speccrew 0.6.69 → 0.7.0

package/.speccrew/skills/{speccrew-knowledge-bizs-dispatch-xml/SKILL.md → speccrew-knowledge-bizs-dispatch/workflow.agentflow.xml}

@@ -1,122 +1,4 @@
----
-name: speccrew-knowledge-bizs-dispatch-xml
-description: Dispatch bizs knowledge base generation tasks with 5-stage pipeline (XML Block version). Handles feature inventory, feature analysis with skill routing, graph data writing, module summarization, UI style pattern extraction, and system summary.
-tools: Read, Write, Task, Bash
----
-
-> **⚠️ MANDATORY EXECUTION PROTOCOL — READ BEFORE EXECUTING ANY BLOCK**
->
-> **Step 1**: Load XML workflow specification: `speccrew-workspace/docs/rules/xml-workflow-spec.md` — this defines all block types and action-to-tool mappings
->
-> **Step 2**: Execute this SKILL.md's XML workflow **block by block in document order**. For EVERY block, you MUST follow this 3-step cycle:
->
-> ```
-> 📋 Block [ID] (action=[action]) — [desc]
-> 🔧 Tool: [which IDE tool to call]
-> ✅ Result: [output or status]
-> ```
->
-> Action-to-tool mapping:
-> - `action="run-script"` → Execute via **Terminal tool** (pass the `<field name="command">` value EXACTLY)
-> - `action="run-skill"` → Invoke via **Skill tool** (pass the `<field name="skill">` value EXACTLY)
-> - `action="dispatch-to-worker"` → Create **Task** via **Task tool** for `speccrew-task-worker` (Worker loads and executes the skill, NOT you)
-> - `action="confirm"` (event) → Present to user and wait for response
->
-> **Step 3**: Execute ALL stages sequentially without pausing (only stop at explicit `<event action="confirm">` blocks)
->
-> **FORBIDDEN**:
-> - Do NOT skip the block announcement format above — every block must be announced before execution
-> - Do NOT run terminal commands as substitute for Skill tool calls
-> - Do NOT do Worker's job yourself — when `action="dispatch-to-worker"`, create a Task and let Worker handle it
-> - Do NOT skip blocks or improvise your own commands
-> - Do NOT read a skill's SKILL.md file yourself — use the Skill tool which resolves paths automatically
-
-# Bizs Knowledge Dispatch (XML Block Version)
-
-Orchestrate **bizs knowledge base generation** with a 5-stage pipeline using **XML Block system**: Feature Inventory → Feature Analysis + Graph Write → Module Summarize → UI Style Pattern Extract → System Summary.
-
-## Invocation Method
-
-**CRITICAL**: This skill is an **orchestration playbook** — it MUST be loaded directly by Team Leader via Skill tool (NOT via Worker Agent).
-
-```
-Correct: Leader uses Skill tool to load this playbook directly
-Incorrect: Dispatch this skill to speccrew-task-worker
-```
-
-**Why?** This skill defines the orchestration workflow and prepares task plans for downstream workers. The Team Leader reads this playbook and dispatches individual worker tasks via Task tool → speccrew-task-worker for each stage.
-
-**Correct Invocation Pattern**:
-```xml
-<block type="task" action="run-skill" desc="Leader directly invokes bizs-dispatch as orchestration playbook">
-  <field name="skill">speccrew-knowledge-bizs-dispatch-xml</field>
-  <field name="note">Leader directly calls this dispatch skill as an orchestration playbook. The dispatch skill defines the workflow; Leader dispatches downstream workers via Task tool → speccrew-task-worker for each stage.</field>
-</block>
-```
-
-**Worker Dispatch Rule**:
-- Dispatch skills (bizs-dispatch-xml, techs-dispatch-xml): Leader calls directly via Skill tool
-- Downstream worker skills (identify-entries, init-features, ui-analyze, module-summarize, etc.): Leader dispatches via Task tool → speccrew-task-worker
-
-**FORBIDDEN**: Worker Agents MUST NOT execute this dispatch skill. If a Worker Agent loads this skill, it must report error and abort.
-
-## Quick Reference — Execution Flow
-
-```
-Stage 0: Platform Detection
-  └─ Detect platforms → Confirm platform list
-        ↓
-Stage 1: Feature Inventory Init
-  └─ 1a: Entry directory recognition (identify-entries)
-  └─ 1b: Feature inventory generation (init-features)
-  └─ 1c: Feature merge (incremental mode)
-        ↓
-Stage 2: Feature Analysis (Batch Loop)
-  └─ Step 0: Ensure completed_dir exists
-  └─ Step 1: Get next batch of pending features
-  └─ Step 2: Dispatch Worker for analysis (UI/API routing)
-  └─ Step 2.5: Dispatch Graph Worker
-  └─ Step 3: Process batch results → Update status
-  └─ Loop until all features complete
-        ↓
-Stage 3: Module Summarize
-  └─ Generate module overview for each module
-        ↓
-Stage 3.5: UI Style Pattern Extract
-  └─ Extract UI style patterns for frontend platforms
-        ↓
-Stage 4: System Summary
-  └─ Generate system-level business knowledge summary
-```
-
-## Language Adaptation
-
-**CRITICAL**: All generated documents must match the user's language. Detect the language from the user's input and pass it to all downstream Worker Agents.
-
-- User writes in 中文 → Generate Chinese documents, pass `language: "zh"` to workers
-- User writes in English → Generate English documents, pass `language: "en"` to workers
-- User writes in other languages → Use appropriate language code
-
-**All downstream skills must receive the `language` parameter and generate content in that language only.**
-
-## Trigger Scenarios
-
-- "Initialize bizs knowledge base"
-- "Generate business knowledge from source code"
-- "Dispatch bizs knowledge generation"
-- "Generate knowledge base from src/views directory"
-- "Analyze this subdirectory for knowledge base"
-
----
-
-## XML Workflow Definition
-
-> **REQUIRED**: Before executing this workflow, read the XML workflow specification: `speccrew-workspace/docs/rules/xml-workflow-spec.md`
->
-> After reading the specification, parse the XML workflow below and **strictly execute each `<block>` in document order**. Every `<block type="task">` is a literal tool-call instruction — use the `action` attribute to determine which IDE tool to invoke, and pass the `<field name="command">` or `<field name="skill">` value **exactly as written**. Do NOT interpret the workflow as a goal description or improvise your own approach.
-
-```xml
-<?xml version="1.0" encoding="UTF-8"?>
+<?xml version="1.0" encoding="UTF-8"?>
 <workflow id="bizs-dispatch-main" status="pending" version="1.0" desc="bizs knowledge base generation 5-stage pipeline">
 
