siesa-agents 2.1.78 → 2.1.79

package/siesa-agents/bmm/workflows/4-implementation/code-review/steps/step-07-commit-push.md

@@ -0,0 +1,174 @@
+---
+name: 'step-07-commit-push'
+description: 'Safely commit and push verified code following centralized GitFlow guidelines'
+
+# Path Definitions
+workflow_path: '{project-root}/_siesa-agents/bmm/workflows/4-implementation/code-review'
+
+# File References
+thisStepFile: '{workflow_path}/steps/step-07-commit-push.md'
+workflowFile: '{project-root}/_siesa-agents/bmm/workflows/4-implementation/code-review/workflow.md'
+outputFile: '{output_folder}/review-{story_key}.md'
+
+# Data References
+sprint_status_file: '{implementation_artifacts}/sprint-status.yaml'
+
+# Centralized GitFlow Guidelines
+gitFlowGuide: '{project-root}/_siesa-agents/bmm/data/git-flow-siesa.md'
+---
+
+# Step 7: Commit & Push
+
+## STEP GOAL:
+
+To securely persist the verified and approved code changes to the repository following the **centralized GitFlow guidelines** defined in `{gitFlowGuide}`.
+
+## MANDATORY EXECUTION RULES:
+
+- 📖 **LOAD AND READ** `{gitFlowGuide}` before any Git operation
+- 🛑 ONLY execute if the story status is explicitly 'done' or 'completed'
+- 🌳 Ensure development branch follows the naming convention from the centralized guide
+- 📝 Commit messages must follow the standard from `{gitFlowGuide}` (Conventional Commits)
+
+## Sequence of Instructions
+
+### 1. Load GitFlow Guidelines
+
+<action>
+1. Load and read the entire file at `{gitFlowGuide}`.
+2. Extract and apply:
+   - **Commit Message Format**: From Section 3 (Conventional Commits)
+   - **Governance Rules**: From Section 4 (lowercase, protected branches)
+</action>
+
+### 2. Verification of Status
+
+**Goal**: Ensure we are authorized to push code.
+
+<action>
+1. Load `{sprint_status_file}`.
+2. Find the entry for `{{story_key}}` under `development_status`.
+3. Check if the value is `done` (or `completed`).
+</action>
+
+<check if="status != 'done' AND status != 'completed'">
+  <output>
+  ⚠️ **COMMIT ABORTED**: Story status is '{{status}}'.
+  Changes are only committed and pushed when the story is marked as 'done'.
+  </output>
+  <action>STOP execution. Do NOT run git commands.</action>
+</check>
+
+### 3. Branch Validation
+
+**Goal**: Ensure code is committed to the correct branch per GitFlow guidelines.
+
+<check if="status == 'done' OR status == 'completed'">
+
+  <action>
+  1. Run `git branch --show-current` to get `current_branch`.
+  2. Validate the branch follows the naming convention from `{gitFlowGuide}`:
+     - Pattern: `{parent}-{team}-{owner}-{rq}-{description}`
+     - Must be lowercase
+     - Must NOT be `main` or `develop` (protected branches)
+  </action>
+
+  <check if="current_branch == 'main' OR current_branch == 'develop'">
+      <output>
+      🛑 **COMMIT BLOCKED**: Cannot commit directly to protected branch '{{current_branch}}'.
+      Per GitFlow guidelines, please switch to your feature branch first.
+      </output>
+      <action>STOP execution.</action>
+  </check>
+
+  <check if="branch naming is valid">
+      <output>✅ Branch '{{current_branch}}' follows GitFlow naming convention.</output>
+  </check>
+
+</check>
+
+### 4. Git Operations
+
+**Goal**: Persist changes following commit standards from `{gitFlowGuide}`.
+
+<check if="status == 'done' OR status == 'completed'">
+
+  1. **Stage Changes**:
+     <action>Run command `git add .`</action>
+
+  2. **Construct Commit Message**:
+     <action>
+     Per Section 3 of `{gitFlowGuide}`, use Conventional Commits format:
+     - For features: `feat: {description}`
+     - For fixes: `fix: {description}`
+
+     Derive type from story context and construct message.
+     </action>
+
+  3. **User Confirmation**:
+     <output>
+     READY TO COMMIT:
+     - Branch: {{current_branch}}
+     - Message: "feat: implementation for story {{story_key}}"
+
+     Do you want to proceed with the commit and push?
+     </output>
+
+     <menu>
+        <item cmd="C" action="continue">Yes, Commit & Push</item>
+        <item cmd="M" action="exit">No, Cancel (Manual Handling)</item>
+     </menu>
+
+     <logic>
+       <if selection="M">
+          <output>🚫 Commit cancelled by user.</output>
+          <output>Changes are staged. You can now commit manually.</output>
+          <action>Update frontmatter of `{outputFile}`: `stepsCompleted: [1, 2, 3, 4, 5, 6, 7]`</action>
+          <action>EXIT</action>
+       </if>
+     </logic>
+
+  4. **Commit Changes**:
+     <action>Run command `git commit -m "feat: implementation for story {{story_key}}"`</action>
+     <check if="Commit failed (no changes?)">
+        <output>ℹ️ No changes to commit.</output>
+     </check>
+
+  5. **Push to Remote**:
+     <action>
+     1. Get current branch: `git branch --show-current`
+     2. Push: `git push origin {{current_branch}}`
+     </action>
+
+     <check if="Push failed">
+        <output>❌ **Push Failed**. Please check your network or permissions and try pushing manually.</output>
+     </check>
+     <check if="Push success">
+        <output>✅ **Success**: Code pushed to origin/{{current_branch}}.</output>
+     </check>
+
+</check>
+
+### 5. Final Logging
+
+<action>Append to `{outputFile}`:</action>
+<template-output>
+## Repository Sync
+- **Branch**: {{current_branch}}
+- **Commit**: [Performed/Skipped]
+- **Push**: [Performed/Skipped]
+- **GitFlow Compliance**: ✅ Verified against `{gitFlowGuide}`
+- **Status**: Workflow Completed Successfully
+</template-output>
+
+### 6. Workflow Completion
+
+<output>
+🎉 **Workflow Completed**
+The code review cycle for **{{story_key}}** is finished.
+All Git operations followed the centralized GitFlow guidelines.
+</output>
+
+<action>Update frontmatter of `{outputFile}`: `stepsCompleted: [1, 2, 3, 4, 5, 6, 7]`</action>
+
+<action>EXIT workflow.</action>

