speccrew 0.6.34 → 0.6.36

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

@@ -0,0 +1,297 @@
+---
+name: speccrew-knowledge-techs-generate-xml
+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
+---
+
+> **⚠️ DEPRECATED**: This skill has been superseded by `speccrew-knowledge-techs-generate-conventions-xml` and `speccrew-knowledge-techs-generate-ui-style-xml`. Use those skills for new requests. This file is kept for backward compatibility only.
+>
+> **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 (XML Workflow)
+
+Generate comprehensive technology documentation for a specific platform by analyzing its configuration files and source code structure.
+
+## Language Adaptation
+
+**CRITICAL**: Generate all content in the language specified by the `language` parameter.
+
+## Input
+
+- `platform_id`: Platform identifier (e.g., "web-react", "backend-nestjs")
+- `platform_type`: Platform type (web, mobile, backend, desktop)
+- `framework`: Primary framework (react, nestjs, flutter, etc.)
+- `source_path`: Platform source directory
+- `config_files`: List of configuration file paths
+- `convention_files`: List of convention file paths (eslint, prettier, etc.)
+- `output_path`: Output directory for generated documents
+- `language`: Target language (e.g., "zh", "en") - **REQUIRED**
+- `completed_dir`: (Optional) Directory for analysis coverage report output
+
+## Output
+
+**Required Documents (All Platforms)**: INDEX.md, tech-stack.md, architecture.md, conventions-design.md, conventions-dev.md, conventions-unit-test.md, conventions-system-test.md, conventions-build.md
+
+**Optional Documents**: conventions-data.md (backend required), ui-style/ (frontend only)
+
+**Quality Assurance**: After document generation, quality checks are performed by `speccrew-knowledge-techs-generate-quality` skill.
+
+## Workflow
+
+<!--
+== Block Types ==
+input      : Workflow input parameters (required=mandatory, default=default value)
+output     : Workflow output results (from=data source variable)
+task       : Execute action (action: run-skill | run-script | dispatch-to-worker)
+gateway    : Conditional branch/gate (mode: exclusive | guard | parallel)
+loop       : Iterate over collection (over=collection, as=current item)
+event      : Log/confirm/signal (action: log | confirm | signal)
+error-handler : Exception handling (try > catch > finally)
+checkpoint : Persistent milestone (name=checkpoint name, verify=verification condition)
+rule       : Constraint declaration (level: forbidden | mandatory | note)
+-->
+
+<workflow>
+
+  <!-- Global Rules -->
+  <rule id="GLOBAL-R1" level="mandatory" description="Continuous Execution: Execute all steps in sequence without interruption. Worker must complete all steps before reporting results." />
+  <rule id="GLOBAL-R-TECHSTACK" level="mandatory" description="Technology Stack Constraint: All generated documents must align with the detected technology stack of the platform." />
+
+  <!-- Input Block -->
+  <input name="platform_id" type="string" required="true" description="Platform identifier (e.g., web-react, backend-nestjs)" />
+  <input name="platform_type" type="string" required="true" description="Platform type (web, mobile, backend, desktop)" />
+  <input name="framework" type="string" required="true" description="Primary framework (react, nestjs, flutter, etc.)" />
+  <input name="source_path" type="string" required="true" description="Platform source directory" />
+  <input name="config_files" type="array" required="true" description="List of configuration file paths" />
+  <input name="convention_files" type="array" required="false" description="List of convention file paths" />
+  <input name="output_path" type="string" required="true" description="Output directory for generated documents" />
+  <input name="language" type="string" required="true" description="Target language (e.g., zh, en)" />
+  <input name="completed_dir" type="string" required="false" description="Directory for analysis coverage report output" />
+
+  <!-- Step 0: Read Document Templates -->
+  <task id="step0-read-templates" action="run-skill" description="Read document templates from templates directory">
+    <run-skill skill="read-templates" template-path="../speccrew-knowledge-techs-generate/templates/" />
+  </task>
+
+  <!-- Step 1: Read Configuration Files -->