   <!-- ============================================================
@@ -141,39 +23,39 @@ Stage 4: System Summary
   <!-- ============================================================
        Global Invocation Rules
        ============================================================ -->
-  <block type="rule" id="GLOBAL-R-INVOCATION" level="forbidden" desc="Invocation constraints — NEVER violate">
-    <field name="text">This skill is an ORCHESTRATION PLAYBOOK — it MUST be loaded directly by Team Leader via Skill tool</field>
-    <field name="text">Worker Agents MUST NOT execute this dispatch skill — if loaded by a Worker, report error and abort</field>
-    <field name="text">Downstream worker skills (identify-entries, init-features, ui-analyze, module-summarize, etc.) MUST be dispatched via Task tool → speccrew-task-worker</field>
+  <block type="rule" id="GLOBAL-R-INVOCATION" level="forbidden" desc="Invocation constraints 鈥?NEVER violate">
+    <field name="text">This skill is an ORCHESTRATION PLAYBOOK 鈥?it MUST be loaded directly by Team Leader via Skill tool</field>
+    <field name="text">Worker Agents MUST NOT execute this dispatch skill 鈥?if loaded by a Worker, report error and abort</field>
+    <field name="text">Downstream worker skills (identify-entries, init-features, ui-analyze, module-summarize, etc.) MUST be dispatched via Task tool 鈫?speccrew-task-worker</field>
   </block>
 
