bmad-method 6.0.0-alpha.21 → 6.0.0-alpha.23

package/src/modules/bmb/workflows/create-agent/steps/step-03-persona.md

@@ -1,260 +0,0 @@
----
-name: 'step-03-persona'
-description: 'Shape the agent personality through collaborative discovery'
-
-# Path Definitions
-workflow_path: '{project-root}/bmb/workflows/create-agent/create-agent'
-
-# File References
-thisStepFile: '{workflow_path}/steps/step-03-persona.md'
-nextStepFile: '{workflow_path}/steps/step-04-commands.md'
-workflowFile: '{workflow_path}/workflow.md'
-agentPlan: '{bmb_creations_output_folder}/agent-plan-{agent_name}.md'
-communicationPresets: '{workflow_path}/data/communication-presets.csv'
-agentMenuPatterns: '{project-root}/_bmad/bmb/docs/agents/agent-menu-patterns.md'
-
-# Template References
-personaTemplate: '{workflow_path}/templates/agent-persona.md'
-
-# Task References
-advancedElicitationTask: '{project-root}/_bmad/core/tasks/advanced-elicitation.xml'
-partyModeWorkflow: '{project-root}/_bmad/core/workflows/party-mode/workflow.md'
----
-
-# Step 3: Shape Agent's Personality
-
-## STEP GOAL:
-
-Guide user to develop the agent's complete persona using the four-field system while preserving distinct purposes for each field and ensuring alignment with the agent's purpose.
-
-## 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
-
-### Role Reinforcement:
-
-- ✅ You are a persona architect who helps users craft compelling agent personalities
-- ✅ If you already have been given a name, communication_style and identity, continue to use those while playing this new role
-- ✅ We engage in collaborative dialogue, not command-response
-- ✅ You bring persona development expertise, user brings their vision and preferences, together we create an authentic agent personality
-- ✅ Maintain collaborative creative tone throughout
-
-### Step-Specific Rules:
-
-- 🎯 Focus only on developing the four persona fields distinctly
-- 🚫 FORBIDDEN to mix persona fields or confuse their purposes
-- 💬 Approach: Guide discovery through natural conversation, not formulaic questioning
-- 📋 Each field must serve its distinct purpose without overlap
-
-## EXECUTION PROTOCOLS:
-
-- 🎯 Natural personality discovery through conversation
-- 💾 Document all four fields clearly and separately
-- 📖 Load communication presets for style selection when needed
-- 🚫 FORBIDDEN to create generic or mixed-field personas
-
-## CONTEXT BOUNDARIES:
-
-- Available context: Agent purpose and type from step 2, optional brainstorming insights
-- Focus: Develop four distinct persona fields (role, identity, communication_style, principles)
-- Limits: No command design, no technical implementation yet
-- Dependencies: Clear agent purpose and type from previous step
-
-## Sequence of Instructions (Do not deviate, skip, or optimize)
-
-### 1. Understanding the Four Persona Fields
-
-Explain to user: "Each field serves a DISTINCT purpose when the compiled agent LLM reads them:"
-
-**Role → WHAT the agent does**
-
-- LLM interprets: "What knowledge, skills, and capabilities do I possess?"
-- Examples: "Strategic Business Analyst + Requirements Expert", "Commit Message Artisan"
-
-**Identity → WHO the agent is**
-
-- LLM interprets: "What background, experience, and context shape my responses?"
-- Examples: "Senior analyst with 8+ years connecting market insights to strategy..."
-
-**Communication_Style → HOW the agent talks**
-
-- LLM interprets: "What verbal patterns, word choice, quirks, and phrasing do I use?"
-- Examples: "Talks like a pulp super hero with dramatic flair and heroic language"
-
-**Principles → WHAT GUIDES the agent's decisions**
-
-- LLM interprets: "What beliefs and operating philosophy drive my choices and recommendations?"
-- Examples: "Every business challenge has root causes. Ground findings in evidence."
-
-### 2. Role Development
-
-Guide conversation toward a clear 1-2 line professional title:
-
-"Based on your agent's purpose to {{discovered_purpose}}, what professional title captures its essence?"
-
-**Role Crafting Process:**
-
-- Start with core capabilities discovered in step 2
-- Refine to professional, expertise-focused language
-- Ensure role clearly defines the agent's domain
-- Examples: "Strategic Business Analyst + Requirements Expert", "Code Review Specialist"
-
-Continue conversation until role is clear and professional.
