@zeyue0329/xiaoma-cli 1.12.0 → 1.15.0

package/src/core/skills/xiaoma-advanced-elicitation/SKILL.md

@@ -1,6 +0,0 @@
----
-name: xiaoma-advanced-elicitation
-description: 'Push the LLM to reconsider, refine, and improve its recent output.'
----
-
-Follow the instructions in ./workflow.md.

package/src/core/skills/xiaoma-advanced-elicitation/methods.csv

@@ -1,51 +0,0 @@
-num,category,method_name,description,output_pattern
-1,collaboration,Stakeholder Round Table,Convene multiple personas to contribute diverse perspectives - essential for requirements gathering and finding balanced solutions across competing interests,perspectives → synthesis → alignment
-2,collaboration,Expert Panel Review,Assemble domain experts for deep specialized analysis - ideal when technical depth and peer review quality are needed,expert views → consensus → recommendations
-3,collaboration,Debate Club Showdown,Two personas argue opposing positions while a moderator scores points - great for exploring controversial decisions and finding middle ground,thesis → antithesis → synthesis
-4,collaboration,User Persona Focus Group,Gather your product's user personas to react to proposals and share frustrations - essential for validating features and discovering unmet needs,reactions → concerns → priorities
-5,collaboration,Time Traveler Council,Past-you and future-you advise present-you on decisions - powerful for gaining perspective on long-term consequences vs short-term pressures,past wisdom → present choice → future impact
-6,collaboration,Cross-Functional War Room,Product manager + engineer + designer tackle a problem together - reveals trade-offs between feasibility desirability and viability,constraints → trade-offs → balanced solution
-7,collaboration,Mentor and Apprentice,Senior expert teaches junior while junior asks naive questions - surfaces hidden assumptions through teaching,explanation → questions → deeper understanding
-8,collaboration,Good Cop Bad Cop,Supportive persona and critical persona alternate - finds both strengths to build on and weaknesses to address,encouragement → criticism → balanced view
-9,collaboration,Improv Yes-And,Multiple personas build on each other's ideas without blocking - generates unexpected creative directions through collaborative building,idea → build → build → surprising result
-10,collaboration,Customer Support Theater,Angry customer and support rep roleplay to find pain points - reveals real user frustrations and service gaps,complaint → investigation → resolution → prevention
-11,advanced,Tree of Thoughts,Explore multiple reasoning paths simultaneously then evaluate and select the best - perfect for complex problems with multiple valid approaches,paths → evaluation → selection
-12,advanced,Graph of Thoughts,Model reasoning as an interconnected network of ideas to reveal hidden relationships - ideal for systems thinking and discovering emergent patterns,nodes → connections → patterns
-13,advanced,Thread of Thought,Maintain coherent reasoning across long contexts by weaving a continuous narrative thread - essential for RAG systems and maintaining consistency,context → thread → synthesis
-14,advanced,Self-Consistency Validation,Generate multiple independent approaches then compare for consistency - crucial for high-stakes decisions where verification matters,approaches → comparison → consensus
-15,advanced,Meta-Prompting Analysis,Step back to analyze the approach structure and methodology itself - valuable for optimizing prompts and improving problem-solving,current → analysis → optimization
-16,advanced,Reasoning via Planning,Build a reasoning tree guided by world models and goal states - excellent for strategic planning and sequential decision-making,model → planning → strategy
-17,competitive,Red Team vs Blue Team,Adversarial attack-defend analysis to find vulnerabilities - critical for security testing and building robust solutions,defense → attack → hardening
-18,competitive,Shark Tank Pitch,Entrepreneur pitches to skeptical investors who poke holes - stress-tests business viability and forces clarity on value proposition,pitch → challenges → refinement
-19,competitive,Code Review Gauntlet,Senior devs with different philosophies review the same code - surfaces style debates and finds consensus on best practices,reviews → debates → standards
-20,technical,Architecture Decision Records,Multiple architect personas propose and debate architectural choices with explicit trade-offs - ensures decisions are well-reasoned and documented,options → trade-offs → decision → rationale
-21,technical,Rubber Duck Debugging Evolved,Explain your code to progressively more technical ducks until you find the bug - forces clarity at multiple abstraction levels,simple → detailed → technical → aha
-22,technical,Algorithm Olympics,Multiple approaches compete on the same problem with benchmarks - finds optimal solution through direct comparison,implementations → benchmarks → winner
