speccrew 0.6.68 → 0.7.0

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

@@ -1,12 +1,12 @@
 ---
 name: speccrew-knowledge-techs-generate-quality
-description: Quality assurance for generated tech documentation. Performs cross-validation, consistency checks, completeness verification, and generates quality reports. Used after speccrew-knowledge-techs-generate to ensure documentation quality.
+description: Quality assurance for generated tech documentation using XML workflow blocks. Performs cross-validation, consistency checks, completeness verification, and generates quality reports.
 tools: Read, Write, Glob, Grep, Bash
 ---
 
-# Tech Documentation Quality Assurance
+# Tech Documentation Quality Assurance (XML Workflow)
 
-Perform comprehensive quality checks on generated technology documentation to ensure completeness, consistency, and accuracy.
+Perform comprehensive quality checks on generated technology documentation to ensure completeness, consistency, and accuracy using XML workflow blocks.
 
 ## Role Definition
 
@@ -29,226 +29,289 @@ You are a Technical Documentation Quality Assurance Specialist. Your role is to
 
 Worker Agent (speccrew-task-worker)
 
-## Input Parameters
-
-| Parameter | Required | Description |
-|-----------|----------|-------------|
-| platform_dir | Yes | Path to platform's techs directory containing generated docs (e.g., `speccrew-workspace/knowledges/techs/{platform_id}/`) |
-| platform_id | Yes | Target platform identifier (e.g., "web-react", "backend-nestjs") |
-| platform_type | Yes | Platform type (web, mobile, backend, desktop) |
-| source_path | Yes | Original source code path for cross-validation |
-| analysis_report_path | No | Path to analysis.json for reference (default: `{platform_dir}/{platform_id}.analysis.json`) |
-
-## Output
-
-- Quality Report: `{platform_dir}/quality-report.json`
-- Completion Marker: `{platform_dir}/quality-done.json`
-- Console summary of check results
-
-## Workflow
-
-```mermaid
-flowchart TD
-    Start([Start]) --> Step1[Step 1: Read Generated Documentation]
-    Step1 --> Step2[Step 2: Completeness Check]
-    Step2 --> Step3[Step 3: Cross-Validation]
-    Step3 --> Step4[Step 4: Consistency Check]
-    Step4 --> Step5[Step 5: Source Traceability Check]
-    Step5 --> Step6[Step 6: Mermaid Compatibility Check]
-    Step6 --> Step7[Step 7: Generate Quality Report]
-    Step7 --> Step8[Step 8: Write Completion Marker]
-    Step8 --> End([End])
-```
-
-### Step 1: Read Generated Documentation
-
-Read all generated documentation files in the platform directory:
-
-**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 platforms or platforms with data layer)
-- `ui-style/ui-style-guide.md` (frontend platforms)
-
-**Analysis Report**:
-- `{platform_id}.analysis.json`
-
-Record all files found and their sizes.
-
-### Step 2: Completeness Check
-
-Verify that all expected documents and sections exist.
-
-**2.1 Document Existence Check**:
-
-| Platform Type | Required Documents |
-|---------------|-------------------|
-| All | INDEX.md, tech-stack.md, architecture.md, conventions-design.md, conventions-dev.md, conventions-unit-test.md, conventions-system-test.md, conventions-build.md |
-| backend | + conventions-data.md |
-| web/mobile/desktop | + ui-style/ui-style-guide.md |
-
-**2.2 Section Completeness Check**:
-
-For each document, verify mandatory sections exist:
-
-**INDEX.md**:
-- [ ] Platform summary
-- [ ] Technology stack overview
-- [ ] Navigation links to all convention documents
-- [ ] Agent usage guide
-
-**tech-stack.md**:
-- [ ] Overview section
-- [ ] Core Technologies table
-- [ ] Dependencies section (grouped by category)
-- [ ] Development Tools section
-- [ ] Configuration Files list
-
-**architecture.md**:
-- [ ] Component/Module Architecture section
-- [ ] State Management / Dependency Injection section
-- [ ] API Integration / Module Organization section
-- [ ] Styling Approach / Middleware section
-
-**conventions-dev.md**:
-- [ ] Naming Conventions section
-- [ ] Directory Structure section
-- [ ] Code Style section
-- [ ] Import/Export Patterns section
-- [ ] Pre-Development Checklist section