+  <task id="step1-read-configs" action="read-files" description="Read primary configuration and convention files">
+    <read-files files="{config_files}, {convention_files}" />
+  </task>
+
+  <!-- Step 2: Extract Technology Stack -->
+  <task id="step2-extract-techstack" action="analyze" description="Parse configuration files to extract technology stack">
+    <extract>
+      <item name="core_framework" source="package.json|pom.xml|requirements.txt|pubspec.yaml|go.mod" />
+      <item name="dependencies" source="dependencies section" />
+      <item name="build_tools" source="devDependencies, scripts" />
+    </extract>
+  </task>
+
+  <!-- Step 3: Analyze Conventions -->
+  <task id="step3-analyze-conventions" action="analyze" description="Extract conventions from config files and analyze project structure">
+    <analyze>
+      <read file="speccrew-workspace/docs/rules/mermaid-rule.md" />
+      <extract from="ESLint/Prettier configs" />
+      <analyze-dir path="{source_path}" for="directory-conventions" />
+    </analyze>
+  </task>
+
+  <!-- Step 4: UI Style Analysis (Frontend Platforms Only) -->
+  <gateway id="step4-gateway" mode="exclusive" description="Check if platform is frontend">
+    <condition test="platform_type in [web, mobile, desktop]">
+      <task id="step4-ui-analyze" action="run-skill" description="Invoke UI style analysis skill">
+        <run-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}" />
+      </task>
+    </condition>
+    <fallback>
+      <event action="log" message="UI style analysis skipped for backend platform" />
+    </fallback>
+  </gateway>
+
+  <!-- Step 5: Generate Documents -->
+  <task id="step5-generate-docs" action="generate" description="Generate all required documents using template fill workflow">
+    <generate-docs template-path="../speccrew-knowledge-techs-generate/templates/" output-path="{output_path}">
+      <doc name="INDEX.md" template="INDEX-TEMPLATE.md" />
+      <doc name="tech-stack.md" template="TECH-STACK-TEMPLATE.md" />
+      <doc name="architecture.md" template="ARCHITECTURE-TEMPLATE.md" />
+      <doc name="conventions-design.md" template="CONVENTIONS-DESIGN-TEMPLATE.md" />
+      <doc name="conventions-dev.md" template="CONVENTIONS-DEV-TEMPLATE.md" />
+      <doc name="conventions-unit-test.md" template="CONVENTIONS-UNIT-TEST-TEMPLATE.md" />
+      <doc name="conventions-system-test.md" template="CONVENTIONS-SYSTEM-TEST-TEMPLATE.md" />
+      <doc name="conventions-build.md" template="CONVENTIONS-BUILD-TEMPLATE.md" />
+    </generate-docs>
+  </task>
+
+  <!-- Step 5b: Generate conventions-data.md for Backend -->
+  <gateway id="step5b-gateway" mode="exclusive" description="Check if data layer document needed">
+    <condition test="platform_type == backend or data_layer_detected">
+      <task id="step5b-generate-data" action="generate" description="Generate data layer conventions">
+        <generate-doc template="CONVENTIONS-DATA-TEMPLATE.md" output="{output_path}/conventions-data.md" />
+      </task>
+    </condition>
+  </gateway>
+
+  <!-- Step 6: Write Output Files -->
+  <task id="step6-write-output" action="write" description="Write all generated documents to output directory">
+    <write-files to="{output_path}" />
+  </task>
+
+  <!-- Step 7: Generate Analysis Coverage Report -->
+  <task id="step7-coverage-report" action="generate" description="Generate analysis coverage JSON report">
+    <generate-report output="{completed_dir}/{platform_id}.analysis.json" format="json">
+      <include name="topics_analysis" />
+      <include name="config_files_analyzed" />
+      <include name="source_dirs_scanned" />
+      <include name="documents_generated" />
+    </generate-report>
+  </task>
+
+  <!-- Step 8: Report Results -->
+  <event id="step8-report" action="log" description="Report generation results">
+    <report format="structured">
+      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)
+      - Output Directory: {output_path}
+    </report>
+  </event>
+
+  <!-- Output Block -->
+  <output name="status" from="generation_status" />
+  <output name="documents_generated" from="generated_files_list" />
+  <output name="coverage_report" from="analysis_coverage" />
+
+</workflow>
+
+---
+
+## Reference Guides
+
+### Mermaid Diagram Guide
+
+**Key Requirements:** Use basic node definitions only. No HTML tags, no nested subgraphs, no `direction` keyword, no `style` definitions.