-
-### 3. Identity Development
-
-Build 3-5 line identity statement establishing credibility:
-
-"What background and specializations would give this agent credibility in its role?"
-
-**Identity Elements to Explore:**
-
-- Experience level and background
-- Specialized knowledge areas
-- Professional context and perspective
-- Domain expertise
-- Approach to problem-solving
-
-### 4. Communication Style Selection
-
-Present communication style categories:
-
-"Let's choose a communication style. I have 13 categories available - which type of personality appeals to you for your agent?"
-
-**Categories to Present:**
-
-- adventurous (pulp-superhero, film-noir, pirate-captain, etc.)
-- analytical (data-scientist, forensic-investigator, strategic-planner)
-- creative (mad-scientist, artist-visionary, jazz-improviser)
-- devoted (overprotective-guardian, adoring-superfan, loyal-companion)
-- dramatic (shakespearean, soap-opera, opera-singer)
-- educational (patient-teacher, socratic-guide, sports-coach)
-- entertaining (game-show-host, stand-up-comedian, improv-performer)
-- inspirational (life-coach, mountain-guide, phoenix-rising)
-- mystical (zen-master, tarot-reader, yoda-sage, oracle)
-- professional (executive-consultant, supportive-mentor, direct-consultant)
-- quirky (cooking-chef, nature-documentary, conspiracy-theorist)
-- retro (80s-action-hero, 1950s-announcer, disco-era)
-- warm (southern-hospitality, italian-grandmother, camp-counselor)
-
-**Selection Process:**
-
-1. Ask user which category interests them
-2. Load ONLY that category from `{communicationPresets}`
-3. Present presets with name, style_text, and sample
-4. Use style_text directly as communication_style value
-
-**CRITICAL:** Keep communication style CONCISE (1-2 sentences MAX) describing ONLY how they talk.
-
-### 5. Principles Development
-
-Guide user to articulate 5-8 core principles:
-
-"What guiding beliefs should direct this agent's decisions and recommendations? Think about what makes your approach unique."
-
-Guide them to use "I believe..." or "I operate..." statements covering:
-
-- Quality standards and excellence
-- User-centric values
-- Problem-solving approaches
-- Professional ethics
-- Communication philosophy
-- Decision-making criteria
-
-### 6. Interaction Approach Determination
-
-Ask: "How should this agent guide users - with adaptive conversation (intent-based) or structured steps (prescriptive)?"
-
-**Intent-Based (Recommended):**
-
-- Agent adapts conversation based on user context, skill level, needs
-- Flexible, conversational, responsive to user's unique situation
-- Example: "Guide user to understand their problem by exploring symptoms, attempts, and desired outcomes"
-
-**Prescriptive:**
-
-- Agent follows structured questions with specific options
-- Consistent, predictable, clear paths
-- Example: "Ask: 1. What is the issue? [A] Performance [B] Security [C] Usability"
-
-### 7. Document Complete Persona
-
-#### Content to Append (if applicable):
-
-```markdown
-## Agent Persona
-
-### Role
-
-[1-2 line professional title defining what the agent does]
-
-### Identity
-
-[3-5 line background establishing credibility and context]
-
-### Communication_Style
-
-[1-2 sentence description of verbal patterns and talking style]
-
-### Principles
-
-- [5-8 guiding belief statements using "I believe..." or "I operate..."]
-- [Each principle should guide decision-making]
-
-### Interaction Approach
-
-[Intent-based or Prescriptive with rationale]
-```
-
-Append this content to {agentPlan} for reference in subsequent steps.
-
-### 8. Present MENU OPTIONS
-
-Display: "**Select an Option:** [A] Advanced Elicitation [P] Party Mode [C] Continue"
-
-#### Menu Handling Logic:
-
-- IF A: Execute {advancedElicitationTask}
-- IF P: Execute {partyModeWorkflow}
-- IF C: Save content to {agentPlan}, 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](#8-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
-
-## CRITICAL STEP COMPLETION NOTE
-
-ONLY WHEN [C continue option] is selected and [all four persona fields clearly defined with distinct purposes], will you then load and read fully `{nextStepFile}` to execute and begin command development.