-
-**conventions-build.md**:
-- [ ] Build Tool & Configuration section
-- [ ] Environment Management section
-- [ ] Build Profiles & Outputs section
-
-**2.3 Analysis Report Completeness**:
-
-Verify `{platform_id}.analysis.json` contains:
-- [ ] `platform_id` field
-- [ ] `platform_type` field
-- [ ] `analyzed_at` timestamp
-- [ ] `topics` object with all expected topics
-- [ ] `documents_generated` array
-- [ ] `coverage_summary` object
-
-### Step 3: Cross-Validation
-
-Verify that information is consistent across documents and with source code.
-
-**3.1 Version Consistency Check**: Read `source_path/package.json` and verify framework, key dependency, and build tool versions match documentation.
-
-**3.2 Dependency Reference Consistency**: Verify each dependency in `tech-stack.md` exists in package.json with consistent version format.
-
-**3.3 Cross-Document Reference Check**:
-
-Verify internal references between documents:
-- `INDEX.md` links to all other documents
-- `conventions-design.md` references `ui-style/ui-style-guide.md` (frontend platforms)
-- All documents have consistent platform_id and platform_type references
-
-**3.4 Configuration File Reference Check**:
-
-Verify configuration files mentioned in documentation exist:
-- ESLint config path → file exists
-- Prettier config path → file exists
-- Build config path → file exists
-
-### Step 4: Consistency Check
-
-Verify naming conventions and style are uniform across all documents.
-
-**4.1 Naming Convention Consistency**:
-
-Check that naming patterns described in `conventions-dev.md` are actually used in examples throughout other documents:
-- Component naming (PascalCase vs camelCase)
-- File naming conventions
-- Variable naming conventions
-
-**4.2 Platform Terminology Consistency**:
-
-Verify consistent use of:
-- Platform identifier (e.g., "web-react" vs "react-web")
-- Framework name (e.g., "React" vs "react")
-- Language name (e.g., "TypeScript" vs "Typescript")
-
-**4.3 Code Style Consistency**:
-
-Verify code examples across documents follow the style defined in `conventions-dev.md`:
-- Quote style (single vs double)
-- Semicolon usage
-- Indentation style
-
-**4.4 UI Reference Consistency (Frontend Platforms)**:
-
-Verify `conventions-design.md` contains:
-- Reference to `ui-style/ui-style-guide.md`
-- `ui_style_analysis_level` indicator
-
-### Step 5: Source Traceability Check
-
-Verify that all documents properly cite their sources.
-
-**5.1 File Reference Block Check**:
-
-For each document, verify:
-- [ ] File reference block exists at document beginning (previously used `<cite>` tags, now use pure Markdown for VS Code preview compatibility)
-- [ ] Contains list of referenced files
-- [ ] File paths use relative paths (NOT absolute or file://)
-
-**5.2 Diagram Source Annotation Check**:
-
-For each Mermaid diagram in documents:
-- [ ] `**Diagram Source**` annotation exists after diagram
-- [ ] Source file path is provided
-- [ ] Path uses relative format
-
-**5.3 Section Source Annotation Check**:
-
-For each major section:
-- [ ] `**Section Source**` annotation exists at section end
-- [ ] Or generic guidance note is present
-
-**5.4 Path Format Validation**:
-
-Check that all file paths:
-- Do NOT start with drive letter (e.g., `d:/`, `C:\`)
-- Do NOT use `file://` protocol
-- Use correct relative depth (e.g., `../../../../` for 4 levels deep)
-
-### Step 6: Mermaid Compatibility Check
-
-Verify all Mermaid diagrams are compatible with standard rendering.
-
-**6.1 Forbidden Elements Check**:
-
-Scan all Mermaid diagrams for:
-- [ ] No `style` definitions
-- [ ] No `direction` keyword
-- [ ] No HTML tags (e.g., `<br/>`, `<div>`)
-- [ ] No nested subgraphs
-
-**6.2 Syntax Validation**: Valid diagram type declaration, properly closed brackets, valid node syntax.
-
-**6.3 Diagram Type Usage**: Verify appropriate diagram types (`graph TB/LR` for structure, `flowchart TD` for process, `sequenceDiagram` for API).
-
-### Step 7: Generate Quality Report
-
-Generate a comprehensive quality report in JSON format.
-
-**Output File**: `{platform_dir}/quality-report.json`
-
-**Report Format**:
+---
 