package/siesa-agents/bmm/workflows/4-implementation/code-review/workflow.md

@@ -0,0 +1,57 @@
+---
+name: code-review
+description: "Adversarial Senior Developer Code Review. Validates stories, checks git changes, enforces strict quality, and syncs status with Jira."
+web_bundle: true
+---
+
+# Code Review
+
+**Goal:** Perform an adversarial code review to validate implementation against story requirements, finding at least 3-10 specific issues, and synchronize status with project tracking.
+
+**Your Role:** In addition to your name, communication_style, and persona, you are an **Adversarial Senior Developer**. You verify claims against reality. You doubt everything until proven. You bring deep code quality expertise, while the user brings the implementation to be reviewed. Work together to perfect the code.
+
+## WORKFLOW ARCHITECTURE
+
+### Core Principles
+
+- **Micro-file Design**: Each step of the overall goal is a self contained instruction file that you will adhere too 1 file as directed at a time
+- **Just-In-Time Loading**: Only 1 current step file will be loaded, read, and executed to completion - never load future step files until told to do so
+- **Sequential Enforcement**: Sequence within the step files must be completed in order, no skipping or optimization allowed
+- **State Tracking**: Document progress in output file frontmatter using `stepsCompleted` array when a workflow produces a document
+- **Append-Only Building**: Build documents by appending content as directed to the output file
+
+### Step Processing Rules
+
+1. **READ COMPLETELY**: Always read the entire step file before taking any action
+2. **FOLLOW SEQUENCE**: Execute all numbered sections in order, never deviate
+3. **WAIT FOR INPUT**: If a menu is presented, halt and wait for user selection
+4. **CHECK CONTINUATION**: If the step has a menu with Continue as an option, only proceed to next step when user selects 'C' (Continue)
+5. **SAVE STATE**: Update `stepsCompleted` in frontmatter before loading next step
+6. **LOAD NEXT**: When directed, load, read entire file, then execute the next step file
+
+### Critical Rules (NO EXCEPTIONS)
+
+- 🛑 **NEVER** load multiple step files simultaneously
+- 📖 **ALWAYS** read entire step file before execution
+- 🚫 **NEVER** skip steps or optimize the sequence
+- 💾 **ALWAYS** update frontmatter of output files when writing the final output for a specific step
+- 🎯 **ALWAYS** follow the exact instructions in the step file
+- ⏸️ **ALWAYS** halt at menus and wait for user input
+- 📋 **NEVER** create mental todo lists from future steps
+
+---
+
+## INITIALIZATION SEQUENCE
+
+### 1. Module Configuration Loading
+
+Load and read full config from `{project-root}/_siesa-agents/bmm/config.yaml` and resolve:
+
+- `project_name`, `output_folder`, `user_name`, `communication_language`, `document_output_language`
+- `user_skill_level`, `planning_artifacts`, `implementation_artifacts`
+
+### 2. First Step EXECUTION
+
+Load, read the full file and then execute `{workflow_root}/steps/step-01-load-story.md` to begin the workflow.
+
+*(Note: `workflow_root` is `{project-root}/_siesa-agents/bmm/workflows/4-implementation/code-review`)*