-23,technical,Security Audit Personas,Hacker + defender + auditor examine system from different threat models - comprehensive security review from multiple angles,vulnerabilities → defenses → compliance
-24,technical,Performance Profiler Panel,Database expert + frontend specialist + DevOps engineer diagnose slowness - finds bottlenecks across the full stack,symptoms → analysis → optimizations
-25,creative,SCAMPER Method,Apply seven creativity lenses (Substitute/Combine/Adapt/Modify/Put/Eliminate/Reverse) - systematic ideation for product innovation,S→C→A→M→P→E→R
-26,creative,Reverse Engineering,Work backwards from desired outcome to find implementation path - powerful for goal achievement and understanding endpoints,end state → steps backward → path forward
-27,creative,What If Scenarios,Explore alternative realities to understand possibilities and implications - valuable for contingency planning and exploration,scenarios → implications → insights
-28,creative,Random Input Stimulus,Inject unrelated concepts to spark unexpected connections - breaks creative blocks through forced lateral thinking,random word → associations → novel ideas
-29,creative,Exquisite Corpse Brainstorm,Each persona adds to the idea seeing only the previous contribution - generates surprising combinations through constrained collaboration,contribution → handoff → contribution → surprise
-30,creative,Genre Mashup,Combine two unrelated domains to find fresh approaches - innovation through unexpected cross-pollination,domain A + domain B → hybrid insights
-31,research,Literature Review Personas,Optimist researcher + skeptic researcher + synthesizer review sources - balanced assessment of evidence quality,sources → critiques → synthesis
-32,research,Thesis Defense Simulation,Student defends hypothesis against committee with different concerns - stress-tests research methodology and conclusions,thesis → challenges → defense → refinements
-33,research,Comparative Analysis Matrix,Multiple analysts evaluate options against weighted criteria - structured decision-making with explicit scoring,options → criteria → scores → recommendation
-34,risk,Pre-mortem Analysis,Imagine future failure then work backwards to prevent it - powerful technique for risk mitigation before major launches,failure scenario → causes → prevention
-35,risk,Failure Mode Analysis,Systematically explore how each component could fail - critical for reliability engineering and safety-critical systems,components → failures → prevention
-36,risk,Challenge from Critical Perspective,Play devil's advocate to stress-test ideas and find weaknesses - essential for overcoming groupthink,assumptions → challenges → strengthening
-37,risk,Identify Potential Risks,Brainstorm what could go wrong across all categories - fundamental for project planning and deployment preparation,categories → risks → mitigations
-38,risk,Chaos Monkey Scenarios,Deliberately break things to test resilience and recovery - ensures systems handle failures gracefully,break → observe → harden
-39,core,First Principles Analysis,Strip away assumptions to rebuild from fundamental truths - breakthrough technique for innovation and solving impossible problems,assumptions → truths → new approach
-40,core,5 Whys Deep Dive,Repeatedly ask why to drill down to root causes - simple but powerful for understanding failures,why chain → root cause → solution
-41,core,Socratic Questioning,Use targeted questions to reveal hidden assumptions and guide discovery - excellent for teaching and self-discovery,questions → revelations → understanding
-42,core,Critique and Refine,Systematic review to identify strengths and weaknesses then improve - standard quality check for drafts,strengths/weaknesses → improvements → refined
-43,core,Explain Reasoning,Walk through step-by-step thinking to show how conclusions were reached - crucial for transparency,steps → logic → conclusion
-44,core,Expand or Contract for Audience,Dynamically adjust detail level and technical depth for target audience - matches content to reader capabilities,audience → adjustments → refined content
-45,learning,Feynman Technique,Explain complex concepts simply as if teaching a child - the ultimate test of true understanding,complex → simple → gaps → mastery
-46,learning,Active Recall Testing,Test understanding without references to verify true knowledge - essential for identifying gaps,test → gaps → reinforcement
-47,philosophical,Occam's Razor Application,Find the simplest sufficient explanation by eliminating unnecessary complexity - essential for debugging,options → simplification → selection
-48,philosophical,Trolley Problem Variations,Explore ethical trade-offs through moral dilemmas - valuable for understanding values and difficult decisions,dilemma → analysis → decision
-49,retrospective,Hindsight Reflection,Imagine looking back from the future to gain perspective - powerful for project reviews,future view → insights → application
-50,retrospective,Lessons Learned Extraction,Systematically identify key takeaways and actionable improvements - essential for continuous improvement,experience → lessons → actions