-```json
+## AgentFlow Definition
+
+<!-- @agentflow: workflow.agentflow.xml -->
+
+> **REQUIRED**: Before executing this workflow, read the XML workflow specification: `speccrew-workspace/docs/rules/agentflow-spec.md`
+
+  <!-- ============================================================
+       Input Parameters Definition
+       ============================================================ -->
+  <block type="input" id="I1" desc="Quality check input parameters">
+    <field name="platform_dir" required="true" type="string" desc="Path to platform's techs directory (e.g., speccrew-workspace/knowledges/techs/{platform_id}/)"/>
+    <field name="platform_id" required="true" type="string" desc="Target platform identifier (e.g., web-react, backend-nestjs)"/>
+    <field name="platform_type" required="true" type="string" desc="Platform type (web, mobile, backend, desktop)"/>
+    <field name="source_path" required="true" type="string" desc="Original source code path for cross-validation"/>
+    <field name="analysis_report_path" required="false" type="string" default="{platform_dir}/{platform_id}.analysis.json" desc="Path to analysis.json for reference"/>
+  </block>
+
+  <!-- ============================================================
+       Global Continuous Execution Rules
+       ============================================================ -->
+  <block type="rule" id="GLOBAL-R1" level="forbidden" desc="Continuous execution constraints — NEVER violate">
+    <field name="text">DO NOT ask user "Should I continue?" or "How would you like to proceed?" between steps</field>
+    <field name="text">DO NOT offer options like "Full execution / Sample execution / Pause" — always execute ALL steps to completion</field>
+    <field name="text">DO NOT suggest "Let me split this into batches" or "Let's do this in parts" — process ALL items 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 ask for confirmation before generating output files</field>
+    <field name="text">ONLY pause at explicit &lt;event action="confirm"&gt; blocks defined in the workflow</field>
+  </block>
+
+  <!-- ============================================================
+       Global Technology Stack Constraints
+       ============================================================ -->
+  <block type="rule" id="GLOBAL-R-TECHSTACK" level="forbidden" desc="Technology stack constraints — 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</field>
+    <field name="text">For JSON validation use: node -e "JSON.parse(require('fs').readFileSync('file.json','utf8'))"</field>
+    <field name="text">DO NOT create temporary .py, .rb, .pl, .bat files — use inline commands via run_in_terminal</field>
+  </block>
+
+  <!-- ============================================================
+       Pre-completion Validation Rule
+       ============================================================ -->
+  <block type="rule" id="PRE-COMPLETION-R1" level="mandatory" desc="Completion marker validation — MUST verify before writing done marker">
+    <field name="text">MUST verify quality-report.json exists before writing quality-done.json marker</field>
+    <field name="text">NEVER write completion marker with missing quality report</field>
+  </block>
+
+  <!-- ============================================================
+       Step 1: Read Generated Documentation
+       ============================================================ -->
+  <!-- Step 1: Read Generated Documentation -->
+  <block type="task" id="S1-B1" action="run-skill" status="pending" desc="Read all generated documentation files">
+    <field name="description">Read all generated documentation files in the platform directory</field>
+    <field name="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</field>
+    <field name="optional_documents">conventions-data.md (backend OR has_data_layer), ui-style/ui-style-guide.md (frontend)</field>
+    <field name="analysis_report">{platform_id}.analysis.json</field>
+    <field name="output" var="documents_read"/>
+    <field name="record">All files found, File sizes</field>
+  </block>
+
+  <block type="checkpoint" id="CP1" name="documents_read" desc="All documents read">
+    <field name="verify" value="${documents_read.count} >= 8"/>
+  </block>
+
+  <!-- ============================================================
+       Step 2: Completeness Check
+       ============================================================ -->
+  <block type="task" id="S2-B1" action="run-skill" status="pending" desc="Perform completeness check">
+    <field name="description">Verify all expected documents and sections exist</field>
+
+    <!-- 2.1 Document Existence Check -->
+    <!-- document_existence: Check documents based on platform_type -->
+    <field name="check">All platforms require: INDEX.md, tech-stack.md, architecture.md, conventions-design.md, conventions-dev.md, conventions-unit-test.md, conventions-system-test.md, conventions-build.md</field>
+    <field name="check">Backend platforms additionally require: conventions-data.md</field>
+    <field name="check">Web/mobile/desktop platforms additionally require: ui-style/ui-style-guide.md</field>
+
+    <!-- 2.2 Section Completeness Check -->
+    <!-- section_completeness: Verify required sections in each document -->
+    <field name="check">INDEX.md must contain: Platform summary, Technology stack overview, Navigation links to all convention documents, Agent usage guide</field>
