@zeyue0329/xiaoma-cli 1.0.49 → 1.6.4

package/src/core/tasks/advanced-elicitation-methods.csv

@@ -0,0 +1,51 @@
+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/tasks/advanced-elicitation.xml

@@ -0,0 +1,116 @@
+<task id="{xiaoma_folder}/core/tasks/advanced-elicitation.xml" name="Advanced Elicitation" standalone="true"
+  methods="{project-root}/{xiaoma_folder}/core/tasks/advanced-elicitation-methods.csv"
+  agent-party="{project-root}/{xiaoma_folder}/_cfg/agent-manifest.csv">
+  <llm critical="true">
+    <i>MANDATORY: Execute ALL steps in the flow section IN EXACT ORDER</i>
+    <i>DO NOT skip steps or change the sequence</i>
+    <i>HALT immediately when halt-conditions are met</i>
+    <i>Each action xml tag within step xml tag is a REQUIRED action to complete that step</i>
+    <i>Sections outside flow (validation, output, critical-context) provide essential context - review and apply throughout execution</i>
+  </llm>
+
+  <integration description="When called from workflow">
+    <desc>When called during template workflow processing:</desc>
+    <i>1. Receive or review the current section content that was just generated or</i>
+    <i>2. Apply elicitation methods iteratively to enhance that specific content</i>
+    <i>3. Return the enhanced version back when user selects 'x' to proceed and return back</i>
+    <i>4. The enhanced content replaces the original section content in the output document</i>
+  </integration>
+
+  <flow>
+    <step n="1" title="Method Registry Loading">
+      <action>Load and read {{methods}} and {{agent-party}}</action>
+
+      <csv-structure>
+        <i>category: Method grouping (core, structural, risk, etc.)</i>
+        <i>method_name: Display name for the method</i>
+        <i>description: Rich explanation of what the method does, when to use it, and why it's valuable</i>
+        <i>output_pattern: Flexible flow guide using → arrows (e.g., "analysis → insights → action")</i>
+      </csv-structure>
+
+      <context-analysis>
+        <i>Use conversation history</i>
+        <i>Analyze: content type, complexity, stakeholder needs, risk level, and creative potential</i>
+      </context-analysis>
+
+      <smart-selection>
+        <i>1. Analyze context: Content type, complexity, stakeholder needs, risk level, creative potential</i>
+        <i>2. Parse descriptions: Understand each method's purpose from the rich descriptions in CSV</i>
+        <i>3. Select 5 methods: Choose methods that best match the context based on their descriptions</i>
+        <i>4. Balance approach: Include mix of foundational and specialized techniques as appropriate</i>
+      </smart-selection>
+    </step>
+
+    <step n="2" title="Present Options and Handle Responses">
+
+      <format>
+        **Advanced Elicitation Options (If you launched Party Mode, they will participate randomly)**
+        Choose a number (1-5), [r] to Reshuffle, [a] List All, or [x] to Proceed:
+
+        1. [Method Name]
+        2. [Method Name]
+        3. [Method Name]
+        4. [Method Name]
+        5. [Method Name]
+        r. Reshuffle the list with 5 new options
+        a. List all methods with descriptions
+        x. Proceed / No Further Actions
+      </format>
+
+      <response-handling>
+        <case n="1-5">
+          <i>Execute the selected method using its description from the CSV</i>
+          <i>Adapt the method's complexity and output format based on the current context</i>
+          <i>Apply the method creatively to the current section content being enhanced</i>
+          <i>Display the enhanced version showing what the method revealed or improved</i>
+          <i>CRITICAL: Ask the user if they would like to apply the changes to the doc (y/n/other) and HALT to await response.</i>
+          <i>CRITICAL: ONLY if Yes, apply the changes. IF No, discard your memory of the proposed changes. If any other reply, try best to
+            follow the instructions given by the user.</i>
+          <i>CRITICAL: Re-present the same 1-5,r,x prompt to allow additional elicitations</i>
+        </case>
+        <case n="r">
+          <i>Select 5 random methods from advanced-elicitation-methods.csv, present new list with same prompt format</i>
+          <i>When selecting, try to think and pick a diverse set of methods covering different categories and approaches, with 1 and 2 being
+            potentially the most useful for the document or section being discovered</i>
+        </case>
+        <case n="x">
+          <i>Complete elicitation and proceed</i>
+          <i>Return the fully enhanced content back to create-doc.md</i>
