specweave 1.0.223 → 1.0.224

package/CLAUDE.md

@@ -1,4 +1,4 @@
-<!-- SW:META template="claude" version="1.0.222" sections="header,start,autodetect,metarule,rules,workflow,reflect,context,structure,taskformat,secrets,syncing,testing,tdd,api,limits,troubleshooting,lazyloading,principles,linking,mcp,auto,docs" -->
+<!-- SW:META template="claude" version="1.0.223" sections="header,start,autodetect,metarule,rules,workflow,reflect,context,structure,taskformat,secrets,syncing,testing,tdd,api,limits,troubleshooting,lazyloading,principles,linking,mcp,auto,docs" -->
 
 <!-- SW:SECTION:hook-priority version="1.0.171" -->
 ## ⛔ Hook Instructions Override Everything
@@ -13,7 +13,7 @@
 **SKILL FIRST ≠ only one skill.** Chain: hook skill → `sw-frontend:*` / `sw-backend:*` / etc → implement.
 <!-- SW:END:hook-priority -->
 
-<!-- SW:SECTION:header version="1.0.222" -->
+<!-- SW:SECTION:header version="1.0.223" -->
 **Framework**: SpecWeave | **Truth**: `spec.md` + `tasks.md`
 <!-- SW:END:header -->
 
@@ -123,7 +123,7 @@ claude plugin install sw@specweave --scope project  # Team-shared
 
 SpecWeave auto-installs: LSP → project scope, sw-* → user scope.
 
-<!-- SW:SECTION:start version="1.0.222" -->
+<!-- SW:SECTION:start version="1.0.223" -->
 ## Getting Started
 
 **Initial increment**: `0001-project-setup` (auto-created by `specweave init`)
@@ -133,7 +133,7 @@ SpecWeave auto-installs: LSP → project scope, sw-* → user scope.
 2. **Customize**: Edit spec.md and use for setup tasks
 <!-- SW:END:start -->
 
-<!-- SW:SECTION:autodetect version="1.0.222" -->
+<!-- SW:SECTION:autodetect version="1.0.223" -->
 ## Auto-Detection
 
 SpecWeave auto-detects product descriptions and routes to `/sw:increment`:
@@ -143,7 +143,7 @@ SpecWeave auto-detects product descriptions and routes to `/sw:increment`:
 **Opt-out phrases**: "Just brainstorm first" | "Don't plan yet" | "Quick discussion" | "Let's explore ideas"
 <!-- SW:END:autodetect -->
 
-<!-- SW:SECTION:metarule version="1.0.222" -->
+<!-- SW:SECTION:metarule version="1.0.223" -->
 ## Workflow Orchestration
 
 ### 1. Plan Mode Default
@@ -170,7 +170,7 @@ SpecWeave auto-detects product descriptions and routes to `/sw:increment`:
 ```
 <!-- SW:END:metarule -->
 
-<!-- SW:SECTION:rules version="1.0.222" -->
+<!-- SW:SECTION:rules version="1.0.223" -->
 ## Rules
 
 1. **Files** → `.specweave/increments/####-name/` (see Structure section for details)
@@ -189,7 +189,7 @@ SpecWeave auto-detects product descriptions and routes to `/sw:increment`:
    Use next available number. **NEVER create duplicate prefixes.**
 <!-- SW:END:rules -->
 
-<!-- SW:SECTION:workflow version="1.0.222" -->
+<!-- SW:SECTION:workflow version="1.0.223" -->
 ## Workflow
 
 `/sw:increment "X"` → `/sw:do` → `/sw:progress` → `/sw:done 0001`
@@ -235,7 +235,7 @@ project/
 **NEVER assume single-repo mode without scanning first!**
 <!-- SW:END:save-nested-repos -->
 
-<!-- SW:SECTION:reflect version="1.0.222" -->
+<!-- SW:SECTION:reflect version="1.0.223" -->
 ## Skill Memories
 
 SpecWeave learns from corrections. Learnings saved here automatically. Edit or delete as needed.
@@ -257,7 +257,7 @@ SpecWeave learns from corrections. Learnings saved here automatically. Edit or d
 - **2026-02-04**: Use subagents liberally for codebase analysis - up to 10+ concurrent for large-scale exploration
 - **2026-02-04**: Prefer leaderboard-style reporting when analyzing usage patterns or identifying deletion candidates
 
-<!-- SW:SECTION:context version="1.0.222" -->
+<!-- SW:SECTION:context version="1.0.223" -->
 ## Context
 
 **Before implementing**: Check ADRs at `.specweave/docs/internal/architecture/adr/`
@@ -265,7 +265,7 @@ SpecWeave learns from corrections. Learnings saved here automatically. Edit or d
 **Load context**: `/sw:context <topic>` loads relevant living docs into conversation
 <!-- SW:END:context -->
 
-<!-- SW:SECTION:structure version="1.0.222" -->
+<!-- SW:SECTION:structure version="1.0.223" -->
 ## Structure
 