+    <field name="check">tech-stack.md must contain: Overview section, Core Technologies table, Dependencies section (grouped by category), Development Tools section, Configuration Files list</field>
+    <field name="check">architecture.md must contain: Component/Module Architecture section, State Management / Dependency Injection section, API Integration / Module Organization section, Styling Approach / Middleware section</field>
+    <field name="check">conventions-dev.md must contain: Naming Conventions section, Directory Structure section, Code Style section, Import/Export Patterns section, Pre-Development Checklist section</field>
+    <field name="check">conventions-build.md must contain: Build Tool &amp; Configuration section, Environment Management section, Build Profiles &amp; Outputs section</field>
+
+    <!-- 2.3 Analysis Report Completeness -->
+    <!-- analysis_report_completeness: Verify analysis.json structure -->
+    <field name="check">{platform_id}.analysis.json must contain: platform_id field, platform_type field, analyzed_at timestamp, topics object with all expected topics, documents_generated array, coverage_summary object</field>
+
+    <field name="output" var="completeness_result"/>
+  </block>
+
+  <block type="event" id="E2" action="log" level="info" desc="Completeness check result">
+    <field name="message">Completeness check: ${completeness_result.documents_found}/${completeness_result.documents_expected} documents, ${completeness_result.sections_passed}/${completeness_result.sections_checked} sections</field>
+  </block>
+
+  <block type="checkpoint" id="CP2" name="completeness_checked" desc="Completeness check complete">
+    <field name="verify" value="${completeness_result.status} IN ['passed', 'partial']"/>
+  </block>
+
+  <!-- ============================================================
+       Step 3: Cross-Validation
+       ============================================================ -->
+  <block type="task" id="S3-B1" action="run-skill" status="pending" desc="Perform cross-validation">
+    <field name="description">Verify information is consistent across documents and with source code</field>
+
+    <!-- 3.1 Version Consistency Check -->
+    <!-- version_consistency: Read {source_path}/package.json and verify versions -->
+    <field name="action">Read {source_path}/package.json</field>
+    <field name="check">Framework versions match documentation</field>
+    <field name="check">Key dependency versions match documentation</field>
+    <field name="check">Build tool versions match documentation</field>
+    <field name="output" var="version_checks"/>
+
+    <!-- 3.2 Dependency Reference Consistency -->
+    <!-- dependency_consistency: Verify dependencies exist and formats match -->
+    <field name="check">Each dependency in tech-stack.md exists in package.json</field>
+    <field name="check">Version format is consistent</field>
+    <field name="output" var="dependency_checks"/>
+
+    <!-- 3.3 Cross-Document Reference Check -->
+    <!-- cross_document_references: Verify cross-references between documents -->
+    <field name="check">INDEX.md links to all other documents</field>
+    <field name="check">conventions-design.md references ui-style/ui-style-guide.md (for frontend)</field>
+    <field name="check">All documents have consistent platform_id references</field>
+    <field name="check">All documents have consistent platform_type references</field>
+    <field name="output" var="reference_checks"/>
+
+    <!-- 3.4 Configuration File Reference Check -->
+    <!-- config_file_references: Verify config file paths point to existing files -->
+    <field name="check">ESLint config path → file exists</field>
+    <field name="check">Prettier config path → file exists</field>
+    <field name="check">Build config path → file exists</field>
+    <field name="output" var="config_checks"/>
+
+    <field name="output" var="cross_validation_result"/>
+  </block>
+
+  <block type="event" id="E3" action="log" level="info" desc="Cross-validation result">
+    <field name="message">Cross-validation: ${cross_validation_result.version_checks.passed}/${cross_validation_result.version_checks.total} version checks, ${cross_validation_result.reference_checks.passed}/${cross_validation_result.reference_checks.total} reference checks</field>
+  </block>
+
+  <block type="checkpoint" id="CP3" name="cross_validation_complete" desc="Cross-validation complete">
+    <field name="verify" value="true"/>
+  </block>
+
+  <!-- ============================================================
+       Step 4: Consistency Check
+       ============================================================ -->
+  <block type="task" id="S4-B1" action="run-skill" status="pending" desc="Perform consistency check">
+    <field name="description">Verify naming conventions and style are uniform across all documents</field>
+
+    <!-- 4.1 Naming Convention Consistency -->
+    <!-- naming_conventions: Check naming patterns match conventions-dev.md -->
+    <field name="check">Component naming (PascalCase vs camelCase) matches conventions-dev.md</field>
+    <field name="check">File naming conventions match conventions-dev.md</field>
+    <field name="check">Variable naming conventions match conventions-dev.md</field>
+    <field name="output" var="naming_issues"/>
+
