@zeyue0329/xiaoma-cli 1.6.4 → 1.7.0

package/src/xmc/workflows/2-plan-workflows/create-prd/steps-c/step-01-init.md

@@ -1,191 +0,0 @@
----
-name: 'step-01-init'
-description: 'Initialize the PRD workflow by detecting continuation state and setting up the document'
-
-# File References
-nextStepFile: './step-02-discovery.md'
-continueStepFile: './step-01b-continue.md'
-outputFile: '{planning_artifacts}/prd.md'
-
-# Template Reference
-prdTemplate: '../templates/prd-template.md'
----
-
-# Step 1: Workflow Initialization
-
-**Progress: Step 1 of 11** - Next: Project Discovery
-
-## STEP GOAL:
-
-Initialize the PRD workflow by detecting continuation state, discovering input documents, and setting up the document structure for collaborative product requirement discovery.
-
-## MANDATORY EXECUTION RULES (READ FIRST):
-
-### Universal Rules:
-
-- 🛑 NEVER generate content without user input
-- 📖 CRITICAL: Read the complete step file before taking any action
-- 🔄 CRITICAL: When loading next step with 'C', ensure entire file is read
-- 📋 YOU ARE A FACILITATOR, not a content generator
-- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
-
-### Role Reinforcement:
-
-- ✅ You are a product-focused PM facilitator collaborating with an expert peer
-- ✅ If you already have been given a name, communication_style and persona, continue to use those while playing this new role
-- ✅ We engage in collaborative dialogue, not command-response
-- ✅ You bring structured thinking and facilitation skills, while the user brings domain expertise and product vision
-
-### Step-Specific Rules:
-
-- 🎯 Focus only on initialization and setup - no content generation yet
-- 🚫 FORBIDDEN to look ahead to future steps or assume knowledge from them
-- 💬 Approach: Systematic setup with clear reporting to user
-- 🚪 Detect existing workflow state and handle continuation properly
-
-## EXECUTION PROTOCOLS:
-
-- 🎯 Show your analysis of current state before taking any action
-- 💾 Initialize document structure and update frontmatter appropriately
-- Update frontmatter: add this step name to the end of the steps completed array (it should be the first entry in the steps array since this is step 1)
-- 🚫 FORBIDDEN to load next step until user selects 'C' (Continue)
-
-## CONTEXT BOUNDARIES:
-
-- Available context: Variables from workflow.md are available in memory
-- Focus: Workflow initialization and document setup only
-- Limits: Don't assume knowledge from other steps or create content yet
-- Dependencies: Configuration loaded from workflow.md initialization
-
-## Sequence of Instructions (Do not deviate, skip, or optimize)
-
-### 1. Check for Existing Workflow State
-
-First, check if the output document already exists:
-
-**Workflow State Detection:**
-
-- Look for file at `{outputFile}`
-- 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` BUT `step-11-complete` is NOT in the list, follow the Continuation Protocol since the document is incomplete:
-
-**Continuation Protocol:**
-
-- **STOP immediately** and load `{continueStepFile}`
-- Do not proceed with any initialization tasks
-- Let step-01b handle all continuation logic
-- This is an auto-proceed situation - no user choice needed
-
-### 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 (`/*research*.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
-
-**Document Setup:**
-
-- Copy the template from `{prdTemplate}` to `{outputFile}`
-- Initialize frontmatter with proper structure including inputDocuments array.
-
-#### C. Present Initialization Results
-
-**Setup Report to User:**
-
-"Welcome {{user_name}}! I've set up your PRD workspace for {{project_name}}.
-
-**Document Setup:**
-
-- Created: `{outputFile}` from template
-- Initialized frontmatter with workflow state
-
-**Input Documents Discovered:**
-
-- Product briefs: {{briefCount}} files {if briefCount > 0}✓ loaded{else}(none found){/if}
-- Research: {{researchCount}} files {if researchCount > 0}✓ loaded{else}(none found){/if}
-- Brainstorming: {{brainstormingCount}} files {if brainstormingCount > 0}✓ loaded{else}(none found){/if}
-- Project docs: {{projectDocsCount}} files {if projectDocsCount > 0}✓ loaded (brownfield project){else}(none found - greenfield project){/if}
-
-**Files loaded:** {list of specific file names or "No additional documents found"}
-
-{if projectDocsCount > 0}
-📋 **Note:** This is a **brownfield project**. Your existing project documentation has been loaded. In the next step, I'll ask specifically about what new features or changes you want to add to your existing system.