package/siesa-agents/bmm/workflows/4-implementation/code-review/workflow_ext.md

@@ -1,11 +1,5 @@
 # MANDATORY RULE: CODE REVIEW WORKFLOW
 
-**TRIGGER:** Every time the user requests a CODE REVIEW, such as `/code-review`.
-
-**CONTEXT TO INJECT (apply throughout the entire workflow):**
-
-The following rules must be kept in memory and applied at the appropriate moment without altering the standard workflow flow:
-
 ## 1. During step-01-load-story: use the following definition for point 3. Discover Git Changes
 
 ### 3. Discover Git Changes
@@ -27,6 +21,7 @@ Sub-agents **must NOT be used** when the code review workflow is invoked directl
 
 - If invoked directly → follow the standard sequential workflow steps without spawning any sub-agents.
 - If invoked from quick-dev → sub-agents may be used as defined by the quick-dev orchestration.
+
 ---
 
 ## 3. During step-06-jira-sync: REPLACE entirely with Automated sa-jira-sync-api
@@ -219,3 +214,10 @@ node "{project_root}/_siesa-agents/observability/scripts/sa-emit.js" --event wor
 - If any `sa-emit` call fails, log the error and **continue the workflow normally**. Observability must never block the workflow.
 - Use the exact `{{story_key}}` value as resolved in step-01 (e.g., `1-1-user-authentication`).
 - Do NOT wait for user confirmation to execute these commands — they are silent background operations.
+
+Step-06 of the Siesa extension declares its own `nextStepFile` pointing to:
+```
+{project-root}/_siesa-agents/bmm/workflows/4-implementation/code-review/steps/step-07-commit-push.md
+```
+
+No additional redirect rule is needed — the wiring is handled by step-06's frontmatter. This section exists only for documentation clarity.

package/siesa-agents/bmm/workflows/4-implementation/correct-course/workflow_ext.md

@@ -1,11 +1,11 @@
 ## Step 1: Load Company Standards Context
 Load ALL the following company standards documents to understand the architectural constraints and preferences:
 