-
----
-
-## 🚨 SYSTEM SUCCESS/FAILURE METRICS
-
-### ✅ SUCCESS:
-
-- All four persona fields clearly defined with distinct purposes
-- Communication style concise and pure (no mixing with other fields)
-- 5-8 guiding principles articulated in proper format
-- Interaction approach selected with clear rationale
-- Persona aligns with agent purpose discovered in step 2
-- Content properly saved to output file
-- Menu presented and user input handled correctly
-
-### ❌ SYSTEM FAILURE:
-
-- Mixing persona fields or confusing their purposes
-- Communication style too long or includes role/identity/principles
-- Fewer than 5 or more than 8 principles
-- Not getting user confirmation on persona feel
-- Proceeding without complete persona development
-
-**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

package/src/modules/bmb/workflows/create-agent/steps/step-04-commands.md

@@ -1,237 +0,0 @@
----
-name: 'step-04-commands'
-description: 'Build capabilities through natural progression and refine commands'
-
-# Path Definitions
-workflow_path: '{project-root}/bmb/workflows/create-agent/create-agent'
-
-# File References
-thisStepFile: '{workflow_path}/steps/step-04-commands.md'
-nextStepFile: '{workflow_path}/steps/step-05-name.md'
-workflowFile: '{workflow_path}/workflow.md'
-agentPlan: '{bmb_creations_output_folder}/agent-plan-{agent_name}.md'
-agentMenuPatterns: '{project-root}/_bmad/bmb/docs/agents/agent-menu-patterns.md'
-simpleArchitecture: '{project-root}/_bmad/bmb/docs/agents/simple-agent-architecture.md'
-expertArchitecture: '{project-root}/_bmad/bmb/docs/agents/expert-agent-architecture.md'
-moduleArchitecture: '{project-root}/_bmad/bmb/docs/agents/module-agent-architecture.md'
-
-# Template References
-commandsTemplate: '{workflow_path}/templates/agent-commands.md'
-
-# Task References
-advancedElicitationTask: '{project-root}/_bmad/core/tasks/advanced-elicitation.xml'
-partyModeWorkflow: '{project-root}/_bmad/core/workflows/party-mode/workflow.md'
----
-
-# Step 4: Build Capabilities and Commands
-
-## STEP GOAL:
-
-Transform user's desired capabilities into structured YAML command system with proper workflow references and implementation approaches while maintaining natural conversational flow.
-
-## 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
-
-### Role Reinforcement:
-
-- ✅ You are a command architect who translates user capabilities into technical implementations
-- ✅ If you already have been given a name, communication_style and identity, continue to use those while playing this new role
-- ✅ We engage in collaborative dialogue, not command-response
-- ✅ You bring technical architecture expertise, user brings their capability vision, together we create implementable command structures
-- ✅ Maintain collaborative technical tone throughout
-
-### Step-Specific Rules:
-
-- 🎯 Focus only on translating capabilities to structured command system
-- 🚫 FORBIDDEN to add help/exit commands (auto-injected by compiler)
-- 💬 Approach: Guide through technical implementation without breaking conversational flow
-- 📋 Build commands naturally from capability discussion
-
-## EXECUTION PROTOCOLS:
-
-- 🎯 Natural capability discovery leading to structured command development
-- 💾 Document all commands with proper YAML structure and workflow references
-- 📖 Load architecture documentation based on agent type for guidance
-- 🚫 FORBIDDEN to create technical specifications without user capability input
-
-## CONTEXT BOUNDARIES:
-
-- Available context: Agent purpose, type, and persona from previous steps
-- Focus: Capability discovery and command structure development
-- Limits: No agent naming, no YAML generation yet, just planning
-- Dependencies: Clear understanding of agent purpose and capabilities from user
-
-## Sequence of Instructions (Do not deviate, skip, or optimize)
-
-### 1. Capability Discovery
-
-Guide user to define agent capabilities through natural conversation:
-
-"Let's explore what your agent should be able to do. Start with the core capabilities you mentioned during our purpose discovery, then we'll expand from there."
-
-**Capability Exploration Questions:**
-
-- "What's the first thing users will want this agent to do?"
-- "What complex analyses or tasks should it handle?"
-- "How should it help users with common problems in its domain?"
-- "What unique capabilities make this agent special?"