+    <!-- 4.2 Platform Terminology Consistency -->
+    <!-- terminology_consistency: Verify consistent terminology usage -->
+    <field name="check">Platform identifier is consistent (e.g., web-react vs react-web)</field>
+    <field name="check">Framework name is consistent (e.g., React vs react)</field>
+    <field name="check">Language name is consistent (e.g., TypeScript vs Typescript)</field>
+    <field name="output" var="terminology_issues"/>
+
+    <!-- 4.3 Code Style Consistency -->
+    <!-- code_style_consistency: Verify code style matches conventions-dev.md -->
+    <field name="check">Quote style matches conventions-dev.md (single vs double)</field>
+    <field name="check">Semicolon usage matches conventions-dev.md</field>
+    <field name="check">Indentation style matches conventions-dev.md</field>
+    <field name="output" var="style_issues"/>
+
+    <!-- 4.4 UI Reference Consistency (Frontend Platforms) -->
+    <block type="gateway" id="G4" mode="guard" test="${platform_type} IN ['web', 'mobile', 'desktop']" desc="Check UI reference for frontend platforms">
+      <!-- ui_reference_consistency: Verify UI style references for frontend platforms -->
+      <field name="check">conventions-design.md contains reference to ui-style/ui-style-guide.md</field>
+      <field name="check">ui_style_analysis_level indicator exists</field>
+      <field name="output" var="ui_reference_issues"/>
+    </block>
+
+    <field name="output" var="consistency_result"/>
+  </block>
+
+  <block type="event" id="E4" action="log" level="info" desc="Consistency check result">
+    <field name="message">Consistency: ${consistency_result.status} - ${consistency_result.issues.length} issues found</field>
+  </block>
+
+  <block type="checkpoint" id="CP4" name="consistency_checked" desc="Consistency check complete">
+    <field name="verify" value="true"/>
+  </block>
+
+  <!-- ============================================================
+       Step 5: Source Traceability Check
+       ============================================================ -->
+  <block type="task" id="S5-B1" action="run-skill" status="pending" desc="Perform source traceability check">
+    <field name="description">Verify all documents properly cite their sources</field>
+
+    <!-- 5.1 File Reference Block Check -->
+    <!-- file_reference_blocks: For each document, verify file reference blocks -->
+    <field name="check">File reference block exists at document beginning</field>
+    <field name="check">Contains list of referenced files</field>
+    <field name="check">File paths use relative paths (NOT absolute or file://)</field>
+    <field name="output" var="cite_block_checks"/>
+
+    <!-- 5.2 Diagram Source Annotation Check -->
+    <!-- diagram_source_annotations: For each Mermaid diagram, verify source annotations -->
+    <field name="check">**Diagram Source** annotation exists after diagram</field>
+    <field name="check">Source file path is provided</field>
+    <field name="check">Path uses relative format</field>
+    <field name="output" var="diagram_source_checks"/>
+
+    <!-- 5.3 Section Source Annotation Check -->
+    <!-- section_source_annotations: For each major section, verify source annotations -->
+    <field name="check">**Section Source** annotation exists at section end OR generic guidance note is present</field>
+    <field name="output" var="section_source_checks"/>
+
+    <!-- 5.4 Path Format Validation -->
+    <!-- path_format_validation: Verify path formats are correct -->
+    <field name="check">No paths start with drive letter (e.g., d:/, C:\)</field>
+    <field name="check">No paths use file:// protocol</field>
+    <field name="check">Correct relative depth used (e.g., ../../../../ for 4 levels)</field>
+    <field name="output" var="path_format_issues"/>
+
+    <field name="output" var="traceability_result"/>
+  </block>
+
+  <block type="event" id="E5" action="log" level="info" desc="Source traceability result">
+    <field name="message">Source Traceability: ${traceability_result.documents_with_cite_block}/${traceability_result.documents_total} documents with cite blocks, ${traceability_result.absolute_paths_found} absolute paths, ${traceability_result.file_protocol_found} file:// protocols</field>
+  </block>
+
+  <block type="checkpoint" id="CP5" name="traceability_checked" desc="Source traceability check complete">
+    <field name="verify" value="true"/>
+  </block>
+
+  <!-- ============================================================
+       Step 6: Mermaid Compatibility Check
+       ============================================================ -->
+  <block type="task" id="S6-B1" action="run-skill" status="pending" desc="Perform Mermaid compatibility check">
+    <field name="description">Verify all Mermaid diagrams are compatible with standard rendering</field>
+
+    <!-- 6.1 Forbidden Elements Check -->
+    <!-- forbidden_elements: For each Mermaid diagram, check for forbidden elements -->
+    <field name="check">No `style` definitions</field>
+    <field name="check">No `direction` keyword</field>
+    <field name="check">No HTML tags (e.g., &lt;br/>, &lt;div>)</field>
+    <field name="check">No nested subgraphs</field>
+    <field name="output" var="forbidden_element_issues"/>
+
+    <!-- 6.2 Syntax Validation -->
+    <!-- syntax_validation: For each Mermaid diagram, verify syntax -->