-1. LOAD the FULL @{project-root}/_bmad/bmm/workflows/3-solutioning/create-architecture/data/company-standards/technology-stack.md - Complete summary of frontend and backend stack
-2. LOAD the FULL @{project-root}/_bmad/bmm/workflows/3-solutioning/create-architecture/data/company-standards/architecture-patterns.md - Detailed folder structures (Frontend + Backend)
-3. LOAD the FULL @{project-root}/_bmad/bmm/workflows/3-solutioning/create-architecture/data/company-standards/backend-standards.md - .NET, EF Core, PostgreSQL, Testing standards
-4. LOAD the FULL @{project-root}/_bmad/bmm/workflows/3-solutioning/create-architecture/data/company-standards/frontend-standards.md - React, Vite, TanStack Router, Testing standards
-5. LOAD the FULL @{project-root}/_bmad/bmm/workflows/3-solutioning/create-architecture/data/company-standards/vite-config-standard.md - Vite configuration for Single-SPA and Module Federation
-6. LOAD the FULL @{project-root}/_bmad/bmm/workflows/3-solutioning/create-architecture/data/company-standards/database-conventions.md - PostgreSQL conventions (naming, schemas, mappings)
-7. LOAD the FULL @{project-root}/_bmad/bmm/workflows/3-solutioning/create-architecture/data/company-standards/technical-preferences-ux.md - Design system, colors, typography, accessibility 
-8. LOAD the FULL @{project-root}/_bmad/bmm/workflows/3-solutioning/create-architecture/data/company-standards/mastercrud-use-reference.md - MasterCrud is the highest-level orchestrator component in Siesa UI Kit. It coordinates data grids, forms, filters, and CRUD operations into a unified, configurable interface
+1. LOAD the FULL @{project-root}/_siesa-agents/bmm/workflows/3-solutioning/create-architecture/data/company-standards/technology-stack.md - Complete summary of frontend and backend stack
+2. LOAD the FULL @{project-root}/_siesa-agents/bmm/workflows/3-solutioning/create-architecture/data/company-standards/architecture-patterns.md - Detailed folder structures (Frontend + Backend)
+3. LOAD the FULL @{project-root}/_siesa-agents/bmm/workflows/3-solutioning/create-architecture/data/company-standards/backend-standards.md - .NET, EF Core, PostgreSQL, Testing standards
+4. LOAD the FULL @{project-root}/_siesa-agents/bmm/workflows/3-solutioning/create-architecture/data/company-standards/frontend-standards.md - React, Vite, TanStack Router, Testing standards
+5. LOAD the FULL @{project-root}/_siesa-agents/bmm/workflows/3-solutioning/create-architecture/data/company-standards/vite-config-standard.md - Vite configuration for Single-SPA and Module Federation
+6. LOAD the FULL @{project-root}/_siesa-agents/bmm/workflows/3-solutioning/create-architecture/data/company-standards/database-conventions.md - PostgreSQL conventions (naming, schemas, mappings)
+7. LOAD the FULL @{project-root}/_siesa-agents/bmm/workflows/3-solutioning/create-architecture/data/company-standards/technical-preferences-ux.md - Design system, colors, typography, accessibility 
+8. LOAD the FULL @{project-root}/_siesa-agents/bmm/workflows/3-solutioning/create-architecture/data/company-standards/mastercrud-use-reference.md - MasterCrud is the highest-level orchestrator component in Siesa UI Kit. It coordinates data grids, forms, filters, and CRUD operations into a unified, configurable interface

package/siesa-agents/bmm/workflows/4-implementation/create-story/steps/step-01-determine-story.md

@@ -0,0 +1,85 @@
+---
+name: 'step-01-determine-story'
+description: 'Determine which story to work on next'
+
+# Path Definitions
+workflow_path: '{project-root}/_siesa-agents/bmm/workflows/4-implementation/create-story'
+
+# File References
+thisStepFile: '{workflow_path}/steps/step-01-determine-story.md'
+nextStepFile: '{workflow_path}/steps/step-02-analyze.md'
+workflowFile: '{workflow_path}/workflow.md'
+
+# Variables
+sprint_status: '{implementation_artifacts}/sprint-status.yaml || {output_folder}/sprint-status.yaml'
+
+# Task References
+advancedElicitationTask: 'skill:bmad-advanced-elicitation'
+partyModeWorkflow: 'skill:bmad-party-mode'
+---
+
+# Step 1: Determine Target Story
+
+## STEP GOAL:
+To identify exactly which user story needs to be created, either from user input or by auto-discovering the next backlog item from the sprint status.
+
+## 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
+
+### Step-Specific Rules:
+- 🎯 Focus only on identifying the story ID (e.g., "1-2") and Title
+- 🚫 FORBIDDEN to analyze deep context yet
+- 💬 Ask strictly for story ID if not found automatically
+
+## EXECUTION PROTOCOLS:
+
+- 🎯 Identify story to create
+- 💾 Set {{story_id}}, {{epic_num}}, {{story_num}}, {{story_key}} memory variables
+- 📖 No file output in this step, only memory state
+
+## INSTRUCTIONS:
+
+### 1. Check User Input
+Check if the user provided a story path or ID (e.g., "1-2-user-auth").
+- IF YES: Parse it, set {{story_id}} variables, and [GO TO Section 4]
+- IF NO: Proceed to Section 2
+
+### 2. Auto-Discovery
+Check if `{sprint_status}` file exists.
+- IF NO: Display options to user:
+  1. Run `sprint-planning` (Recommended)
+  2. Enter specific epic-story number
+  3. Quit
+  [Wait for selection]
+
+- IF YES: Load and read `{sprint_status}`.
+  - Parse `development_status` section.
+  - Find FIRST story where status is "backlog".
+  - IF NONE FOUND: Display "No backlog stories found" and HALT.
+  - IF FOUND: Extract `epic_num`, `story_num`, `story_title`.
+  - Set variables.
+
+### 3. Verify Epic Status
+Check the status of the Epic {{epic_num}} in `sprint_status`.
+- If "done": HALT. Cannot add to done epic.
+- If "backlog": Update to "in-progress" in `sprint_status` (save file).
+- If "in-progress": Continue.
+
+### 4. Present MENU OPTIONS
+
+Display: "**Target Story Identified: {{story_id}} - {{story_title}}**"
+Display: "**Select an Option:** [A] Advanced Elicitation [P] Party Mode [C] Continue to Analysis"
+
+#### Menu Handling Logic:
+- IF A: Execute {advancedElicitationTask}
+- IF P: Execute {partyModeWorkflow}
+- IF C: Load, read entire file, then execute {nextStepFile}
+
+#### EXECUTION RULES:
+- ALWAYS halt and wait for user input after presenting menu
+- ONLY proceed to next step when user selects 'C'