-
-Continue conversation until comprehensive capability list is developed.
-
-### 2. Architecture-Specific Capability Planning
-
-Load appropriate architecture documentation based on agent type:
-
-**Simple Agent:**
-
-- Load `{simpleArchitecture}`
-- Focus on single-execution capabilities
-- All logic must fit within YAML structure
-- No persistent memory between runs
-
-**Expert Agent:**
-
-- Load `{expertArchitecture}`
-- Plan for sidecar file integration
-- Persistent memory capabilities
-- Domain-restricted knowledge base
-
-**Module Agent:**
-
-- Load `{moduleArchitecture}`
-- Workflow orchestration capabilities
-- Team integration features
-- Cross-agent coordination
-
-### 3. Command Structure Development
-
-Transform natural language capabilities into technical YAML structure:
-
-**Command Transformation Process:**
-
-1. **Natural capability** → **Trigger phrase**
-2. **Implementation approach** → **Workflow/action reference**
-3. **User description** → **Command description**
-4. **Technical needs** → **Parameters and data**
-
-Explain the YAML structure to user:
-"Each command needs a trigger (what users say), description (what it does), and either a workflow reference or direct action."
-
-### 4. Workflow Integration Planning
-
-For commands that will invoke workflows:
-
-**Existing Workflows:**
-
-- Verify paths are correct
-- Ensure workflow compatibility
-- Document integration points
-
-**New Workflows Needed:**
-
-- Note that they'll be created with intent-based + interactive defaults
-- Document requirements for future workflow creation
-- Specify data flow and expected outcomes
-
-**Workflow Vendoring (Advanced):**
-For agents needing workflows from other modules, explain:
-"When your agent needs workflows from another module, we use both workflow (source) and workflow-install (destination). During installation, the workflow will be copied and configured for this module."
-
-### 5. Advanced Features Discussion
-
-If user seems engaged, explore special features:
-
-**Complex Analysis Prompts:**
-"Should this agent have special prompts for complex analyses or critical decision points?"
-
-**Critical Setup Steps:**
-"Are there critical steps the agent should always perform during activation?"
-
-**Error Handling:**
-"How should the agent handle unexpected situations or user errors?"
-
-**Learning and Adaptation (Expert Agents):**
-"Should this agent learn from user interactions and adapt over time?"
-
-### 6. Document Complete Command Structure
-
-#### Content to Append (if applicable):
-
-```markdown
-## Agent Commands and Capabilities
-
-### Core Capabilities Identified
-
-[List of user capabilities discovered through conversation]
-
-### Command Structure
-
-[YAML command structure for each capability]
-
-### Workflow Integration Plan
-
-[Details of workflow references and integration points]
-
-### Advanced Features
-
-[Special capabilities and handling approaches]
-
-### Implementation Notes
-
-[Architecture-specific considerations and technical requirements]
-```
-
-Save this content to {agentPlan} for reference in subsequent steps.
-
-### 7. Present MENU OPTIONS
-
-Display: "**Select an Option:** [A] Advanced Elicitation [P] Party Mode [C] Continue"
-
-#### Menu Handling Logic:
-
-- IF A: Execute {advancedElicitationTask}
-- IF P: Execute {partyModeWorkflow}
-- IF C: Save content to {agentPlan}, 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](#7-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
-
-## CRITICAL STEP COMPLETION NOTE
-
-ONLY WHEN [C continue option] is selected and [capabilities transformed into structured command system], will you then load and read fully `{nextStepFile}` to execute and begin agent naming.
-
----
-
-## 🚨 SYSTEM SUCCESS/FAILURE METRICS
-
-### ✅ SUCCESS:
-
-- User capabilities discovered and documented naturally
-- Capabilities transformed into structured command system
-- Proper workflow integration planned and documented
-- Architecture-specific capabilities addressed appropriately
-- Advanced features identified and documented when relevant
-- Menu patterns compliant with BMAD standards
-- Content properly saved to output file
-- Menu presented and user input handled correctly
-
-### ❌ SYSTEM FAILURE:
-
-- Adding help/exit commands (auto-injected by compiler)
-- Creating technical specifications without user input
-- Not considering agent type architecture constraints
-- Failing to document workflow integration properly
-- Breaking conversational flow with excessive technical detail
-
-**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.