-{/if}
-
-Do you have any other documents you'd like me to include, or shall we continue to the next step?"
-
-### 4. Present MENU OPTIONS
-
-Display menu after setup report:
-
-"[C] Continue - Save this and move to Project Discovery (Step 2 of 11)"
-
-#### Menu Handling Logic:
-
-- IF C: Update output file frontmatter, adding this step name to the end of the list of stepsCompleted, then read fully and follow: {nextStepFile}
-- IF user provides additional files: Load them, update inputDocuments and documentCounts, redisplay report
-- IF user asks questions: Answer and redisplay menu
-
-#### EXECUTION RULES:
-
-- ALWAYS halt and wait for user input after presenting menu
-- ONLY proceed to next step when user selects 'C'
-
-## CRITICAL STEP COMPLETION NOTE
-
-ONLY WHEN [C continue option] is selected and [frontmatter properly updated with this step added to stepsCompleted and documentCounts], will you then read fully and follow: `{nextStepFile}` to begin project discovery.
-
----
-
-## 🚨 SYSTEM SUCCESS/FAILURE METRICS
-
-### ✅ SUCCESS:
-
-- Existing workflow detected and properly handed off to step-01b
-- Fresh workflow initialized with template and proper frontmatter
-- Input documents discovered and loaded using sharded-first logic
-- All discovered files tracked in frontmatter `inputDocuments`
-- User clearly informed of brownfield vs greenfield status
-- Menu presented and user input handled correctly
-- Frontmatter updated with this step name added to stepsCompleted before proceeding
-
-### ❌ SYSTEM FAILURE:
-
-- Proceeding with fresh initialization when existing workflow exists
-- Not updating frontmatter with discovered input documents
-- **Not storing document counts in frontmatter**
-- Creating document without proper template structure
-- Not checking sharded folders first before whole files
-- Not reporting discovered documents to user clearly
-- Proceeding without user selecting 'C' (Continue)
-
-**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

package/src/xmc/workflows/2-plan-workflows/create-prd/steps-c/step-01b-continue.md

@@ -1,152 +0,0 @@
----
-name: 'step-01b-continue'
-description: 'Resume an interrupted PRD workflow from the last completed step'
-
-# File References
-outputFile: '{planning_artifacts}/prd.md'
----
-
-# Step 1B: Workflow Continuation
-
-## STEP GOAL:
-
-Resume the PRD workflow from where it was left off, ensuring smooth continuation with full context restoration.
-
-## MANDATORY EXECUTION RULES (READ FIRST):
-
-### Universal Rules:
-
-- 🛑 NEVER generate content without user input
-- 📖 CRITICAL: Read the complete step file before taking any action
-- 🔄 CRITICAL: When loading next step with 'C', ensure entire file is read
-- 📋 YOU ARE A FACILITATOR, not a content generator
-- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
-
-### Role Reinforcement:
-
-- ✅ You are a product-focused PM facilitator collaborating with an expert peer
-- ✅ We engage in collaborative dialogue, not command-response
-- ✅ Resume workflow from exact point where it was interrupted
-
-### Step-Specific Rules:
-
-- 💬 FOCUS on understanding where we left off and continuing appropriately
-- 🚫 FORBIDDEN to modify content completed in previous steps
-- 📖 Only reload documents that were already tracked in `inputDocuments`
-
-## EXECUTION PROTOCOLS:
-
-- 🎯 Show your analysis of current state before taking action
-- Update frontmatter: add this step name to the end of the steps completed array
-- 📖 Only load documents that were already tracked in `inputDocuments`
-- 🚫 FORBIDDEN to discover new input documents during continuation
-
-## CONTEXT BOUNDARIES:
-
-- Available context: Current document and frontmatter are already loaded
-- Focus: Workflow state analysis and continuation logic only
-- Limits: Don't assume knowledge beyond what's in the document
-- Dependencies: Existing workflow state from previous session
-
-## Sequence of Instructions (Do not deviate, skip, or optimize)
-
-### 1. Analyze Current State
-
-**State Assessment:**
-Review the frontmatter to understand:
-
-- `stepsCompleted`: Array of completed step filenames
-- Last element of `stepsCompleted` array: The most recently completed step
-- `inputDocuments`: What context was already loaded
-- All other frontmatter variables
-
-### 2. Restore Context Documents
-
-**Context Reloading:**
-
-- For each document in `inputDocuments`, load the complete file
-- This ensures you have full context for continuation
-- Don't discover new documents - only reload what was previously processed
-
-### 3. Determine Next Step
-
-**Simplified Next Step Logic:**
-1. Get the last element from the `stepsCompleted` array (this is the filename of the last completed step, e.g., "step-03-success.md")
-2. Load that step file and read its frontmatter
-3. Extract the `nextStepFile` value from the frontmatter
-4. That's the next step to load!
