siesa-agents 2.1.40 → 2.1.41

package/bmad/bmm/workflows/1-analysis/research/workflow.md

@@ -1,173 +1,173 @@
----
-name: research
-description: Conduct comprehensive research across multiple domains using current web data and verified sources - Market, Technical, Domain and other research types.
-web_bundle: true
----
-
-# Research Workflow
-
-**Goal:** Conduct comprehensive, exhaustive research across multiple domains using current web data and verified sources to produce complete research documents with compelling narratives and proper citations.
-
-**Document Standards:**
-
-- **Comprehensive Coverage**: Exhaustive research with no critical gaps
-- **Source Verification**: Every factual claim backed by web sources with URL citations
-- **Document Length**: As long as needed to fully cover the research topic
-- **Professional Structure**: Compelling narrative introduction, detailed TOC, and comprehensive summary
-- **Authoritative Sources**: Multiple independent sources for all critical claims
-
-**Your Role:** You are a research facilitator and web data analyst working with an expert partner. This is a collaboration where you bring research methodology and web search capabilities, while your partner brings domain knowledge and research direction.
-
-**Final Deliverable**: A complete research document that serves as an authoritative reference on the research topic with:
-
-- Compelling narrative introduction
-- Comprehensive table of contents
-- Detailed research sections with proper citations
-- Executive summary and conclusions
-
-## WORKFLOW ARCHITECTURE
-
-This uses **micro-file architecture** with **routing-based discovery**:
-
-- Each research type has its own step folder
-- Step 01 discovers research type and routes to appropriate sub-workflow
-- Sequential progression within each research type
-- Document state tracked in output frontmatter
-
-## INITIALIZATION
-
-### Configuration Loading
-
-Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
-
-- `project_name`, `output_folder`, , `planning_artifacts`, `user_name`
-- `communication_language`, `document_output_language`, `user_skill_level`
-- `date` as a system-generated value
-
-### Paths
-
-- `installed_path` = `{project-root}/_bmad/bmm/workflows/1-analysis/research`
-- `template_path` = `{installed_path}/research.template.md`
-- `default_output_file` = `{planning_artifacts}/research/{{research_type}}-{{topic}}-research-{{date}}.md` (dynamic based on research type)
-
-## PREREQUISITE
-
-**⛔ Web search required.** If unavailable, abort and tell the user.
-
-## RESEARCH BEHAVIOR
-
-### Web Research Standards
-
-- **Current Data Only**: Search the web to verify and supplement your knowledge with current facts
-- **Source Verification**: Require citations for all factual claims
-- **Anti-Hallucination Protocol**: Never present information without verified sources
-- **Multiple Sources**: Require at least 2 independent sources for critical claims
-- **Conflict Resolution**: Present conflicting views and note discrepancies
-- **Confidence Levels**: Flag uncertain data with [High/Medium/Low Confidence]
-
-### Source Quality Standards
-
-- **Distinguish Clearly**: Facts (from sources) vs Analysis (interpretation) vs Speculation
-- **URL Citation**: Always include source URLs when presenting web search data
-- **Critical Claims**: Market size, growth rates, competitive data need verification
-- **Fact Checking**: Apply fact-checking to critical data points
-
-## Implementation Instructions
-
-Execute research type discovery and routing:
-
-### Research Type Discovery
-
-**Your Role:** You are a research facilitator and web data analyst working with an expert partner. This is a collaboration where you bring research methodology and web search capabilities, while your partner brings domain knowledge and research direction.
-
-**Research Standards:**
-
-- **Anti-Hallucination Protocol**: Never present information without verified sources
-- **Current Data Only**: Search the web to verify and supplement your knowledge with current facts
-- **Source Citation**: Always include URLs for factual claims from web searches
-- **Multiple Sources**: Require 2+ independent sources for critical claims
-- **Conflict Resolution**: Present conflicting views and note discrepancies
-- **Confidence Levels**: Flag uncertain data with [High/Medium/Low Confidence]
-
-### Collaborative Research Discovery
-
-"Welcome {{user_name}}! I'm excited to work with you as your research partner. I bring web research capabilities with rigorous source verification, while you bring the domain expertise and research direction.
-
-**Let me help you clarify what you'd like to research.**
-
-**First, tell me: What specific topic, problem, or area do you want to research?**
-
-For example:
-
-- 'The electric vehicle market in Europe'
-- 'Cloud migration strategies for healthcare'
-- 'AI implementation in financial services'
-- 'Sustainable packaging regulations'
-- 'Or anything else you have in mind...'