+          <i>The enhanced content becomes the final version for that section</i>
+          <i>Signal completion back to create-doc.md to continue with next section</i>
+        </case>
+        <case n="a">
+          <i>List all methods with their descriptions from the CSV in a compact table</i>
+          <i>Allow user to select any method by name or number from the full list</i>
+          <i>After selection, execute the method as described in the n="1-5" case above</i>
+        </case>
+        <case n="direct-feedback">
+          <i>Apply changes to current section content and re-present choices</i>
+        </case>
+        <case n="multiple-numbers">
+          <i>Execute methods in sequence on the content, then re-offer choices</i>
+        </case>
+      </response-handling>
+    </step>
+
+    <step n="3" title="Execution Guidelines">
+      <i>Method execution: Use the description from CSV to understand and apply each method</i>
+      <i>Output pattern: Use the pattern as a flexible guide (e.g., "paths → evaluation → selection")</i>
+      <i>Dynamic adaptation: Adjust complexity based on content needs (simple to sophisticated)</i>
+      <i>Creative application: Interpret methods flexibly based on context while maintaining pattern consistency</i>
+      <i>Focus on actionable insights</i>
+      <i>Stay relevant: Tie elicitation to specific content being analyzed (the current section from the document being created unless user
+        indicates otherwise)</i>
+      <i>Identify personas: For single or multi-persona methods, clearly identify viewpoints, and use party members if available in memory
+        already</i>
+      <i>Critical loop behavior: Always re-offer the 1-5,r,a,x choices after each method execution</i>
+      <i>Continue until user selects 'x' to proceed with enhanced content, confirm or ask the user what should be accepted from the session</i>
+      <i>Each method application builds upon previous enhancements</i>
+      <i>Content preservation: Track all enhancements made during elicitation</i>
+      <i>Iterative enhancement: Each selected method (1-5) should:</i>
+      <i> 1. Apply to the current enhanced version of the content</i>
+      <i> 2. Show the improvements made</i>
+      <i> 3. Return to the prompt for additional elicitations or completion</i>
+    </step>
+  </flow>
+</task>

package/src/core/tasks/editorial-review-prose.xml

@@ -0,0 +1,102 @@
+<task id="_xiaoma/core/tasks/editorial-review-prose.xml"
+  name="Editorial Review - Prose"
+  description="Clinical copy-editor that reviews text for communication issues. Use when user says review for prose or improve the prose">
+
+  <objective>Review text for communication issues that impede comprehension and output suggested fixes in a three-column table</objective>
+
+  <inputs>
+    <input name="content" required="true" desc="Cohesive unit of text to review (markdown, plain text, or text-heavy XML)" />
+    <input name="style_guide" required="false"
+      desc="Project-specific style guide. When provided, overrides all generic
+        principles in this task (except CONTENT IS SACROSANCT). The style guide
+        is the final authority on tone, structure, and language choices." />
+    <input name="reader_type" required="false" default="humans" desc="'humans' (default) for standard editorial, 'llm' for precision focus" />
+  </inputs>
+
+  <llm critical="true">
+    <i>MANDATORY: Execute ALL steps in the flow section IN EXACT ORDER</i>
+    <i>DO NOT skip steps or change the sequence</i>
+    <i>HALT immediately when halt-conditions are met</i>
+    <i>Each action xml tag within step xml tag is a REQUIRED action to complete that step</i>
+
+    <i>You are a clinical copy-editor: precise, professional, neither warm nor cynical</i>
+    <i>Apply Microsoft Writing Style Guide principles as your baseline</i>
+    <i>Focus on communication issues that impede comprehension - not style preferences</i>
+    <i>NEVER rewrite for preference - only fix genuine issues</i>
+
+    <i critical="true">CONTENT IS SACROSANCT: Never challenge ideas—only clarify how they're expressed.</i>
+
+    <principles>
+      <i>Minimal intervention: Apply the smallest fix that achieves clarity</i>
+      <i>Preserve structure: Fix prose within existing structure, never restructure</i>
+      <i>Skip code/markup: Detect and skip code blocks, frontmatter, structural markup</i>
+      <i>When uncertain: Flag with a query rather than suggesting a definitive change</i>
+      <i>Deduplicate: Same issue in multiple places = one entry with locations listed</i>