package/siesa-agents/bmm/workflows/4-implementation/create-story/steps/step-02-analyze.md

@@ -0,0 +1,67 @@
+---
+name: 'step-02-analyze'
+description: 'Load and analyze core artifacts'
+
+# Path Definitions
+workflow_path: '{project-root}/_siesa-agents/bmm/workflows/4-implementation/create-story'
+
+# File References
+thisStepFile: '{workflow_path}/steps/step-02-analyze.md'
+nextStepFile: '{workflow_path}/steps/step-03-architecture.md'
+workflowFile: '{workflow_path}/workflow.md'
+
+# Variables
+output_folder: '{implementation_artifacts}'
+
+# Task References
+advancedElicitationTask: 'skill:bmad-advanced-elicitation'
+partyModeWorkflow: 'skill:bmad-party-mode'
+---
+
+# Step 2: Load and Analyze Core Artifacts
+
+## STEP GOAL:
+To gather all necessary context from Epics, previous stories, and Git history to build a solid foundation for the new story.
+
+## EXECUTION PROTOCOLS:
+- 🎯 Deep analysis of available artifacts
+- 💾 Extract key requirements into memory/context
+
+## INSTRUCTIONS:
+
+### 1. Discover Inputs
+Identify available files matching patterns:
+- Epics: `{output_folder}/*epic*.md`
+- PRD: `{output_folder}/*prd*.md`
+- Architecture: `{output_folder}/*architecture*.md`
+- Review findings.
+
+### 2. Epic Analysis
+Load the relevant Epic file ({{epic_num}}).
+- Extract "Epic Objectives" and "Business Value".
+- Extract THIS specific story's requirements (User Story, AC).
+- Extract technical constraints listed in the Epic.
+
+### 3. Previous Story Intelligence
+Check if {{story_num}} > 1.
+- IF YES: Look for `{{story_dir}}/{{epic_num}}-{{previous_story_num}}-*.md`.
+- IF FOUND: Read it. Extract "Dev Notes", "Learnings", "Testing Approaches".
+
+### 4. Git Intelligence
+Check if this is a git repo.
+- IF YES: Get last 5 commit titles.
+- Analyze patterns relevant to this story (naming, file locations).
+
+### 5. Present MENU OPTIONS
+
+Display: "**Artifact Analysis Complete.**"
+Display: "**Select an Option:** [A] Advanced Elicitation [P] Party Mode [C] Continue to Architecture"
+
+#### Menu Handling Logic:
+- IF A: Execute {advancedElicitationTask}
+- IF P: Execute {partyModeWorkflow}
+- IF C: Load, read entire file, then execute {nextStepFile}
+
+#### EXECUTION RULES:
+- ALWAYS halt and wait for user input after presenting menu
+- ONLY proceed to next step when user selects 'C'

package/siesa-agents/bmm/workflows/4-implementation/create-story/steps/step-03-architecture.md

