specweave 0.33.4 → 0.33.6

package/plugins/specweave/commands/judge-llm.md

@@ -0,0 +1,296 @@
+---
+name: sw:judge-llm
+description: Ultrathink LLM-as-Judge validation of completed work. Uses extended thinking by DEFAULT for thorough evaluation.
+---
+
+# /sw:judge-llm - Ultrathink LLM-as-Judge Validation
+
+**ULTRATHINK BY DEFAULT** - Validate completed work using extended thinking and the LLM-as-Judge pattern.
+
+## CRITICAL: Extended Thinking is DEFAULT
+
+This command ALWAYS uses **ultrathink (extended thinking)** for thorough LLM-as-Judge evaluation:
+
+```
+DEFAULT BEHAVIOR = ULTRATHINK MODE
+- Extended thinking enabled
+- Deep chain-of-thought reasoning
+- Thorough multi-dimensional analysis
+- ~60-90 seconds for comprehensive evaluation
+```
+
+Use `--quick` only if you explicitly need faster (but less thorough) validation.
+
+## Purpose
+
+Use when you've completed work and want **maximum-quality AI validation**:
+- Works on **any files** (not just SpecWeave increments)
+- Uses **ultrathink extended thinking** for deepest analysis
+- Returns **clear verdict** with detailed reasoning
+
+## Usage
+
+```bash
+# DEFAULT: Ultrathink validation (recommended)
+/sw:judge-llm src/file.ts
+/sw:judge-llm "src/**/*.ts"
+
+# Validate git changes (ultrathink by default)
+/sw:judge-llm --staged           # Staged changes
+/sw:judge-llm --last-commit      # Last commit
+/sw:judge-llm --diff main        # Diff vs branch
+
+# Quick mode (ONLY if you need speed over thoroughness)
+/sw:judge-llm src/file.ts --quick
+
+# Additional options
+/sw:judge-llm src/file.ts --strict   # Fail on any concern
+/sw:judge-llm src/file.ts --fix      # Include fix suggestions
+/sw:judge-llm src/file.ts --export   # Export report to markdown
+```
+
+## How It Works
+
+When you invoke `/sw:judge-llm`, Claude will:
+
+### Step 1: Gather Input
+
+Determine what to validate:
+- If file paths provided → read those files
+- If `--staged` → get staged git changes
+- If `--last-commit` → get files from last commit
+- If `--diff <branch>` → get diff against branch
+- If no args → validate recent work in conversation context
+
+### Step 2: ULTRATHINK Analysis (Default)
+
+**MANDATORY**: Use extended thinking for deep LLM-as-Judge evaluation:
+
+```
+Claude MUST use ultrathink/extended thinking to:
+
+1. **DEEP READ**: Thoroughly understand all code, context, and intent
+2. **MULTI-DIMENSIONAL ANALYSIS**: Evaluate across ALL dimensions:
+   - Correctness: Does it work exactly as intended?
+   - Completeness: ALL edge cases handled? ALL requirements met?
+   - Security: ANY vulnerabilities? OWASP Top 10 checked?
+   - Performance: Algorithmic complexity? Memory usage? Bottlenecks?
+   - Maintainability: Clean? Clear? Follows conventions?
+   - Testability: Can it be tested? Are tests adequate?
+   - Error handling: All failure modes covered?
+3. **CRITICAL EVALUATION**: Weigh ALL findings by severity
+4. **REASONED VERDICT**: Form verdict based on thorough analysis
+```
+
+### Step 3: Return Verdict
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+JUDGE-LLM VERDICT: APPROVED | CONCERNS | REJECTED
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+Mode: ULTRATHINK (extended thinking)
+Confidence: 0.XX
+Files Analyzed: N
+
+REASONING:
+[Detailed chain-of-thought from extended thinking]
+
+ISSUES (if any):
+🔴 CRITICAL: [title]
+   [description]
+   📍 [file:line]
+   💡 [suggestion]
+
+🟡 HIGH: [title]
+   ...
+
+🟢 LOW: [title]
+   ...
+
+VERDICT: [summary sentence]
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+```
+
+## Verdict Meanings
+
+| Verdict | Meaning | Action |
+|---------|---------|--------|
+| **APPROVED** | Work is solid, no significant issues | Safe to proceed |
+| **CONCERNS** | Issues found worth addressing | Review and fix recommended |
+| **REJECTED** | Critical issues found | MUST fix before proceeding |
+
+## Validation Modes
+
+### Default Mode (ULTRATHINK) - RECOMMENDED
+- **Extended thinking ENABLED by default**
+- Most thorough validation (~60-90 seconds)
+- Deep multi-dimensional analysis
+- Best for any completed work
+- Cost: ~$0.10-0.25
+
+### Quick Mode (`--quick`)
+- Fast validation (~10-15 seconds)
+- Standard reasoning (no extended thinking)
+- Good for quick sanity checks during development
+- Cost: ~$0.02-0.05
+
+### Strict Mode (`--strict`)
+- Any concern results in REJECTED
+- Use for critical paths, security code, or CI gates
+- Combines with ultrathink by default
+
+## Examples
+
