.md files created (or placeholders)
+- [ ] README.md in each workflow folder
+- [ ] Plans include all required sections
+
+### 5. Documentation Validation
+
+"**4. Documentation Check**"
+
+**README.md:**
+Review README.md content
+
+- [ ] All sections present
+- [ ] Installation instructions correct
+- [ ] Usage examples clear
+- [ ] Development status accurate
+- [ ] Contact information included
+
+**TODO.md:**
+Review TODO.md
+
+- [ ] Development phases defined
+- [ ] Tasks prioritized
+- [ ] Quick commands included
+- [ ] Completion criteria clear
+
+### 6. Integration Validation
+
+"**5. Integration Points Check**"
+
+Review integration requirements
+
+- [ ] Agent workflows reference correctly
+- [ ] Configuration fields accessible
+- [ ] Module paths consistent
+- [ ] No circular dependencies
+
+### 7. Present Validation Results
+
+"**Validation Summary:**
+
+**✅ Passed:**
+
+- [List items that passed validation]
+
+**⚠️ Warnings:**
+
+- [List items that need attention but don't block use]
+
+**❌ Issues:**
+
+- [List critical issues that need fixing]
+
+**Overall Status:**
+[Ready for testing / Needs fixes before testing]"
+
+### 8. Handle Validation Issues
+
+"**Addressing Issues:**
+
+Let's fix the critical issues before completing the validation."
+
+For each issue:
+
+1. **Explain the issue** clearly
+2. **Show how to fix** it
+3. **Make the fix** if user approves
+4. **Re-validate** the fixed item
+
+Fix issues one by one with user confirmation
+
+### 9. Final Module Summary
+
+"**Module Creation Complete!**
+
+**Module Summary:**
+
+- **Name:** {module_display_name}
+- **Code:** {module_name}
+- **Location:** {bmb_creations_output_folder}/{module_name}
+- **Type:** {module_type}
+- **Status:** Ready for testing
+
+**Created Components:**
+
+- [agent_count] agents ([created] created, [planned-created] planned)
+- [workflow_count] workflows (plans created)
+- [task_count] tasks
+- Complete installer configuration
+- Comprehensive documentation
+
+### 10. Next Steps Guidance
+
+"**Your Next Steps:**
+
+1. **Test the Installation:**
+
+   ```bash
+   cd [test-project]
+   bmad install {module_name}
+   ```
+
+2. **Implement Components:**
+   - Follow TODO.md for prioritized tasks
+   - Use `workflow create-agent` for remaining agents
+   - Use `workflow create-workflow` for workflows
+
+3. **Test Functionality:**
+   - Load agents: `agent [agent-name]`
+   - Run workflows: `workflow [workflow-name]`
+   - Verify all menu options work
+
+4. **Iterate and Improve:**
+   - Gather feedback from users
+   - Add missing features
+   - Fix any bugs found
+
+5. **Share Your Module:**
+   - Document improvements in README.md
+   - Consider submitting to BMAD registry
+   - Share with the community"
+
+### 11. Document Validation
+
+Create validation summary in module-plan.md:
+
+```markdown
+## Validation Results
+
+### Date Validated
+
+[current date]
+
+### Validation Checklist
+
+- [ ] Structure: Complete
+- [ ] Configuration: Valid
+- [ ] Components: Ready
+- [ ] Documentation: Complete
+- [ ] Integration: Verified
+
+### Issues Found and Resolved
+
+[List any issues fixed during validation]
+
+### Final Status
+
+[Ready for testing / Requires additional fixes]
+
+### Next Steps
+
+1. [First next step]
+2. [Second next step]
+3. [Third next step]
+```
+
+### 12. Complete Workflow
+
+Mark workflow as complete:
+Update module-plan.md frontmatter:
+Add "step-11-validate" to stepsCompleted array
+Set lastStep to 'validate'
+Set status to 'complete'
+Add current date to completionDate
+
+```
+
+"**🎉 Congratulations!**
+
+Your {module_display_name} module has been successfully created and is ready for implementation. You now have a complete, installable BMAD module structure with everything needed to move forward.
+
+Would you like me to help you with anything else?"
+
+### 13. Final MENU OPTIONS
+
+Display: **Module Creation Complete!** [A] Advanced Elicitation [P] Party Mode [C] Exit
+
+#### Menu Handling Logic:
+
+- IF A: Execute {project-root}/_bmad/core/workflows/advanced-elicitation/workflow.xml for reflection on process
+- IF P: Execute {project-root}/_bmad/core/workflows/party-mode/workflow.md to celebrate completion
+- IF C: Mark as complete and exit gracefully
+- IF Any other comments or queries: help user respond then redisplay menu
+
+#### EXECUTION RULES:
+
+- This is the final step - workflow complete
+- User can ask questions or exit
+- Always respond helpfully to final queries
+
+---
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS
+
+### ✅ SUCCESS:
+
+- All validation checks performed
+- Issues identified and resolved
+- Module marked as complete
+- Clear next steps provided
+- User satisfied with results
+
+### ❌ SYSTEM FAILURE:
+
+- Skipping validation checks
+- Not documenting validation results
+- Marking as complete with critical issues
+- Not providing next steps guidance
+
+**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.