-
-**Example:**
-- If `stepsCompleted = ["step-01-init.md", "step-02-discovery.md", "step-03-success.md"]`
-- Last element is `"step-03-success.md"`
-- Load `{project-root}/_xiaoma/xmc/workflows/2-plan-workflows/create-prd/steps-c/step-03-success.md`, read its frontmatter
-- Read fully and follow: `{project-root}/_xiaoma/xmc/workflows/2-plan-workflows/create-prd/steps-c/step-04-journeys.md`
-
-### 4. Handle Workflow Completion
-
-**If `stepsCompleted` array contains `"step-11-complete.md"`:**
-"Great news! It looks like we've already completed the PRD workflow for {{project_name}}.
-
-The final document is ready at `{outputFile}` with all sections completed.
-
-Would you like me to:
-
-- Review the completed PRD with you
-- Suggest next workflow steps (like architecture or epic creation)
-- Start a new PRD revision
-
-What would be most helpful?"
-
-### 5. Present Current Progress
-
-**If workflow not complete:**
-"Welcome back {{user_name}}! I'm resuming our PRD collaboration for {{project_name}}.
-
-**Current Progress:**
-- Last completed: {last step filename from stepsCompleted array}
-- Next up: {nextStepFile determined from that step's frontmatter}
-- Context documents available: {len(inputDocuments)} files
-
-**Document Status:**
-- Current PRD document is ready with all completed sections
-- Ready to continue from where we left off
-
-Does this look right, or do you want to make any adjustments before we proceed?"
-
-### 6. Present MENU OPTIONS
-
-Display: "**Select an Option:** [C] Continue to {next step name}"
-
-#### Menu Handling Logic:
-
-- IF C: Read fully and follow the {nextStepFile} determined in step 3
-- IF Any other comments or queries: respond and redisplay menu
-
-#### EXECUTION RULES:
-
-- ALWAYS halt and wait for user input after presenting menu
-- ONLY proceed to next step when user selects 'C'
-
-## CRITICAL STEP COMPLETION NOTE
-
-ONLY WHEN [C continue option] is selected and [current state confirmed], will you then read fully and follow: {nextStepFile} to resume the workflow.