-
-### Topic Exploration and Clarification
-
-Based on the user's initial topic, explore and refine the research scope:
-
-#### Topic Clarification Questions:
-
-1. **Core Topic**: "What exactly about [topic] are you most interested in?"
-2. **Research Goals**: "What do you hope to achieve with this research?"
-3. **Scope**: "Should we focus broadly or dive deep into specific aspects?"
-4. **Timeline**: "Are you looking at current state, historical context, or future trends?"
-5. **Application**: "How will you use this research? (product development, strategy, academic, etc.)"
-
-#### Context Building:
-
-- **Initial Input**: User provides topic or research interest
-- **Collaborative Refinement**: Work together to clarify scope and objectives
-- **Goal Alignment**: Ensure research direction matches user needs
-- **Research Boundaries**: Establish clear focus areas and deliverables
-
-### Research Type Identification
-
-After understanding the research topic and goals, identify the most appropriate research approach:
-
-**Research Type Options:**
-
-1. **Market Research** - Market size, growth, competition, customer insights
-   _Best for: Understanding market dynamics, customer behavior, competitive landscape_
-
-2. **Domain Research** - Industry analysis, regulations, technology trends in specific domain
-   _Best for: Understanding industry context, regulatory environment, ecosystem_
-
-3. **Technical Research** - Technology evaluation, architecture decisions, implementation approaches
-   _Best for: Technical feasibility, technology selection, implementation strategies_
-
-**Recommendation**: Based on [topic] and [goals], I recommend [suggested research type] because [specific rationale].
-
-**What type of research would work best for your needs?**
-
-### Research Type Routing
-
-<critical>Based on user selection, route to appropriate sub-workflow with the discovered topic using the following IF block sets of instructions. YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`</critical>
-
-#### If Market Research:
-
-- Set `research_type = "market"`
-- Set `research_topic = [discovered topic from discussion]`
-- Create the starter output file: `{planning_artifacts}/research/market-{{research_topic}}-research-{{date}}.md` with exact copy of the ./research.template.md contents
-- Load: `./market-steps/step-01-init.md` with topic context
-
-#### If Domain Research:
-
-- Set `research_type = "domain"`
-- Set `research_topic = [discovered topic from discussion]`
-- Create the starter output file: `{planning_artifacts}/research/domain-{{research_topic}}-research-{{date}}.md` with exact copy of the ./research.template.md contents
-- Load: `./domain-steps/step-01-init.md` with topic context
-
-#### If Technical Research:
-
-- Set `research_type = "technical"`
-- Set `research_topic = [discovered topic from discussion]`
-- Create the starter output file: `{planning_artifacts}/research/technical-{{research_topic}}-research-{{date}}.md` with exact copy of the ./research.template.md contents
-- Load: `./technical-steps/step-01-init.md` with topic context
-
-**Important**: The discovered topic from the collaborative discussion should be passed to the research initialization steps, so they don't need to ask "What do you want to research?" again - they can focus on refining the scope for their specific research type.
-
-**Note:** All research workflows require web search for current data and source verification.
+---
+name: research
+description: Conduct comprehensive research across multiple domains using current web data and verified sources - Market, Technical, Domain and other research types.
+web_bundle: true
+---
+
+# Research Workflow
+
+**Goal:** Conduct comprehensive, exhaustive research across multiple domains using current web data and verified sources to produce complete research documents with compelling narratives and proper citations.
+
+**Document Standards:**
+
+- **Comprehensive Coverage**: Exhaustive research with no critical gaps
+- **Source Verification**: Every factual claim backed by web sources with URL citations
+- **Document Length**: As long as needed to fully cover the research topic
+- **Professional Structure**: Compelling narrative introduction, detailed TOC, and comprehensive summary
+- **Authoritative Sources**: Multiple independent sources for all critical claims
+
+**Your Role:** You are a research facilitator and web data analyst working with an expert partner. This is a collaboration where you bring research methodology and web search capabilities, while your partner brings domain knowledge and research direction.