+    <field name="check">Valid diagram type declaration</field>
+    <field name="check">Properly closed brackets</field>
+    <field name="check">Valid node syntax</field>
+    <field name="output" var="syntax_issues"/>
+
+    <!-- 6.3 Diagram Type Usage -->
+    <!-- diagram_type_usage: Verify correct diagram types are used -->
+    <field name="check">Use graph TB/LR for structure diagrams</field>
+    <field name="check">Use flowchart TD for process diagrams</field>
+    <field name="check">Use sequenceDiagram for API diagrams</field>
+    <field name="output" var="type_usage_issues"/>
+
+    <field name="output" var="mermaid_result"/>
+  </block>
+
+  <block type="event" id="E6" action="log" level="info" desc="Mermaid compatibility result">
+    <field name="message">Mermaid Compatibility: ${mermaid_result.diagrams_passed}/${mermaid_result.diagrams_checked} diagrams passed, ${mermaid_result.issues.length} issues found</field>
+  </block>
+
+  <block type="checkpoint" id="CP6" name="mermaid_checked" desc="Mermaid compatibility check complete">
+    <field name="verify" value="true"/>
+  </block>
+
+  <!-- ============================================================
+       Step 7: Generate Quality Report
+       ============================================================ -->
+  <block type="task" id="S7-B1" action="run-script" status="pending" desc="Generate quality report JSON">
+    <field name="description">Generate comprehensive quality report in JSON format</field>
+    <field name="output_file">{platform_dir}/quality-report.json</field>
+    <field name="format">
 {
   "platform_id": "{platform_id}",
   "platform_type": "{platform_type}",
@@ -270,26 +333,13 @@ Generate a comprehensive quality report in JSON format.
   },
   "cross_validation": {
     "status": "passed",
-    "version_checks": {
-      "total": 5,
-      "passed": 5,
-      "mismatches": []
-    },
-    "reference_checks": {
-      "total": 12,
-      "passed": 12,
-      "broken_links": []
-    }
+    "version_checks": { "total": 5, "passed": 5, "mismatches": [] },
+    "reference_checks": { "total": 12, "passed": 12, "broken_links": [] }
   },
   "consistency": {
     "status": "warning",
     "naming_issues": [],
-    "terminology_issues": [
-      {
-        "location": "tech-stack.md:15",
-        "issue": "Inconsistent framework name: 'react' should be 'React'"
-      }
-    ],
+    "terminology_issues": [],
     "style_issues": []
   },
   "source_traceability": {
@@ -300,38 +350,30 @@ Generate a comprehensive quality report in JSON format.
     "file_protocol_found": 0
   },
   "mermaid_compatibility": {
-    "status": "failed",
+    "status": "failed|passed",
     "diagrams_checked": 5,
     "diagrams_passed": 4,
-    "issues": [
-      {
-        "file": "architecture.md",
-        "line": 45,
-        "issue": "Found 'style' definition in Mermaid diagram"
-      }
-    ]
+    "issues": []
   },
-  "recommendations": [
-    "Fix Mermaid 'style' definition in architecture.md:45",
-    "Standardize framework name to 'React' in tech-stack.md"
-  ]
+  "recommendations": []
 }
-```
-
-**Quality Score Calculation**:
-- quality_score = (passed / total_checks) * 100
-- Warnings count as 0.5 towards failed
-- Critical failures (missing required documents) deduct 10 points each
-
-### Step 8: Write Completion Marker
-
-Create a completion marker file to signal quality check completion.
-
-**Output File**: `{platform_dir}/quality-done.json`
-
-**Marker Format**:
-
-```json
+    </field>
+    <field name="quality_score_calculation">quality_score = (passed / total_checks) * 100; Warnings count as 0.5 towards failed; Critical failures (missing required documents) deduct 10 points each</field>
+    <field name="output" var="quality_report"/>
+  </block>
+
+  <block type="checkpoint" id="CP7" name="quality_report_generated" desc="Quality report generated">
+    <field name="verify" value="file_exists({platform_dir}/quality-report.json)"/>
+  </block>
+
+  <!-- ============================================================
+       Step 8: Write Completion Marker
+       ============================================================ -->
+  <block type="task" id="S8-B1" action="run-script" status="pending" desc="Write completion marker">
+    <field name="description">Create completion marker file to signal quality check completion</field>
+    <field name="validation">MUST verify quality-report.json exists before writing marker</field>
+    <field name="output_file">{platform_dir}/quality-done.json</field>
+    <field name="format">
 {
   "platform_id": "{platform_id}",
   "status": "completed",
@@ -339,15 +381,135 @@ Create a completion marker file to signal quality check completion.
   "report_path": "quality-report.json",
   "completed_at": "{ISO 8601 timestamp}"
 }
-```
+    </field>
+    <field name="status_values">completed: Quality check finished successfully; failed: Critical error during quality check</field>
+    <field name="output" var="completion_marker"/>
+  </block>
+
+  <block type="event" id="E8" action="log" level="info" desc="Quality check complete">
+    <field name="message">Quality check complete for {platform_id}
+- Total Checks: ${quality_report.summary.total_checks}
+- Passed: ${quality_report.summary.passed}
+- Warnings: ${quality_report.summary.warnings}
+- Failed: ${quality_report.summary.failed}
+- Quality Score: ${quality_report.summary.quality_score}%
 