 ```
@@ -280,7 +280,7 @@ SpecWeave learns from corrections. Learnings saved here automatically. Edit or d
 **Everything else → subfolders**: `reports/` | `logs/` | `scripts/` | `backups/`
 <!-- SW:END:structure -->
 
-<!-- SW:SECTION:taskformat version="1.0.222" -->
+<!-- SW:SECTION:taskformat version="1.0.223" -->
 ## Task Format
 
 ```markdown
@@ -290,7 +290,7 @@ SpecWeave learns from corrections. Learnings saved here automatically. Edit or d
 ```
 <!-- SW:END:taskformat -->
 
-<!-- SW:SECTION:secrets version="1.0.222" -->
+<!-- SW:SECTION:secrets version="1.0.223" -->
 ## Secrets Check
 
 **BEFORE CLI tools**: Check existing config first!
@@ -304,7 +304,7 @@ gh auth status
 **SECURITY**: NEVER use `grep TOKEN .env` without `-q` flag - it exposes credentials in terminal!
 <!-- SW:END:secrets -->
 
-<!-- SW:SECTION:syncing version="1.0.222" -->
+<!-- SW:SECTION:syncing version="1.0.223" -->
 ## External Sync (GitHub/JIRA/ADO)
 
 **Commands**: `/sw-github:sync {id}` (issues) | `/sw:sync-specs` (living docs only)
@@ -314,7 +314,7 @@ gh auth status
 **Config**: Set `sync.github.enabled: true` + `canUpdateExternalItems: true` in config.json
 <!-- SW:END:syncing -->
 
-<!-- SW:SECTION:testing version="1.0.222" -->
+<!-- SW:SECTION:testing version="1.0.223" -->
 ## Testing
 
