specweave 0.32.2 → 0.32.5

package/plugins/specweave/skills/code-standards-analyzer/SKILL.md

@@ -408,9 +408,15 @@ Full standards: .specweave/docs/internal/governance/coding-standards.md"
 ### Supported Languages
 - ✅ TypeScript (primary)
 - ✅ JavaScript (ES6+)
-- 🔜 Python (future)
-- 🔜 Java (future)
-- 🔜 Go (future)
+- ✅ Python (pyproject.toml, .pylintrc, ruff.toml, .flake8, mypy.ini)
+- ✅ Java/Kotlin (checkstyle.xml, pmd.xml, spotbugs.xml, detekt.yml)
+- ✅ Go (go.mod, .golangci.yml, staticcheck.conf)
+- ✅ C#/.NET (.editorconfig, StyleCop.json, Directory.Build.props)
+- ✅ Rust (rustfmt.toml, clippy.toml, Cargo.toml)
+- ✅ React (package.json, ESLint plugin:react/*)
+- ✅ Angular (angular.json, ESLint @angular-eslint)
+- ✅ Vue (package.json, ESLint plugin:vue/*)
+- ✅ Svelte (package.json, svelte.config.js)
 
 ### Detection Algorithms
 
@@ -439,14 +445,60 @@ Full standards: .specweave/docs/internal/governance/coding-standards.md"
 
 1. **Implicit Standards**: Requires representative codebase sample
 2. **False Positives**: Anti-pattern detection may flag intentional code
-3. **Language Support**: Currently TypeScript/JavaScript only
-4. **Context**: Can't understand business rationale for patterns
+3. **Context**: Can't understand business rationale for patterns
+
+---
+
+## Multi-Technology Support
+
+**Status**: ✅ Implemented (increment 0122-multi-technology-governance)
+
+| Technology | Config Files | Status |
+|------------|--------------|--------|
+| TypeScript/JavaScript | `.eslintrc.*`, `.prettierrc`, `tsconfig.json` | ✅ Implemented |
+| Python | `pyproject.toml`, `.pylintrc`, `ruff.toml`, `.flake8`, `mypy.ini` | ✅ Implemented |
+| Go | `go.mod`, `.golangci.yml`, `staticcheck.conf` | ✅ Implemented |
+| Java/Kotlin | `checkstyle.xml`, `pmd.xml`, `spotbugs.xml`, `detekt.yml` | ✅ Implemented |
+| C#/.NET | `.editorconfig`, `StyleCop.json`, `Directory.Build.props` | ✅ Implemented |
+| Rust | `rustfmt.toml`, `clippy.toml`, `Cargo.toml` | ✅ Implemented |
+| React | ESLint + `plugin:react/*`, `package.json` | ✅ Implemented |
+| Angular | `angular.json`, `.eslintrc` | ✅ Implemented |
+| Vue | ESLint + `plugin:vue/*`, `vite.config.*` | ✅ Implemented |
+| Svelte | `svelte.config.js`, `package.json` | ✅ Implemented |
+
+**Output Structure:**
+```
+.specweave/docs/internal/governance/
+├── coding-standards.md          # Unified summary of ALL technologies
+├── shared-conventions.md        # EditorConfig, Git conventions
+└── standards/
+    ├── typescript.md
+    ├── python.md
+    ├── golang.md
+    ├── java.md
+    ├── react.md
+    ├── angular.md
+    ├── vue.md
+    └── svelte.md
+```
+
+**Usage**:
+```typescript
+import {
+  detectEcosystems,
+  parsePythonStandards,
+  parseGoStandards,
+  parseJavaStandards,
+  parseFrontendStandards,
+  generateStandardsMarkdown,
+  generateUnifiedSummary
+} from 'src/core/living-docs/governance/index.js';
+```
 
 ---
 
 ## Future Enhancements
 
-- [ ] Multi-language support (Python, Java, Go)
 - [ ] Auto-generate ESLint rules from detected patterns
 - [ ] AI-powered suggestions from top OSS projects
 - [ ] Team-specific standards in multi-project mode

package/plugins/specweave/skills/increment-planner/SKILL.md

@@ -176,39 +176,68 @@ echo "Using coverageTarget: $coverageTarget"
 
 **Store these values for use in STEP 4 and STEP 7!**
 
-### STEP 0B: Detect Structure Level & Select Project/Board (MANDATORY!)
+### STEP 0B: Get Project Context (MANDATORY - BLOCKING!)
 