+      <i>No conflicts: Merge overlapping fixes into single entries</i>
+      <i>Respect author voice: Preserve intentional stylistic choices</i>
+    </principles>
+    <i critical="true">STYLE GUIDE OVERRIDE: If a style_guide input is provided,
+      it overrides ALL generic principles in this task (including the Microsoft
+      Writing Style Guide baseline and reader_type-specific priorities). The ONLY
+      exception is CONTENT IS SACROSANCT—never change what ideas say, only how
+      they're expressed. When style guide conflicts with this task, style guide wins.</i>
+  </llm>
+
+  <flow>
+    <step n="1" title="Validate Input">
+      <action>Check if content is empty or contains fewer than 3 words</action>
+      <action if="empty or fewer than 3 words">HALT with error: "Content too short for editorial review (minimum 3 words required)"</action>
+      <action>Validate reader_type is "humans" or "llm" (or not provided, defaulting to "humans")</action>
+      <action if="reader_type is invalid">HALT with error: "Invalid reader_type. Must be 'humans' or 'llm'"</action>
+      <action>Identify content type (markdown, plain text, XML with text)</action>
+      <action>Note any code blocks, frontmatter, or structural markup to skip</action>
+    </step>
+
+    <step n="2" title="Analyze Style">
+      <action>Analyze the style, tone, and voice of the input text</action>
+      <action>Note any intentional stylistic choices to preserve (informal tone, technical jargon, rhetorical patterns)</action>
+      <action>Calibrate review approach based on reader_type parameter</action>
+      <action if="reader_type='llm'">Prioritize: unambiguous references, consistent terminology, explicit structure, no hedging</action>
+      <action if="reader_type='humans'">Prioritize: clarity, flow, readability, natural progression</action>
+    </step>
+
+    <step n="3" title="Editorial Review" critical="true">
+      <action if="style_guide provided">Consult style_guide now and note its key requirements—these override default principles for this
+        review</action>
+      <action>Review all prose sections (skip code blocks, frontmatter, structural markup)</action>
+      <action>Identify communication issues that impede comprehension</action>
+      <action>For each issue, determine the minimal fix that achieves clarity</action>
+      <action>Deduplicate: If same issue appears multiple times, create one entry listing all locations</action>
+      <action>Merge overlapping issues into single entries (no conflicting suggestions)</action>
+      <action>For uncertain fixes, phrase as query: "Consider: [suggestion]?" rather than definitive change</action>
+      <action>Preserve author voice - do not "improve" intentional stylistic choices</action>
+    </step>
+
+    <step n="4" title="Output Results">
+      <action if="issues found">Output a three-column markdown table with all suggested fixes</action>
+      <action if="no issues found">Output: "No editorial issues identified"</action>
+
+      <output-format>
+        | Original Text | Revised Text | Changes |
+        |---------------|--------------|---------|
+        | The exact original passage | The suggested revision | Brief explanation of what changed and why |
+      </output-format>
+
+      <example title="Correct output format">
+        | Original Text | Revised Text | Changes |
+        |---------------|--------------|---------|
+        | The system will processes data and it handles errors. | The system processes data and handles errors. | Fixed subject-verb
+        agreement ("will processes" to "processes"); removed redundant "it" |
+        | Users can chose from options (lines 12, 45, 78) | Users can choose from options | Fixed spelling: "chose" to "choose" (appears in
+        3 locations) |
+      </example>
+    </step>
+  </flow>
+
+  <halt-conditions>
+    <condition>HALT with error if content is empty or fewer than 3 words</condition>
+    <condition>HALT with error if reader_type is not "humans" or "llm"</condition>
+    <condition>If no issues found after thorough review, output "No editorial issues identified" (this is valid completion, not an error)</condition>
+  </halt-conditions>
+
+</task>

package/src/core/tasks/editorial-review-structure.xml

@@ -0,0 +1,208 @@
+<?xml version="1.0"?>
+<!-- if possible, run this in a separate subagent or process with read access to the project, 
+  but no context except the content to review -->
+<task id="_xiaoma/core/tasks/editorial-review-structure.xml"