package/src/core/skills/xiaoma-editorial-review-prose/SKILL.md

@@ -1,6 +0,0 @@
----
-name: xiaoma-editorial-review-prose
-description: 'Clinical copy-editor that reviews text for communication issues. Use when user says review for prose or improve the prose'
----
-
-Follow the instructions in ./workflow.md.

package/src/core/skills/xiaoma-editorial-review-structure/SKILL.md

@@ -1,6 +0,0 @@
----
-name: xiaoma-editorial-review-structure
-description: 'Structural editor that proposes cuts, reorganization, and simplification while preserving comprehension. Use when user requests structural review or editorial review of structure'
----
-
-Follow the instructions in ./workflow.md.

package/src/core/skills/xiaoma-help/SKILL.md

@@ -1,6 +0,0 @@
----
-name: xiaoma-help
-description: 'Analyzes current state and user query to answer XiaoMa questions or recommend the next workflow or agent. Use when user says what should I do next, what do I do now, or asks a question about XiaoMa'
----
-
-Follow the instructions in ./workflow.md.

package/src/core/skills/xiaoma-help/workflow.md

@@ -1,88 +0,0 @@
-
-# Task: XiaoMa Help
-
-## ROUTING RULES
-
-- **Empty `phase` = anytime** — Universal tools work regardless of workflow state
-- **Numbered phases indicate sequence** — Phases like `1-discover` → `2-define` → `3-build` → `4-ship` flow in order (naming varies by module)
-- **Phase with no Required Steps** - If an entire phase has no required, true items, the entire phase is optional. If it is sequentially before another phase, it can be recommended, but always be clear with the use what the true next required item is.
-- **Stay in module** — Guide through the active module's workflow based on phase+sequence ordering
-- **Descriptions contain routing** — Read for alternate paths (e.g., "back to previous if fixes needed")
-- **`required=true` blocks progress** — Required workflows must complete before proceeding to later phases
-- **Artifacts reveal completion** — Search resolved output paths for `outputs` patterns, fuzzy-match found files to workflow rows
-
-## DISPLAY RULES
-
-### Command-Based Workflows
-When `command` field has a value:
-- Show the command as a skill name in backticks (e.g., `xiaoma-xmc-create-prd`)
-
-### Skill-Referenced Workflows
-When `workflow-file` starts with `skill:`:
-- The value is a skill reference (e.g., `skill:xiaoma-quick-dev-new-preview`), NOT a file path
-- Do NOT attempt to resolve or load it as a file path
-- Display using the `command` column value as a skill name in backticks (same as command-based workflows)
-
-### Agent-Based Workflows
-When `command` field is empty:
-- User loads agent first by invoking the agent skill (e.g., `xiaoma-pm`)
-- Then invokes by referencing the `code` field or describing the `name` field
-- Do NOT show a slash command — show the code value and agent load instruction instead
-
-Example presentation for empty command:
-```
-Explain Concept (EC)
-Load: tech-writer agent skill, then ask to "EC about [topic]"
-Agent: Tech Writer
-Description: Create clear technical explanations with examples...
-```
-
-## MODULE DETECTION
-
-- **Empty `module` column** → universal tools (work across all modules)
-- **Named `module`** → module-specific workflows
-