+
+**Diagram Types**: `graph TB/LR` (structure), `flowchart TD` (logic), `sequenceDiagram` (interactions), `classDiagram` (classes), `erDiagram` (database), `stateDiagram-v2` (states)
+
+### Source Traceability Requirements
+
+**CRITICAL: All source file links MUST use RELATIVE PATHS.** No absolute paths, no `file://` protocol.
+
+**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
+2. `**Diagram Source**` annotation after each Mermaid diagram
+3. `**Section Source**` annotation at end of major sections
+
+### Document Content Specifications
+
+#### INDEX.md
+Platform summary, technology stack overview, navigation links, agent usage guide.
+
+#### tech-stack.md
+Overview, Core Technologies table, Dependencies (grouped), Development Tools, Configuration Files.
+
+#### architecture.md
+**Web**: Component Architecture, State Management, Routing, API Integration, Styling. **Backend**: Layered Architecture, DI, Module Organization, API Design, Middleware. **Mobile**: Widget Structure, State Management, Navigation, Platform considerations.
+
+#### conventions-design.md
+Design Principles (SOLID, DRY), Design Patterns, UI Design Conventions (reference ui-style/), Data Flow, Error Handling, Security, Performance.
+
+#### conventions-dev.md
+Naming Conventions, Directory Structure, Code Style (from ESLint/Prettier), Import/Export Patterns, Git Commit Conventions, Pre-Development Checklist, Code Review Checklist.
+
+**Source extraction**: Prettier (.prettierrc), ESLint (.eslintrc), EditorConfig (.editorconfig), Git hooks (.husky/), Commit conventions (.commitlintrc), Runtime version (.nvmrc), IDE config (.vscode/).
+
+#### conventions-unit-test.md / conventions-system-test.md
+Unit Testing (framework, naming, location, template, run command), Integration Testing, E2E Testing (frontend only), Database Testing (backend only), Performance Testing, Coverage Requirements, Troubleshooting.
+
+#### conventions-build.md
+Build Tool & Configuration, Environment Management, Build Profiles & Outputs, CI/CD (if detected), Docker (if detected), Dependency Management.
+
+#### conventions-data.md (Optional)
+ORM/Database Tool, Data Modeling, Migrations, Query Optimization, Caching.
+
+---
+
+## Template Usage
+
+Templates are located at `../speccrew-knowledge-techs-generate/templates/`:
+
+| Template File | Purpose |
+|---------------|---------|
+| INDEX-TEMPLATE.md | Platform overview |
+| TECH-STACK-TEMPLATE.md | Technology stack |
+| ARCHITECTURE-TEMPLATE.md | Architecture patterns |
+| CONVENTIONS-DESIGN-TEMPLATE.md | Design principles |
+| CONVENTIONS-DEV-TEMPLATE.md | Development conventions |
+| CONVENTIONS-UNIT-TEST-TEMPLATE.md | Unit testing |
+| CONVENTIONS-SYSTEM-TEST-TEMPLATE.md | System testing |
+| CONVENTIONS-BUILD-TEMPLATE.md | Build/deployment |
+| CONVENTIONS-DATA-TEMPLATE.md | Data layer |
+
+## Checklist
+
+### Pre-Generation
+- [ ] All configuration files read and parsed
+- [ ] Technology stack extracted accurately
+- [ ] Conventions analyzed from config files
+- [ ] Platform type identified
+- [ ] Data layer detection completed for non-backend platforms
+
+### Required Documents (All Platforms)
+- [ ] INDEX.md, tech-stack.md, architecture.md
+- [ ] conventions-design.md, conventions-dev.md
+- [ ] conventions-unit-test.md, conventions-system-test.md, conventions-build.md
+
+### Optional Document
+- [ ] conventions-data.md (if applicable)
+
+### UI Style Analysis (Frontend Platforms)
+- [ ] ui-analyze skill invoked
+- [ ] ui-style-guide.md generated
+- [ ] UI conventions referenced in conventions-design.md
+
+## Task Completion Report
+
+Upon completion, output the following structured report:
+
+```json
+{
+  "status": "success | partial | failed",
+  "skill": "speccrew-knowledge-techs-generate-xml",
+  "output_files": [
+    "{output_path}/INDEX.md",
+    "{output_path}/tech-stack.md",
+    "{output_path}/architecture.md"
+  ],
+  "summary": "Tech documentation generated for {platform_id}",
+  "metrics": {
+    "documents_generated": 0,
+    "sections_filled": 0,
+    "code_examples_included": 0
+  },
+  "errors": [],
+  "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.

