speccrew 0.6.69 → 0.7.0

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

@@ -1,141 +1,3 @@
----
-name: speccrew-knowledge-techs-dispatch-xml
-description: Dispatch techs knowledge base generation tasks with 3-stage pipeline (XML Block version). Handles platform detection, tech document generation, and root index creation.
-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
-
-# Techs Knowledge Dispatch (XML Block Version)
-
-Orchestrate **techs knowledge base generation** with a 3-stage pipeline using **XML Block system**: Platform Detection → Tech Doc Generation → Root Index.
-
-## 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 techs-dispatch as orchestration playbook">
-  <field name="skill">speccrew-knowledge-techs-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 (techs-init, techs-generate-conventions, techs-generate-ui-style, 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 1: Platform Detection
-  └─ Read techs-manifest.json → Identify platforms & tech stacks
-        ↓
-Stage 2: Tech Doc Generation (PARALLEL)
-  └─ Prepare task plans for techs-generate workers per platform
-  └─ After generate workers complete → prepare quality check worker task plans
-  └─ Monitor completion markers
-        ↓
-Stage 2.5: Completion Verification
-  └─ Step A: Scan completion markers
-  └─ Step B: Verify output integrity
-  └─ Step C: Update progress status
-        ↓
-Stage 3: Root Index Generation
-  └─ Generate techs/README.md root index
-  └─ Cross-platform consistency check
-```
-
-> **NOTE**: All worker dispatch operations are handled by the calling Agent (Team Leader). This Skill only prepares task plans and monitors completion markers.
-
-## 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 techs knowledge base"
-- "Generate technology knowledge from source code"
-- "Dispatch techs knowledge generation"
-
-## User
-
-Leader Agent (speccrew-team-leader)
-
-## Platform Naming Convention
-
-Read `speccrew-workspace/docs/configs/platform-mapping.json` for standardized platform mapping rules.
-
-| Concept | techs-init (techs-manifest.json) | Example (UniApp) |
-|---------|----------------------------------|------------------|
-| **Category** | `platform_type` | `mobile` |
-| **Technology** | `framework` | `uniapp` |
-| **Identifier** | `platform_id` | `mobile-uniapp` |
-
-## Input
-
-| Variable | Description | Default |
-|----------|-------------|---------|
-| `source_path` | Source code root path | project root |
-| `language` | User's language code (e.g., "zh", "en") | **REQUIRED** |
-
-## Output
-
-- Platform manifest: `speccrew-workspace/knowledges/base/sync-state/knowledge-techs/techs-manifest.json`
-- Tech docs: `speccrew-workspace/knowledges/techs/{platform_id}/`
-- Root index: `speccrew-workspace/knowledges/techs/INDEX.md`
-- Status files: `speccrew-workspace/knowledges/base/sync-state/knowledge-techs/stage{N}-status.json`
-
----
-
-## 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"?>
 <workflow id="techs-dispatch-main" status="pending" version="1.0" desc="techs knowledge base generation 3-stage pipeline">
 
@@ -208,7 +70,7 @@ Read `speccrew-workspace/docs/configs/platform-mapping.json` for standardized pl
 
     <!-- Step 2: Prepare Task Plan for techs-init -->
     <block type="event" id="S1-E1" action="log" level="info" desc="Prepare techs-init task plan">
-    <field name="message">Stage 1: Preparing task plan for speccrew-knowledge-techs-init-xml
+    <field name="message">Stage 1: Preparing task plan for speccrew-knowledge-techs-init
 - Source path: ${source_path}
 - Output path: ${sync_state_techs_dir}
 - Language: ${language}</field>
@@ -216,7 +78,7 @@ Read `speccrew-workspace/docs/configs/platform-mapping.json` for standardized pl
 