   <!-- ============================================================
        Global Continuous Execution Rules
        ============================================================ -->
-  <block type="rule" id="GLOBAL-R1" level="forbidden" desc="Continuous execution constraints — NEVER violate">
+  <block type="rule" id="GLOBAL-R1" level="forbidden" desc="Continuous execution constraints 鈥?NEVER violate">
     <field name="text">DO NOT ask user "Should I continue?" or "How would you like to proceed?" between stages</field>
-    <field name="text">DO NOT offer options like "Full execution / Sample execution / Pause" — always execute ALL stages to completion</field>
-    <field name="text">DO NOT suggest "Let me split this into batches" or "Let's do this in parts" — process ALL features sequentially</field>
-    <field name="text">DO NOT pause to list what you plan to do next — just do it</field>
+    <field name="text">DO NOT offer options like "Full execution / Sample execution / Pause" 鈥?always execute ALL stages to completion</field>
+    <field name="text">DO NOT suggest "Let me split this into batches" or "Let's do this in parts" 鈥?process ALL features sequentially</field>
+    <field name="text">DO NOT pause to list what you plan to do next 鈥?just do it</field>
     <field name="text">DO NOT ask for confirmation before generating output files</field>
-    <field name="text">DO NOT warn about "large number of files" or "this may take a while" — proceed with generation</field>
+    <field name="text">DO NOT warn about "large number of files" or "this may take a while" 鈥?proceed with generation</field>
     <field name="text">ONLY pause at explicit &lt;event action="confirm"&gt; blocks defined in the workflow</field>
-    <field name="text">DO NOT offer "continue/pause/partial" options — EVER</field>
-    <field name="text">DO NOT estimate workload and suggest breaking it into phases — execute ALL phases in sequence</field>
-    <field name="text">When many features need analysis, dispatch ALL of them — do NOT skip or defer any</field>
-    <field name="text">Context window management: if approaching limit, save progress to checkpoint file and resume — do NOT ask user for guidance</field>
+    <field name="text">DO NOT offer "continue/pause/partial" options 鈥?EVER</field>
+    <field name="text">DO NOT estimate workload and suggest breaking it into phases 鈥?execute ALL phases in sequence</field>
+    <field name="text">When many features need analysis, dispatch ALL of them 鈥?do NOT skip or defer any</field>
+    <field name="text">Context window management: if approaching limit, save progress to checkpoint file and resume 鈥?do NOT ask user for guidance</field>
   </block>
 
   <!-- ============================================================
        Global Technology Stack Constraints
        ============================================================ -->
-  <block type="rule" id="GLOBAL-R-TECHSTACK" level="forbidden" desc="Technology stack constraints — NEVER violate">
+  <block type="rule" id="GLOBAL-R-TECHSTACK" level="forbidden" desc="Technology stack constraints 鈥?NEVER violate">
     <field name="text">FORBIDDEN: Python, Ruby, Perl, compiled binaries, or any runtime requiring separate installation</field>
     <field name="text">PERMITTED scripting: PowerShell (Windows) and Bash (Linux/Mac) ONLY</field>
     <field name="text">PERMITTED Node.js: ONLY for existing project scripts (e.g., node scripts/update-progress.js)</field>
     <field name="text">For JSON validation use: node -e "JSON.parse(require('fs').readFileSync('file.json','utf8'))"</field>
     <field name="text">For JSON creation use: node -e with inline script, or PowerShell ConvertTo-Json</field>
-    <field name="text">DO NOT create temporary .py, .rb, .pl, .bat files — use inline commands via run_in_terminal</field>
+    <field name="text">DO NOT create temporary .py, .rb, .pl, .bat files 鈥?use inline commands via run_in_terminal</field>
   </block>
 
   <!-- ============================================================
@@ -182,7 +64,7 @@ Stage 4: System Summary
   <sequence id="S0" name="Stage 0: Platform Detection" status="pending" desc="Automatically discover ALL platforms in the project">
     
     <block type="rule" id="S0-R1" level="mandatory" desc="Stage 0 mandatory rules">
-      <field name="text">MUST scan project directory to discover ALL platforms — NEVER hardcode a fixed number of platforms</field>
+      <field name="text">MUST scan project directory to discover ALL platforms 鈥?NEVER hardcode a fixed number of platforms</field>
       <field name="text">Missing a platform means incomplete knowledge base generation</field>
     </block>
 
@@ -205,7 +87,7 @@ Stage 4: System Summary
         <field name="message">Skipping empty directory: ${module.name}</field>
       </block>
       <block type="event" id="S0-E1" action="log" level="info" desc="Log backend module">
-        <field name="message">Discovered backend module: ${module.name} → Platform type: backend-${module.business_name}</field>
+        <field name="message">Discovered backend module: ${module.name} 鈫?Platform type: backend-${module.business_name}</field>
       </block>
     </block>
 
@@ -218,7 +100,7 @@ Stage 4: System Summary
         <field name="message">Skipping non-frontend directory: ${frontend.name}</field>
       </block>
       <block type="event" id="S0-E2" action="log" level="info" desc="Log frontend platform">
-        <field name="message">Discovered frontend platform: ${frontend.name} → Tech stack: Vue/React/UniApp</field>
+        <field name="message">Discovered frontend platform: ${frontend.name} 鈫?Tech stack: Vue/React/UniApp</field>
       </block>
     </block>
 