package/.speccrew/skills/speccrew-knowledge-techs-index-xml/SKILL.md

@@ -0,0 +1,277 @@
+---
+name: speccrew-knowledge-techs-index-xml
+description: Stage 3 of technology knowledge initialization - Generate root INDEX.md by aggregating all platform technology documents using XML workflow blocks. Creates the master index that maps platforms to their documentation and provides Agent-to-Platform mapping guide. Used by Worker Agent after all platform documents are generated.
+tools: Read, Write, Skill
+---
+
+# Stage 3: Generate Root Technology Index (XML Workflow)
+
+Aggregate all platform technology documentation into a single root INDEX.md that serves as the master navigation hub for technology knowledge.
+
+## Language Adaptation
+
+**CRITICAL**: Generate all content in the language specified by the `language` parameter.
+
+- `language: "zh"` → Generate all content in 中文
+- `language: "en"` → Generate all content in English
+- Other languages → Use the specified language
+
+## Trigger Scenarios
+
+- "Generate techs root index"
+- "Create technology knowledge index"
+- "Aggregate platform tech docs"
+- "Generate master tech index"
+
+## User
+
+Worker Agent (speccrew-task-worker)
+
+## Input
+
+- `manifest_path`: Path to techs-manifest.json
+- `techs_base_path`: Base path for techs documentation (default: `speccrew-workspace/knowledges/techs/`)
+- `output_path`: Output path for root INDEX.md (default: `speccrew-workspace/knowledges/techs/`)
+- `language`: Target language (e.g., "zh", "en") - **REQUIRED**
+
+## Output
+
+- `{{output_path}}/INDEX.md` - Root technology knowledge index
+
+**INDEX.md Content Structure**:
+- Introduction (generation info, platform count)
+- Platform Overview (table with links to all platform docs)
+- Quick Reference (links organized by document type)
+- Agent-to-Platform Mapping (maps agents to their platform docs)
+- Document Guide (explains each document type)
+- Usage Guide (how to use the knowledge)
+
+## Workflow
+
+<!--
+== Block Types ==
+input      : Workflow input parameters (required=mandatory, default=default value)
+output     : Workflow output results (from=data source variable)
+task       : Execute action (action: run-skill | run-script | dispatch-to-worker)
+gateway    : Conditional branch/gate (mode: exclusive | guard | parallel)
+loop       : Iterate over collection (over=collection, as=current item)
+event      : Log/confirm/signal (action: log | confirm | signal)
+error-handler : Exception handling (try > catch > finally)
+checkpoint : Persistent milestone (name=checkpoint name, verify=verification condition)
+rule       : Constraint declaration (level: forbidden | mandatory | note)
+-->
+
+<workflow>
+
+  <!-- Global Rules -->
+  <rule id="GLOBAL-R1" level="mandatory" description="Continuous Execution: Execute all steps in sequence without interruption. Worker must complete all steps before reporting results." />
+  <rule id="GLOBAL-R-TECHSTACK" level="mandatory" description="Technology Stack Constraint: All generated index documents must accurately reflect detected platform technology stacks." />
+
+  <!-- Input Block -->
+  <input name="manifest_path" type="string" required="true" description="Path to techs-manifest.json" />
+  <input name="techs_base_path" type="string" required="false" default="speccrew-workspace/knowledges/techs/" description="Base path for techs documentation" />
+  <input name="output_path" type="string" required="false" default="speccrew-workspace/knowledges/techs/" description="Output path for root INDEX.md" />
+  <input name="language" type="string" required="true" description="Target language (e.g., zh, en)" />
+
+  <!-- Step 0: Read Root Index Template -->
+  <task id="step0-read-template" action="read" description="Read root index template to understand required structure">