-**⚠️ CRITICAL: Before generating spec.md, you MUST know the target project (and board for 2-level structures)!**
+**⛔ DO NOT PROCEED TO STEP 1 WITHOUT COMPLETING THIS STEP!**
 
-**Structure Levels:**
-- **1-Level**: `internal/specs/{project}/FS-XXX/` - requires `project` in spec.md
-- **2-Level**: `internal/specs/{project}/{board}/FS-XXX/` - requires BOTH `project` AND `board`
+Before generating ANY spec.md content, you MUST run this CLI command:
+
+```bash
+specweave context projects
+```
 
-**Detection Logic** (use `src/utils/structure-level-detector.ts`):
+This returns JSON with available projects and structure level:
 
-```typescript
-import { detectStructureLevel, getRequiredSpecFields } from './utils/structure-level-detector.js';
-
-const structureConfig = detectStructureLevel(projectRoot);
-console.log(`Structure level: ${structureConfig.level}`);
-console.log(`Detection reason: ${structureConfig.detectionReason}`);
-console.log(`Available projects: ${structureConfig.projects.map(p => p.id).join(', ')}`);
-
-if (structureConfig.level === 2 && structureConfig.boardsByProject) {
-  console.log('Available boards by project:');
-  for (const [projectId, boards] of Object.entries(structureConfig.boardsByProject)) {
-    console.log(`  ${projectId}: ${boards.map(b => b.id).join(', ')}`);
-  }
+```json
+{
+  "level": 1,
+  "projects": [{"id": "my-app", "name": "My App"}],
+  "detectionReason": "multiProject configuration",
+  "source": "multi-project"
 }
 ```
 
-**Manual Detection:**
+**For 2-level structures**, output includes boards:
+```json
+{
+  "level": 2,
+  "projects": [{"id": "acme-corp", "name": "ACME Corporation"}],
+  "boardsByProject": {
+    "acme-corp": [
+      {"id": "digital-ops", "name": "Digital Operations"},
+      {"id": "mobile-team", "name": "Mobile Team"}
+    ]
+  },
+  "detectionReason": "ADO area path mapping configured",
+  "source": "ado-area-path"
+}
+```
+
+**VALIDATION RULES:**
+
+```
+✅ REQUIRED: Parse the JSON output and use ONLY those project/board values
+✅ REQUIRED: project field MUST match one of the returned projects[].id
+✅ REQUIRED: board field (2-level) MUST match one of boardsByProject[project].id
+❌ FORBIDDEN: Inventing or guessing project names
+❌ FORBIDDEN: Using folder name as project (e.g., "sw-olysense")
+❌ FORBIDDEN: Creating spec.md with {{PROJECT_ID}} placeholder
+❌ FORBIDDEN: Creating spec.md for 2-level without board: field
+```
+
+**Structure Levels:**
+- **1-Level**: `internal/specs/{project}/FS-XXX/` - requires `project` in spec.md
+- **2-Level**: `internal/specs/{project}/{board}/FS-XXX/` - requires BOTH `project` AND `board`
+
+**Alternative: Interactive Selection:**
 ```bash
-# Check if 2-level (ADO area paths or JIRA boards)
-jq '.sync.profiles | to_entries[] | select(.value.provider == "ado") | .value.config.areaPathMapping' .specweave/config.json
+specweave context select
+# Returns auto-selected or prompts for selection
+```
 