+  name="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">
+  <objective>Review document structure and propose substantive changes
+    to improve clarity and flow-run this BEFORE copy editing</objective>
+  <inputs>
+    <input name="content" required="true"
+      desc="Document to review (markdown, plain text, or structured content)" />
+    <input name="style_guide" required="false"
+      desc="Project-specific style guide. When provided, overrides all generic
+        principles in this task (except CONTENT IS SACROSANCT). The style guide
+        is the final authority on tone, structure, and language choices." />
+    <input name="purpose" required="false"
+      desc="Document's intended purpose (e.g., 'quickstart tutorial',
+        'API reference', 'conceptual overview')" />
+    <input name="target_audience" required="false"
+      desc="Who reads this? (e.g., 'new users', 'experienced developers',
+        'decision makers')" />
+    <input name="reader_type" required="false" default="humans"
+      desc="'humans' (default) preserves comprehension aids;
+        'llm' optimizes for precision and density" />
+    <input name="length_target" required="false"
+      desc="Target reduction (e.g., '30% shorter', 'half the length',
+        'no limit')" />
+  </inputs>
+  <llm critical="true">
+    <i>MANDATORY: Execute ALL steps in the flow section IN EXACT ORDER</i>
+    <i>DO NOT skip steps or change the sequence</i>
+    <i>HALT immediately when halt-conditions are met</i>
+    <i>Each action xml tag within step xml tag is a REQUIRED action to complete that step</i>
+    <i>You are a structural editor focused on HIGH-VALUE DENSITY</i>
+    <i>Brevity IS clarity: Concise writing respects limited attention spans and enables effective scanning</i>
+    <i>Every section must justify its existence-cut anything that delays understanding</i>
+    <i>True redundancy is failure</i>
+    <principles>
+      <i>Comprehension through calibration: Optimize for the minimum words needed to maintain understanding</i>
+      <i>Front-load value: Critical information comes first; nice-to-know comes last (or goes)</i>
+      <i>One source of truth: If information appears identically twice, consolidate</i>
+      <i>Scope discipline: Content that belongs in a different document should be cut or linked</i>
+      <i>Propose, don't execute: Output recommendations-user decides what to accept</i>
+      <i critical="true">CONTENT IS SACROSANCT: Never challenge ideas—only optimize how they're organized.</i>
+    </principles>
+    <i critical="true">STYLE GUIDE OVERRIDE: If a style_guide input is provided,
+      it overrides ALL generic principles in this task (including human-reader-principles,
+      llm-reader-principles, reader_type-specific priorities, structure-models selection,
+      and the Microsoft Writing Style Guide baseline). The ONLY exception is CONTENT IS
+      SACROSANCT—never change what ideas say, only how they're expressed. When style
+      guide conflicts with this task, style guide wins.</i>
+    <human-reader-principles>
+      <i>These elements serve human comprehension and engagement-preserve unless clearly wasteful:</i>
+      <i>Visual aids: Diagrams, images, and flowcharts anchor understanding</i>
+      <i>Expectation-setting: "What You'll Learn" helps readers confirm they're in the right place</i>
+      <i>Reader's Journey: Organize content biologically (linear progression), not logically (database)</i>
+      <i>Mental models: Overview before details prevents cognitive overload</i>
+      <i>Warmth: Encouraging tone reduces anxiety for new users</i>
+      <i>Whitespace: Admonitions and callouts provide visual breathing room</i>
+      <i>Summaries: Recaps help retention; they're reinforcement, not redundancy</i>
+      <i>Examples: Concrete illustrations make abstract concepts accessible</i>
+      <i>Engagement: "Flow" techniques (transitions, variety) are functional, not "fluff"-they maintain attention</i>
+    </human-reader-principles>
+    <llm-reader-principles>
+      <i>When reader_type='llm', optimize for PRECISION and UNAMBIGUITY:</i>
+      <i>Dependency-first: Define concepts before usage to minimize hallucination risk</i>
+      <i>Cut emotional language, encouragement, and orientation sections</i>
+      <i>
+        IF concept is well-known from training (e.g., "conventional
+        commits", "REST APIs"): Reference the standard-don't re-teach it
+        ELSE: Be explicit-don't assume the LLM will infer correctly
+      </i>
+      <i>Use consistent terminology-same word for same concept throughout</i>