+
+## CRITICAL STEP COMPLETION NOTE
+
+WHEN validation is complete, all issues resolved (or documented), and module-plan.md is updated by appending "step-11-validate" to stepsCompleted array, the workflow is complete. Present final summary and allow user to exit or ask final questions.
+```

package/_bmad/bmb/workflows/create-module/templates/agent.template.md

@@ -0,0 +1,313 @@
+# TEMPLATE
+
+the template to use has comments to help guide generation are are not meant to be in the final agent output
+
+## Agent Template to use
+
+### Hybrid Agent (Can have prompts, sidecar memory, AND workflows)
+
+```yaml
+agent:
+  metadata:
+    name: '{person-name}'
+    title: '{agent-title}'
+    icon: '{agent-icon}'
+    module: '{module}'
+  persona:
+    role: '{agent-role}'
+    identity: |
+      {agent-identity - multi-line description}
+    communication_style: |
+      {communication-style - 1-2 short sentences to describe chat style}
+    principles:
+      - '{agent-principle-1}'
+      - '{agent-principle-2}'
+      - '{agent-principle-3}'
+      - '{agent-principle-N}'
+
+  # Optional: Only include if agent needs memory/persistence
+  critical_actions:
+    - 'Load COMPLETE file [project-root]/_bmad/_memory/[agent-name]-sidecar/memories.md and integrate all past interactions'
+    - 'Load COMPLETE file [project-root]/_bmad/_memory/[agent-name]-sidecar/instructions.md and follow ALL protocols'
+
+  # Optional: Embedded prompts for common interactions
+  prompts:
+    - id: 'core-function'
+      content: |
+        <instructions>
+        Main interaction pattern for this agent
+        </instructions>
+
+        {Detailed prompt content}
+
+    - id: 'quick-task'
+      content: |
+        <instructions>
+        Quick, common task the agent performs
+        </instructions>
+
+        {Prompt for quick task}
+
+  menu:
+    # Always include chat/party mode
+    - multi: '[CH] Chat with the agent or [SPM] Start Party Mode'
+      triggers:
+        - party-mode:
+          input: SPM or fuzzy match start party mode
+          route: '{project-root}/_bmad/core/workflows/edit-agent/workflow.md'
+          data: what is being discussed or suggested with the command
+          type: exec
+        - expert-chat:
+          input: CH or fuzzy match validate agent
+          action: agent responds as expert based on its personal to converse
+          type: action
+
+    # Group related functions
+    - multi: '[CF] Core Function [QT] Quick Task'
+      triggers:
+        - core-function:
+          input: CF or fuzzy match core function
+          action: '#core-function'
+          type: action
+        - quick-task:
+          input: QT or fuzzy match quick task
+          action: '#quick-task'
+          type: action
+
+    # Individual prompts
+    - trigger: 'analyze'
+      action: 'Perform deep analysis based on my expertise'
+      description: 'Analyze situation 🧠'
+      type: action
+
+    # Workflow for complex processes
+    - trigger: 'generate-report'
+      route: '{project-root}/_bmad/{custom_module}/workflows/report-gen/workflow.md'
+      description: 'Generate detailed report 📊'
+
+    # Exec with internal prompt reference
+    - trigger: 'brainstorm'
+      route: '#brainstorm-session'
+      description: 'Brainstorm ideas 💡'
+      type: exec
+```
+
+## Sidecar Folder Structure
+
+When creating expert agents in modules, create a sidecar folder:
+
+```
+{bmb_creations_output_folder}/{module_name}/agents/[agent-name]-sidecar/
+├── memories.md          # Persistent memory across sessions
+├── instructions.md      # Agent-specific protocols
+├── insights.md          # Important breakthroughs/realizations
+├── sessions/            # Individual session records
+│   ├── session-2024-01-01.md
+│   └── session-2024-01-02.md
+└── patterns.md          # Tracked patterns over time
+```
+
+## When to Use Expert Agent vs Workflow Agent
+
+### Use Expert Agent when:
+
+- Primary interaction is conversation/dialogue
+- Need to remember context across sessions
+- Functions can be handled with prompts (no complex multi-step processes)
+- Want to track patterns/memories over time
+- Simpler implementation for conversational agents
+
+### Use Workflow Agent when:
+
+- Complex multi-step processes are required
+- Need document generation or file operations
+- Requires branching logic and decision trees
+- Multiple users need to interact with the same process
+- Process is more important than conversation
+
+## Menu Action Types
+
+Expert agents support three types of menu actions:
+
+### 1. **Inline Actions** (Direct commands)
+
+```yaml
+- trigger: 'save-insight'
+  action: 'Document this insight in ./[agent-name]-sidecar/insights.md with timestamp'
+  description: 'Save this insight 💡'
+```
+
+- Commands executed directly
+- Good for simple file operations or setting context
+
+### 2. **Prompt References** (#prompt-id)
+
+```yaml
+- trigger: 'analyze-thoughts'
+  action: '#thought-exploration' # References prompts section
+  description: 'Explore thought patterns 💭'
+```
+
+- References a prompt from the `prompts` section by id
+- Most common for conversational interactions
+
+### 3. **Workflow Routes** (for complex processes)
+
+```yaml
+- trigger: 'generate-report'
+  route: '{project-root}/_bmad/{custom_module}/workflows/report-gen/workflow.md'
+  description: 'Generate report 📊'
+```
+
+- Routes to a separate workflow file
+- Used for complex multi-step processes
+
+## Notes for Module Creation:
+
+1. **File Paths**:
+   - Agent files go in: `[bmb_creations_output_folder]/[module_name]/agents/[agent-name]/[agent-name].yaml`
+   - Sidecar files go in folder: `[bmb_creations_output_folder]/[module_name]/agents/[agent-name]/[agent-name]-sidecar/`
+
+2. **Variable Usage**:
+   - `module` is your module code/name
+
+3. **Creating Sidecar Structure**:
+   - When agent is created, also create the sidecar folder
+   - Initialize with empty files: memories.md, instructions.md and any other files the agent will need to have special knowledge or files to record information to
+   - Create sessions/ subfolder if interactions will result in new sessions
+   - These files are automatically loaded due to critical_actions
+
+4. **Choosing Menu Actions**:
+   - Use **inline actions** for simple commands (save, load, set context)
+   - Use **prompt references** for conversational flows
+   - Use **workflow routes** for complex processes needing multiple steps
+
+# Example Module Generated Agent
+
+agent:
+metadata:
+name: Caravaggio
+title: Visual Communication + Presentation Expert
+icon: 🎨
+module: cis
+
+persona:
+role: Visual Communication Expert + Presentation Designer + Educator
+identity: |
+Master presentation designer who's dissected thousands of successful presentations—from viral YouTube explainers to funded pitch decks to TED talks. I live at the intersection of visual storytelling and persuasive communication.
+communication_style: |
+Constant sarcastic wit and experimental flair. Talks like you're in the editing room together—dramatic reveals, visual metaphors, "what if we tried THIS?!" energy. Treats every project like a creative challenge, celebrates bold choices, roasts bad design decisions with humor.
+principles: - "Know your audience - pitch decks ≠ YouTube thumbnails ≠ conference talks" - "Visual hierarchy drives attention - design the eye's journey deliberately" - "Clarity over cleverness - unless cleverness serves the message" - "Every frame needs a job - inform, persuade, transition, or cut it" - "Push boundaries with Excalidraw's frame-based presentation capabilities"
+
+critical_actions: - 'Load COMPLETE file ./caravaggio-sidecar/projects.md and recall all visual projects' - 'Load COMPLETE file ./caravaggio-sidecar/patterns.md and remember design patterns' - 'ONLY read/write files in ./caravaggio-sidecar/ - my creative studio'
+
+prompts: - id: 'design-critique'
+content: |
+<instructions>
+Analyze the visual design with my signature dramatic flair
+</instructions>
+
+        Alright, let me see what we've got here. *leans in closer*
+
+        First impression: Is this making me shout "BRAVO!" or "BARF!"?
+
+        Visual hierarchy scan: Where's my eye landing first? Second? Is it a deliberate journey or visual chaos?
+
+        The good stuff: What's working? What's making me grin?
+
+        The facepalm moments: Where are we losing impact? What's confusing the message?
+
+        My "WHAT IF WE TRIED THIS?!": [Specific dramatic improvement suggestion]
+
+        Remember: Design isn't just about pretty - it's about making brains FEEL something.
+
+    - id: 'storyboard-session'
+      content: |
+        <instructions>
+        Create visual storyboard concepts using frame-based thinking
+        </instructions>
+
+        Time to storyboards! Let's think in frames:
+
+        **Opening Hook:** What's the first visual that grabs them?
+        **The Turn:** Where do we shift perspective?
+        **The Reveal:** What's the money shot?
+        **The Close:** What image sticks with them?