-Detect the active module from conversation context, recent workflows, or user query keywords. If ambiguous, ask the user.
-
-## INPUT ANALYSIS
-
-Determine what was just completed:
-- Explicit completion stated by user
-- Workflow completed in current conversation
-- Artifacts found matching `outputs` patterns
-- If `index.md` exists, read it for additional context
-- If still unclear, ask: "What workflow did you most recently complete?"
-
-## EXECUTION
-
-1. **Load catalog** — Load `{project-root}/_xiaoma/_config/xiaoma-help.csv`
-
-2. **Resolve output locations and config** — Scan each folder under `{project-root}/_xiaoma/` (except `_config`) for `config.yaml`. For each workflow row, resolve its `output-location` variables against that module's config so artifact paths can be searched. Also extract `communication_language` and `project_knowledge` from each scanned module's config.
-
-3. **Ground in project knowledge** — If `project_knowledge` resolves to an existing path, read available documentation files (architecture docs, project overview, tech stack references) for grounding context. Use discovered project facts when composing any project-specific output. Never fabricate project-specific details — if documentation is unavailable, state so.
-
-4. **Detect active module** — Use MODULE DETECTION above
-
-5. **Analyze input** — Task may provide a workflow name/code, conversational phrase, or nothing. Infer what was just completed using INPUT ANALYSIS above.
-
-6. **Present recommendations** — Show next steps based on:
-   - Completed workflows detected
-   - Phase/sequence ordering (ROUTING RULES)
-   - Artifact presence
-
-   **Optional items first** — List optional workflows until a required step is reached
-   **Required items next** — List the next required workflow
-
-   For each item, apply DISPLAY RULES above and include:
-   - Workflow **name**
-   - **Command** OR **Code + Agent load instruction** (per DISPLAY RULES)
-   - **Agent** title and display name from the CSV (e.g., "🎨 Alex (Designer)")
-   - Brief **description**
-
-7. **Additional guidance to convey**:
-   - Present all output in `{communication_language}`
-   - Run each workflow in a **fresh context window**
-   - For **validation workflows**: recommend using a different high-quality LLM if available
-   - For conversational requests: match the user's tone while presenting clearly
-
-8. Return to the calling process after presenting recommendations.

package/src/core/skills/xiaoma-help/xiaoma-skill-manifest.yaml

@@ -1 +0,0 @@
-type: skill

package/src/core/skills/xiaoma-index-docs/SKILL.md

@@ -1,6 +0,0 @@
----
-name: xiaoma-index-docs
-description: 'Generates or updates an index.md to reference all docs in the folder. Use if user requests to create or update an index of all files in a specific folder'
----
-
-Follow the instructions in ./workflow.md.

package/src/core/skills/xiaoma-index-docs/xiaoma-skill-manifest.yaml

@@ -1 +0,0 @@
-type: skill

package/src/core/skills/xiaoma-party-mode/SKILL.md

@@ -1,6 +0,0 @@
----
-name: xiaoma-party-mode
-description: 'Orchestrates group discussions between all installed XiaoMa agents, enabling natural multi-agent conversations. Use when user requests party mode.'
----
-
-Follow the instructions in ./workflow.md.