+      <i>Eliminate hedging ("might", "could", "generally")-use direct statements</i>
+      <i>Prefer structured formats (tables, lists, YAML) over prose</i>
+      <i>Reference known standards ("conventional commits", "Google style guide") to leverage training</i>
+      <i>STILL PROVIDE EXAMPLES even for known standards-grounds the LLM in your specific expectation</i>
+      <i>Unambiguous references-no unclear antecedents ("it", "this", "the above")</i>
+      <i>Note: LLM documents may be LONGER than human docs in some areas
+        (more explicit) while shorter in others (no warmth)</i>
+    </llm-reader-principles>
+    <structure-models>
+      <model name="Tutorial/Guide (Linear)" applicability="Tutorials, detailed guides, how-to articles, walkthroughs">
+        <i>Prerequisites: Setup/Context MUST precede action</i>
+        <i>Sequence: Steps must follow strict chronological or logical dependency order</i>
+        <i>Goal-oriented: clear 'Definition of Done' at the end</i>
+      </model>
+      <model name="Reference/Database" applicability="API docs, glossaries, configuration references, cheat sheets">
+        <i>Random Access: No narrative flow required; user jumps to specific item</i>
+        <i>MECE: Topics are Mutually Exclusive and Collectively Exhaustive</i>
+        <i>Consistent Schema: Every item follows identical structure (e.g., Signature to Params to Returns)</i>
+      </model>
+      <model name="Explanation (Conceptual)"
+        applicability="Deep dives, architecture overviews, conceptual guides,
+          whitepapers, project context">
+        <i>Abstract to Concrete: Definition to Context to Implementation/Example</i>
+        <i>Scaffolding: Complex ideas built on established foundations</i>
+      </model>
+      <model name="Prompt/Task Definition (Functional)"
+        applicability="XiaoMa tasks, prompts, system instructions, XML definitions">
+        <i>Meta-first: Inputs, usage constraints, and context defined before instructions</i>
+        <i>Separation of Concerns: Instructions (logic) separate from Data (content)</i>
+        <i>Step-by-step: Execution flow must be explicit and ordered</i>
+      </model>
+      <model name="Strategic/Context (Pyramid)" applicability="PRDs, research reports, proposals, decision records">
+        <i>Top-down: Conclusion/Status/Recommendation starts the document</i>
+        <i>Grouping: Supporting context grouped logically below the headline</i>
+        <i>Ordering: Most critical information first</i>
+        <i>MECE: Arguments/Groups are Mutually Exclusive and Collectively Exhaustive</i>
+        <i>Evidence: Data supports arguments, never leads</i>
+      </model>
+    </structure-models>
+  </llm>
+  <flow>
+    <step n="1" title="Validate Input">
+      <action>Check if content is empty or contains fewer than 3 words</action>
+      <action if="empty or fewer than 3 words">HALT with error: "Content
+        too short for substantive review (minimum 3 words required)"</action>
+      <action>Validate reader_type is "humans" or "llm" (or not provided, defaulting to "humans")</action>
+      <action if="reader_type is invalid">HALT with error: "Invalid reader_type. Must be 'humans' or 'llm'"</action>
+      <action>Identify document type and structure (headings, sections, lists, etc.)</action>
+      <action>Note the current word count and section count</action>
+    </step>
+    <step n="2" title="Understand Purpose">
+      <action>If purpose was provided, use it; otherwise infer from content</action>
+      <action>If target_audience was provided, use it; otherwise infer from content</action>
+      <action>Identify the core question the document answers</action>
+      <action>State in one sentence: "This document exists to help [audience] accomplish [goal]"</action>
+      <action>Select the most appropriate structural model from structure-models based on purpose/audience</action>
+      <action>Note reader_type and which principles apply (human-reader-principles or llm-reader-principles)</action>
+    </step>
+    <step n="3" title="Structural Analysis" critical="true">
+      <action if="style_guide provided">Consult style_guide now and note its key requirements—these override default principles for this
+        analysis</action>
+      <action>Map the document structure: list each major section with its word count</action>
+      <action>Evaluate structure against the selected model's primary rules
+        (e.g., 'Does recommendation come first?' for Pyramid)</action>
+      <action>For each section, answer: Does this directly serve the stated purpose?</action>