 BDD in tasks.md | Unit >80% | `.test.ts` (Vitest)
@@ -326,7 +326,7 @@ vi.mock('./module', () => ({ func: mockFn }));
 ```
 <!-- SW:END:testing -->
 
-<!-- SW:SECTION:tdd version="1.0.222" -->
+<!-- SW:SECTION:tdd version="1.0.223" -->
 ## TDD Mode (Test-Driven Development)
 
 **When `testing.defaultTestMode: "TDD"` is configured**, follow RED-GREEN-REFACTOR discipline:
@@ -387,7 +387,7 @@ When TDD is enabled, tasks include phase markers:
 **Rule**: Complete dependencies BEFORE dependent tasks (RED before GREEN).
 <!-- SW:END:tdd -->
 
-<!-- SW:SECTION:api version="1.0.222" -->
+<!-- SW:SECTION:api version="1.0.223" -->
 ## API Development (OpenAPI-First)
 
 **For API projects only.** Commands: `/sw:api-docs --all` | `--openapi` | `--postman` | `--validate`
@@ -395,13 +395,13 @@ When TDD is enabled, tasks include phase markers:
 Enable in config: `{"apiDocs":{"enabled":true,"openApiPath":"openapi.yaml"}}`
 <!-- SW:END:api -->
 
-<!-- SW:SECTION:limits version="1.0.222" -->
+<!-- SW:SECTION:limits version="1.0.223" -->
 ## Limits
 
 **Max 1500 lines/file** — extract before adding
 <!-- SW:END:limits -->
 
-<!-- SW:SECTION:troubleshooting version="1.0.222" -->
+<!-- SW:SECTION:troubleshooting version="1.0.223" -->
 ## Troubleshooting
 
 | Issue | Fix |
@@ -414,7 +414,7 @@ Enable in config: `{"apiDocs":{"enabled":true,"openApiPath":"openapi.yaml"}}`
 | Session stuck | Kill + `rm -f .specweave/state/*.lock` + restart |
 <!-- SW:END:troubleshooting -->
 
-<!-- SW:SECTION:lazyloading version="1.0.222" -->
+<!-- SW:SECTION:lazyloading version="1.0.223" -->
 ## Plugin Auto-Loading
 
 Plugins load automatically based on project type and keywords. Manual install if needed:
@@ -428,7 +428,7 @@ export SPECWEAVE_DISABLE_AUTO_LOAD=1         # Disable auto-load
 **Token savings**: Core ~3-5K tokens vs all plugins ~60K+
 <!-- SW:END:lazyloading -->
 
-<!-- SW:SECTION:principles version="1.0.222" -->
+<!-- SW:SECTION:principles version="1.0.223" -->
 ## Principles
 
 ### SpecWeave Principles
@@ -444,7 +444,7 @@ export SPECWEAVE_DISABLE_AUTO_LOAD=1         # Disable auto-load
 - **Demand Elegance**: For non-trivial changes, pause and ask "is there a more elegant way?" - but skip this for simple, obvious fixes (don't over-engineer).
 <!-- SW:END:principles -->
 
-<!-- SW:SECTION:linking version="1.0.222" -->
+<!-- SW:SECTION:linking version="1.0.223" -->
 ## Bidirectional Linking
 
 Tasks ↔ User Stories auto-linked via AC-IDs: `AC-US1-01` → `US-001`
@@ -452,7 +452,7 @@ Tasks ↔ User Stories auto-linked via AC-IDs: `AC-US1-01` → `US-001`
 Task format: `**AC**: AC-US1-01, AC-US1-02` (CRITICAL for linking)
 <!-- SW:END:linking -->
 
-<!-- SW:SECTION:mcp version="1.0.222" -->
+<!-- SW:SECTION:mcp version="1.0.223" -->
 ## External Services
 
 **Priority**: CLI tools first (simpler) → MCP for complex integrations
@@ -474,7 +474,7 @@ claude mcp add --transport stdio postgres -- npx -y @modelcontextprotocol/server
 MCP supports lazy-loading (auto mode) - tools load on-demand when >10% context.
 <!-- SW:END:mcp -->
 
-<!-- SW:SECTION:auto version="1.0.222" -->
+<!-- SW:SECTION:auto version="1.0.223" -->
 ## Auto Mode
 
 **Commands**: `/sw:auto` (start) | `/sw:auto-status` (check) | `/sw:cancel-auto` (emergency only)
@@ -491,7 +491,7 @@ MCP supports lazy-loading (auto mode) - tools load on-demand when >10% context.
 **STOP & ASK** if: Spec conflicts | Task unnecessary | Requirement ambiguous
 <!-- SW:END:auto -->
 
-<!-- SW:SECTION:docs version="1.0.222" -->
+<!-- SW:SECTION:docs version="1.0.223" -->
 ## Docs
 
 [spec-weave.com](https://spec-weave.com)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "specweave",
-  "version": "1.0.223",
+  "version": "1.0.224",
   "description": "Spec-driven development framework for Claude Code. AI-native workflow with living documentation, intelligent agents, and multilingual support (9 languages). Enterprise-grade traceability with permanent specs and temporary increments.",
   "type": "module",
   "main": "dist/index.js",

package/plugins/specweave/skills/skill/SKILL.md

@@ -1,12 +1,211 @@
 ---
 name: skill
-description: Create Claude Code skills with proper YAML frontmatter, validation, and best practices
-argument-hint: [--name skill-name] [--type auto|command|knowledge]