@@ -278,7 +160,7 @@ Continue with knowledge base generation?
   <sequence id="S1a" name="Stage 1a: Entry Directory Recognition" status="pending" desc="Identify entry directories for each platform and classify into business modules">
     
     <block type="rule" id="S1a-R1" level="mandatory" desc="Stage 1a mandatory rules">
-      <field name="text">ALL platform entry directory recognition tasks MUST be dispatched IN PARALLEL — sequential execution is FORBIDDEN</field>
+      <field name="text">ALL platform entry directory recognition tasks MUST be dispatched IN PARALLEL 鈥?sequential execution is FORBIDDEN</field>
       <field name="text">ALL Worker dispatch calls in S1a-L1 MUST be issued SIMULTANEOUSLY in a SINGLE orchestration turn</field>
       <field name="text">DO NOT wait for any Worker to complete before dispatching the next Worker</field>
       <field name="text">Dispatch all ${max_concurrent_workers} workers at once, then wait for ALL to complete</field>
@@ -288,7 +170,7 @@ Continue with knowledge base generation?
     <block type="loop" id="S1a-L1" over="${platforms}" as="platform" parallel="true" max-concurrency="${max_concurrent_workers}" desc="Dispatch entry directory recognition for each platform IN PARALLEL">
       <!-- Step 1: Read source directory tree -->
       <block type="task" id="S1a-B1" action="dispatch-to-worker" status="pending" desc="Dispatch entry identification to Worker">
-        <field name="worker">speccrew-knowledge-bizs-identify-entries-xml</field>
+        <field name="worker">speccrew-knowledge-bizs-identify-entries</field>
         <field name="source_path" value="${platform.sourcePath}"/>
         <field name="platform_id" value="${platform.platformId}"/>
         <field name="platform_type" value="${platform.platformType}"/>
@@ -321,7 +203,7 @@ Continue with knowledge base generation?
   <sequence id="S1b" name="Stage 1b: Generate Feature Inventory" status="pending" desc="Generate Feature inventory for each platform">
     
     <block type="rule" id="S1b-R1" level="mandatory" desc="Stage 1b mandatory rules">
-      <field name="text">ALL platform feature inventory generation tasks MUST be dispatched IN PARALLEL — sequential execution is FORBIDDEN</field>
+      <field name="text">ALL platform feature inventory generation tasks MUST be dispatched IN PARALLEL 鈥?sequential execution is FORBIDDEN</field>
       <field name="text">ALL Worker dispatch calls in S1b-L1 MUST be issued SIMULTANEOUSLY in a SINGLE orchestration turn</field>
       <field name="text">DO NOT wait for any Worker to complete before dispatching the next Worker</field>
       <field name="text">Dispatch all ${max_concurrent_workers} workers at once, then wait for ALL to complete</field>
@@ -332,7 +214,7 @@ Continue with knowledge base generation?
     <block type="loop" id="S1b-L1" over="${platforms}" as="platform" parallel="true" max-concurrency="${max_concurrent_workers}" desc="Generate Feature inventory for each platform IN PARALLEL">
       <!-- Step 1: Dispatch Worker to generate feature inventory -->
       <block type="task" id="S1b-B1" action="dispatch-to-worker" status="pending" desc="Dispatch Worker to generate feature inventory">
-        <field name="worker">speccrew-knowledge-bizs-init-features-xml</field>
+        <field name="worker">speccrew-knowledge-bizs-init-features</field>
         <field name="instructions">
 Generate feature inventory for the specified platform by analyzing entry directories.
 