     <!-- Step 3: Prepare task specification -->
     <block type="task" id="S1-B2" action="prepare-task" status="pending" desc="Prepare techs-init task specification">
-      <field name="skill_name">speccrew-knowledge-techs-init-xml</field>
+      <field name="skill_name">speccrew-knowledge-techs-init</field>
       <field name="context">
         <field name="source_path">${source_path}</field>
         <field name="output_path">${sync_state_techs_dir}</field>
@@ -228,7 +90,7 @@ Read `speccrew-workspace/docs/configs/platform-mapping.json` for standardized pl
     <!-- Step 4: Monitor completion -->
     <block type="event" id="S1-E2" action="log" level="info" desc="Stage 1 task prepared">
     <field name="message">Stage 1 task plan prepared. Waiting for calling Agent to dispatch.
-Task: speccrew-knowledge-techs-init-xml
+Task: speccrew-knowledge-techs-init
 Output: ${sync_state_techs_dir}/techs-manifest.json</field>
     </block>
 
@@ -311,7 +173,7 @@ if (platform) {
 
     <block type="loop" id="S2-L2" over="${techs_manifest.platforms}" as="platform" parallel="true" max-concurrency="${techs_manifest.platforms.length}" desc="Prepare conventions worker task for each platform">
       <block type="task" id="S2-B2" action="prepare-task" status="pending" desc="Prepare conventions worker task specification">
-        <field name="skill_name">speccrew-knowledge-techs-generate-conventions-xml</field>
+        <field name="skill_name">speccrew-knowledge-techs-generate-conventions</field>
         <field name="context">
           <field name="platform_id">${platform.platform_id}</field>
           <field name="platform_type">${platform.platform_type}</field>
@@ -337,7 +199,7 @@ if (platform) {
         <field name="message">Skipping UI-style for backend platform: ${platform.platform_id}</field>
       </block>
       <block type="task" id="S2-B3" action="prepare-task" status="pending" desc="Prepare UI-style worker task specification">
-        <field name="skill_name">speccrew-knowledge-techs-generate-ui-style-xml</field>
+        <field name="skill_name">speccrew-knowledge-techs-generate-ui-style</field>
         <field name="context">
           <field name="platform_id">${platform.platform_id}</field>
           <field name="platform_type">${platform.platform_type}</field>
@@ -406,7 +268,7 @@ if (platform) {
       <!-- Prepare Quality Check Worker Task Plans -->
       <block type="gateway" id="S2-G4" mode="guard" test="${conventions_done.status} == 'completed'" fail-action="continue" desc="Prepare quality check for conventions">
         <block type="task" id="S2-B5a" action="prepare-task" status="pending" desc="Prepare conventions quality worker">
-          <field name="skill_name">speccrew-knowledge-techs-generate-quality-xml</field>
+          <field name="skill_name">speccrew-knowledge-techs-generate-quality</field>
           <field name="context">
             <field name="platform_dir">${workspace_path}/knowledges/techs/${platform.platform_id}/</field>
             <field name="platform_id">${platform.platform_id}</field>
@@ -419,7 +281,7 @@ if (platform) {
 
       <block type="gateway" id="S2-G5" mode="guard" test="${ui_style_done.status} == 'completed'" fail-action="continue" desc="Prepare quality check for UI-style">
         <block type="task" id="S2-B5b" action="prepare-task" status="pending" desc="Prepare UI-style quality worker">
-          <field name="skill_name">speccrew-knowledge-techs-generate-quality-xml</field>
+          <field name="skill_name">speccrew-knowledge-techs-generate-quality</field>
           <field name="context">
             <field name="platform_dir">${workspace_path}/knowledges/techs/${platform.platform_id}/ui-style/</field>
             <field name="platform_id">${platform.platform_id}</field>
@@ -585,7 +447,7 @@ console.log('stage2-status.json written');
 