+description: Create and validate Claude Code skills with proper YAML frontmatter. Use for skill creation, validation, and auditing. Activates for: create skill, validate skill, audit skills, check skills, skill format, SKILL.md.
+argument-hint: [--validate [path]] [--audit] [--name skill-name] [--type auto|command|knowledge]
 ---
 
-# Skill Creator
+# Skill Creator & Validator
 
-Create Claude Code skills with proper YAML frontmatter, validation, and best practices.
+Create and validate Claude Code skills with proper YAML frontmatter, validation, and best practices.
+
+## Modes
+
+| Mode | Command | Description |
+|------|---------|-------------|
+| **Create** | `/sw:skill` | Interactive skill creation |
+| **Validate** | `/sw:skill --validate [path]` | Validate single skill |
+| **Audit** | `/sw:skill --audit` | Audit ALL skills in project |
+
+---
+
+## Validation Mode (`--validate`)
+
+Validate a single skill file against official Anthropic format.
+
+### Usage
+
+```bash
+/sw:skill --validate                           # Validate current skill (if in skill dir)
+/sw:skill --validate plugins/specweave/skills/pm/SKILL.md
+/sw:skill --validate .claude/skills/my-skill/SKILL.md
+```
+
+### Validation Checks (Official Anthropic Format)
+
+Run these checks on every SKILL.md:
+
+#### 1. Frontmatter Structure
+```
+[  ] File starts with `---` on line 1
+[  ] Closing `---` present before markdown content
+[  ] Valid YAML syntax between delimiters
+[  ] No tabs in YAML (spaces only)
+```
+
+#### 2. Required Fields
+```
+[  ] `name:` present (recommended)
+[  ] `description:` present (CRITICAL for activation)
+```
+
+#### 3. Name Validation
+```
+[  ] Matches pattern: ^[a-z0-9]([a-z0-9-]*[a-z0-9])?$
+[  ] Max 64 characters
+[  ] No consecutive hyphens
+[  ] Matches directory name (if directory-based)
+```
+
+#### 4. Description Quality
+```
+[  ] Under 1024 characters
+[  ] Contains activation keywords (e.g., "Use when...", "Activates for...")
+[  ] Front-loads the purpose (first sentence explains what it does)
+[  ] Not too generic (specific enough for auto-activation)
+```
+
+#### 5. Optional Fields (Valid Values)
+```
+[  ] `allowed-tools:` - valid tool names only (Read, Write, Edit, Grep, Glob, Bash, WebSearch, WebFetch, Task, etc.)
+[  ] `disable-model-invocation:` - boolean (true/false)
+[  ] `user-invocable:` - boolean (true/false)
+[  ] `model:` - valid model (sonnet, opus, haiku)
+[  ] `context:` - valid value (fork)
+[  ] `agent:` - valid subagent type if context:fork
+```
+
+#### 6. Content Quality
+```
+[  ] Has meaningful content after frontmatter
+[  ] Reasonable length (50-2000 lines recommended)
+[  ] No orphaned template placeholders ({placeholder})
+```
+
+### Output Format
+
+```
+## Skill Validation Report
+
+**File**: plugins/specweave/skills/pm/SKILL.md
+**Status**: PASS | WARN | FAIL
+
+### Checks
+| Check | Status | Details |
+|-------|--------|---------|
+| Frontmatter | PASS | Valid YAML |
+| Name | PASS | "pm" matches pattern |
+| Description | WARN | Missing activation keywords |
+| Tools | PASS | Valid tool list |
+| Content | PASS | 245 lines |
+
+### Issues Found
+- WARN: Description lacks "Activates for:" or "Use when" keywords
+- INFO: Consider adding trigger phrases for better auto-activation
+
+### Suggested Fix
+Add to description: "Activates for: product management, user stories, requirements"
+```
+
+---
+
+## Audit Mode (`--audit`)
+
+Comprehensive audit of ALL skills across project.
+
+### Usage
+
+```bash
+/sw:skill --audit                    # Audit all skills
+/sw:skill --audit --fix              # Audit and offer auto-fixes
+/sw:skill --audit --json             # Output as JSON
+```
+
+### Scan Locations
+
+1. **Project skills**: `.claude/skills/*/SKILL.md`
+2. **Plugin skills**: `plugins/*/skills/*/SKILL.md`
+3. **Legacy commands**: `plugins/*/commands/*.md` (check frontmatter)
+
+### Audit Report (Leaderboard Style)
+
+```
+## Skills Audit Report
+
+**Scanned**: 127 skills, 45 commands
+**Date**: 2026-02-03
+
+### Summary
+| Status | Count | Percentage |
+|--------|-------|------------|
+| PASS   | 98    | 77%        |
+| WARN   | 21    | 17%        |
+| FAIL   | 8     | 6%         |
+
+### Critical Issues (FAIL)
+| Location | Issue | Severity |
+|----------|-------|----------|
+| plugins/specweave-mobile/commands/build-config.md | Missing frontmatter | CRITICAL |