package/src/core/skills/xiaoma-party-mode/steps/step-01-agent-loading.md

@@ -1,138 +0,0 @@
-# Step 1: Agent Loading and Party Mode Initialization
-
-## MANDATORY EXECUTION RULES (READ FIRST):
-
-- ✅ YOU ARE A PARTY MODE FACILITATOR, not just a workflow executor
-- 🎯 CREATE ENGAGING ATMOSPHERE for multi-agent collaboration
-- 📋 LOAD COMPLETE AGENT ROSTER from manifest with merged personalities
-- 🔍 PARSE AGENT DATA for conversation orchestration
-- 💬 INTRODUCE DIVERSE AGENT SAMPLE to kick off discussion
-- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
-
-## EXECUTION PROTOCOLS:
-
-- 🎯 Show agent loading process before presenting party activation
-- ⚠️ Present [C] continue option after agent roster is loaded
-- 💾 ONLY save when user chooses C (Continue)
-- 📖 Update frontmatter `stepsCompleted: [1]` before loading next step
-- 🚫 FORBIDDEN to start conversation until C is selected
-
-## CONTEXT BOUNDARIES:
-
-- Agent manifest CSV is available at `{project-root}/_xiaoma/_config/agent-manifest.csv`
-- User configuration from config.yaml is loaded and resolved
-- Party mode is standalone interactive workflow
-- All agent data is available for conversation orchestration
-
-## YOUR TASK:
-
-Load the complete agent roster from manifest and initialize party mode with engaging introduction.
-
-## AGENT LOADING SEQUENCE:
-
-### 1. Load Agent Manifest
-
-Begin agent loading process:
-
-"Now initializing **Party Mode** with our complete XiaoMa agent roster! Let me load up all our talented agents and get them ready for an amazing collaborative discussion.
-
-**Agent Manifest Loading:**"
-
-Load and parse the agent manifest CSV from `{project-root}/_xiaoma/_config/agent-manifest.csv`
-
-### 2. Extract Agent Data
-
-Parse CSV to extract complete agent information for each entry:
-
-**Agent Data Points:**
-
-- **name** (agent identifier for system calls)
-- **displayName** (agent's persona name for conversations)
-- **title** (formal position and role description)
-- **icon** (visual identifier emoji)
-- **role** (capabilities and expertise summary)
-- **identity** (background and specialization details)
-- **communicationStyle** (how they communicate and express themselves)
-- **principles** (decision-making philosophy and values)
-- **module** (source module organization)
-- **path** (file location reference)
-
-### 3. Build Agent Roster
-
-Create complete agent roster with merged personalities:
-
-**Roster Building Process:**
-
-- Combine manifest data with agent file configurations
-- Merge personality traits, capabilities, and communication styles
-- Validate agent availability and configuration completeness
-- Organize agents by expertise domains for intelligent selection
-
-### 4. Party Mode Activation
-
-Generate enthusiastic party mode introduction:
-
-"🎉 PARTY MODE ACTIVATED! 🎉
-
-Welcome {{user_name}}! I'm excited to facilitate an incredible multi-agent discussion with our complete XiaoMa team. All our specialized agents are online and ready to collaborate, bringing their unique expertise and perspectives to whatever you'd like to explore.
-
-**Our Collaborating Agents Include:**
-
-[Display 3-4 diverse agents to showcase variety]:
-
-- [Icon Emoji] **[Agent Name]** ([Title]): [Brief role description]
-- [Icon Emoji] **[Agent Name]** ([Title]): [Brief role description]
-- [Icon Emoji] **[Agent Name]** ([Title]): [Brief role description]
-
-**[Total Count] agents** are ready to contribute their expertise!
-
-**What would you like to discuss with the team today?**"
-
-### 5. Present Continue Option
-
-After agent loading and introduction:
-
-"**Agent roster loaded successfully!** All our XiaoMa experts are excited to collaborate with you.
-
-**Ready to start the discussion?**
-[C] Continue - Begin multi-agent conversation
-
-### 6. Handle Continue Selection
-
-#### If 'C' (Continue):
-
-- Update frontmatter: `stepsCompleted: [1]`
-- Set `agents_loaded: true` and `party_active: true`
-- Load: `./step-02-discussion-orchestration.md`
-
-## SUCCESS METRICS:
-
-✅ Agent manifest successfully loaded and parsed
-✅ Complete agent roster built with merged personalities
-✅ Engaging party mode introduction created
-✅ Diverse agent sample showcased for user
-✅ [C] continue option presented and handled correctly
-✅ Frontmatter updated with agent loading status
-✅ Proper routing to discussion orchestration step
-
-## FAILURE MODES:
-
-❌ Failed to load or parse agent manifest CSV
-❌ Incomplete agent data extraction or roster building
-❌ Generic or unengaging party mode introduction
-❌ Not showcasing diverse agent capabilities
-❌ Not presenting [C] continue option after loading
-❌ Starting conversation without user selection
-
-## AGENT LOADING PROTOCOLS:
-
-- Validate CSV format and required columns
-- Handle missing or incomplete agent entries gracefully
-- Cross-reference manifest with actual agent files
-- Prepare agent selection logic for intelligent conversation routing
-
-## NEXT STEP:
-
-After user selects 'C', load `./step-02-discussion-orchestration.md` to begin the interactive multi-agent conversation with intelligent agent selection and natural conversation flow.
-
-Remember: Create an engaging, party-like atmosphere while maintaining professional expertise and intelligent conversation orchestration!

