siesa-agents 2.1.36 → 2.1.37

package/_bmad/bmb/workflows/agent/steps-c/step-08b-metadata-validation.md

@@ -0,0 +1,135 @@
+---
+name: 'step-07b-metadata-validation'
+description: 'Validate agent metadata properties'
+
+# File References
+nextStepFile: './step-08c-persona-validation.md'
+agentMetadata: ../data/agent-metadata.md
+builtYaml: '{bmb_creations_output_folder}/{agent-name}/{agent-name}.agent.yaml'
+
+# Task References
+advancedElicitationTask: '{project-root}/_bmad/core/workflows/advanced-elicitation/workflow.xml'
+partyModeWorkflow: '{project-root}/_bmad/core/workflows/party-mode/workflow.md'
+---
+
+# STEP GOAL
+
+Validate that the agent's metadata properties (name, description, version, tags, category, etc.) are properly formatted, complete, and follow BMAD standards.
+
+## MANDATORY EXECUTION RULES
+
+- **NEVER skip validation checks** - All metadata fields must be verified
+- **ALWAYS load both reference documents** - agentMetadata.md AND the builtYaml
+- **NEVER modify files without user approval** - Report findings first, await menu selection
+- **ALWAYS use absolute paths** when referencing files
+- **CRITICAL:** This is a validation step, not an editing step
+
+## EXECUTION PROTOCOLS
+
+### Protocol 1: Load and Compare
+1. Read the metadata validation reference from `{agentMetadata}`
+2. Read the built agent YAML from `{builtYaml}`
+3. Extract the metadata section from the builtYaml
+4. Compare actual metadata against validation rules
+
+### Protocol 2: Validation Checks
+Perform these checks systematically:
+
+1. **Required Fields Existence**
+   - [ ] name: Present and non-empty
+   - [ ] description: Present and non-empty
+   - [ ] version: Present and follows semantic versioning (X.Y.Z)
+   - [ ] category: Present and matches valid category
+   - [ ] tags: Present as array, not empty
+
+2. **Format Validation**
+   - [ ] name: Uses kebab-case, no spaces
+   - [ ] description: 50-200 characters (unless intentionally brief)
+   - [ ] version: Follows semver pattern (e.g., 1.0.0)
+   - [ ] tags: Array of lowercase strings with hyphens
+   - [ ] category: Matches one of the allowed categories
+
+3. **Content Quality**
+   - [ ] description: Clear and concise, explains what the agent does
+   - [ ] tags: Relevant to agent's purpose (3-7 tags recommended)
+   - [ ] category: Most appropriate classification
+
+4. **Standards Compliance**
+   - [ ] No prohibited characters in fields
+   - [ ] No redundant or conflicting information
+   - [ ] Consistent formatting with other agents
+
+### Protocol 3: Report Findings
+Organize your report into three sections:
+
+**PASSING CHECKS** (List what passed)
+```
+✓ Required fields present
+✓ Version format valid (1.0.0)
+✓ Name follows kebab-case convention
+```
+
+**WARNINGS** (Non-blocking issues)
+```
+⚠ Description is brief (45 chars, recommended 50-200)
+⚠ Only 2 tags provided, 3-7 recommended
+```
+
+**FAILURES** (Blocking issues that must be fixed)
+```
+✗ Missing required field: version
+✗ Invalid version format: "v1.0" (should be "1.0.0")
+✗ Category "custom-type" not in allowed list
+```
+
+### Protocol 4: Menu System
+
+#### 5. Present MENU OPTIONS
+
+Display: "**Select an Option:** [A] Advanced Elicitation [F] Fix Findings [P] Party Mode [C] Continue"
+
+#### Menu Handling Logic:
+
+- IF A: Execute {advancedElicitationTask}, and when finished redisplay the menu
+- IF F: Apply auto-fixes to {builtYaml} for identified issues, then redisplay the menu
+- IF P: Execute {partyModeWorkflow}, and when finished redisplay the menu
+- IF C: Proceed to next validation step, update frontmatter, then only then load, read entire file, then execute {nextStepFile}
+- IF Any other comments or queries: help user respond then [Redisplay Menu Options](#5-present-menu-options)
+
+#### EXECUTION RULES:
+
+- ALWAYS halt and wait for user input after presenting menu
+- ONLY proceed to next step when user selects 'C'
+- After other menu items execution, return to this menu
+- User can chat or ask questions - always respond and then end with display again of the menu options
+
+## CONTEXT BOUNDARIES
+
+**IN SCOPE:**
+- Metadata section of agent.yaml (name, description, version, tags, category, author, license, etc.)