+    <read-file path="../speccrew-knowledge-techs-index/templates/INDEX-TEMPLATE.md" />
+  </task>
+
+  <!-- Step 1: Read Manifest -->
+  <task id="step1-read-manifest" action="read" description="Read techs-manifest.json to get platform list">
+    <read-file path="{manifest_path}" />
+  </task>
+
+  <!-- Step 2: Verify Platform Documents -->
+  <loop id="step2-verify-docs" over="platforms" as="platform" description="Scan each platform directory for document availability">
+    <task id="step2a-scan-dir" action="list" description="List all .md files in platform directory">
+      <list-dir path="{techs_base_path}/{platform.platform_id}/" filter="*.md" />
+    </task>
+    <task id="step2b-verify-required" action="verify" description="Check required documents exist">
+      <verify-docs>
+        <required name="INDEX.md" on-missing="skip-platform" />
+        <required name="tech-stack.md" on-missing="mark-incomplete" />
+        <required name="architecture.md" on-missing="mark-incomplete" />
+        <required name="conventions-design.md" on-missing="mark-incomplete" />
+        <required name="conventions-dev.md" on-missing="mark-incomplete" />
+        <required name="conventions-test.md" on-missing="mark-incomplete" />
+        <required name="conventions-build.md" on-missing="mark-incomplete" />
+        <optional name="conventions-data.md" />
+      </verify-docs>
+    </task>
+  </loop>
+
+  <!-- Step 3: Extract Platform Summaries -->
+  <loop id="step3-extract-summaries" over="platforms" as="platform" description="Read each platform INDEX.md for summary extraction">
+    <gateway mode="guard" condition="platform.documents.INDEX.md exists">
+      <task action="read" description="Read platform INDEX.md">
+        <read-file path="{techs_base_path}/{platform.platform_id}/INDEX.md" />
+      </task>
+      <task action="extract" description="Extract platform name, framework, language, key technologies">
+        <extract-fields>
+          <field name="platform_name" />
+          <field name="framework" />
+          <field name="language" />
+          <field name="key_technologies" />
+        </extract-fields>
+      </task>
+    </gateway>
+  </loop>
+
+  <!-- Step 4: Get Timestamp -->
+  <task id="step4-get-timestamp" action="run-skill" description="Get current timestamp for generated_at field">
+    <run-skill skill="speccrew-get-timestamp" />
+  </task>
+
+  <!-- Step 5: Generate Root INDEX.md -->
+  <task id="step5-generate-index" action="generate" description="Generate root INDEX.md using template fill workflow">
+    <generate-index template-path="../speccrew-knowledge-techs-index/templates/INDEX-TEMPLATE.md" output-path="{output_path}/INDEX.md">
+      <copy-template />
+      <fill-sections>
+        <section name="header" with="{generated_at}, {source_path}, {platform_count}" />
+        <section name="platform-overview" with="dynamic_links_from_verification" />
+        <section name="quick-reference" with="organized_links" />
+        <section name="agent-mapping" with="platform_agent_documents" />
+        <section name="document-guide" with="document_descriptions" />
+        <section name="usage-guide" with="agent_usage_instructions" />
+      </fill-sections>
+    </generate-index>
+  </task>
+
+  <!-- Step 6: Write Output -->
+  <task id="step6-write-output" action="write" description="Write generated INDEX.md to output path">
+    <write-file path="{output_path}/INDEX.md" />
+  </task>
+
+  <!-- Step 7: Report Results -->
+  <event id="step7-report" action="log" description="Report generation results">
+    <report format="structured">
+      Stage 3 completed: Root Technology Index Generated
+      - Platforms Indexed: {platform_count}
+        - web-react: ✓
+        - backend-nestjs: ✓
+      - Root Index: {output_path}/INDEX.md
+      - Agent Mappings: Documented for all platforms