@@ -0,0 +1,71 @@
+---
+name: 'step-03-architecture'
+description: 'Architecture analysis and tech stack validation'
+
+# Path Definitions
+workflow_path: '{project-root}/_siesa-agents/bmm/workflows/4-implementation/create-story'
+
+# File References
+thisStepFile: '{workflow_path}/steps/step-03-architecture.md'
+nextStepFile: '{workflow_path}/steps/step-04-web-research.md'
+workflowFile: '{workflow_path}/workflow.md'
+
+# Variables
+output_folder: '{implementation_artifacts}'
+
+# Task References
+advancedElicitationTask: 'skill:bmad-advanced-elicitation'
+partyModeWorkflow: 'skill:bmad-party-mode'
+---
+
+# Step 3: Architecture Intelligence & Compliance
+
+## STEP GOAL:
+To extract architectural constraints and SPECIFICALLY detect Frontend/UI requirements to enforce `siesa-ui-kit` usage.
+
+## EXECUTION PROTOCOLS:
+- 🎯 Analyze architecture documents
+- 🕵️ Detect UI/Frontend requirements in the current story
+- 💾 Set {{has_ui_component}} flag and {{siesa_instructions}}
+
+## INSTRUCTIONS:
+
+### 1. Load Architecture
+Load `{output_folder}/*architecture*.md`.
+- Analyze: Technical Stack, Code Structure, API Patterns, Database Schemas.
+
+### 2. UI/Frontend Detection (CRITICAL)
+Analyze the Story Requirements (from previous step) and Architecture.
+- ASK: "Does this story involve creating views, components, or user interfaces?"
+- LOOK FOR keywords: "Page", "View", "Button", "Form", "Screen", "UI", "Frontend", "React", "Vue", "Component".
+
+### 3. Siesa UI Kit Enforcement
+IF {{has_ui_component}} IS TRUE:
+- **MANDATE**: Store the following requirements for the final story:
+  1.  **Installation**: `npm install siesa-ui-kit` for installation.
+  2.  **Usage**: "You MUST use components and patterns from `siesa-ui-kit` for all UI elements."
+  3.  **Pattern**: "Do not build custom UI components if a `siesa-ui-kit` equivalent exists."
+- Log: "✅ UI Story Detected - siesa-ui-kit requirements injected."
+
+IF {{has_ui_component}} IS FALSE:
+- Log: "ℹ️ No specific UI requirements detected. Standard backend/logic rules apply."
+
+### 4. Extract Other Constraints
+- Security: Auth/Authz rules.
+- Performance: Caching, specific queries.
+- Testing: Standards for this module.
+
+### 5. Present MENU OPTIONS
+
+Display: "**Architecture & UI Analysis Complete.**"
+Display: "**UI Detected:** {{has_ui_component}}"
+Display: "**Select an Option:** [A] Advanced Elicitation [P] Party Mode [C] Continue to Research"
+
+#### Menu Handling Logic:
+- IF A: Execute {advancedElicitationTask}
+- IF P: Execute {partyModeWorkflow}
+- IF C: Load, read entire file, then execute {nextStepFile}
+
+#### EXECUTION RULES:
+- ALWAYS halt and wait for user input after presenting menu
+- ONLY proceed to next step when user selects 'C'

package/siesa-agents/bmm/workflows/4-implementation/create-story/steps/step-04-web-research.md