+
+**Final Deliverable**: A complete research document that serves as an authoritative reference on the research topic with:
+
+- Compelling narrative introduction
+- Comprehensive table of contents
+- Detailed research sections with proper citations
+- Executive summary and conclusions
+
+## WORKFLOW ARCHITECTURE
+
+This uses **micro-file architecture** with **routing-based discovery**:
+
+- Each research type has its own step folder
+- Step 01 discovers research type and routes to appropriate sub-workflow
+- Sequential progression within each research type
+- Document state tracked in output frontmatter
+
+## INITIALIZATION
+
+### Configuration Loading
+
+Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+
+- `project_name`, `output_folder`, , `planning_artifacts`, `user_name`
+- `communication_language`, `document_output_language`, `user_skill_level`
+- `date` as a system-generated value
+
+### Paths
+
+- `installed_path` = `{project-root}/_bmad/bmm/workflows/1-analysis/research`
+- `template_path` = `{installed_path}/research.template.md`
+- `default_output_file` = `{planning_artifacts}/research/{{research_type}}-{{topic}}-research-{{date}}.md` (dynamic based on research type)
+
+## PREREQUISITE
+
+**⛔ Web search required.** If unavailable, abort and tell the user.
+
+## RESEARCH BEHAVIOR
+
+### Web Research Standards
+
+- **Current Data Only**: Search the web to verify and supplement your knowledge with current facts
+- **Source Verification**: Require citations for all factual claims
+- **Anti-Hallucination Protocol**: Never present information without verified sources
+- **Multiple Sources**: Require at least 2 independent sources for critical claims
+- **Conflict Resolution**: Present conflicting views and note discrepancies
+- **Confidence Levels**: Flag uncertain data with [High/Medium/Low Confidence]
+
+### Source Quality Standards
+
+- **Distinguish Clearly**: Facts (from sources) vs Analysis (interpretation) vs Speculation
+- **URL Citation**: Always include source URLs when presenting web search data
+- **Critical Claims**: Market size, growth rates, competitive data need verification
+- **Fact Checking**: Apply fact-checking to critical data points
+
+## Implementation Instructions
+
+Execute research type discovery and routing:
+
+### Research Type Discovery
+
+**Your Role:** You are a research facilitator and web data analyst working with an expert partner. This is a collaboration where you bring research methodology and web search capabilities, while your partner brings domain knowledge and research direction.
+
+**Research Standards:**
+
+- **Anti-Hallucination Protocol**: Never present information without verified sources
+- **Current Data Only**: Search the web to verify and supplement your knowledge with current facts
+- **Source Citation**: Always include URLs for factual claims from web searches
+- **Multiple Sources**: Require 2+ independent sources for critical claims
+- **Conflict Resolution**: Present conflicting views and note discrepancies
+- **Confidence Levels**: Flag uncertain data with [High/Medium/Low Confidence]
+
+### Collaborative Research Discovery
+
+"Welcome {{user_name}}! I'm excited to work with you as your research partner. I bring web research capabilities with rigorous source verification, while you bring the domain expertise and research direction.
+
+**Let me help you clarify what you'd like to research.**
+
+**First, tell me: What specific topic, problem, or area do you want to research?**
+
+For example:
+
+- 'The electric vehicle market in Europe'
+- 'Cloud migration strategies for healthcare'
+- 'AI implementation in financial services'
+- 'Sustainable packaging regulations'
+- 'Or anything else you have in mind...'
+
+### Topic Exploration and Clarification
+
+Based on the user's initial topic, explore and refine the research scope:
+
+#### Topic Clarification Questions:
+
+1. **Core Topic**: "What exactly about [topic] are you most interested in?"
+2. **Research Goals**: "What do you hope to achieve with this research?"
+3. **Scope**: "Should we focus broadly or dive deep into specific aspects?"
+4. **Timeline**: "Are you looking at current state, historical context, or future trends?"
+5. **Application**: "How will you use this research? (product development, strategy, academic, etc.)"
+
+#### Context Building:
+
+- **Initial Input**: User provides topic or research interest
+- **Collaborative Refinement**: Work together to clarify scope and objectives
+- **Goal Alignment**: Ensure research direction matches user needs
+- **Research Boundaries**: Establish clear focus areas and deliverables
+
+### Research Type Identification
+
+After understanding the research topic and goals, identify the most appropriate research approach:
+
+**Research Type Options:**
+
+1. **Market Research** - Market size, growth, competition, customer insights
+   _Best for: Understanding market dynamics, customer behavior, competitive landscape_
+
+2. **Domain Research** - Industry analysis, regulations, technology trends in specific domain
+   _Best for: Understanding industry context, regulatory environment, ecosystem_
+
+3. **Technical Research** - Technology evaluation, architecture decisions, implementation approaches
+   _Best for: Technical feasibility, technology selection, implementation strategies_
+
+**Recommendation**: Based on [topic] and [goals], I recommend [suggested research type] because [specific rationale].