-# Check existing folder structure
-ls -la .specweave/docs/internal/specs/*/  # If sub-folders exist (not FS-XXX) → 2-level
+**Get boards for a specific project (2-level):**
+```bash
+specweave context boards --project=acme-corp
 ```
 
 **Project/Board Selection - ULTRA-SMART LOGIC (MANDATORY BEFORE STEP 4!):**
@@ -217,6 +246,70 @@ ls -la .specweave/docs/internal/specs/*/  # If sub-folders exist (not FS-XXX)
 
 ---
 
+### RULE 0: LEVERAGE ALL AVAILABLE CONTEXT (v0.33.0+ CRITICAL!)
+
+**🧠 YOU ARE AN LLM WITH FULL CONTEXT ACCESS - USE IT!**
+
+Before asking the user ANYTHING about project/board, you MUST analyze:
+
+**1. Living Docs Structure** (`.specweave/docs/internal/specs/`):
+```bash
+# List existing project folders
+ls -la .specweave/docs/internal/specs/
+# Example output: frontend-app/, backend-api/, mobile-app/, shared-lib/
+```
+→ These ARE the actual project IDs! Use them directly.
+
+**2. Existing Increment Patterns** (`.specweave/increments/`):
+```bash
+# Read recent increments to see project assignments
+grep -r "^\*\*Project\*\*:" .specweave/increments/*/spec.md | tail -20
+```
+→ Learn from how past USs were assigned to projects.
+
+**3. Config projectMappings** (`.specweave/config.json`):
+```bash
+cat .specweave/config.json | jq '.projectMappings'
+```
+→ Use ACTUAL project IDs from config, not generic keywords.
+
+**4. Git Remotes** (for repo-based projects):
+```bash
+git remote -v | head -2
+```
+→ If repo is `myorg/frontend-app`, that's likely the project.
+
+**5. Feature Description + US Content**:
+- Analyze the feature user is describing
+- Match against project patterns from above sources
+- Map generic terms to actual project IDs
+
+**MAPPING EXAMPLE:**
+```
+User says: "Add login form to the frontend"
+You detect: "frontend" keyword
+
+WRONG: Assign project = "frontend" (generic, may not exist!)
+RIGHT: Check living docs → find "frontend-app" folder → Assign project = "frontend-app"
+```
+
+**RESOLUTION PRIORITY:**
+```
+1. Exact match in projectMappings keys → USE IT
+2. Exact match in living docs folders → USE IT
+3. Pattern match in recent increment specs → USE SAME PROJECT
+4. Keyword → Map to closest projectMappings/folder
+5. ONLY IF ALL ABOVE FAIL → Ask user with dropdown of valid options
+```
+
+**FORBIDDEN:**
+- ❌ Inventing project names not in config/folders
+- ❌ Using generic keywords ("frontend") when actual ID exists ("frontend-app")
+- ❌ Asking user when context provides clear answer
+- ❌ Assigning `{{PROJECT_ID}}` placeholder
+
+---
+
 ### SMART SELECTION DECISION TREE
 
 **RULE 1: NO QUESTION IF ONLY 1 OPTION**
@@ -225,9 +318,20 @@ IF 1-level AND only 1 project → AUTO-SELECT silently
 IF 2-level AND only 1 project AND only 1 board → AUTO-SELECT silently
 ```
 
-**RULE 2: KEYWORD-BASED AUTO-DETECTION**
+**RULE 2: KEYWORD-BASED AUTO-DETECTION (v0.33.0+)**
 
-Analyze feature description and US content for keywords:
+Use `CrossCuttingDetector` utility for programmatic detection:
+
+```typescript
+import { detectCrossCutting } from 'src/utils/cross-cutting-detector.js';
+
+const result = detectCrossCutting("OAuth with React frontend and Node backend");
+// result.isCrossCutting = true
+// result.suggestedProjects = ["frontend", "backend"]
+// result.confidence = "high"
+```
+
+Or analyze feature description and US content for keywords:
 