+### Example 1: Default ultrathink validation
+
+```
+User: /sw:judge-llm src/core/auth/login.ts
+
+Claude: [Uses extended thinking for deep analysis]
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+JUDGE-LLM VERDICT: APPROVED
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+Mode: ULTRATHINK (extended thinking)
+Confidence: 0.91
+Files Analyzed: 1
+
+REASONING:
+After thorough analysis with extended thinking:
+
+The login implementation demonstrates excellent security practices:
+- Password hashing uses bcrypt with cost factor 12 (appropriate)
+- Rate limiting implemented correctly (5 attempts, 15 min exponential backoff)
+- Input validation prevents SQL injection and XSS
+- Error messages are generic (don't leak user existence)
+- Session tokens use cryptographically secure random generation
+- CSRF protection properly implemented
+
+Edge cases handled:
+- Empty input validation ✓
+- Unicode normalization for usernames ✓
+- Timing attack mitigation via constant-time comparison ✓
+
+No security, performance, or maintainability issues found.
+
+VERDICT: Production-ready implementation with excellent security posture.
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+```
+
+### Example 2: Validate staged changes
+
+```
+User: /sw:judge-llm --staged
+
+Claude: [Uses extended thinking]
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+JUDGE-LLM VERDICT: CONCERNS
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+Mode: ULTRATHINK (extended thinking)
+Confidence: 0.84
+Files Analyzed: 3
+
+REASONING:
+Extended thinking analysis of staged changes reveals:
+
+Positive aspects:
+- New API endpoint follows existing patterns
+- TypeScript types are correct
+- Error handling present
+
+However, thorough analysis found issues:
+
+🟡 HIGH: Missing Input Validation
+   User input passed to database without sanitization
+   📍 src/api/users.ts:45
+   💡 Add Zod schema validation:
+   ```typescript
+   const schema = z.object({ userId: z.string().uuid() });
+   const { userId } = schema.parse(req.body);
+   ```
+
+🟡 HIGH: Information Disclosure Risk
+   Stack traces exposed in error responses
+   📍 src/api/users.ts:62
+   💡 Use production error handler that sanitizes output
+
+🟢 LOW: Missing rate limiting
+   New endpoint has no rate limiting
+   📍 src/api/users.ts:30
+   💡 Add rate limiter middleware
+
+VERDICT: Address HIGH issues before merging. LOW can be follow-up.
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+```
+
+### Example 3: Quick validation (when needed)
+
+```
+User: /sw:judge-llm src/utils/format.ts --quick
+
+Claude: [Standard reasoning, no extended thinking]
+
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+JUDGE-LLM VERDICT: APPROVED
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+Mode: QUICK (standard reasoning)
+Confidence: 0.75
+Files Analyzed: 1
+
+REASONING:
+Utility formatting functions look correct. No obvious issues.
+
+VERDICT: Looks good for a utility file.
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+```
+
+## Simplest Usage
+
+Just say in your prompt:
+```
+"judge-llm my work"
+"use judge-llm"
+"judge-llm this"
+```
+
+Claude will:
+1. Automatically gather context from the conversation
+2. Use ULTRATHINK extended thinking by default
+3. Apply thorough LLM-as-Judge evaluation
+
+## Difference from /sw:qa
+
+| Aspect | `/sw:qa` | `/sw:judge-llm` |
+|--------|-----------------|------------------------|
+| **Scope** | Increments only | Any files |
+| **Input** | Increment ID | Files, git diff, context |
+| **Default Mode** | Standard | **ULTRATHINK** |
+| **Pattern** | 7-dimension scoring | Judge LLM reasoning |
+| **Focus** | Spec quality, risks | Code correctness |
+| **When** | Before increment close | After any work |
+
+## Best Practices
+
+1. **Use by default**: Ultrathink is worth the extra time for quality
+2. **Use `--staged`**: Validate before committing
+3. **Use `--strict` for critical code**: Payment, auth, security
+4. **Fix CRITICAL issues immediately**: Never ignore these
+5. **Trust the ultrathink analysis**: Extended thinking catches subtle issues
+
+## Limitations
+
+- ❌ Doesn't execute tests (use test runners)
+- ❌ Doesn't auto-apply fixes (only suggests)
+- ❌ May miss domain-specific issues
+- ❌ Not a replacement for human review
+
+## Related
+
+- `/sw:qa` - Increment-bound quality assessment
+- `/sw:validate` - Rule-based increment validation
+- `ado-sync-judge` agent - Uses judge pattern for sync validation