package/src/core/skills/xiaoma-party-mode/steps/step-02-discussion-orchestration.md

@@ -1,187 +0,0 @@
-# Step 2: Discussion Orchestration and Multi-Agent Conversation
-
-## MANDATORY EXECUTION RULES (READ FIRST):
-
-- ✅ YOU ARE A CONVERSATION ORCHESTRATOR, not just a response generator
-- 🎯 SELECT RELEVANT AGENTS based on topic analysis and expertise matching
-- 📋 MAINTAIN CHARACTER CONSISTENCY using merged agent personalities
-- 🔍 ENABLE NATURAL CROSS-TALK between agents for dynamic conversation
-- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
-
-## EXECUTION PROTOCOLS:
-
-- 🎯 Analyze user input for intelligent agent selection before responding
-- ⚠️ Present [E] exit option after each agent response round
-- 💾 Continue conversation until user selects E (Exit)
-- 📖 Maintain conversation state and context throughout session
-- 🚫 FORBIDDEN to exit until E is selected or exit trigger detected
-
-## CONTEXT BOUNDARIES:
-
-- Complete agent roster with merged personalities is available
-- User topic and conversation history guide agent selection
-- Exit triggers: `*exit`, `goodbye`, `end party`, `quit`
-
-## YOUR TASK:
-
-Orchestrate dynamic multi-agent conversations with intelligent agent selection, natural cross-talk, and authentic character portrayal.
-
-## DISCUSSION ORCHESTRATION SEQUENCE:
-
-### 1. User Input Analysis
-
-For each user message or topic:
-
-**Input Analysis Process:**
-"Analyzing your message for the perfect agent collaboration..."
-
-**Analysis Criteria:**
-
-- Domain expertise requirements (technical, business, creative, etc.)
-- Complexity level and depth needed
-- Conversation context and previous agent contributions
-- User's specific agent mentions or requests
-
-### 2. Intelligent Agent Selection
-
-Select 2-3 most relevant agents based on analysis:
-
-**Selection Logic:**
-
-- **Primary Agent**: Best expertise match for core topic
-- **Secondary Agent**: Complementary perspective or alternative approach
-- **Tertiary Agent**: Cross-domain insight or devil's advocate (if beneficial)
-
-**Priority Rules:**
-
-- If user names specific agent → Prioritize that agent + 1-2 complementary agents
-- Rotate agent participation over time to ensure inclusive discussion
-- Balance expertise domains for comprehensive perspectives
-
-### 3. In-Character Response Generation
-
-Generate authentic responses for each selected agent:
-
-**Character Consistency:**
-
-- Apply agent's exact communication style from merged data
-- Reflect their principles and values in reasoning
-- Draw from their identity and role for authentic expertise
-- Maintain their unique voice and personality traits
-
-**Response Structure:**
-[For each selected agent]:
-
-"[Icon Emoji] **[Agent Name]**: [Authentic in-character response]
-
-[Bash: .claude/hooks/xiaoma-speak.sh \"[Agent Name]\" \"[Their response]\"]"
-
-### 4. Natural Cross-Talk Integration
-
-Enable dynamic agent-to-agent interactions:
-
-**Cross-Talk Patterns:**
-
-- Agents can reference each other by name: "As [Another Agent] mentioned..."
-- Building on previous points: "[Another Agent] makes a great point about..."
-- Respectful disagreements: "I see it differently than [Another Agent]..."
-- Follow-up questions between agents: "How would you handle [specific aspect]?"
-
-**Conversation Flow:**
-
-- Allow natural conversational progression
-- Enable agents to ask each other questions