+- Referencing the agentMetadata.md validation rules
+- Comparing against BMAD standards
+
+**OUT OF SCOPE:**
+- Persona fields (handled in step-07c)
+- Menu items (handled in step-07d)
+- System architecture (handled in step-07e)
+- Capability implementation (handled in step-07f)
+
+**DO NOT:**
+- Validate persona properties in this step
+- Suggest major feature additions
+- Question the agent's core purpose
+- Modify fields beyond metadata
+
+## CRITICAL STEP COMPLETION NOTE
+
+ONLY WHEN [C continue option] is selected and [validation complete with any findings addressed], will you then load and read fully `{nextStepFile}` to execute and begin [persona validation].
+
+## SUCCESS METRICS
+
+✓ **Complete Success:** All checks pass, no failures, warnings are optional
+✓ **Partial Success:** Failures fixed via [F] option, warnings acknowledged
+✓ **Failure:** Blocking failures remain when user selects [C]
+
+**CRITICAL:** Never proceed to next step if blocking failures exist and user hasn't acknowledged them.

package/_bmad/bmb/workflows/agent/steps-c/step-08c-persona-validation.md

@@ -0,0 +1,161 @@
+---
+name: 'step-07c-persona-validation'
+description: 'Validate persona fields and principles'
+
+# File References
+nextStepFile: './step-08d-menu-validation.md'
+personaProperties: ../data/persona-properties.md
+principlesCrafting: ../data/principles-crafting.md
+builtYaml: '{bmb_creations_output_folder}/{agent-name}/{agent-name}.agent.yaml'
+
+# Task References
+advancedElicitationTask: '{project-root}/_bmad/core/workflows/advanced-elicitation/workflow.xml'
+partyModeWorkflow: '{project-root}/_bmad/core/workflows/party-mode/workflow.md'
+---
+
+# STEP GOAL
+
+Validate that the agent's persona (role, tone, expertise, principles, constraints) is well-defined, consistent, and aligned with its purpose.
+
+## MANDATORY EXECUTION RULES
+
+- **NEVER skip validation checks** - All persona fields must be verified
+- **ALWAYS load both reference documents** - personaProperties.md AND principlesCrafting.md
+- **NEVER modify files without user approval** - Report findings first, await menu selection
+- **ALWAYS use absolute paths** when referencing files
+- **CRITICAL:** This is a validation step, not an editing step
+
+## EXECUTION PROTOCOLS
+
+### Protocol 1: Load and Compare
+1. Read the persona validation reference from `{personaProperties}`
+2. Read the principles crafting guide from `{principlesCrafting}`
+3. Read the built agent YAML from `{builtYaml}`
+4. Extract the persona section from the builtYaml
+5. Compare actual persona against validation rules
+
+### Protocol 2: Validation Checks
+Perform these checks systematically:
+
+1. **Required Fields Existence**
+   - [ ] role: Present, clear, and specific
+   - [ ] tone: Present and appropriate to role
+   - [ ] expertise: Present and relevant to agent's purpose
+   - [ ] principles: Present as array, not empty (if applicable)
+   - [ ] constraints: Present as array, not empty (if applicable)
+
+2. **Content Quality - Role**
+   - [ ] Role is specific (not generic like "assistant")
+   - [ ] Role aligns with agent's purpose and menu items
+   - [ ] Role is achievable within LLM capabilities
+   - [ ] Role scope is appropriate (not too broad/narrow)
+
+3. **Content Quality - Tone**
+   - [ ] Tone is clearly defined (professional, friendly, authoritative, etc.)