 **Project-Level Keywords (1-level and 2-level):**
 ```
@@ -766,19 +870,21 @@ When creating tasks, assign optimal models:
 - Simple CRUD, configuration, setup
 - Mechanical work with defined approach
 
-**🧠 Sonnet** (thinking, balanced):
+**💎 Opus** (best quality, default):
 - Architecture decisions
 - Multiple valid approaches
 - Integration between components
 - Complex business logic
 - Error handling strategies
-
-**💎 Opus** (critical, expensive):
 - Critical system architecture
 - Security-critical decisions
 - Performance-critical algorithms
 - Novel problem-solving
 
+**🧠 Sonnet** (legacy, rarely needed):
+- Use only for backwards compatibility
+- Prefer Opus or Haiku instead
+
 ---
 
 ## Validation Checklist

package/plugins/specweave/skills/increment-planner/templates/spec-multi-project.md

@@ -8,8 +8,10 @@ created: {{DATE}}
 structure: user-stories
 test_mode: {{TEST_MODE}}
 coverage_target: {{COVERAGE_TARGET}}
-default_project: {{PROJECT_ID}}
-default_board: {{BOARD_ID}}
+# MANDATORY: Run "specweave context projects" to get valid project/board IDs
+# For 2-level structures: BOTH project AND board are REQUIRED
+project: {{PROJECT_ID}}
+board: {{BOARD_ID}}
 multi_project: true
 projects:
   - id: {{PROJECT_FE_ID}}

package/plugins/specweave/skills/increment-planner/templates/spec-single-project.md

@@ -8,7 +8,8 @@ created: {{DATE}}
 structure: user-stories
 test_mode: {{TEST_MODE}}
 coverage_target: {{COVERAGE_TARGET}}
-default_project: {{PROJECT_ID}}
+# MANDATORY: Run "specweave context projects" to get valid project ID
+project: {{PROJECT_ID}}
 ---
 
 # Feature: {{FEATURE_TITLE}}

package/plugins/specweave/skills/increment-planner/templates/tasks-multi-project.md

@@ -6,7 +6,7 @@
 - `[P]`: Parallelizable
 - `[ ]`: Not started
 - `[x]`: Completed
-- Model hints: ⚡ haiku, 🧠 sonnet, 💎 opus
+- Model hints: ⚡ haiku (simple), 💎 opus (default)
 
 ## Phase 1: Foundation & Setup
 

package/plugins/specweave/skills/increment-planner/templates/tasks-single-project.md

@@ -6,7 +6,7 @@
 - `[P]`: Parallelizable
 - `[ ]`: Not started
 - `[x]`: Completed
-- Model hints: ⚡ haiku, 🧠 sonnet, 💎 opus
+- Model hints: ⚡ haiku (simple), 💎 opus (default)
 
 ## Phase 1: Setup
 

package/plugins/specweave/skills/spec-generator/SKILL.md

@@ -66,18 +66,53 @@ board: my-board              # REQUIRED for 2-level structures (ADO area paths,
 ## User Stories & Acceptance Criteria
 
 <!--
-⚠️ MULTI-PROJECT MODE: If umbrella.enabled=true in config.json,
-   user stories MUST be project-scoped! See section below.
+⚠️ PER-US PROJECT TARGETING (v0.33.0+):
+Each user story MUST have **Project**: (and **Board**: for 2-level) fields.
+The LLM MUST resolve these from context - see RULE 0 in increment-planner.
 -->
 
 ### US-001: [Title]
+**Project**: [resolved-from-context]    <!-- REQUIRED - actual project ID from config/folders -->
+**Board**: [resolved-from-context]      <!-- REQUIRED for 2-level structures -->
+
 **As a** [user type]
 **I want** [goal]
 **So that** [benefit]
 
 **Acceptance Criteria**:
-- ✅ [Criterion 1]
-- ✅ [Criterion 2]
+- [ ] **AC-US1-01**: [Criterion 1]
+- [ ] **AC-US1-02**: [Criterion 2]
+
+---
+
+### Per-US Project Resolution (v0.33.0+ MANDATORY)
+
+**🧠 USE ALL AVAILABLE CONTEXT TO RESOLVE PROJECT/BOARD:**
+
+Before generating spec.md, analyze:
+1. **Living docs folders**: `ls .specweave/docs/internal/specs/` → actual project IDs
+2. **Recent increment patterns**: `grep "**Project**:" .specweave/increments/*/spec.md`
+3. **Config projectMappings**: Exact project IDs from config
+4. **Feature keywords**: Map to actual projects (not generic terms)
+
+**Resolution Example:**
+```
+Feature: "Add OAuth login to React frontend"
+Detected: "React", "frontend", "login"
+
+Step 1: Check living docs → folders: frontend-app/, backend-api/, shared/
+Step 2: "frontend" keyword → matches "frontend-app" folder
+Step 3: Assign **Project**: frontend-app (NOT "frontend"!)
+
+If cross-cutting ("OAuth" = both frontend + backend):
+  US-001 (Login UI) → **Project**: frontend-app
+  US-002 (Auth API) → **Project**: backend-api
+```
+
+**NEVER:**
+- ❌ Use generic keywords as project names ("frontend", "backend")
+- ❌ Ask user when context provides the answer
+- ❌ Leave `{{PROJECT_ID}}` placeholders
 
 ## Success Metrics
 [How we'll measure success]
@@ -392,9 +427,45 @@ spec_generator:
 - Multiple project folders exist in `specs/` (e.g., `sw-app-fe/`, `sw-app-be/`, `sw-app-shared/`)
 - User prompt mentions: "3 repos", "frontend repo", "backend API", "shared library"
 
-### Project-Scoped User Story Format (MANDATORY in Multi-Project Mode)
+### Per-User-Story Project Targeting (v0.33.0+ PREFERRED)
+
+**v0.33.0+ introduces per-US project targeting** - each user story specifies its target project inline:
+
+```markdown
+## User Stories
+
+### US-001: Thumbnail Upload & Comparison (P1)
+**Project**: frontend-app
+**Board**: ui-team        <!-- 2-level structures only -->
+**As a** content creator
+**I want** to upload multiple thumbnail variants
+**So that** I can visually evaluate my options
+
+**Acceptance Criteria**:
+- [ ] **AC-US1-01**: User can drag-and-drop up to 5 images
+
+---
+
+### US-002: CTR Prediction API (P1)
+**Project**: backend-api
+**Board**: ml-team        <!-- 2-level structures only -->
+**As a** frontend application
+**I want** to call POST /predict-ctr endpoint
+**So that** I can get AI-powered predictions
+
+**Acceptance Criteria**:
+- [ ] **AC-US2-01**: POST /predict-ctr accepts thumbnail image
+```
+
+**Benefits of per-US targeting:**
+- Each US syncs to correct project/repo
+- Single increment can span multiple projects
+- Living docs auto-grouped by project
+- External tools (GitHub/JIRA/ADO) receive issues in correct project
+
+### Legacy Project-Scoped User Story Format (Pre-v0.33.0)
 
-**❌ WRONG (Single-Project Format - DO NOT USE in multi-project!):**
+**❌ LEGACY (Project prefixes - still works but per-US targeting preferred):**
 ```markdown
 ## User Stories
 