-
----
-
-## 🚨 SYSTEM SUCCESS/FAILURE METRICS
-
-### ✅ SUCCESS:
-
-- All previous input documents successfully reloaded
-- Current workflow state accurately analyzed and presented
-- User confirms understanding of progress before continuation
-- Correct next step identified and prepared for loading
-
-### ❌ SYSTEM FAILURE:
-
-- Discovering new input documents instead of reloading existing ones
-- Modifying content from already completed steps
-- Failing to extract nextStepFile from the last completed step's frontmatter
-- Proceeding without user confirmation of current state
-
-**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

package/src/xmc/workflows/2-plan-workflows/create-prd/steps-c/step-02-discovery.md

@@ -1,224 +0,0 @@
----
-name: 'step-02-discovery'
-description: 'Discover project type, domain, and context through collaborative dialogue'
-
-# File References
-nextStepFile: '{project-root}/_xiaoma/xmc/workflows/2-plan-workflows/create-prd/steps-c/step-02b-vision.md'
-outputFile: '{planning_artifacts}/prd.md'
-
-# Data Files
-projectTypesCSV: '../data/project-types.csv'
-domainComplexityCSV: '../data/domain-complexity.csv'
-
-# Task References
-advancedElicitationTask: '{project-root}/_xiaoma/core/workflows/advanced-elicitation/workflow.md'
-partyModeWorkflow: '{project-root}/_xiaoma/core/workflows/party-mode/workflow.md'
----
-
-# Step 2: Project Discovery
-
-**Progress: Step 2 of 13** - Next: Product Vision
-
-## STEP GOAL:
-
-Discover and classify the project - understand what type of product this is, what domain it operates in, and the project context (greenfield vs brownfield).
-
-## 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 the entire file is read
-- ✅ ALWAYS treat this as collaborative discovery between PM peers
-- 📋 YOU ARE A FACILITATOR, not a content generator
-- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
-
-### Role Reinforcement:
-
-- ✅ You are a product-focused PM facilitator collaborating with an expert peer
-- ✅ We engage in collaborative dialogue, not command-response
-- ✅ You bring structured thinking and facilitation skills, while the user brings domain expertise and product vision
-
-### Step-Specific Rules:
-
-- 🎯 Focus on classification and understanding - no content generation yet
-- 🚫 FORBIDDEN to generate executive summary or vision statements (that's next steps)
-- 💬 APPROACH: Natural conversation to understand the project
-- 🎯 LOAD classification data BEFORE starting discovery conversation
-
-## EXECUTION PROTOCOLS:
-
-- 🎯 Show your analysis before taking any action
-- ⚠️ Present A/P/C menu after classification complete
-- 💾 ONLY save classification to frontmatter when user chooses C (Continue)
-- 📖 Update frontmatter, adding this step to the end of the list of stepsCompleted
-- 🚫 FORBIDDEN to load next step until C is selected
-
-## CONTEXT BOUNDARIES:
-
-- Current document and frontmatter from step 1 are available
-- Input documents already loaded are in memory (product briefs, research, brainstorming, project docs)
-- **Document counts available in frontmatter `documentCounts`**
-- Classification CSV data will be loaded in this step only
-- No executive summary or vision content yet (that's steps 2b and 2c)
-
-## YOUR TASK:
-
-Discover and classify the project through natural conversation:
-- What type of product is this? (web app, API, mobile, etc.)
-- What domain does it operate in? (healthcare, fintech, e-commerce, etc.)
-- What's the project context? (greenfield new product vs brownfield existing system)
-- How complex is this domain? (low, medium, high)
-
-## DISCOVERY SEQUENCE:
-
-### 1. Check Document State
-
-Read the frontmatter from `{outputFile}` to get document counts:
-- `briefCount` - Product briefs available
-- `researchCount` - Research documents available
-- `brainstormingCount` - Brainstorming docs available
-- `projectDocsCount` - Existing project documentation
-
-**Announce your understanding:**
-
-"From step 1, I have loaded:
-- Product briefs: {{briefCount}}
-- Research: {{researchCount}}
-- Brainstorming: {{brainstormingCount}}
-- Project docs: {{projectDocsCount}}
-
-{{if projectDocsCount > 0}}This is a brownfield project - I'll focus on understanding what you want to add or change.{{else}}This is a greenfield project - I'll help you define the full product vision.{{/if}}"
-
-### 2. Load Classification Data
-
-**Attempt subprocess data lookup:**
-
-**Project Type Lookup:**
-"Your task: Lookup data in {projectTypesCSV}
-
-**Search criteria:**
-- Find row where project_type matches {{detectedProjectType}}
-
-**Return format:**
-Return ONLY the matching row as a YAML-formatted object with these fields:
-project_type, detection_signals
-
-**Do NOT return the entire CSV - only the matching row.**"
-
-**Domain Complexity Lookup:**
-"Your task: Lookup data in {domainComplexityCSV}
-
-**Search criteria:**
-- Find row where domain matches {{detectedDomain}}
-
-**Return format:**
-Return ONLY the matching row as a YAML-formatted object with these fields:
-domain, complexity, typical_concerns, compliance_requirements
-
-**Do NOT return the entire CSV - only the matching row.**"
-
-**Graceful degradation (if Task tool unavailable):**
-- Load the CSV files directly
-- Find the matching rows manually
-- Extract required fields
-- Keep in memory for intelligent classification
-
-### 3. Begin Discovery Conversation
-
-**Start with what you know:**
-
-If the user has a product brief or project docs, acknowledge them and share your understanding. Then ask clarifying questions to deepen your understanding.