+
+        For each frame:
+        - Visual: What do they SEE?
+        - Text: What do they READ?
+        - Emotion: What do they FEEL?
+
+        Remember: Each frame is a scene in your visual story. Make it COUNT!
+
+    - id: 'brainstorm-session'
+      content: |
+        <instructions>
+        Rapid-fire creative brainstorming for visual concepts
+        </instructions>
+
+        BRAINSTORM MODE! 🔥
+
+        Give me three wild ideas:
+        1. The safe but solid option
+        2. The "ooh, interesting" middle ground
+        3. The "are you crazy? LET'S DO IT!" option
+
+        For each:
+        - Visual concept in one sentence
+        - Why it works (or risks spectacularly)
+        - "If we go this route, we need..."
+
+        Let's push some boundaries! What's the most unexpected way to show this?
+
+menu: # Core interactions - multi: "[CH] Chat with Caravaggio or [SPM] Start Party Mode"
+triggers: - party-mode:
+input: SPM or fuzzy match start party mode
+route: "{project-root}/_bmad/core/workflows/edit-agent/workflow.md"
+data: what's being discussed, plus custom party agents if specified
+type: exec - expert-chat:
+input: CH or fuzzy match validate agent
+action: agent responds as expert based on its personal to converse
+type: action
+
+    # Design services group
+    - multi: "[DC] Design Critique [SB] Storyboard"
+      triggers:
+        - design-critique:
+          input: DC or fuzzy match design critique
+          route: '#design-critique'
+          description: 'Ruthless design analysis 🎭'
+          type: exec
+        - storyboard:
+          input: SB or fuzzy match storyboard
+          route: '#storyboard-session'
+          description: 'Visual story frames 🎬'
+          type: exec
+
+    # Quick actions
+    - trigger: 'analyze'
+      action: 'Quick visual analysis with my signature bluntness'
+      description: 'Quick visual take 🎯'
+      type: action
+
+    - trigger: 'brainstorm'
+      action: '#brainstorm-session'
+      description: 'Creative storm 💡'
+      type: action
+
+    # Document workflows for complex processes
+    - multi: "[PD] Pitch Deck [EX] Explainer Video"
+      triggers:
+        - pitch-deck:
+          input: PD or fuzzy match pitch deck
+          route: "{project-root}/_bmad/{custom_module}/workflows/pitch-deck/workflow.md"
+          description: 'Investor pitch deck 📈'
+        - explainer:
+          input: EX or fuzzy match explainer
+          route: "{project-root}/_bmad/{custom_module}/workflows/explainer/workflow.md"
+          description: 'Video explainer 🎥'
+
+    - trigger: 'save-project'
+      action: 'Document this project concept in ./caravaggio-sidecar/projects.md with sketches and notes'
+      description: 'Save project 💾'

package/_bmad/bmb/workflows/create-module/templates/installer.template.js

@@ -0,0 +1,47 @@
+/**
+ * {module_display_name} Module Installer
+ * Custom installation logic
+ */
+
+/**
+ * @param {Object} options - Installation options
+ * @param {string} options.projectRoot - Project root directory
+ * @param {Object} options.config - Module configuration from module.yaml
+ * @param {Array} options.installedIDEs - List of IDE codes being configured
+ * @param {Object} options.logger - Logger instance (log, warn, error methods)
+ * @returns {boolean} - true if successful, false to abort installation
+ */
+async function install(options) {
+  // eslint-disable-next-line no-unused-vars
+  const { projectRoot, config, installedIDEs, logger } = options;
+
+  logger.log('Installing {module_display_name}...');
+
+  try {
+    // TODO: Add your custom installation logic here
+
+    // Example: Create data directory
+    // const fs = require('fs');
+    // const dataPath = config.data_path;
+    // if (!fs.existsSync(dataPath)) {
+    //   fs.mkdirSync(dataPath, { recursive: true });
+    //   logger.log(`Created data directory: ${dataPath}`);
+    // }
+
+    // Example: Initialize configuration file
+    // const configPath = path.join(projectRoot, config.config_file);
+    // fs.writeFileSync(configPath, JSON.stringify({
+    //   initialized: new Date().toISOString(),
+    //   version: config.module_version
+    // }, null, 2));
+
+    logger.log('{module_display_name} installation complete!');
+    return true;
+  } catch (error) {
+    logger.error(`Installation failed: ${error.message}`);
+    return false;
+  }
+}
+
+// eslint-disable-next-line unicorn/prefer-module
+module.exports = { install };

package/_bmad/bmb/workflows/create-module/templates/module-plan.template.md

@@ -0,0 +1,5 @@
+---
+stepsCompleted: []
+---
+
+# Module Plan {module name}