package/plugins/specweave/commands/{specweave-living-docs.md → living-docs.md}

@@ -1,12 +1,12 @@
 ---
-name: specweave:living-docs
+name: sw:living-docs
 description: Launch or resume Living Docs Builder independently. Generates documentation from codebase analysis with AI-powered insights.
-usage: /specweave:living-docs [--resume <jobId>] [--depth <level>] [--priority <modules>] [--sources <folders>] [--depends-on <jobIds>] [--foreground]
+usage: /sw:living-docs [--resume <jobId>] [--depth <level>] [--priority <modules>] [--sources <folders>] [--depends-on <jobIds>] [--foreground] [--full-scan]
 ---
 
 # Living Docs Builder (Standalone)
 
-**Usage**: `/specweave:living-docs [options]`
+**Usage**: `/sw:living-docs [options]`
 
 ---
 
@@ -31,7 +31,8 @@ Launch the Living Docs Builder independently of `specweave init`. This is essent
 | `--sources <folders>` | Additional doc folders (comma-separated): `docs/,wiki/` |
 | `--depends-on <jobIds>` | Wait for jobs before starting (comma-separated) |
 | `--foreground` | Run in current session instead of background |
-| `--full` | Force full rebuild by clearing cache and checkpoints (bypasses incremental mode) |
+| `--force` | Force run even for greenfield projects |
+| `--full-scan` | **Force full deep scan** - All phases (repos, org, arch, inconsistencies, strategy) |
 
 ---
 
@@ -40,7 +41,7 @@ Launch the Living Docs Builder independently of `specweave init`. This is essent
 ### Launch New Analysis (Interactive)
 
 ```bash
-/specweave:living-docs
+/sw:living-docs
 
 # Prompts for:
 # 1. Analysis depth (quick/standard/deep-native/deep-api)
@@ -53,13 +54,13 @@ Launch the Living Docs Builder independently of `specweave init`. This is essent
 
 ```bash
 # Check for orphaned jobs first
-/specweave:jobs
+/sw:jobs
 
 # If you see an orphaned living-docs-builder job:
-/specweave:living-docs --resume abc12345
+/sw:living-docs --resume abc12345
 
 # Or let it auto-detect:
-/specweave:living-docs
+/sw:living-docs
 # → "Found orphaned job abc12345. Resume? [Y/n]"
 ```
 
@@ -67,16 +68,16 @@ Launch the Living Docs Builder independently of `specweave init`. This is essent
 
 ```bash
 # Quick scan - 5-10 minutes
-/specweave:living-docs --depth quick
+/sw:living-docs --depth quick
 
 # Standard analysis - 15-30 minutes
-/specweave:living-docs --depth standard --priority auth,payments
+/sw:living-docs --depth standard --priority auth,payments
 
 # AI-powered deep analysis (FREE with MAX subscription)
-/specweave:living-docs --depth deep-native --priority core,api
+/sw:living-docs --depth deep-native --priority core,api
 