-**Status values**:
-- `completed` — Quality check finished successfully
-- `failed` — Critical error during quality check
+## Status by Category
+- Completeness: ${quality_report.completeness.status}
+- Cross-Validation: ${quality_report.cross_validation.status}
+- Consistency: ${quality_report.consistency.status}
+- Source Traceability: ${quality_report.source_traceability.status}
+- Mermaid Compatibility: ${quality_report.mermaid_compatibility.status}</field>
+  </block>
+
+  <!-- ============================================================
+       Output Results
+       ============================================================ -->
+  <block type="output" id="O1" desc="Quality check results">
+    <field name="platform_id" from="${platform_id}" type="string"/>
+    <field name="status" value="completed"/>
+    <field name="quality_score" from="${quality_report.summary.quality_score}" type="number"/>
+    <field name="quality_report" from="${platform_dir}/quality-report.json" type="string"/>
+    <field name="completion_marker" from="${platform_dir}/quality-done.json" type="string"/>
+    <field name="summary">total_checks: ${quality_report.summary.total_checks}, passed: ${quality_report.summary.passed}, warnings: ${quality_report.summary.warnings}, failed: ${quality_report.summary.failed}</field>
+  </block>
+
+  <!-- ============================================================
+       Error Handling
+       ============================================================ -->
+  <block type="error-handler" id="EH1" desc="Global error handling">
+    <try>
+      <!-- Main workflow defined in steps above -->
+    </try>
+    <catch on="platform_dir_not_found">
+      <block type="event" id="EH1-E1" action="log" level="error" desc="Platform directory not found">
+        <field name="message">Platform directory not found: {platform_dir}</field>
+      </block>
+      <block type="output" id="EH1-O1">
+        <field name="status" value="failed"/>
+        <field name="error" value="Platform directory not found"/>
+      </block>
+    </catch>
+    <catch on="required_document_missing">
+      <block type="event" id="EH1-E2" action="log" level="warn" desc="Required document missing">
+        <field name="message">Required document missing: {missing_document}</field>
+      </block>
+      <field name="continue" value="true"/>
+      <field name="record_in" value="completeness.documents_missing"/>
+    </catch>
+    <catch on="analysis_report_missing">
+      <block type="event" id="EH1-E3" action="log" level="warn" desc="Analysis report missing">
+        <field name="message">Analysis report missing, skipping cross-validation with source</field>
+      </block>
+      <field name="continue" value="true"/>
+    </catch>
+    <catch on="mermaid_parsing_error">
+      <block type="event" id="EH1-E4" action="log" level="warn" desc="Mermaid parsing error">
+        <field name="message">Mermaid parsing error in {diagram_location}</field>
+      </block>
+      <field name="continue" value="true"/>
+      <field name="record_in" value="mermaid_compatibility.issues"/>
+    </catch>
+  </block>
+
+---
+
+## Input Parameters
+
+| Parameter | Required | Description |
+|-----------|----------|-------------|
+| platform_dir | Yes | Path to platform's techs directory containing generated docs (e.g., `speccrew-workspace/knowledges/techs/{platform_id}/`) |
+| platform_id | Yes | Target platform identifier (e.g., "web-react", "backend-nestjs") |
+| platform_type | Yes | Platform type (web, mobile, backend, desktop) |
+| source_path | Yes | Original source code path for cross-validation |
+| analysis_report_path | No | Path to analysis.json for reference (default: `{platform_dir}/{platform_id}.analysis.json`) |
+
+---
+
+## Output Files
+
+- Quality Report: `{platform_dir}/quality-report.json`
+- Completion Marker: `{platform_dir}/quality-done.json`
+- Console summary of check results
+
+---
+
+## Quality Thresholds
+
+| Score | Status |
+|-------|--------|
+| 90-100 | EXCELLENT |
+| 80-89 | GOOD |
+| 70-79 | ACCEPTABLE |
+| 60-69 | NEEDS_IMPROVEMENT |
+| 0-59 | FAILED |
+
+---
+
+## Constraints
+
+1. **Read-Only Source Access**: Only READ from source_path, never modify
+2. **Relative Paths Only**: All file references must use relative paths
+3. **JSON Output Only**: Quality report must be valid JSON
+4. **Complete All Steps**: Must complete all 8 steps even if early failures are found
+5. **Detailed Issue Reporting**: Include file paths and line numbers for issues when possible
+
+---
+
+## Error Handling
+
+| Error Type | Action |
+|------------|--------|
+| Platform directory not found | Report error, terminate with failed status |
+| Required document missing | Record in completeness check, continue |
+| Analysis report missing | Skip cross-validation with source, continue |
+| Mermaid parsing error | Record in compatibility check, continue |
+
+---
 