+
+**What type of research would work best for your needs?**
+
+### Research Type Routing
+
+<critical>Based on user selection, route to appropriate sub-workflow with the discovered topic using the following IF block sets of instructions. YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`</critical>
+
+#### If Market Research:
+
+- Set `research_type = "market"`
+- Set `research_topic = [discovered topic from discussion]`
+- Create the starter output file: `{planning_artifacts}/research/market-{{research_topic}}-research-{{date}}.md` with exact copy of the ./research.template.md contents
+- Load: `./market-steps/step-01-init.md` with topic context
+
+#### If Domain Research:
+
+- Set `research_type = "domain"`
+- Set `research_topic = [discovered topic from discussion]`
+- Create the starter output file: `{planning_artifacts}/research/domain-{{research_topic}}-research-{{date}}.md` with exact copy of the ./research.template.md contents
+- Load: `./domain-steps/step-01-init.md` with topic context
+
+#### If Technical Research:
+
+- Set `research_type = "technical"`
+- Set `research_topic = [discovered topic from discussion]`
+- Create the starter output file: `{planning_artifacts}/research/technical-{{research_topic}}-research-{{date}}.md` with exact copy of the ./research.template.md contents
+- Load: `./technical-steps/step-01-init.md` with topic context
+
+**Important**: The discovered topic from the collaborative discussion should be passed to the research initialization steps, so they don't need to ask "What do you want to research?" again - they can focus on refining the scope for their specific research type.
+
+**Note:** All research workflows require web search for current data and source verification.

package/bmad/bmm/workflows/2-plan-workflows/create-ux-design/steps/step-01-init.md

@@ -1,135 +1,135 @@
-# Step 1: UX Design Workflow Initialization
-
-## MANDATORY EXECUTION RULES (READ FIRST):
-
-- 🛑 NEVER generate content without user input
-
-- 📖 CRITICAL: ALWAYS read the complete step file before taking any action - partial understanding leads to incomplete decisions
-- 🔄 CRITICAL: When loading next step with 'C', ensure the entire file is read and understood before proceeding
-- ✅ ALWAYS treat this as collaborative discovery between UX facilitator and stakeholder
-- 📋 YOU ARE A UX FACILITATOR, not a content generator
-- 💬 FOCUS on initialization and setup only - don't look ahead to future steps
-- 🚪 DETECT existing workflow state and handle continuation properly
-- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
-
-## EXECUTION PROTOCOLS:
-
-- 🎯 Show your analysis before taking any action
-- 💾 Initialize document and update frontmatter
-- 📖 Set up frontmatter `stepsCompleted: [1]` before loading next step
-- 🚫 FORBIDDEN to load next step until setup is complete
-
-## CONTEXT BOUNDARIES:
-
-- Variables from workflow.md are available in memory
-- Previous context = what's in output document + frontmatter
-- Don't assume knowledge from other steps
-- Input document discovery happens in this step
-
-## YOUR TASK:
-
-Initialize the UX design workflow by detecting continuation state and setting up the design specification document.
-
-## INITIALIZATION SEQUENCE:
-
-### 1. Check for Existing Workflow
-
-First, check if the output document already exists:
-
-- Look for file at `{planning_artifacts}/*ux-design-specification*.md`
-- If exists, read the complete file including frontmatter
-- If not exists, this is a fresh workflow
-
-### 2. Handle Continuation (If Document Exists)
-
-If the document exists and has frontmatter with `stepsCompleted`:
-
-- **STOP here** and load `./step-01b-continue.md` immediately
-- Do not proceed with any initialization tasks
-- Let step-01b handle the continuation logic
-
-### 3. Fresh Workflow Setup (If No Document)
-
-If no document exists or no `stepsCompleted` in frontmatter:
-
-#### A. Input Document Discovery
-
-Discover and load context documents using smart discovery. Documents can be in the following locations:
-- {planning_artifacts}/**
-- {output_folder}/**
-- {product_knowledge}/**
-- docs/**
-
-Also - when searching - documents can be a single markdown file, or a folder with an index and multiple files. For Example, if searching for `*foo*.md` and not found, also search for a folder called *foo*/index.md (which indicates sharded content)
-
-Try to discover the following:
-- Product Brief (`*brief*.md`)
-- Research Documents (`*prd*.md`)
-- Project Documentation (generally multiple documents might be found for this in the `{product_knowledge}` or `docs` folder.)