-# Force full rebuild (clears cache and checkpoints)
-/specweave:living-docs --full --depth standard
+# Force FULL deep scan (all phases: repos, org, arch, inconsistencies, strategy)
+/sw:living-docs --full-scan
 ```
 
 ---
@@ -90,6 +91,48 @@ Launch the Living Docs Builder independently of `specweave init`. This is essent
 | `deep-native` | Progress-based | AI analysis via Claude Code CLI | FREE (MAX) |
 | `deep-api` | Progress-based | AI analysis via API key | API costs |
 
+### Full Scan Mode (--full-scan)
+
+**What it does**: Forces a comprehensive deep analysis with ALL phases, regardless of brownfield detection.
+
+**When to use**:
+- Initial setup - want complete documentation structure
+- After major refactoring - need fresh analysis of everything
+- Imported external repos - want full org structure, inconsistencies, strategy docs
+- Complete living docs - need `review-needed/` and `strategy/` folders populated
+
+**What you get** (beyond standard depths):
+```
+.specweave/docs/internal/
+├── repos/                      # All repos analyzed (Phase B)
+│   └── {repo-name}/
+│       ├── overview.md
+│       └── api-surface.md
+├── organization/               # Team structure (Phase C)
+│   ├── teams/
+│   └── org-chart.mmd
+├── architecture/               # System architecture (Phase D)
+│   ├── adr/                   # Auto-detected ADRs
+│   └── system-architecture.md
+├── review-needed/              # Inconsistencies (Phase E) ✨
+│   ├── questions-for-cto.md
+│   ├── questions-for-po.md
+│   └── inconsistencies.md
+└── strategy/                   # Strategic recommendations (Phase F) ✨
+    ├── tech-debt-catalog.md
+    ├── modernization-candidates.md
+    └── recommendations.md
+```
+
+**Command**:
+```bash
+/sw:living-docs --full-scan
+
+# Uses deep-native if Claude MAX available, otherwise deep-api
+# Runs ALL phases: B → C → D → E → F
+# Duration: Variable (depends on project size)
+```
+
 ### Deep-Native (Recommended for MAX Users)
 
 Uses your Claude MAX subscription via `claude --print`:
@@ -99,10 +142,10 @@ Uses your Claude MAX subscription via `claude --print`:
 - Uses **Opus 4.5** for best quality
 
 ```bash
-/specweave:living-docs --depth deep-native
+/sw:living-docs --depth deep-native
 
 # Monitor progress:
-/specweave:jobs --follow <jobId>
+/sw:jobs --follow <jobId>
 ```
 
 ---
@@ -166,8 +209,8 @@ const { job, pid, isBackground } = await launchLivingDocsJob({
    Priority: auth, payments, api
    PID: 45678
 
-   Monitor: /specweave:jobs --follow ldb-abc12345
-   Logs: /specweave:jobs --logs ldb-abc12345
+   Monitor: /sw:jobs --follow ldb-abc12345
+   Logs: /sw:jobs --logs ldb-abc12345
 
 💡 This job runs in background and survives terminal close.
    Output will be saved to:
@@ -194,7 +237,7 @@ When resuming a job:
 
 ```bash
 # Example: Job crashed during deep-dive phase
-/specweave:living-docs --resume abc12345
+/sw:living-docs --resume abc12345
 
 # Output:
 # Resuming from checkpoint: phase=deep-dive, module=auth (5/18)
@@ -210,10 +253,10 @@ For umbrella projects with clone/import jobs:
 
 ```bash
 # Launch after clone completes
-/specweave:living-docs --depends-on clone-xyz123 --depth standard
+/sw:living-docs --depends-on clone-xyz123 --depth standard
 
 # Launch after both clone and import complete
-/specweave:living-docs --depends-on clone-xyz123,import-abc456
+/sw:living-docs --depends-on clone-xyz123,import-abc456
 ```
 
 The job will:
@@ -284,11 +327,11 @@ After completion:
 # Claude crashed after init, living docs job orphaned
 
 # Step 1: Check what's there
-/specweave:jobs
+/sw:jobs
 # Shows: [ldb-abc123] living-docs-builder - ORPHANED (worker died)
 
 # Step 2: Resume
-/specweave:living-docs --resume ldb-abc123
+/sw:living-docs --resume ldb-abc123
 
 # Output:
 # ✅ Resuming Living Docs Builder (ldb-abc123)
@@ -300,12 +343,12 @@ After completion:
 
 ```bash
 # Focus on critical modules first
-/specweave:living-docs --depth deep-native \
+/sw:living-docs --depth deep-native \
   --priority auth,payments,billing,core \
   --depends-on clone-main123
 
 # Monitor in another terminal
-/specweave:jobs --follow ldb-xyz789
+/sw:jobs --follow ldb-xyz789
 ```
 