     <!-- Step 2: Prepare Task Plan for techs-index -->
     <block type="event" id="S3-E1" action="log" level="info" desc="Prepare techs-index task plan">
-    <field name="message">Stage 3: Preparing task plan for speccrew-knowledge-techs-index-xml
+    <field name="message">Stage 3: Preparing task plan for speccrew-knowledge-techs-index
 - Manifest: ${sync_state_techs_dir}/techs-manifest.json
 - Output: ${workspace_path}/knowledges/techs/
 - Language: ${language}</field>
@@ -593,7 +455,7 @@ console.log('stage2-status.json written');
 
     <!-- Step 3: Prepare task specification -->
     <block type="task" id="S3-B2" action="prepare-task" status="pending" desc="Prepare techs-index task specification">
-      <field name="skill_name">speccrew-knowledge-techs-index-xml</field>
+      <field name="skill_name">speccrew-knowledge-techs-index</field>
       <field name="context">
         <field name="manifest_path">${sync_state_techs_dir}/techs-manifest.json</field>
         <field name="techs_base_path">${workspace_path}/knowledges/techs/</field>
@@ -606,7 +468,7 @@ console.log('stage2-status.json written');
     <!-- Step 4: Monitor completion -->
     <block type="event" id="S3-E2" action="log" level="info" desc="Stage 3 task prepared">
     <field name="message">Stage 3 task plan prepared. Waiting for calling Agent to dispatch.
-Task: speccrew-knowledge-techs-index-xml
+Task: speccrew-knowledge-techs-index
 Output: ${workspace_path}/knowledges/techs/INDEX.md</field>
     </block>
 