@@ -447,9 +329,9 @@ Requirements:
     </block>
 
     <block type="rule" id="S2-R1" level="mandatory" desc="Stage 2 mandatory rules">
-      <field name="text">MUST use batch-orchestrator for batch management — DO NOT manually track batches</field>
-      <field name="text">MUST dispatch Workers for feature analysis — DO NOT analyze features yourself</field>
-      <field name="text">ALL workers for the same stage MUST be dispatched in PARALLEL — sequential execution is FORBIDDEN</field>
+      <field name="text">MUST use batch-orchestrator for batch management 鈥?DO NOT manually track batches</field>
+      <field name="text">MUST dispatch Workers for feature analysis 鈥?DO NOT analyze features yourself</field>
+      <field name="text">ALL workers for the same stage MUST be dispatched in PARALLEL 鈥?sequential execution is FORBIDDEN</field>
       <field name="text">ALL Worker dispatch calls in S2-L2 MUST be issued SIMULTANEOUSLY in a SINGLE orchestration turn</field>
       <field name="text">DO NOT wait for any Worker to complete before dispatching the next Worker</field>
       <field name="text">Dispatch all ${max_concurrent_workers} workers at once, then wait for ALL to complete</field>
@@ -458,8 +340,8 @@ Requirements:
     </block>
 
     <block type="rule" id="S2-R2" level="forbidden" desc="Stage 2 forbidden actions">
-      <field name="text">DO NOT skip pending features — every feature must be analyzed</field>
-      <field name="text">DO NOT generate feature analysis content yourself — always dispatch to Worker</field>
+      <field name="text">DO NOT skip pending features 鈥?every feature must be analyzed</field>
+      <field name="text">DO NOT generate feature analysis content yourself 鈥?always dispatch to Worker</field>
       <field name="text">DO NOT proceed to next Stage until ALL workers in current Stage have completed or failed</field>
     </block>
 
@@ -473,7 +355,7 @@ Requirements:
       <field name="text">Relative paths will cause Worker marker file writes to fail silently</field>
     </block>
 
-    <!-- Batch Loop: Step 1→2→2.5→3 loop until all features processed -->
+    <!-- Batch Loop: Step 1鈫?鈫?.5鈫? loop until all features processed -->
     <block type="loop" id="S2-L-Main" over="${batches}" as="batch_iteration" desc="Batch loop to process Features">
       
       <!-- Step 1: Get next batch -->
@@ -509,22 +391,22 @@ Requirements:
             <block type="gateway" id="S2-G1" mode="exclusive" desc="Route analysis Skill based on platform type">
               <branch test="${feature.platformType} == 'web' or ${feature.platformType} == 'mobile' or ${feature.platformType} == 'desktop'" name="UI platform">
                 <block type="task" id="S2-B2a" action="dispatch-to-worker" status="pending" desc="Dispatch UI Feature analysis Worker">
-                  <field name="worker">speccrew-knowledge-bizs-ui-analyze-xml</field>
+                  <field name="worker">speccrew-knowledge-bizs-ui-analyze</field>
                   <field name="instructions">
 Analyze the following source code file and generate detailed feature documentation.
 
 CRITICAL - Template Fill-in Workflow (MANDATORY):
 1. First, copy the analysis template to documentPath (template structure = document skeleton)
 2. Then fill each Section using search_replace to replace placeholders with actual data
-3. NEVER use create_file to rewrite the entire document — this destroys template structure
-4. NEVER delete or skip any template Section — if no data available, fill with "N/A"
-5. NEVER create custom Section structures — use ONLY the template's predefined Sections
+3. NEVER use create_file to rewrite the entire document 鈥?this destroys template structure
+4. NEVER delete or skip any template Section 鈥?if no data available, fill with "N/A"
+5. NEVER create custom Section structures 鈥?use ONLY the template's predefined Sections
 
 Requirements:
 - Read source code file, understand related functionality interfaces
 - Generate detailed documentation to documentPath
 - Create two marker files to completed_dir
-- Use speccrew-knowledge-bizs-ui-analyze-xml skill to complete this task
+- Use speccrew-knowledge-bizs-ui-analyze skill to complete this task
                   </field>
                   <field name="context">{
   "fileName": "${feature.fileName}",
@@ -544,7 +426,7 @@ Requirements:
               </branch>
               <branch default="true" name="Backend platform">
                 <block type="task" id="S2-B2b" action="dispatch-to-worker" status="pending" desc="Dispatch API Feature analysis Worker">
-                  <field name="worker">speccrew-knowledge-bizs-api-analyze-xml</field>
+                  <field name="worker">speccrew-knowledge-bizs-api-analyze</field>
                   <field name="instructions">
 Analyze the following source code file and generate detailed API feature documentation.
 