 ### Example 3: CI/CD Integration
@@ -325,10 +368,10 @@ specweave jobs --wait ldb-latest  # Wait for completion
 
 ### Worker Crashed
 ```
-/specweave:jobs
+/sw:jobs
 # Shows: ORPHANED status
 
-/specweave:living-docs --resume <jobId>
+/sw:living-docs --resume <jobId>
 # Resumes from last checkpoint
 ```
 
@@ -346,15 +389,15 @@ Some repositories may be missing from analysis.
 ℹ️  No existing code detected (greenfield project)
     Living docs will sync automatically as you create increments.
 
-    To force analysis anyway: /specweave:living-docs --force
+    To force analysis anyway: /sw:living-docs --force
 ```
 
 ---
 
 ## See Also
 
-- `/specweave:jobs` - Monitor all background jobs
-- `/specweave:import-docs` - Import existing documentation
+- `/sw:jobs` - Monitor all background jobs
+- `/sw:import-docs` - Import existing documentation
 - `specweave:brownfield-analyzer` skill - Analyze doc gaps
 - `specweave:brownfield-onboarder` skill - Merge existing docs
 

package/plugins/specweave/commands/migrate-config.md

@@ -1,5 +1,5 @@
 ---
-name: specweave:migrate-config
+name: sw:migrate-config
 description: Migrate .env-only configuration to split secrets/config format (v0.24.0+)
 ---
 
@@ -100,5 +100,5 @@ Variables classified as **config** (move to config.json):
 **See also:**
 
 - ADR-0050: Secrets vs Configuration Separation
-- `/specweave:validate` - Validate configuration after migration
+- `/sw:validate` - Validate configuration after migration
 - Documentation: `CLAUDE.md` → Configuration Management section

package/plugins/specweave/commands/{specweave-next.md → next.md}

@@ -1,5 +1,5 @@
 ---
-name: specweave:next
+name: sw:next
 description: Smart increment transition - auto-close current if ready, intelligently suggest next work (backlog or new feature)
 ---
 
@@ -14,7 +14,7 @@ You are helping the user complete their current increment and move to the next o
 ## Usage
 