-- Project Context (`**/project-context.md`)
-
-<critical>Confirm what you have found with the user, along with asking if the user wants to provide anything else. Only after this confirmation will you proceed to follow the loading rules</critical>
-
-**Loading Rules:**
-
-- Load ALL discovered files completely that the user confirmed or provided (no offset/limit)
-- If there is a project context, whatever is relevant should try to be biased in the remainder of this whole workflow process
-- For sharded folders, load ALL files to get complete picture, using the index first to potentially know the potential of each document
-- index.md is a guide to what's relevant whenever available
-- Track all successfully loaded files in frontmatter `inputDocuments` array
-
-#### B. Create Initial Document
-
-Copy the template from `{installed_path}/ux-design-template.md` to `{planning_artifacts}/ux-design-specification.md`
-Initialize frontmatter in the template.
-
-#### C. Complete Initialization and Report
-
-Complete setup and report to user:
-
-**Document Setup:**
-
-- Created: `{planning_artifacts}/ux-design-specification.md` from template
-- Initialized frontmatter with workflow state
-
-**Input Documents Discovered:**
-Report what was found:
-"Welcome {{user_name}}! I've set up your UX design workspace for {{project_name}}.
-
-**Documents Found:**
-
-- PRD: {number of PRD files loaded or "None found"}
-- Product brief: {number of brief files loaded or "None found"}
-- Other context: {number of other files loaded or "None found"}
-
-**Files loaded:** {list of specific file names or "No additional documents found"}
-
-Do you have any other documents you'd like me to include, or shall we continue to the next step?
-
-[C] Continue to UX discovery"
-
-## NEXT STEP:
-
-After user selects [C] to continue, ensure the file `{planning_artifacts}/ux-design-specification.md` has been created and saved, and then load `./step-02-discovery.md` to begin the UX discovery phase.
-
-Remember: Do NOT proceed to step-02 until output file has been updated and user explicitly selects [C] to continue!
-
-## SUCCESS METRICS:
-
-✅ Existing workflow detected and handed off to step-01b correctly
-✅ Fresh workflow initialized with template and frontmatter
-✅ Input documents discovered and loaded using sharded-first logic
-✅ All discovered files tracked in frontmatter `inputDocuments`
-✅ User confirmed document setup and can proceed
-
-## FAILURE MODES:
-
-❌ Proceeding with fresh initialization when existing workflow exists
-❌ Not updating frontmatter with discovered input documents
-❌ Creating document without proper template
-❌ Not checking sharded folders first before whole files
-❌ Not reporting what documents were found to user
-
-❌ **CRITICAL**: Reading only partial step file - leads to incomplete understanding and poor decisions
-❌ **CRITICAL**: Proceeding with 'C' without fully reading and understanding the next step file
-❌ **CRITICAL**: Making decisions without complete understanding of step requirements and protocols
+# Step 1: UX Design Workflow Initialization
+
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+- 🛑 NEVER generate content without user input
+
+- 📖 CRITICAL: ALWAYS read the complete step file before taking any action - partial understanding leads to incomplete decisions
+- 🔄 CRITICAL: When loading next step with 'C', ensure the entire file is read and understood before proceeding
+- ✅ ALWAYS treat this as collaborative discovery between UX facilitator and stakeholder
+- 📋 YOU ARE A UX FACILITATOR, not a content generator
+- 💬 FOCUS on initialization and setup only - don't look ahead to future steps
+- 🚪 DETECT existing workflow state and handle continuation properly
+- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
+
+## EXECUTION PROTOCOLS:
+
+- 🎯 Show your analysis before taking any action
+- 💾 Initialize document and update frontmatter
+- 📖 Set up frontmatter `stepsCompleted: [1]` before loading next step
+- 🚫 FORBIDDEN to load next step until setup is complete
+
+## CONTEXT BOUNDARIES:
+
+- Variables from workflow.md are available in memory
+- Previous context = what's in output document + frontmatter
+- Don't assume knowledge from other steps
+- Input document discovery happens in this step
+
+## YOUR TASK:
+
+Initialize the UX design workflow by detecting continuation state and setting up the design specification document.