@@ -652,206 +514,3 @@ console.log('stage3-status.json written');
   </block>
 
 </workflow>
-```
-
----
-
-## Appendix: Reference
-
-### Worker Completion Marker Format
-
-Each Worker MUST create a completion marker file after generating documents.
-
-#### Conventions Worker Done File
-
-**File**: `{completed_dir}/{platform_id}.done-conventions.json`
-
-**Format**:
-```json
-{
-  "platform_id": "web-vue",
-  "worker_type": "conventions",
-  "status": "completed",
-  "documents_generated": [
-    "INDEX.md", "tech-stack.md", "architecture.md",
-    "conventions-dev.md", "conventions-design.md",
-    "conventions-unit-test.md", "conventions-build.md"
-  ],
-  "analysis_file": "web-vue.analysis-conventions.json",
-  "completed_at": "2024-01-15T10:45:00Z"
-}
-```
-
-#### UI-Style Worker Done File
-
-**File**: `{completed_dir}/{platform_id}.done-ui-style.json`
-
-**Format**:
-```json
-{
-  "platform_id": "web-vue",
-  "worker_type": "ui-style",
-  "status": "completed",
-  "ui_analysis_level": "full",
-  "documents_generated": [
-    "ui-style/ui-style-guide.md"
-  ],
-  "analysis_file": "web-vue.analysis-ui-style.json",
-  "completed_at": "2024-01-15T10:45:00Z"
-}
-```
-
-**Status values**:
-- `completed` — All required documents generated successfully
-- `failed` — Critical failure, required documents not generated
-
-If a Worker encounters a fatal error, it should still attempt to create the done file with `status: "failed"` and include error details in an `"error"` field.
-
-#### Quality Worker Done File
-
-**File**: `{completed_dir}/{platform_id}.quality-done.json`
-
-**Format**:
-```json
-{
-  "platform_id": "web-vue",
-  "worker_type": "quality",
-  "status": "completed",
-  "quality_score": 85,
-  "issues_found": 2,
-  "completed_at": "2024-01-15T11:00:00Z"
-}
-```
-
----
-
-### Platform Status Tracking Fields
-
-Each platform entry in techs-manifest.json includes status tracking fields for monitoring the analysis pipeline progress:
-
-| Field | Type | Values | Description |
-|-------|------|--------|-------------|
-| `status` | string | `pending` / `processing` / `completed` / `partial` / `failed` | Current analysis status |
-| `startedAt` | string \| null | ISO 8601 timestamp | When the Worker started analyzing this platform |
-| `completedAt` | string \| null | ISO 8601 timestamp | When the Worker finished analyzing this platform |
-| `analysisLevel` | string \| null | `full` / `minimal` / `reference_only` | Depth of analysis achieved |
-| `topicsCoverage` | number \| null | 0-100 | Percentage of domain topics covered (from analysis.json) |
-| `workers` | object | See below | Per-worker status tracking |
-
-**Workers Object Structure:**
-```json
-{
-  "platform_id": "web-vue",
-  "status": "completed",
-  "workers": {
-    "conventions": {
-      "status": "completed",
-      "skill": "speccrew-knowledge-techs-generate-conventions-xml",
-      "done_file": "web-vue.done-conventions.json"
-    },
-    "ui_style": {
-      "status": "completed",
-      "skill": "speccrew-knowledge-techs-generate-ui-style-xml",
-      "done_file": "web-vue.done-ui-style.json"
-    }
-  }
-}
-```
-
-For backend platforms, `ui_style.status` is set to `"skipped"`.
-
-**Status Lifecycle:**
-```
-pending → processing → completed
-                    → partial (conventions OK, ui-style failed)
-                    → failed
-```
-
----
-
-### Output per Platform
-
-```
-speccrew-workspace/knowledges/techs/{platform_id}/
-├── INDEX.md                    # Required
-├── tech-stack.md              # Required
-├── architecture.md            # Required
-├── conventions-design.md      # Required
-├── conventions-dev.md         # Required
-├── conventions-unit-test.md        # Required
-├── conventions-system-test.md      # Required
-├── conventions-build.md       # Required
-├── conventions-data.md        # Optional — platform-specific
-└── ui-style/                  # Optional — frontend only (web/mobile/desktop)
-    ├── ui-style-guide.md      # Generated by techs Stage 2
-    ├── page-types/            # Populated by bizs pipeline Stage 3.5 (ui-style-extract)
-    ├── components/            # Populated by bizs pipeline Stage 3.5 (ui-style-extract)
-    ├── layouts/               # Populated by bizs pipeline Stage 3.5 (ui-style-extract)
-    └── styles/                # Generated by techs Stage 2
-```
-
-**Cross-Pipeline Note for `ui-style/`**:
-- `ui-style-guide.md` and `styles/` are generated by techs pipeline Stage 2 (technical framework-level style specs)
-- `page-types/`, `components/`, and `layouts/` are populated by bizs pipeline Stage 3.5 (`speccrew-knowledge-bizs-ui-style-extract` skill), which aggregates patterns from analyzed feature documents
-- These two sources are complementary: techs provides framework-level conventions, bizs adds real-page-derived design patterns
-- If bizs pipeline has not been executed, these three subdirectories will be empty
-
-**Optional file `conventions-data.md` rules**:
-
-| Platform Type | Required? | Notes |
-|----------|-----------|-------|
-| `backend` | Required | ORM specs, data modeling, caching |
-| `web` | Depends | Only if using ORM/data layer (Prisma, TypeORM, etc.) |
-| `mobile` | Optional | Based on tech stack |
-| `desktop` | Optional | Based on tech stack |
-
----
-
-### Error Handling
-
-#### Error Handling Strategy
-
-```
-ON Worker Failure:
-  1. Capture error message from worker_result.error
-  2. Mark platform status as "failed" in stage2-status.json
-  3. Record failed platform_id and error details
-  4. Continue processing other platforms (no retry, fail fast)
-  5. After all workers complete, evaluate overall status:
-     - IF all platforms failed → ABORT pipeline
-     - IF some platforms succeeded → CONTINUE to Stage 3 with successful platforms only
-```
-
-#### Stage-Level Failure Handling
-
-| Stage | Failure Handling |
-|-------|-----------------|
-| Stage 1 | Abort pipeline, report error |
-| Stage 2 | Continue with successful platforms, report failed ones |
-| Stage 2.5 | Continue pipeline, report warnings |
-| Stage 3 | Abort if Stage 2 had critical failures |
-
-#### Worker Failure Details
-
-**When a Worker Agent fails:**
-- **No automatic retry**: Worker failures are recorded as-is
-- **Partial success accepted**: Pipeline continues if at least one platform succeeds
-- **Error propagation**: Failed platform details are included in stage2-status.json
-- **Stage 3 decision**: Only platforms with status "complete" are included in root INDEX.md
-
----
-
-### Checklist
-
-- [ ] Stage 1: Platform manifest generated with techs-manifest.json
-- [ ] Stage 2: All platforms processed in parallel
-- [ ] Stage 2: `stage2-status.json` generated with all platform results
-- [ ] Stage 3: Root INDEX.md generated with Agent mapping
-- [ ] Stage 3: `stage3-status.json` generated with index info
-
-#### Document Completeness Verification
-- [ ] Each platform directory contains required documents: INDEX.md, tech-stack.md, architecture.md, conventions-design.md, conventions-dev.md, conventions-unit-test.md, conventions-system-test.md, conventions-build.md
-- [ ] `conventions-data.md` exists only for appropriate platforms (backend required, others optional)
-- [ ] All documents include file reference blocks (pure Markdown format for VS Code preview compatibility)
-- [ ] All documents include AI-TAG and AI-CONTEXT comments
-- [ ] techs/INDEX.md links only to existing documents