+   - [ ] Tone matches the role and target users
+   - [ ] Tone is consistent throughout the definition
+   - [ ] Tone examples or guidance provided if nuanced
+
+4. **Content Quality - Expertise**
+   - [ ] Expertise areas are relevant to role
+   - [ ] Expertise claims are realistic for LLM
+   - [ ] Expertise domains are specific (not just "knowledgeable")
+   - [ ] Expertise supports the menu capabilities
+
+5. **Content Quality - Principles**
+   - [ ] Principles are actionable (not vague platitudes)
+   - [ ] Principles guide behavior and decisions
+   - [ ] Principles are consistent with role
+   - [ ] 3-7 principles recommended (not overwhelming)
+   - [ ] Each principle is clear and specific
+
+6. **Content Quality - Constraints**
+   - [ ] Constraints define boundaries clearly
+   - [ ] Constraints are enforceable (measurable/observable)
+   - [ ] Constraints prevent undesirable behaviors
+   - [ ] Constraints don't contradict principles
+
+7. **Consistency Checks**
+   - [ ] Role, tone, expertise, principles all align
+   - [ ] No contradictions between principles and constraints
+   - [ ] Persona supports the menu items defined
+   - [ ] Language and terminology consistent
+
+### Protocol 3: Report Findings
+Organize your report into three sections:
+
+**PASSING CHECKS** (List what passed)
+```
+✓ Role is specific and well-defined
+✓ Tone clearly articulated and appropriate
+✓ Expertise aligns with agent purpose
+✓ Principles are actionable and clear
+```
+
+**WARNINGS** (Non-blocking issues)
+```
+⚠ Only 2 principles provided, 3-7 recommended for richer guidance
+⚠ No constraints defined - consider adding boundaries
+⚠ Expertise areas are broad, could be more specific
+```
+
+**FAILURES** (Blocking issues that must be fixed)
+```
+✗ Role is generic ("assistant") - needs specificity
+✗ Tone undefined - creates inconsistent behavior
+✗ Principles are vague ("be helpful" - not actionable)
+✗ Contradiction: Principle says "be creative", constraint says "follow strict rules"
+```
+
+### Protocol 4: Menu System
+
+#### 5. Present MENU OPTIONS
+
+Display: "**Select an Option:** [A] Advanced Elicitation [F] Fix Findings [P] Party Mode [C] Continue"
+
+#### Menu Handling Logic:
+
+- IF A: Execute {advancedElicitationTask}, and when finished redisplay the menu
+- IF F: Apply auto-fixes to {builtYaml} for identified issues, then redisplay the menu
+- IF P: Execute {partyModeWorkflow}, and when finished redisplay the menu
+- IF C: Proceed to next validation step, update frontmatter, then only then load, read entire file, then execute {nextStepFile}
+- IF Any other comments or queries: help user respond then [Redisplay Menu Options](#5-present-menu-options)
+
+#### EXECUTION RULES:
+
+- ALWAYS halt and wait for user input after presenting menu
+- ONLY proceed to next step when user selects 'C'
+- After other menu items execution, return to this menu
+- User can chat or ask questions - always respond and then end with display again of the menu options
+
+## CONTEXT BOUNDARIES
+
+**IN SCOPE:**
+- Persona section of agent.yaml (role, tone, expertise, principles, constraints)
+- Referencing personaProperties.md and principlesCrafting.md
+- Evaluating persona clarity, specificity, and consistency
+- Checking alignment between persona elements
+
+**OUT OF SCOPE:**
+- Metadata fields (handled in step-07b)
+- Menu items (handled in step-07d)
+- System architecture (handled in step-07e)
+- Technical implementation details
+
+**DO NOT:**
+- Validate metadata properties in this step
+- Question the agent's core purpose (that's for earlier steps)
+- Suggest additional menu items
+- Modify fields beyond persona
+
+## CRITICAL STEP COMPLETION NOTE
+
+ONLY WHEN [C continue option] is selected and [validation complete with any findings addressed], will you then load and read fully `{nextStepFile}` to execute and begin [menu validation].
+
+## SUCCESS METRICS
+
+✓ **Complete Success:** All checks pass, persona is well-defined and consistent
+✓ **Partial Success:** Failures fixed via [F] option, warnings acknowledged
+✓ **Failure:** Blocking failures remain when user selects [C]
+
+**CRITICAL:** A weak or generic persona is a blocking issue that should be fixed before proceeding.

package/_bmad/bmb/workflows/agent/steps-c/step-08d-menu-validation.md

@@ -0,0 +1,158 @@
+---
+name: 'step-07d-menu-validation'
+description: 'Validate menu items and patterns'
+
+# File References
+nextStepFile: './step-08e-structure-validation.md'
+agentMenuPatterns: ../data/agent-menu-patterns.md
+builtYaml: '{bmb_creations_output_folder}/{agent-name}/{agent-name}.agent.yaml'
+
+# Task References
+advancedElicitationTask: '{project-root}/_bmad/core/workflows/advanced-elicitation/workflow.xml'
+partyModeWorkflow: '{project-root}/_bmad/core/workflows/party-mode/workflow.md'
+---
+
+# STEP GOAL
+
+Validate that the agent's menu (commands/tools) follows BMAD patterns, is well-structured, properly documented, and aligns with the agent's persona and purpose.