@@ -0,0 +1,58 @@
+---
+name: 'step-04-web-research'
+description: 'Web research for latest technical specifics'
+
+# Path Definitions
+workflow_path: '{project-root}/_siesa-agents/bmm/workflows/4-implementation/create-story'
+
+# File References
+thisStepFile: '{workflow_path}/steps/step-04-web-research.md'
+nextStepFile: '{workflow_path}/steps/step-05-create-file.md'
+workflowFile: '{workflow_path}/workflow.md'
+
+# Task References
+advancedElicitationTask: 'skill:bmad-advanced-elicitation'
+partyModeWorkflow: 'skill:bmad-party-mode'
+---
+
+# Step 4: Web Research & Verification
+
+## STEP GOAL:
+To ensure the developer has the absolute latest information on libraries (including `siesa-ui-kit` if relevant) and APIs.
+
+## EXECUTION PROTOCOLS:
+- 🎯 Research latest versions and best practices
+- 💾 Summarize technical specifics for the story
+
+## INSTRUCTIONS:
+
+### 1. Identify Research Targets
+Based on Architecture and Story:
+- List critical libraries/frameworks.
+- **Siesa Check**: If {{has_ui_component}} is TRUE, include `siesa-ui-kit` in research list (check for specific version requirements if public, or internal docs).
+
+### 2. Execute Research
+For each target:
+- Find latest stable version.
+- check for breaking changes relevant to this story.
+- Find specific documentation links for required components.
+
+### 3. Synthesize Findings
+Create a "Latest Tech Info" block:
+- "Library X v.Y.Z recommended"
+- "Specific API endpoint documentation: [Link]"
+- "Security alerts: [Details]"
+
+### 4. Present MENU OPTIONS
+
+Display: "**Tech Research Complete.**"
+Display: "**Select an Option:** [A] Advanced Elicitation [P] Party Mode [C] Continue to Creation"
+
+#### Menu Handling Logic:
+- IF A: Execute {advancedElicitationTask}
+- IF P: Execute {partyModeWorkflow}
+- IF C: Load, read entire file, then execute {nextStepFile}
+
+#### EXECUTION RULES:
+- ALWAYS halt and wait for user input after presenting menu
+- ONLY proceed to next step when user selects 'C'

package/siesa-agents/bmm/workflows/4-implementation/create-story/steps/step-05-create-file.md

@@ -0,0 +1,76 @@
+---
+name: 'step-05-create-file'
+description: 'Create comprehensive story file'
+
+# Path Definitions
+workflow_path: '{project-root}/_siesa-agents/bmm/workflows/4-implementation/create-story'
+
+# File References
+thisStepFile: '{workflow_path}/steps/step-05-create-file.md'
+nextStepFile: '{workflow_path}/steps/step-06-finalize.md'
+workflowFile: '{workflow_path}/workflow.md'
+templateFile: '{workflow_path}/template.md'
+
+# Variables
+story_dir: '{implementation_artifacts}'
+
+# Task References
+advancedElicitationTask: 'skill:bmad-advanced-elicitation'
+partyModeWorkflow: 'skill:bmad-party-mode'
+---
+
+# Step 5: Create Ultimate Story File
+
+## STEP GOAL:
+To generate the final `.md` story file containing ALL gathered context, requirements, and specifically the `siesa-ui-kit` mandates if applicable.
+
+## EXECUTION PROTOCOLS:
+- 🎯 Assemble the story file
+- 💾 Write to `{{story_dir}}/{{story_key}}.md`
+
+## INSTRUCTIONS:
+
+### 1. Initialize File
+Create/Overwrite: `{{story_dir}}/{{story_key}}.md`.
+
+### 2. Write Header & Status
+- Title: Story {{epic_num}}.{{story_num}}: {{story_title}}
+- Status: **ready-for-dev**
+
+### 3. Write Story & AC
+- User Story Format (As a... I want... So that...)
+- Detailed Acceptance Criteria (from Step 2).
+
+### 4. Write Technical Implementation Guide (CRITICAL)
+- Architecture Patterns (from Step 3).
+- **Tech Stack & Libraries**:
+  - List all required libraries.
+  - **UI MANDATE**: IF {{has_ui_component}} is TRUE:
+    ```markdown
+    ### 🎨 UI Implementation Requirements (MANDATORY)
+    - **Library**: `siesa-ui-kit`
+    - **Install**: `npm install siesa-ui-kit` (Ensure dependency is present)
+    - **Usage**: You MUST use `siesa-ui-kit` components for all UI elements.
+    - **Constraint**: Do not create custom components if a Kit equivalent exists.
+    ```
+- Testing Requirements.
+- File Structure requirements.
+
+### 5. Write Contextual Intelligence
+- Previous Story Learnings (from Step 2).
+- Git History Context (from Step 2).
+- Latest Web Research (from Step 4).
+
+### 6. Present MENU OPTIONS
+
+Display: "**Story File Created: {{story_key}}.md**"
+Display: "**Select an Option:** [A] Advanced Elicitation [P] Party Mode [C] Continue to Finalize"
+
+#### Menu Handling Logic:
+- IF A: Execute {advancedElicitationTask}
+- IF P: Execute {partyModeWorkflow}
+- IF C: Load, read entire file, then execute {nextStepFile}
+
+#### EXECUTION RULES:
+- ALWAYS halt and wait for user input after presenting menu
+- ONLY proceed to next step when user selects 'C'