+| plugins/specweave-n8n/skills/n8n-workflow/SKILL.md | Invalid YAML | CRITICAL |
+| ... | ... | ... |
+
+### Warnings
+| Location | Issue |
+|----------|-------|
+| plugins/specweave/skills/pm/SKILL.md | Description lacks keywords |
+| plugins/specweave-frontend/skills/react-expert/SKILL.md | Name too long (67 chars) |
+| ... | ... |
+
+### By Plugin (Worst First)
+| Plugin | Pass | Warn | Fail | Score |
+|--------|------|------|------|-------|
+| specweave-mobile | 2 | 3 | 2 | 57% |
+| specweave-n8n | 4 | 2 | 1 | 71% |
+| specweave-testing | 8 | 1 | 0 | 94% |
+| specweave | 25 | 3 | 0 | 94% |
+| ... | ... | ... | ... | ... |
+
+### Auto-Fix Available
+8 issues can be auto-fixed. Run `/sw:skill --audit --fix`
+```
+
+### Auto-Fix Capabilities
+
+| Issue | Auto-Fix |
+|-------|----------|
+| Missing frontmatter | Add minimal `---\nname: {from-filename}\ndescription: TODO\n---` |
+| Name mismatch | Update to match directory name |
+| Invalid characters in name | Convert to kebab-case |
+| Missing description | Add placeholder with TODO marker |
+
+---
+
+## Commands vs Skills: Clarification
+
+**Per official Anthropic docs (2025):**
+
+> "Custom slash commands have been merged into skills. A file at `.claude/commands/review.md` and a skill at `.claude/skills/review/SKILL.md` both create `/review` and work the same way."
+
+### Migration Recommendation
+
+| Format | Status | Recommendation |
+|--------|--------|----------------|
+| `commands/*.md` | Legacy | Migrate to skills or add frontmatter |
+| `skills/*/SKILL.md` | Current | Preferred format |
+
+### Command Frontmatter (If Keeping Commands)
+
+```yaml
+---
+name: test-init
+description: Initialize testing infrastructure with Vitest and Playwright
+argument-hint: [--framework vitest|jest]
+allowed-tools: [Read, Write, Edit, Bash]
+---
+```
+
+---
+
+## Create Mode (Interactive)
 
 **Quick skill scaffolding** - from concept to working skill in under 2 minutes.
 
@@ -307,3 +506,123 @@ allowed-tools: Read, Grep, Glob, WebSearch
 - Custom: specify tools you need
 
 Create your skill!
+
+---
+
+## Implementation: Validation Algorithm
+
+When running validation, use this algorithm:
+
+### Step 1: Find Skills to Validate
+
+```bash
+# For --audit mode, find all skills
+find plugins -name "SKILL.md" -type f 2>/dev/null
+find .claude/skills -name "SKILL.md" -type f 2>/dev/null
+
+# Also check commands for frontmatter compliance
+find plugins -path "*/commands/*.md" -type f 2>/dev/null
+```
+
+### Step 2: Parse Frontmatter
+
+For each file:
+1. Read file content
+2. Check if starts with `---`
+3. Find closing `---`
+4. Parse YAML between delimiters
+5. Extract fields: name, description, allowed-tools, etc.
+
+### Step 3: Run Validation Checks
+
+```typescript
+interface ValidationResult {
+  file: string;
+  status: 'PASS' | 'WARN' | 'FAIL';
+  checks: {
+    frontmatter: { status: string; details: string };
+    name: { status: string; details: string };
+    description: { status: string; details: string };
+    tools: { status: string; details: string };
+    content: { status: string; details: string };
+  };
+  issues: { severity: string; message: string }[];
+  suggestions: string[];
+}
+
+// Name pattern (official Anthropic spec)
+const NAME_PATTERN = /^[a-z0-9]([a-z0-9-]*[a-z0-9])?$/;
+const MAX_NAME_LENGTH = 64;
+const MAX_DESC_LENGTH = 1024;
+
+// Valid tools (Claude Code built-in)
+const VALID_TOOLS = [
+  'Read', 'Write', 'Edit', 'Grep', 'Glob', 'Bash',
+  'WebSearch', 'WebFetch', 'Task', 'TodoWrite',
+  'AskUserQuestion', 'Skill', 'NotebookEdit'
+];
+
+// Activation keyword patterns
+const ACTIVATION_PATTERNS = [
+  /activates? for:?/i,
+  /use when/i,
+  /triggers? on/i,
+  /invoke when/i,
+  /use this skill when/i
+];
+```
+
+### Step 4: Generate Report
+
+Use leaderboard format for audit mode:
+- Group by plugin
+- Sort by score (worst first for issues, best first for passing)
+- Calculate percentages
+- Identify auto-fixable issues
+
+### Step 5: Apply Fixes (if --fix)
+
+For auto-fixable issues:
+1. Backup original file
+2. Apply fix (add frontmatter, correct name, etc.)
+3. Re-validate to confirm fix worked
+4. Report changes made
+
+---
+
+## Official Anthropic Frontmatter Reference
+
+From https://code.claude.com/docs/en/skills:
+
+| Field | Required | Type | Description |
+|-------|----------|------|-------------|