package/.speccrew/skills/speccrew-knowledge-techs-generate/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: speccrew-knowledge-techs-generate
-description: Stage 2 of technology knowledge initialization - Generate technology documentation for a specific platform. Extracts tech stack, architecture, and conventions from configuration files and source code. Creates INDEX.md, tech-stack.md, architecture.md, and conventions-*.md files. Used by Worker Agent in parallel for each detected platform.
+description: Stage 2 of technology knowledge initialization - Generate technology documentation for a specific platform using XML workflow blocks. Extracts tech stack, architecture, and conventions from configuration files and source code. Creates INDEX.md, tech-stack.md, architecture.md, and conventions-*.md files. Used by Worker Agent in parallel for each detected platform.
 tools: Read, Write, Glob, Grep, Skill
 ---
 
@@ -8,7 +8,7 @@ tools: Read, Write, Glob, Grep, Skill
 >
 > **Do NOT invoke this skill directly.** Use the specialized skills via `speccrew-knowledge-techs-dispatch` Stage 2 dual-worker orchestration.
 
-# Stage 2: Generate Platform Technology Documents
+# Stage 2: Generate Platform Technology Documents (XML Workflow)
 
 Generate comprehensive technology documentation for a specific platform by analyzing its configuration files and source code structure.
 
@@ -36,155 +36,11 @@ Generate comprehensive technology documentation for a specific platform by analy
 
 **Quality Assurance**: After document generation, quality checks are performed by `speccrew-knowledge-techs-generate-quality` skill.
 