 ## Task Completion Report
 
-Upon completion, report the following:
+Upon completion, return the following:
 
 ```
 TASK COMPLETED: speccrew-knowledge-techs-generate-quality
@@ -378,32 +540,7 @@ TASK COMPLETED: speccrew-knowledge-techs-generate-quality
 {list of recommendations if any}
 ```
 
-## Constraints
-
-1. **Read-Only Source Access**: Only READ from source_path, never modify
-2. **Relative Paths Only**: All file references must use relative paths
-3. **JSON Output Only**: Quality report must be valid JSON
-4. **Complete All Steps**: Must complete all 7 steps even if early failures are found
-5. **Detailed Issue Reporting**: Include file paths and line numbers for issues when possible
-
-## Error Handling
-
-| Error Type | Action |
-|------------|--------|
-| Platform directory not found | Report error, terminate with failed status |
-| Required document missing | Record in completeness check, continue |
-| Analysis report missing | Skip cross-validation with source, continue |
-| Mermaid parsing error | Record in compatibility check, continue |
-
-## Quality Thresholds
-
-| Score | Status |
-|-------|--------|
-| 90-100 | EXCELLENT |
-| 80-89 | GOOD |
-| 70-79 | ACCEPTABLE |
-| 60-69 | NEEDS_IMPROVEMENT |
-| 0-59 | FAILED |
+---
 
 ## Integration Notes
 
@@ -412,3 +549,32 @@ This skill is designed to be invoked after `speccrew-knowledge-techs-generate` c
 - `techs-dispatch` to determine if re-generation is needed
 - Development teams to identify documentation issues
 - CI/CD pipelines to enforce documentation quality gates
+
+---
+
+## CONTINUOUS EXECUTION RULES
+
+This skill MUST execute all steps continuously without unnecessary interruptions.
+
+### FORBIDDEN Interruptions
+
+1. DO NOT ask user "Should I continue?" after completing a step
+2. DO NOT suggest "Let me split this into batches" or "Let's do this in parts"
+3. DO NOT pause to list what you plan to do next — just do it
+4. DO NOT ask for confirmation before generating output files
+5. DO NOT warn about "large number of files" — proceed with generation
+6. DO NOT offer "Should I proceed with the remaining items?"
+7. DO NOT present options like "Full execution / Sample execution / Pause"
+
+### When to Pause (ONLY these cases)
+
+1. Explicit `<event action="confirm">` blocks in the workflow
+2. Ambiguous requirements that genuinely need clarification
+3. Unrecoverable errors that prevent further progress
+4. Security-sensitive operations (e.g., deleting existing files)
+
+### Execution Behavior
+
+- When multiple checks need to be performed, execute ALL of them sequentially without asking
+- Continue execution even if individual checks fail — record failures and proceed
+- NEVER voluntarily stop mid-process to ask if user wants to continue