-
-If this is a greenfield project with no docs, start with open-ended discovery:
-- What problem does this solve?
-- Who's it for?
-- What excites you about building this?
-
-**Listen for classification signals:**
-
-As the user describes their product, match against:
-- **Project type signals** (API, mobile, SaaS, etc.)
-- **Domain signals** (healthcare, fintech, education, etc.)
-- **Complexity indicators** (regulated industries, novel technology, etc.)
-
-### 4. Confirm Classification
-
-Once you have enough understanding, share your classification:
-
-"I'm hearing this as:
-- **Project Type:** {{detectedType}}
-- **Domain:** {{detectedDomain}}
-- **Complexity:** {{complexityLevel}}
-
-Does this sound right to you?"
-
-Let the user confirm or refine your classification.
-
-### 5. Save Classification to Frontmatter
-
-When user selects 'C', update frontmatter with classification:
-```yaml
-classification:
-  projectType: {{projectType}}
-  domain: {{domain}}
-  complexity: {{complexityLevel}}
-  projectContext: {{greenfield|brownfield}}
-```
-
-### N. Present MENU OPTIONS
-
-Present the project classification for review, then display menu:
-
-"Based on our conversation, I've discovered and classified your project.
-
-**Here's the classification:**
-
-**Project Type:** {{detectedType}}
-**Domain:** {{detectedDomain}}
-**Complexity:** {{complexityLevel}}
-**Project Context:** {{greenfield|brownfield}}
-
-**What would you like to do?**"
-
-Display: "**Select:** [A] Advanced Elicitation [P] Party Mode [C] Continue to Product Vision (Step 2b of 13)"
-
-#### Menu Handling Logic:
-- IF A: Read fully and follow: {advancedElicitationTask} with the current classification, process the enhanced insights that come back, ask user if they accept the improvements, if yes update classification then redisplay menu, if no keep original classification then redisplay menu
-- IF P: Read fully and follow: {partyModeWorkflow} with the current classification, process the collaborative insights, ask user if they accept the changes, if yes update classification then redisplay menu, if no keep original classification then redisplay menu
-- IF C: Save classification to {outputFile} frontmatter, add this step name to the end of stepsCompleted array, then read fully and follow: {nextStepFile}
-- IF Any other: help user respond, then redisplay menu
-
-#### 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
-
-## CRITICAL STEP COMPLETION NOTE
-
-ONLY WHEN [C continue option] is selected and [classification saved to frontmatter], will you then read fully and follow: `{nextStepFile}` to explore product vision.
-
----
-
-## 🚨 SYSTEM SUCCESS/FAILURE METRICS
-
-### ✅ SUCCESS:
-
-- Document state checked and announced to user
-- Classification data loaded and used intelligently
-- Natural conversation to understand project type, domain, complexity
-- Classification validated with user before saving
-- Frontmatter updated with classification when C selected
-- User's existing documents acknowledged and built upon
-
-### ❌ SYSTEM FAILURE:
-
-- Not reading documentCounts from frontmatter first
-- Skipping classification data loading
-- Generating executive summary or vision content (that's later steps!)
-- Not validating classification with user
-- Being prescriptive instead of having natural conversation
-- Proceeding without user selecting 'C'
-
-**Master Rule:** This is classification and understanding only. No content generation yet. Build on what the user already has. Have natural conversations, don't follow scripts.