-## Workflow
-
-```mermaid
-flowchart TD
-    Start([Start]) --> Step0[Step 0: Read Document Templates]
-    Step0 --> Step1[Step 1: Read Configuration Files]
-    Step1 --> Step2[Step 2: Extract Technology Stack]
-    Step2 --> Step3[Step 3: Analyze Conventions]
-    Step3 --> Step4[Step 4: Invoke UI Style Analysis]
-    Step4 --> Step5[Step 5: Generate Documents]
-    Step5 --> Step6[Step 6: Write Output Files]
-    Step6 --> Step7[Step 7: Generate Analysis Coverage Report]
-    Step7 --> Step8[Step 8: Report Results]
-    Step8 --> End([End])
-```
-
-### Step 0: Read Document Templates
-
-Read all template files from `templates/` directory to understand required content structure for each document type.
-
-### Step 1: Read Configuration Files
-
-**Primary Config Files:** package.json / pom.xml / requirements.txt / pubspec.yaml / go.mod, tsconfig.json, build configs
-
-**Convention Files:** ESLint (.eslintrc.* / eslint.config.*), Prettier (.prettierrc.*), Testing configs, Git files
-
-### Step 2: Extract Technology Stack
-
-Parse configuration files to extract: Core Framework (name, version, language), Dependencies (production, dev, key versions), Build Tools (bundler, transpiler, task runner)
-
-### Step 3: Analyze Conventions
-
-1. Read `speccrew-workspace/docs/rules/mermaid-rule.md` for Mermaid compatibility guidelines
-2. Extract conventions from ESLint/Prettier configs
-3. Analyze project structure for directory conventions
-
-#### Domain-Specific Convention Extraction (MANDATORY)
-
-**For Frontend Platforms (web-vue, mobile-uniapp, etc.):**
-
-| Topic | Where to Look |
-|-------|---------------|
-| i18n/Internationalization | `locales/`, `i18n/`, `lang/` |
-| Authorization & Permissions | `permission/`, `router/`, `store/`, `utils/auth` |
-| Menu Registration | `router/`, `store/`, `layout/` |
-| Data Dictionary | `components/Dict`, `utils/dict`, `store/` |
-| Logging | `utils/log`, `plugins/sentry` |
-| API Request Layer | `utils/request`, `api/`, `config/` |
-| Data Validation | `utils/validate`, form schemas |
-| File Upload | `components/Upload`, `api/file` |
-
-**For Backend Platforms (backend-spring, etc.):**
-
-| Topic | Where to Look |
-|-------|---------------|
-| Authorization & Permissions | Security config, controller annotations |
-| Data Dictionary | `dict/`, `system/` module |
-| Multi-tenancy | MyBatis plugins, framework config |
-| Backend i18n | `resources/i18n/`, `messages*.properties` |
-| Logging | `logback*.xml`, `@OperateLog` |
-| Exception Handling | `handler/`, `exception/`, `GlobalExceptionHandler` |
-| Caching | `cache/`, `redis/`, `@Cacheable` annotations |
-| Data Validation | DTO classes, `validator/` |
-| Scheduled Jobs | `job/`, `task/`, `@Scheduled` methods |
-| File Storage | `file/`, `infra/file/` |
-
-**If a topic is not found**, explicitly state "Not applicable" in the corresponding section.
-
-#### Analysis Tracking (MANDATORY)
-
-For every topic, record: `found` / `not_found` / `partial`, and list all files analyzed. This tracking data is used in Step 7.
-
-### Step 4: UI Style Analysis (Frontend Platforms Only)
-
-If `platform_type` is `web`, `mobile`, or `desktop`:
-
-**Primary Path**: Invoke `speccrew-knowledge-techs-ui-analyze` skill:
-```
-skill: "speccrew-knowledge-techs-ui-analyze"
-args: "source_path={source_path};platform_id={platform_id};platform_type={platform_type};framework={framework};output_path={output_path}/ui-style/;language={language}"
-```
-
-**Fallback Path** (if analyzer fails): Create minimal ui-style/ directory with:
-- ui-style/ui-style-guide.md
-- ui-style/page-types/page-type-summary.md
-- ui-style/components/component-library.md
-- ui-style/layouts/page-layouts.md
-- ui-style/styles/color-system.md
+## AgentFlow Definition
 
-Record: `ui_style_analysis_level = "full" | "minimal" | "reference_only"`
+<!-- @agentflow: workflow.agentflow.xml -->
 