@@ -405,7 +476,7 @@ As a content creator, I want to upload thumbnails...
 As a system, I want to predict click-through rates...
 ```
 
-**✅ CORRECT (Multi-Project Format - ALWAYS USE when umbrella detected!):**
+**✅ LEGACY (Multi-Project Format with prefixes - use per-US targeting instead):**
 ```markdown
 ## User Stories by Project
 

package/plugins/specweave-ado/commands/cleanup-duplicates.md

@@ -0,0 +1,212 @@
+---
+name: specweave-ado:cleanup-duplicates
+description: Clean up duplicate Azure DevOps work items for a Feature. Finds work items with duplicate titles and closes all except the first created item.
+justification: |
+  CRITICAL INCIDENT RESPONSE TOOL - DO NOT DELETE!
+
+  Why This Command Exists:
+  - Prevention systems work for single-process execution
+  - Multiple parallel Claude Code instances bypass all prevention (file-based cache, no distributed locking)
+  - ADO API race conditions: Time gap between "check exists" and "create work item" allows duplicates
+  - Historical duplicates from pre-v0.33.0 users (before prevention was added)
+
+  Evidence of Need:
+  - GitHub had 123 duplicate issues incident (cleaned to 29 unique) - same risk exists for ADO
+  - Parallel execution creates race conditions that prevention CANNOT solve
+  - Industry standard: Prevention + Detection + Cleanup (defense in depth)
+
+  When to Delete:
+  - ONLY if distributed locking implemented
+  - AND parallel execution tested (100+ concurrent syncs with zero duplicates)
+  - AND zero duplicates for 6+ months in production
+---
+
+# Clean Up Duplicate ADO Work Items
+
+**CRITICAL**: This command detects and closes duplicate ADO work items created by multiple syncs.
+
+## Usage
+
+```bash
+/specweave-ado:cleanup-duplicates <feature-id> [--dry-run]
+```
+
+## What It Does
+
+**Duplicate Detection & Cleanup**:
+
+1. **Find all work items** for the Feature (searches by Feature ID in title)
+2. **Group by title** (detect duplicates)
+3. **For each duplicate group**:
+   - Keep the **FIRST created** work item (lowest ID)
+   - Close all **LATER** work items with comment: "Duplicate of #XXX"
+4. **Update Feature README** with correct work item IDs
+
+## Examples
+
+### Dry Run (No Changes)
+
+```bash
+/specweave-ado:cleanup-duplicates FS-031 --dry-run
+```
+
+**Output**:
+```
+Scanning for duplicates in Feature FS-031...
+   Found 25 total work items
+   Detected 10 duplicate groups:
+
+   Group 1: "[FS-031] External Tool Status Synchronization"
+      - #1250 (KEEP) - Created 2025-11-10
+      - #1255 (CLOSE) - Created 2025-11-11 - DUPLICATE
+      - #1260 (CLOSE) - Created 2025-11-12 - DUPLICATE
+
+   Group 2: "[FS-031] Multi-Project ADO Sync"
+      - #1251 (KEEP) - Created 2025-11-10
+      - #1256 (CLOSE) - Created 2025-11-11 - DUPLICATE
+
+   ...
+
+Dry run complete!
+   Total work items: 25
+   Duplicate groups: 10
+   Work items to close: 15
+
+This was a DRY RUN - no changes made.
+   Run without --dry-run to actually close duplicates.
+```
+
+### Actual Cleanup
+
+```bash
+/specweave-ado:cleanup-duplicates FS-031
+```
+
+**Output**:
+```
+Scanning for duplicates in Feature FS-031...
+   Found 25 total work items
+   Detected 10 duplicate groups
+
+CONFIRM: Close 15 duplicate work items? [y/N]
+> y
+
+Closing duplicates...
+   Closed #1255 (duplicate of #1250)
+   Closed #1256 (duplicate of #1251)
+   Closed #1260 (duplicate of #1250)
+   ...
+
+Updating Feature README frontmatter...
+   Updated frontmatter with correct work item IDs
+
+Cleanup complete!
+   Closed: 15 duplicates