 ```bash
-/specweave:next
+/sw:next
 ```
 
 **No arguments needed** - the command intelligently handles the transition.
@@ -23,7 +23,7 @@ You are helping the user complete their current increment and move to the next o
 
 ## What This Does
 
-The `/specweave:next` command is your **workflow continuation** command. It:
+The `/sw:next` command is your **workflow continuation** command. It:
 
 1. **Validates current increment** - Checks if work is complete
 2. **Transitions to ready_for_review** - If all tasks done, auto-transitions to `ready_for_review`
@@ -195,7 +195,7 @@ AskUserQuestion({
 
 Running quality assessment to validate implementation...
 
-/specweave:qa 0001
+/sw:qa 0001
 
 Overall Score: 87/100 (GOOD) ✓
 
@@ -267,7 +267,7 @@ What would you like to do? [A/B/C]
 
 1. **Invoke QA command automatically**:
    ```bash
-   /specweave:qa ${incrementId}
+   /sw:qa ${incrementId}
    ```
 
 2. **Quality assessment evaluates**:
@@ -420,7 +420,7 @@ Proceeding to next work...
       Example: /specweave inc "Admin dashboard"
 
    B. Check existing ideas → Look in .specweave/increments/_backlog/
-      If you have ideas saved, promote them with /specweave:increment
+      If you have ideas saved, promote them with /sw:increment
 
    C. Review roadmap → See .specweave/docs/internal/strategy/roadmap.md
 
@@ -435,7 +435,7 @@ Proceeding to next work...
 
 **User**:
 ```bash
-/specweave:next
+/sw:next
 ```
 
 **Output**:
@@ -510,7 +510,7 @@ Next Action: Run `/specweave do 0002` to begin
 
 **User**:
 ```bash
-/specweave:next
+/sw:next
 ```
 
 **Output**:
@@ -552,7 +552,7 @@ Next Action: Run `/specweave do 0001` to resume at T010
 
 **User**:
 ```bash
-/specweave:next
+/sw:next
 ```
 
 **Output**:
@@ -592,7 +592,7 @@ Options:
 
 **User**:
 ```bash
-/specweave:next
+/sw:next
 ```
 
 **Output**:
@@ -626,16 +626,16 @@ Your choice? [A/B/C] _
 
 | Command | Purpose | When to Use |
 |---------|---------|-------------|
-| `/specweave:increment "feature"` | Create NEW increment with specific feature | Starting fresh work |
-| `/specweave:do` | Execute tasks in increment | Implementing planned work |
-| `/specweave:progress` | Check status (no action) | Quick status check |
-| `/specweave:done` | Explicitly close increment | Manual closure with validation |
-| `/specweave:qa` | Quality assessment only | Standalone QA check |
-| `/specweave:next` ⭐ | **Smart transition** (close + QA + suggest next) | **Natural workflow continuation** |
-
-**Why `/specweave:next` is special**:
+| `/sw:increment "feature"` | Create NEW increment with specific feature | Starting fresh work |
+| `/sw:do` | Execute tasks in increment | Implementing planned work |
+| `/sw:progress` | Check status (no action) | Quick status check |
+| `/sw:done` | Explicitly close increment | Manual closure with validation |
+| `/sw:qa` | Quality assessment only | Standalone QA check |
+| `/sw:next` ⭐ | **Smart transition** (close + QA + suggest next) | **Natural workflow continuation** |
+
+**Why `/sw:next` is special**:
 - ✅ Combines validation + closure + **quality assessment** + suggestion in one command
-- ✅ No need to remember `/specweave:done` then `/specweave:qa` then `/specweave:increment` sequence
+- ✅ No need to remember `/sw:done` then `/sw:qa` then `/sw:increment` sequence
 - ✅ Intelligent suggestions (backlog, WIP, new work)
 - ✅ User stays in control (never forces actions)
 - ✅ Natural "what's next?" workflow
@@ -645,7 +645,7 @@ Your choice? [A/B/C] _
 
 ## Best Practices
 
-1. **Run `/specweave:next` when you feel done** - It validates completion and suggests next steps
+1. **Run `/sw:next` when you feel done** - It validates completion and suggests next steps
 2. **Trust the PM validation** - If gates fail, there's unfinished work
 3. **Follow recommendations** - Backlog items are already planned
 4. **Keep WIP limit in mind** - Don't force multiple increments

package/plugins/specweave/commands/{specweave-notifications.md → notifications.md}

@@ -5,13 +5,13 @@ View and manage sync notifications - import completions, discrepancies, sync fai
 ## Usage
 
 ```bash
-/specweave:notifications                     # List pending notifications
-/specweave:notifications --all               # Include dismissed notifications
-/specweave:notifications --type sync-failure # Filter by type
-/specweave:notifications --severity warning  # Filter by severity
-/specweave:notifications show <id>           # Show notification details
-/specweave:notifications dismiss <id>        # Dismiss a notification
-/specweave:notifications dismiss-all         # Dismiss all pending notifications
+/sw:notifications                     # List pending notifications
+/sw:notifications --all               # Include dismissed notifications
+/sw:notifications --type sync-failure # Filter by type
+/sw:notifications --severity warning  # Filter by severity
+/sw:notifications show <id>           # Show notification details
+/sw:notifications dismiss <id>        # Dismiss a notification
+/sw:notifications dismiss-all         # Dismiss all pending notifications
 ```
 
 ## Arguments
@@ -40,8 +40,8 @@ notif-abc123   ❗ CRITICAL   GitHub sync failed           2m ago
 notif-def456   ⚠️ WARNING    2 discrepancies in FS-045    1h ago
 notif-ghi789   ℹ️ INFO       107 items imported           3h ago
 
-Use '/specweave:notifications show <id>' to view details
-Use '/specweave:notifications dismiss <id>' to dismiss
+Use '/sw:notifications show <id>' to view details
+Use '/sw:notifications dismiss <id>' to dismiss
 ```
 
 ### show <id>
@@ -88,5 +88,5 @@ Proceed? [y/N]: y
 
 ## Related
 
-- `/specweave:sync-monitor`: Dashboard showing notification summary
-- `/specweave:discrepancies`: View and act on discrepancy notifications
+- `/sw:sync-monitor`: Dashboard showing notification summary
+- `/sw:discrepancies`: View and act on discrepancy notifications