@@ -590,7 +472,7 @@ Requirements:
             <block type="gateway" id="S2-G2" mode="exclusive" desc="Route Graph Worker based on analysis type">
               <branch test="${feature.platformType} == 'backend'" name="API Graph">
                 <block type="task" id="S2-B25a" action="dispatch-to-worker" status="pending" desc="Dispatch API Graph Worker">
-                  <field name="worker">speccrew-knowledge-bizs-api-graph-xml</field>
+                  <field name="worker">speccrew-knowledge-bizs-api-graph</field>
                   <field name="instructions">
 Generate graph data nodes and edges from the analyzed API feature document.
 
@@ -619,7 +501,7 @@ Requirements:
               </branch>
               <branch default="true" name="UI Graph">
                 <block type="task" id="S2-B25b" action="dispatch-to-worker" status="pending" desc="Dispatch UI Graph Worker">
-                  <field name="worker">speccrew-knowledge-bizs-ui-graph-xml</field>
+                  <field name="worker">speccrew-knowledge-bizs-ui-graph</field>
                   <field name="instructions">
 Generate graph data nodes and edges from the analyzed UI feature document.
 
@@ -690,7 +572,7 @@ Requirements:
     
     <block type="rule" id="S3-R1" level="mandatory" desc="Stage 3 mandatory rules">
       <field name="text">Worker dispatch is handled by the calling Agent (Team Leader). This Skill only prepares the task plan and parameters.</field>
-      <field name="text">ALL module summary workers MUST be dispatched IN PARALLEL — sequential execution is FORBIDDEN</field>
+      <field name="text">ALL module summary workers MUST be dispatched IN PARALLEL 鈥?sequential execution is FORBIDDEN</field>
       <field name="text">ALL Worker dispatch calls in S3-L2 MUST be issued SIMULTANEOUSLY in a SINGLE orchestration turn</field>
       <field name="text">DO NOT wait for any Worker to complete before dispatching the next Worker</field>
       <field name="text">Dispatch all ${max_concurrent_workers} workers at once, then wait for ALL to complete</field>
@@ -722,7 +604,7 @@ Requirements:
       <!-- PARALLEL EXECUTION MANDATORY: All Module Summary Workers MUST be dispatched SIMULTANEOUSLY in ONE turn -->
       <block type="loop" id="S3-L2" over="${platform_modules}" as="module_name" parallel="true" max-concurrency="${max_concurrent_workers}" desc="Dispatch summary Worker for each module">
         <block type="task" id="S3-B4" action="dispatch-to-worker" status="pending" desc="Dispatch module summary Worker">
-          <field name="worker">speccrew-knowledge-module-summarize-xml</field>
+          <field name="worker">speccrew-knowledge-module-summarize</field>
           <field name="instructions">
 Generate complete module overview documentation for the specified module.
 
@@ -764,7 +646,7 @@ Requirements:
     
     <block type="rule" id="S35-R1" level="mandatory" desc="Stage 3.5 mandatory rules">
       <field name="text">Worker dispatch is handled by the calling Agent (Team Leader). This Skill only prepares the task plan and parameters.</field>
-      <field name="text">ALL UI style extraction workers MUST be dispatched IN PARALLEL — sequential execution is FORBIDDEN</field>
+      <field name="text">ALL UI style extraction workers MUST be dispatched IN PARALLEL 鈥?sequential execution is FORBIDDEN</field>
       <field name="text">ALL Worker dispatch calls in S35-L1 MUST be issued SIMULTANEOUSLY in a SINGLE orchestration turn</field>
       <field name="text">DO NOT wait for any Worker to complete before dispatching the next Worker</field>
       <field name="text">Dispatch all ${max_concurrent_workers} workers at once, then wait for ALL to complete</field>
@@ -778,7 +660,7 @@ Requirements:
       <block type="gateway" id="S35-G1" mode="exclusive" desc="Execute for UI platforms only">
         <branch test="${platform.platformType} in ['web', 'mobile', 'desktop']" name="UI platform">
           <block type="task" id="S35-B1" action="dispatch-to-worker" status="pending" desc="Dispatch UI style extraction Worker">
-            <field name="worker">speccrew-knowledge-bizs-ui-style-extract-xml</field>
+            <field name="worker">speccrew-knowledge-bizs-ui-style-extract</field>
             <field name="instructions">
 Extract UI design patterns from frontend platform Feature documents.
 
@@ -837,7 +719,7 @@ Requirements:
 
     <!-- Step 2: Dispatch System Summarize Worker -->
     <block type="task" id="S4-B2" action="dispatch-to-worker" status="pending" desc="Dispatch system summary Worker">
-      <field name="worker">speccrew-knowledge-system-summarize-xml</field>
+      <field name="worker">speccrew-knowledge-system-summarize</field>
       <field name="instructions">
 Generate complete system-level business knowledge summary.
 