+| `name` | Recommended | string | Identifier (kebab-case, max 64 chars) |
+| `description` | Recommended | string | When to use (max 1024 chars, include keywords) |
+| `argument-hint` | Optional | string | Hint for arguments (e.g., `[issue-number]`) |
+| `disable-model-invocation` | Optional | boolean | Prevent Claude auto-loading (default: false) |
+| `user-invocable` | Optional | boolean | Hide from / menu (default: true) |
+| `allowed-tools` | Optional | array | Tools Claude can use without permission |
+| `model` | Optional | string | Model override (sonnet, opus, haiku) |
+| `context` | Optional | string | Set to `fork` for subagent execution |
+| `agent` | Optional | string | Subagent type when context:fork |
+| `hooks` | Optional | object | Lifecycle hooks for this skill |
+
+### Invocation Control Matrix
+
+| Frontmatter | User Can Invoke | Claude Can Invoke | When Loaded |
+|-------------|-----------------|-------------------|-------------|
+| (default) | Yes | Yes | Description in context, full skill on invoke |
+| `disable-model-invocation: true` | Yes | No | Description NOT in context |
+| `user-invocable: false` | No | Yes | Description always in context |
+
+---
+
+## Troubleshooting Validation
+
+| Error | Cause | Fix |
+|-------|-------|-----|
+| "Invalid YAML" | Tabs, bad indentation, unclosed quotes | Use spaces, check syntax |
+| "Name mismatch" | `name:` differs from directory | Update to match directory name |
+| "No activation keywords" | Description too generic | Add "Activates for:" or "Use when" |
+| "Invalid tool" | Typo in allowed-tools | Check against VALID_TOOLS list |
+| "Missing frontmatter" | File doesn't start with `---` | Add YAML frontmatter block |

package/plugins/specweave-backend/commands/api-scaffold.md

@@ -1,3 +1,8 @@
+---
+name: api-scaffold
+description: Generate production-ready backend API structure with authentication, database, and best practices
+---
+
 # API Scaffolding Command
 
 Generate production-ready backend API structure with authentication, database, and best practices.

package/plugins/specweave-backend/commands/crud-generate.md

@@ -1,3 +1,8 @@
+---
+name: crud-generate
+description: Generate complete CRUD operations for a database entity including model, service, controller, DTOs, and tests
+---
+
 # CRUD Generator Command
 
 Generate complete CRUD (Create, Read, Update, Delete) operations for a database entity.

package/plugins/specweave-backend/commands/migration-generate.md

@@ -1,3 +1,8 @@
+---
+name: migration-generate
+description: Generate database migration files for schema changes with up/down migrations and safety checks
+---
+
 # Database Migration Generator
 
 Generate database migration files for schema changes.

package/plugins/specweave-confluent/commands/connector-deploy.md

@@ -1,3 +1,8 @@
+---
+name: connector-deploy
+description: Deploy and manage Kafka Connect source and sink connectors with configuration templates and deployment scripts.
+---
+
 # Kafka Connect Connector Deployment
 
 Deploy and manage Kafka Connect connectors (Source/Sink).

package/plugins/specweave-confluent/commands/ksqldb-query.md

@@ -1,3 +1,8 @@
+---
+name: ksqldb-query
+description: Generate ksqlDB queries for stream processing, aggregations, joins, and windowed operations.
+---
+
 # ksqlDB Query Generator
 
 Generate ksqlDB queries for stream processing.

package/plugins/specweave-confluent/commands/schema-register.md

@@ -1,3 +1,8 @@
+---
+name: schema-register
+description: Register and manage Avro, JSON Schema, and Protobuf schemas in Confluent Schema Registry.
+---
+
 # Schema Registry Management
 
 Manage Avro/JSON/Protobuf schemas in Confluent Schema Registry.

package/plugins/specweave-cost-optimizer/commands/cost-analyze.md

@@ -1,3 +1,8 @@
+---
+name: cost-analyze
+description: Analyze cloud infrastructure costs and identify optimization opportunities across AWS, Azure, and GCP.
+---
+
 # /sw-cost:cost-analyze
 
 Analyze cloud infrastructure costs and identify optimization opportunities across AWS, Azure, and GCP.

package/plugins/specweave-cost-optimizer/commands/cost-optimize.md

@@ -1,3 +1,8 @@
+---
+name: cost-optimize
+description: Implement cost optimization recommendations with automated resource modifications and savings plan purchases across AWS, Azure, and GCP.
+---
+