+    </report>
+  </event>
+
+  <!-- Output Block -->
+  <output name="status" from="generation_status" />
+  <output name="platforms_indexed" from="indexed_platforms_list" />
+  <output name="output_file" from="index_file_path" />
+
+</workflow>
+
+---
+
+## Template Usage
+
+Templates are located at `../speccrew-knowledge-techs-index/templates/`:
+
+**Template Variables:**
+- `{{generated_at}}`: ISO timestamp
+- `{{source_path}}`: Source path
+- `{{platform_count}}`: Number of platforms
+- `{{#each platforms}}`: Loop through platforms
+  - `{{platform_id}}`: Platform identifier
+  - `{{platform_type}}`: Platform type
+  - `{{framework}}`: Framework name
+  - `{{language}}`: Programming language
+
+---
+
+## Document Structure Details
+
+### Section 1: Header
+
+```markdown
+# Technology Knowledge Index
+
+**Files Referenced in This Document**
+
+- [techs-manifest.json](../../../speccrew-workspace/knowledges/techs/techs-manifest.json)
+
+> **Target Audience**: devcrew-designer-*, devcrew-dev-*, devcrew-test-*
+```
+
+### Section 2: Platform Overview
+
+Summary table of all platforms with **dynamically generated document links**:
+
+```markdown
+## Platform Overview
+
+| Platform | Type | Framework | Stack | Arch | Design | Dev | Test | Build | Data |
+|----------|------|-----------|-------|------|--------|-----|------|-------|------|
+| [web-react](web-react/INDEX.md) | web | React | [Stack](web-react/tech-stack.md) | ... | ... | ... | ... | ... | - |
+```
+
+**Dynamic Link Generation Rules:**
+
+1. **Always include links to required documents** (if they exist)
+2. **Conditionally include conventions-data.md**: Show `-` if not exists
+3. **Link Format**: Use short abbreviations to save space
+
+### Section 3: Quick Reference
+
+Quick links organized by document type (Technology Stacks, Architecture Guidelines, Design Conventions, etc.)
+
+### Section 4: Agent-to-Platform Mapping
+
+Critical section that defines how Agents map to platform documentation. **Must dynamically adjust based on actual document availability.**
+
+**Dynamic Adjustment Rules:**
+
+1. **Designer Agent Documents**: Primary + Optional (conventions-data.md, ui-style-patterns/)
+2. **Developer Agent Documents**: Primary (conventions-dev.md, conventions-build.md) + Optional
+3. **Tester Agent Documents**: Primary (conventions-test.md, conventions-build.md) + Optional
+
+### Section 5: Document Guide
+
+Explain what each document type contains.
+
+### Section 6: Usage Guide
+
+How to use the technology knowledge for Designer, Developer, and Tester Agents.
+
+---
+
+## Checklist
+
+### Pre-Generation
+- [ ] techs-manifest.json read successfully
+- [ ] Platform list extracted from manifest
+
+### Dynamic Document Detection
+- [ ] Each platform directory scanned for actual document existence
+- [ ] Document availability map created for each platform
+- [ ] Required documents verified
+- [ ] Optional conventions-data.md existence checked per platform
+
+### Content Generation
+- [ ] Platform summaries extracted from existing INDEX.md files
+- [ ] Root INDEX.md generated with all sections
+- [ ] **Platform Overview table**: Links dynamically generated based on actual document existence
+- [ ] **Agent-to-Platform mapping**: Document recommendations adjusted per platform
+- [ ] Document guide included
+- [ ] Usage guide included
+
+### Quality & Validation
+- [ ] No broken links to non-existent documents
+- [ ] conventions-data.md links only included for platforms where it exists
+- [ ] **Source traceability**: File reference block added to root INDEX.md
+- [ ] Output file written successfully
+- [ ] Results reported with document availability summary
+
+---
+
+## 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 index documents must accurately reflect detected platform technology stacks.