+
+## MANDATORY EXECUTION RULES
+
+- **NEVER skip validation checks** - All menu items must be verified
+- **ALWAYS load the reference document** - agentMenuPatterns.md
+- **NEVER modify files without user approval** - Report findings first, await menu selection
+- **ALWAYS use absolute paths** when referencing files
+- **CRITICAL:** This is a validation step, not an editing step
+
+## EXECUTION PROTOCOLS
+
+### Protocol 1: Load and Compare
+1. Read the menu patterns reference from `{agentMenuPatterns}`
+2. Read the built agent YAML from `{builtYaml}`
+3. Extract the menu/commands section from the builtYaml
+4. Compare actual menu against validation rules
+
+### Protocol 2: Validation Checks
+Perform these checks systematically:
+
+1. **Menu Structure**
+   - [ ] Menu section exists and is properly formatted
+   - [ ] At least one menu item defined (unless intentionally tool-less)
+   - [ ] Menu items follow proper YAML structure
+   - [ ] Each item has required fields (name, description, pattern)
+
+2. **Menu Item Requirements**
+   For each menu item:
+   - [ ] name: Present, unique, uses kebab-case
+   - [ ] description: Clear and concise
+   - [ ] pattern: Valid regex pattern or tool reference
+   - [ ] scope: Appropriate scope defined (if applicable)
+
+3. **Pattern Quality**
+   - [ ] Patterns are valid and testable
+   - [ ] Patterns are specific enough to match intended inputs
+   - [ ] Patterns are not overly restrictive
+   - [ ] Patterns use appropriate regex syntax
+
+4. **Description Quality**
+   - [ ] Each item has clear description
+   - [ ] Descriptions explain what the item does
+   - [ ] Descriptions are consistent in style
+   - [ ] Descriptions help users understand when to use
+
+5. **Alignment Checks**
+   - [ ] Menu items align with agent's role/purpose
+   - [ ] Menu items are supported by agent's expertise
+   - [ ] Menu items fit within agent's constraints
+   - [ ] Menu items are appropriate for target users
+
+6. **Completeness**
+   - [ ] Core capabilities for this role are covered
+   - [ ] No obvious missing functionality
+   - [ ] Menu scope is appropriate (not too sparse/overloaded)
+   - [ ] Related functionality is grouped logically
+
+7. **Standards Compliance**
+   - [ ] No prohibited patterns or commands
+   - [ ] No security vulnerabilities in patterns
+   - [ ] No ambiguous or conflicting items
+   - [ ] Consistent naming conventions
+
+### Protocol 3: Report Findings
+Organize your report into three sections:
+
+**PASSING CHECKS** (List what passed)
+```
+✓ Menu structure properly formatted
+✓ 5 menu items defined, all with required fields
+✓ All patterns are valid regex
+✓ Menu items align with agent role
+```
+
+**WARNINGS** (Non-blocking issues)
+```
+⚠ Item "analyze-data" description is vague
+⚠ No menu item for [common capability X]
+⚠ Pattern for "custom-command" very broad, may over-match
+```
+
+**FAILURES** (Blocking issues that must be fixed)
+```
+✗ Duplicate menu item name: "process" appears twice
+✗ Invalid regex pattern: "[unclosed bracket"
+✗ Menu item "system-admin" violates security guidelines
+✗ No menu items defined for agent type that requires tools
+```
+
+### Protocol 4: Menu System
+
+#### 5. Present MENU OPTIONS
+
+Display: "**Select an Option:** [A] Advanced Elicitation [F] Fix Findings [P] Party Mode [C] Continue"
+
+#### Menu Handling Logic:
+
+- IF A: Execute {advancedElicitationTask}, and when finished redisplay the menu
+- IF F: Apply auto-fixes to {builtYaml} for identified issues, then redisplay the menu
+- IF P: Execute {partyModeWorkflow}, and when finished redisplay the menu
+- IF C: Proceed to next validation step, update frontmatter, then only then load, read entire file, then execute {nextStepFile}
+- IF Any other comments or queries: help user respond then [Redisplay Menu Options](#5-present-menu-options)
+
+#### EXECUTION RULES:
+
+- ALWAYS halt and wait for user input after presenting menu
+- ONLY proceed to next step when user selects 'C'
+- After other menu items execution, return to this menu
+- User can chat or ask questions - always respond and then end with display again of the menu options
+
+## CONTEXT BOUNDARIES
+
+**IN SCOPE:**
+- Menu/commands section of agent.yaml
+- Referencing agentMenuPatterns.md
+- Menu structure, patterns, and alignment
+- Individual menu item validation
+
+**OUT OF SCOPE:**
+- Metadata fields (handled in step-07b)
+- Persona fields (handled in step-07c)
+- System architecture (handled in step-07e)
+- Workflow/capability implementation (handled in step-07f)
+
+**DO NOT:**
+- Validate metadata or persona in this step
+- Suggest entirely new capabilities (that's for earlier steps)
+- Question whether menu items are "good enough" qualitatively beyond standards
+- Modify fields beyond menu
+
+## CRITICAL STEP COMPLETION NOTE
+
+ONLY WHEN [C continue option] is selected and [validation complete with any findings addressed], will you then load and read fully `{nextStepFile}` to execute and begin [structure validation].
+
+## SUCCESS METRICS
+
+✓ **Complete Success:** All checks pass, menu is well-structured and aligned
+✓ **Partial Success:** Failures fixed via [F] option, warnings acknowledged
+✓ **Failure:** Blocking failures remain when user selects [C]
+
+**CRITICAL:** Invalid regex patterns or security vulnerabilities in menu items are blocking issues.