+   Kept: 10 original work items
+```
+
+## Arguments
+
+- `<feature-id>` - Feature ID (e.g., `FS-031` or just `031`)
+- `--dry-run` - Preview changes without actually closing work items (optional)
+
+## Safety Features
+
+- **Confirmation prompt**: Asks before closing work items (unless --dry-run)
+- **Dry run mode**: Preview changes safely
+- **Keeps oldest work item**: Preserves the first created item
+- **Adds closure comment**: Links to the original work item
+- **Updates metadata**: Fixes Feature README frontmatter
+
+## What Gets Closed
+
+**Closed work items**:
+- Duplicate titles (second, third, etc. occurrences)
+- Closed with comment: "Duplicate of #XXX"
+- Original work item kept open (or maintains its status)
+
+**Example comment on closed duplicate**:
+```markdown
+## Duplicate of #1250
+
+This work item was automatically closed by SpecWeave cleanup because it is a duplicate.
+
+The original work item (#1250) contains the same content and should be used for tracking instead.
+
+Auto-closed by SpecWeave Duplicate Cleanup
+```
+
+## Requirements
+
+1. **Azure DevOps PAT** configured (`AZURE_DEVOPS_PAT`)
+2. **Organization** configured (`AZURE_DEVOPS_ORG`)
+3. **Project** configured (`AZURE_DEVOPS_PROJECT`)
+4. **Write access** to project (for closing work items)
+5. **Feature folder exists** at `.specweave/docs/internal/specs/FS-XXX-name/`
+
+## When to Use
+
+**Use this command when**:
+- You see multiple work items with the same title in ADO
+- Feature sync ran multiple times and created duplicates
+- Feature README frontmatter got corrupted and reset
+- Post-sync validation warns about duplicates
+
+**Example warning that triggers this**:
+```
+WARNING: 10 duplicate(s) detected!
+   Run cleanup command to resolve:
+   /specweave-ado:cleanup-duplicates FS-031
+```
+
+## Architecture
+
+**Duplicate Detection Logic**:
+1. Query WIQL for work items with Feature ID in title
+2. Group work items by **exact title match**
+3. Within each group, sort by **work item ID** (ascending)
+4. Keep **first work item** (lowest ID = oldest)
+5. Close **all others** as duplicates via state transition
+
+**Why lowest ID?**:
+- Lower work item IDs were created first
+- Preserves chronological order
+- Maintains links from old documentation
+
+## Related Commands
+
+- `/specweave-ado:sync` - Sync Feature to ADO (with duplicate detection)
+- `/specweave-ado:reconcile` - Reconcile work item states
+- `/specweave:validate` - Validate increment completeness
+
+## Implementation
+
+**File**: `plugins/specweave-ado/lib/ado-duplicate-detector.ts`
+
+**Class**: `AdoDuplicateDetector`
+
+**Algorithm** (3-phase protection):
+1. **Detection**: WIQL query for existing work items matching pattern
+2. **Verification**: Count check to detect duplicates after creation
+3. **Reflection**: Auto-close duplicates automatically
+
+For manual cleanup:
+1. WIQL query for all work items with Feature ID
+2. Group by title (Map<string, number[]>)
+3. Filter groups with >1 item (duplicates)
+4. For each duplicate group:
+   - Keep first work item (lowest ID)
+   - Close others via ADO REST API
+
+## Next Steps
+
+After cleanup:
+
+1. **Verify cleanup**: Check ADO for remaining work items
+2. **Check Feature FEATURE.md**: Verify frontmatter has correct work item IDs
+3. **Re-run sync**: `/specweave-ado:sync` (should show no duplicates)
+4. **Duplicate detection**: Automatically enabled via AdoDuplicateDetector
+
+---
+
+**SAFE TO USE**: This command is idempotent and safe to run multiple times.