-**In conventions-design.md, include UI reference section** linking to ui-style/ui-style-guide.md.
-
-### Step 5: Generate Documents (MANDATORY: Copy Template + Fill)
-
-**Decision Logic for conventions-data.md**:
-- Backend → Always generate
-- Other platforms → Generate only if data layer detected (prisma/typeorm/sequelize/mongoose/drizzle-orm/firebase)
-
-**Workflow for Each Document**:
-1. Copy template file to output path
-2. Use `search_replace` to fill sections with analyzed data
-3. Preserve all template section headers and structure
-
-**MANDATORY RULES**:
-- Do NOT use create_file to rewrite entire document
-- Do NOT delete or skip any template section
-- Apply Source Traceability Requirements (see below)
-
-### Step 6: Write Output Files
-
-Create output directory if not exists, write all generated documents.
-
-### Step 7: Generate Analysis Coverage Report (MANDATORY)
-
-**Output file**: `{completed_dir}/{platform_id}.analysis.json`
-
-**Report Format**:
-```json
-{
-  "platform_id": "{platform_id}",
-  "platform_type": "{platform_type}",
-  "analyzed_at": "{ISO 8601 timestamp}",
-  "topics": {
-    "i18n": { "status": "found|not_found|partial", "files_analyzed": [], "notes": "" }
-  },
-  "config_files_analyzed": [],
-  "source_dirs_scanned": [],
-  "documents_generated": [],
-  "coverage_summary": { "topics_found": 0, "topics_partial": 0, "topics_not_found": 0, "topics_total": 0, "coverage_percent": 0 }
-}
-```
-
-### Step 8: Report Results
-
-```
-Platform Technology Documents Generated: {{platform_id}}
-- INDEX.md: ✓
-- tech-stack.md: ✓
-- architecture.md: ✓
-- conventions-design.md: ✓
-- conventions-dev.md: ✓
-- conventions-unit-test.md: ✓
-- conventions-system-test.md: ✓
-- conventions-build.md: ✓
-- conventions-data.md: ✓ (or skipped)
-- ui-style-guide.md: ✓ (frontend only, level: {{ui_style_analysis_level}})
-- Output Directory: {{output_path}}
-```
+> **REQUIRED**: Before executing this workflow, read the XML workflow specification: `speccrew-workspace/docs/rules/agentflow-spec.md`
 
 ---
 
@@ -203,7 +59,7 @@ Platform Technology Documents Generated: {{platform_id}}
 **Relative Path Calculation**: Documents at `speccrew-workspace/knowledges/techs/{platform_id}/` are 4 levels deep. Use `../../../../` prefix to reference project root files.
 
 **Required Elements**:
-1. File reference block at document beginning listing referenced files (pure Markdown format, previously used `<cite>` tags removed for VS Code preview compatibility)
+1. File reference block at document beginning listing referenced files
 2. `**Diagram Source**` annotation after each Mermaid diagram
 3. `**Section Source**` annotation at end of major sections
 
@@ -239,6 +95,8 @@ ORM/Database Tool, Data Modeling, Migrations, Query Optimization, Caching.
 
 ## Template Usage
 
+Templates are located at `./templates/`:
+
 | Template File | Purpose |
 |---------------|---------|
 | INDEX-TEMPLATE.md | Platform overview |
@@ -296,3 +154,15 @@ Upon completion, output the following structured report:
   "next_steps": ["Run quality check via speccrew-knowledge-techs-generate-quality"]
 }
 ```
+
+---
+
+## CONTINUOUS EXECUTION RULES
+
+This skill follows the continuous execution pattern defined in `GLOBAL-R1`:
+
+1. **Sequential Execution**: All workflow steps must execute in the defined order without interruption.
+2. **No User Prompts**: Worker must not pause for user confirmation between steps.
+3. **Complete All Steps**: Worker must complete all steps before reporting results.
+4. **Error Handling**: If any step fails, continue with remaining steps if possible, then report all errors together.
+5. **Technology Stack Constraint**: Per `GLOBAL-R-TECHSTACK`, all generated documents must align with the detected technology stack.