-- Maintain professional yet engaging discourse
-- Include personality-driven humor and quirks when appropriate
-
-### 5. Question Handling Protocol
-
-Manage different types of questions appropriately:
-
-**Direct Questions to User:**
-When an agent asks the user a specific question:
-
-- End that response round immediately after the question
-- Clearly highlight: **[Agent Name] asks: [Their question]**
-- Display: _[Awaiting user response...]_
-- WAIT for user input before continuing
-
-**Rhetorical Questions:**
-Agents can ask thinking-aloud questions without pausing conversation flow.
-
-**Inter-Agent Questions:**
-Allow natural back-and-forth within the same response round for dynamic interaction.
-
-### 6. Response Round Completion
-
-After generating all agent responses for the round, let the user know he can speak naturally with the agents, an then show this menu opion"
-
-`[E] Exit Party Mode - End the collaborative session`
-
-### 7. Exit Condition Checking
-
-Check for exit conditions before continuing:
-
-**Automatic Triggers:**
-
-- User message contains: `*exit`, `goodbye`, `end party`, `quit`
-- Immediate agent farewells and workflow termination
-
-**Natural Conclusion:**
-
-- Conversation seems naturally concluding
-- Confirm if the user wants to exit party mode and go back to where they were or continue chatting. Do it in a conversational way with an agent in the party.
-
-### 8. Handle Exit Selection
-
-#### If 'E' (Exit Party Mode):
-
-- Read fully and follow: `./step-03-graceful-exit.md`
-
-## SUCCESS METRICS:
-
-✅ Intelligent agent selection based on topic analysis
-✅ Authentic in-character responses maintained consistently
-✅ Natural cross-talk and agent interactions enabled
-✅ Question handling protocol followed correctly
-✅ [E] exit option presented after each response round
-✅ Conversation context and state maintained throughout
-✅ Graceful conversation flow without abrupt interruptions
-
-## FAILURE MODES:
-
-❌ Generic responses without character consistency
-❌ Poor agent selection not matching topic expertise
-❌ Ignoring user questions or exit triggers
-❌ Not enabling natural agent cross-talk and interactions
-❌ Continuing conversation without user input when questions asked
-
-## CONVERSATION ORCHESTRATION PROTOCOLS:
-
-- Maintain conversation memory and context across rounds
-- Rotate agent participation for inclusive discussions
-- Handle topic drift while maintaining productivity
-- Balance fun and professional collaboration
-- Enable learning and knowledge sharing between agents
-
-## MODERATION GUIDELINES:
-
-**Quality Control:**
-
-- If discussion becomes circular, have xiaoma-master summarize and redirect
-- Ensure all agents stay true to their merged personalities
-- Handle disagreements constructively and professionally
-- Maintain respectful and inclusive conversation environment
-
-**Flow Management:**
-
-- Guide conversation toward productive outcomes
-- Encourage diverse perspectives and creative thinking
-- Balance depth with breadth of discussion
-- Adapt conversation pace to user engagement level
-
-## NEXT STEP:
-
-When user selects 'E' or exit conditions are met, load `./step-03-graceful-exit.md` to provide satisfying agent farewells and conclude the party mode session.
-
-Remember: Orchestrate engaging, intelligent conversations while maintaining authentic agent personalities and natural interaction patterns!