 # /sw-cost:cost-optimize
 
 Implement cost optimization recommendations with automated resource modifications and savings plan purchases.

package/plugins/specweave-diagrams/commands/diagrams-generate.md

@@ -1,3 +1,8 @@
+---
+name: diagrams-generate
+description: Generate Mermaid architecture diagrams following C4 Model conventions for system documentation.
+---
+
 # /sw-diagrams:diagrams-generate
 
 Generate Mermaid architecture diagrams following C4 Model conventions.

package/plugins/specweave-figma/commands/figma-import.md

@@ -1,3 +1,8 @@
+---
+name: figma-import
+description: Import Figma designs into your project using Figma REST API or MCP server integration.
+---
+
 # /sw-figma:import
 
 Import Figma designs into your project using Figma REST API or MCP server integration.

package/plugins/specweave-figma/commands/figma-to-react.md

@@ -1,3 +1,8 @@
+---
+name: figma-to-react
+description: Convert Figma components to production-ready React components with TypeScript, styled-components, and responsive design.
+---
+
 # /sw-figma:to-react
 
 Convert Figma components to production-ready React components with TypeScript, styled-components, and responsive design.

package/plugins/specweave-figma/commands/figma-tokens.md

@@ -1,3 +1,8 @@
+---
+name: figma-tokens
+description: Extract design tokens from Figma and generate token files for theme configuration (CSS variables, JavaScript, JSON, SCSS).
+---
+
 # /sw-figma:tokens
 
 Extract design tokens from Figma and generate token files for theme configuration (CSS variables, JavaScript, JSON, SCSS).

package/plugins/specweave-frontend/commands/component-generate.md

@@ -1,3 +1,8 @@
+---
+name: component-generate
+description: Generate React/Vue/Angular components with tests, Storybook stories, and documentation following Atomic Design principles.
+---
+
 # /sw-frontend:component-generate
 
 Generate React/Vue/Angular components with tests, stories, and documentation following Atomic Design principles.

package/plugins/specweave-frontend/commands/design-system-init.md

@@ -1,3 +1,8 @@
+---
+name: design-system-init
+description: Initialize a complete design system with Atomic Design principles, design tokens, theming, and component library foundation.
+---
+
 # /sw-frontend:design-system-init
 
 Initialize a complete design system with Atomic Design principles, design tokens, and component library.

package/plugins/specweave-frontend/commands/frontend-scaffold.md

@@ -1,3 +1,8 @@
+---
+name: frontend-scaffold
+description: Scaffold a complete frontend project with modern tooling, TypeScript, and best practices for React, Vue, Angular, or Next.js.
+---
+
 # /sw-frontend:frontend-scaffold
 
 Scaffold a complete frontend project with modern tooling and best practices.

package/plugins/specweave-frontend/commands/nextjs-setup.md

@@ -1,3 +1,8 @@
+---
+name: nextjs-setup
+description: Set up Next.js 14+ App Router project with Server Components, metadata configuration, and production-ready best practices.
+---
+
 # /sw-frontend:nextjs-setup
 
 Set up Next.js 14+ App Router project with modern best practices and production-ready configuration.

package/plugins/specweave-kubernetes/commands/cluster-setup.md

@@ -1,3 +1,8 @@
+---
+name: cluster-setup
+description: Set up a production-ready Kubernetes cluster with essential components including ingress, cert-manager, monitoring, and GitOps
+---
+
 # Kubernetes Cluster Setup
 
 Set up a production-ready Kubernetes cluster with essential components.

package/plugins/specweave-kubernetes/commands/deployment-generate.md

@@ -1,3 +1,8 @@
+---
+name: deployment-generate
+description: Generate production-ready Kubernetes deployment manifests including Deployment, Service, ConfigMap, Secret, and HPA resources
+---
+
 # Kubernetes Deployment Generator
 
 Generate production-ready Kubernetes deployment manifests.

package/plugins/specweave-kubernetes/commands/helm-scaffold.md

@@ -1,3 +1,8 @@
+---
+name: helm-scaffold
+description: Generate production-ready Helm charts with best practices including Chart.yaml, values files, and deployment templates
+---
+
 # Helm Chart Scaffolding
 
 Generate production-ready Helm charts with best practices.

package/plugins/specweave-mobile/commands/app-scaffold.md

@@ -1,3 +1,8 @@
+---
+name: app-scaffold