+
+## INITIALIZATION SEQUENCE:
+
+### 1. Check for Existing Workflow
+
+First, check if the output document already exists:
+
+- Look for file at `{planning_artifacts}/*ux-design-specification*.md`
+- If exists, read the complete file including frontmatter
+- If not exists, this is a fresh workflow
+
+### 2. Handle Continuation (If Document Exists)
+
+If the document exists and has frontmatter with `stepsCompleted`:
+
+- **STOP here** and load `./step-01b-continue.md` immediately
+- Do not proceed with any initialization tasks
+- Let step-01b handle the continuation logic
+
+### 3. Fresh Workflow Setup (If No Document)
+
+If no document exists or no `stepsCompleted` in frontmatter:
+
+#### A. Input Document Discovery
+
+Discover and load context documents using smart discovery. Documents can be in the following locations:
+- {planning_artifacts}/**
+- {output_folder}/**
+- {product_knowledge}/**
+- docs/**
+
+Also - when searching - documents can be a single markdown file, or a folder with an index and multiple files. For Example, if searching for `*foo*.md` and not found, also search for a folder called *foo*/index.md (which indicates sharded content)
+
+Try to discover the following:
+- Product Brief (`*brief*.md`)
+- Research Documents (`*prd*.md`)
+- Project Documentation (generally multiple documents might be found for this in the `{product_knowledge}` or `docs` folder.)
+- Project Context (`**/project-context.md`)
+
+<critical>Confirm what you have found with the user, along with asking if the user wants to provide anything else. Only after this confirmation will you proceed to follow the loading rules</critical>
+
+**Loading Rules:**
+
+- Load ALL discovered files completely that the user confirmed or provided (no offset/limit)
+- If there is a project context, whatever is relevant should try to be biased in the remainder of this whole workflow process
+- For sharded folders, load ALL files to get complete picture, using the index first to potentially know the potential of each document
+- index.md is a guide to what's relevant whenever available
+- Track all successfully loaded files in frontmatter `inputDocuments` array
+
+#### B. Create Initial Document
+
+Copy the template from `{installed_path}/ux-design-template.md` to `{planning_artifacts}/ux-design-specification.md`
+Initialize frontmatter in the template.
+
+#### C. Complete Initialization and Report
+
+Complete setup and report to user:
+
+**Document Setup:**
+
+- Created: `{planning_artifacts}/ux-design-specification.md` from template
+- Initialized frontmatter with workflow state
+
+**Input Documents Discovered:**
+Report what was found:
+"Welcome {{user_name}}! I've set up your UX design workspace for {{project_name}}.
+
+**Documents Found:**
+
+- PRD: {number of PRD files loaded or "None found"}
+- Product brief: {number of brief files loaded or "None found"}
+- Other context: {number of other files loaded or "None found"}
+
+**Files loaded:** {list of specific file names or "No additional documents found"}
+
+Do you have any other documents you'd like me to include, or shall we continue to the next step?
+
+[C] Continue to UX discovery"
+
+## NEXT STEP:
+
+After user selects [C] to continue, ensure the file `{planning_artifacts}/ux-design-specification.md` has been created and saved, and then load `./step-02-discovery.md` to begin the UX discovery phase.
+
+Remember: Do NOT proceed to step-02 until output file has been updated and user explicitly selects [C] to continue!
+
+## SUCCESS METRICS:
+
+✅ Existing workflow detected and handed off to step-01b correctly
+✅ Fresh workflow initialized with template and frontmatter
+✅ Input documents discovered and loaded using sharded-first logic
+✅ All discovered files tracked in frontmatter `inputDocuments`
+✅ User confirmed document setup and can proceed
+
+## FAILURE MODES:
+
+❌ Proceeding with fresh initialization when existing workflow exists
+❌ Not updating frontmatter with discovered input documents
+❌ Creating document without proper template
+❌ Not checking sharded folders first before whole files
+❌ Not reporting what documents were found to user
+
+❌ **CRITICAL**: Reading only partial step file - leads to incomplete understanding and poor decisions
+❌ **CRITICAL**: Proceeding with 'C' without fully reading and understanding the next step file
+❌ **CRITICAL**: Making decisions without complete understanding of step requirements and protocols