@@ -922,115 +804,3 @@ Requirements:
     <field name="graph_root" from="${graph_root}" type="string" desc="Graph data output directory"/>
   </block>
 </workflow>
-```
-
----
-
-## Appendix: Reference
-
-### Skill Routing Table (Stage 2)
-
-> **Note**: Detailed routing logic is defined in XML Stage 2 gateway (S2-G1).
-
-| platformType | skill_name | Description |
-|--------------|------------|-------------|
-| `web` | `speccrew-knowledge-bizs-ui-analyze-xml` | Web frontend (Vue/React/Angular) |
-| `mobile` | `speccrew-knowledge-bizs-ui-analyze-xml` | Mobile apps (Flutter/React Native/UniApp) |
-| `desktop` | `speccrew-knowledge-bizs-ui-analyze-xml` | Desktop apps (Electron/WPF) |
-| `backend` | `speccrew-knowledge-bizs-api-analyze-xml` | Backend APIs (Java/Python/Node.js) |
-
----
-
-### Platform Types
-
-| Platform Type | Platform Subtype | Description |
-|---------------|------------------|-------------|
-| `web` | `vue`, `react`, `angular` | Web frontend applications |
-| `mobile` | `uniapp`, `flutter`, `react-native` | Mobile applications |
-| `desktop` | `electron`, `wpf` | Desktop applications |
-| `backend` | `spring`, `nodejs`, `python` | Backend services |
-
----
-
-### Worker Completion Marker Format
-
-#### Marker File Naming Convention
-
-**Pattern**: `{module}-{subpath}-{fileName}.{type}.json`
-
-| Component | Description | Example |
-|-----------|-------------|---------|
-| `module` | Business module name | `chat`, `user`, `order` |
-| `subpath` | Sub-path within module, `/` replaced with `-`. Empty if file is directly under module | `admin`, `api-v2` |
-| `fileName` | Source file name WITHOUT extension | `UserController`, `ChatService` |
-| `type` | Marker type: `done`, `error`, or `skip` | `done` |
-
-**Examples**:
-
-| Source File Path | Marker File Name |
-|------------------|------------------|
-| `chat/ChatController.java` | `chat-ChatController.done.json` |
-| `user/admin/UserController.java` | `user-admin-UserController.done.json` |
-| `order/api/v2/OrderService.java` | `order-api-v2-OrderService.done.json` |
-
-#### .done.json Required Fields
-
-```json
-{
-  "fileName": "<class name without extension>",
-  "sourcePath": "<relative source file path>",
-  "sourceFile": "<features JSON filename, e.g. features-backend-ai.json>",
-  "module": "<business module name>",
-  "status": "success|partial|failed",
-  "analysisNotes": "<brief notes>"
-}
-```
-
-> WRONG: Writing plain text like "COMPLETED" or "Analysis done"
-> CORRECT: Writing valid JSON with all required fields
-
----
-
-### Batch Processing Details
-
-#### get-batch Script Output Format
-
-```json
-{
-  "action": "process|done",
-  "batch": [
-    {
-      "id": "feature-001",
-      "fileName": "UserController",
-      "sourcePath": "controller/admin/user/UserController.java",
-      "module": "user",
-      "documentPath": "speccrew-workspace/knowledges/bizs/backend-system/user/UserController.md",
-      "platformType": "backend",
-      "platformSubtype": "spring",
-      "platformId": "backend-system",
-      "sourceFile": "features-backend-system.json"
-    }
-  ]
-}
-```
-
-#### process-results Script Behavior
-
-- Scans `.done.json` files → updates feature status to `completed` in features-*.json
-- Scans `.graph-done.json` files → confirms graph data generation complete
-- Scans `.graph.json` files → writes graph data (nodes + edges) grouped by module
-- Cleans up all marker files
-
----
-
-### Stateless Design
-
-Dispatch adopts a fully stateless file-driven design. Re-execute loop to recover: `get-batch` auto-recovers from file state; `process-results` handles uncleaned markers. The entire flow is safely re-entrant.
-
----
-
-### Large-Scale Scenario Guidance
-
-For modules with >20 features: dispatch multiple Worker Agents in parallel (each handles a subset). Use `get-next-batch` for resume support across sessions. Run `process-batch-results --validateDocs` after completion to verify.
-
-