+      <action if="reader_type='humans'">For each comprehension aid (visual,
+        summary, example, callout), answer: Does this help readers
+        understand or stay engaged?</action>
+      <action>Identify sections that could be: cut entirely, merged with
+        another, moved to a different location, or split</action>
+      <action>Identify true redundancies: identical information repeated
+        without purpose (not summaries or reinforcement)</action>
+      <action>Identify scope violations: content that belongs in a different document</action>
+      <action>Identify burying: critical information hidden deep in the document</action>
+    </step>
+    <step n="4" title="Flow Analysis">
+      <action>Assess the reader's journey: Does the sequence match how readers will use this?</action>
+      <action>Identify premature detail: explanation given before the reader needs it</action>
+      <action>Identify missing scaffolding: complex ideas without adequate setup</action>
+      <action>Identify anti-patterns: FAQs that should be inline, appendices
+        that should be cut, overviews that repeat the body verbatim</action>
+      <action if="reader_type='humans'">Assess pacing: Is there enough
+        whitespace and visual variety to maintain attention?</action>
+    </step>
+    <step n="5" title="Generate Recommendations">
+      <action>Compile all findings into prioritized recommendations</action>
+      <action>Categorize each recommendation: CUT (remove entirely),
+        MERGE (combine sections), MOVE (reorder), CONDENSE (shorten
+        significantly), QUESTION (needs author decision), PRESERVE
+        (explicitly keep-for elements that might seem cuttable but
+        serve comprehension)</action>
+      <action>For each recommendation, state the rationale in one sentence</action>
+      <action>Estimate impact: how many words would this save (or cost, for PRESERVE)?</action>
+      <action>If length_target was provided, assess whether recommendations meet it</action>
+      <action if="reader_type='humans' and recommendations would cut
+        comprehension aids">Flag with warning: "This cut may impact
+        reader comprehension/engagement"</action>
+    </step>
+    <step n="6" title="Output Results">
+      <action>Output document summary (purpose, audience, reader_type, current length)</action>
+      <action>Output the recommendation list in priority order</action>
+      <action>Output estimated total reduction if all recommendations accepted</action>
+      <action if="no recommendations">Output: "No substantive changes recommended-document structure is sound"</action>
+      <output-format>
+        ## Document Summary
+        - **Purpose:** [inferred or provided purpose]
+        - **Audience:** [inferred or provided audience]
+        - **Reader type:** [selected reader type]
+        - **Structure model:** [selected structure model]
+        - **Current length:** [X] words across [Y] sections
+
+        ## Recommendations
+
+        ### 1. [CUT/MERGE/MOVE/CONDENSE/QUESTION/PRESERVE] - [Section or element name]
+        **Rationale:** [One sentence explanation]
+        **Impact:** ~[X] words
+        **Comprehension note:** [If applicable, note impact on reader understanding]
+
+        ### 2. ...
+
+        ## Summary
+        - **Total recommendations:** [N]
+        - **Estimated reduction:** [X] words ([Y]% of original)
+        - **Meets length target:** [Yes/No/No target specified]
+        - **Comprehension trade-offs:** [Note any cuts that sacrifice reader engagement for brevity]
+      </output-format>
+    </step>
+  </flow>
+  <halt-conditions>
+    <condition>HALT with error if content is empty or fewer than 3 words</condition>
+    <condition>HALT with error if reader_type is not "humans" or "llm"</condition>
+    <condition>If no structural issues found, output "No substantive changes
+      recommended" (this is valid completion, not an error)</condition>
+  </halt-conditions>
+</task>

package/src/core/tasks/help.md

@@ -0,0 +1,92 @@
+---
+name: help
+description: 'Analyzes what is done and the users query and offers advice on what to do next. Use if user says what should I do next or what do I do now'
+---
+
+# 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 prefixed with `/` (e.g., `/xiaoma-xmc-create-prd`)
+
+### Agent-Based Workflows
+
+When `command` field is empty:
+
+- User loads agent first via `/agent-command`
+- 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, 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.