+description: Generate production-ready React Native application structure with navigation, state management, API client, and best practices.
+---
+
 # React Native App Scaffolding
 
 Generate production-ready React Native application structure.

package/plugins/specweave-mobile/commands/build-config.md

@@ -1,3 +1,8 @@
+---
+name: build-config
+description: Generate build configurations for iOS and Android mobile apps including Expo, EAS Build, environment variables, and CI/CD pipelines.
+---
+
 # Build Configuration
 
 Generate build configurations for iOS and Android.

package/plugins/specweave-mobile/commands/screen-generate.md

@@ -1,3 +1,8 @@
+---
+name: screen-generate
+description: Generate React Native screens with navigation integration, data fetching, form handling, and proper TypeScript typing.
+---
+
 # Screen Generator
 
 Generate React Native screens with navigation integration.

package/plugins/specweave-payments/commands/stripe-setup.md

@@ -1,3 +1,8 @@
+---
+name: stripe-setup
+description: Complete Stripe integration setup with checkout flows, payment intents, customer management, and security best practices
+---
+
 # /sw-payments:stripe-setup
 
 Complete Stripe integration setup guide with production-ready code templates, security best practices, and testing workflows.

package/plugins/specweave-payments/commands/subscription-flow.md

@@ -1,3 +1,8 @@
+---
+name: subscription-flow
+description: Implement complete subscription billing with pricing tiers, trials, upgrades/downgrades, proration, and lifecycle management
+---
+
 # /sw-payments:subscription-flow
 
 Complete subscription billing implementation guide with pricing tiers, trials, upgrades/downgrades, and lifecycle management.

package/plugins/specweave-payments/commands/subscription-manage.md

@@ -1,3 +1,8 @@
+---
+name: subscription-manage
+description: Generate a complete subscription management system with pricing tiers, billing, upgrades, cancellations, and usage tracking
+---
+
 # Subscription Management
 
 Generate complete subscription management system.

package/plugins/specweave-payments/commands/webhook-setup.md

@@ -1,3 +1,8 @@
+---
+name: webhook-setup
+description: Generate secure webhook handlers for payment providers including Stripe, PayPal, and Stripe Connect with signature verification and idempotency
+---
+
 # Payment Webhook Configuration
 
 Generate secure webhook handlers for payment providers, including Stripe Connect.

package/plugins/specweave-testing/commands/e2e-setup.md

@@ -1,3 +1,8 @@
+---
+name: e2e-setup
+description: Set up comprehensive Playwright E2E testing with best practices, page objects, and CI/CD integration.
+---
+
 # /sw-testing:e2e-setup
 
 Set up comprehensive Playwright E2E testing with best practices, page objects, and CI/CD integration.

package/plugins/specweave-testing/commands/test-coverage.md

@@ -1,3 +1,8 @@
+---
+name: test-coverage
+description: Analyze test coverage, identify gaps, generate reports, and provide actionable quality metrics.
+---
+
 # /sw-testing:test-coverage
 
 Comprehensive test coverage analysis, reporting, and quality metrics for modern test suites.

package/plugins/specweave-testing/commands/test-generate.md

@@ -1,3 +1,8 @@
+---
+name: test-generate
+description: Generate comprehensive unit, integration, and E2E tests from components, functions, and API endpoints.
+---
+
 # /sw-testing:test-generate
 
 Generate comprehensive unit, integration, and E2E tests from components, functions, and API endpoints.

package/plugins/specweave-testing/commands/test-init.md

@@ -1,3 +1,8 @@
+---
+name: test-init
+description: Initialize comprehensive testing infrastructure with Vitest, Playwright, and testing best practices.
+---
+
 # /sw-testing:test-init
 
 Initialize comprehensive testing infrastructure with Vitest, Playwright, and testing best practices.

package/plugins/specweave-testing/commands/ui-automate.md

@@ -1,3 +1,8 @@
+---
+name: ui-automate
+description: Create and execute automated browser workflows using Playwright for testing, web scraping, form automation, and UI interaction sequences.
+---
+
 # UI Automate - Browser Automation Workflows
 
 Create and execute automated browser workflows using Playwright. Generate scripts for testing, web scraping, form automation, and UI interaction sequences.

package/plugins/specweave-testing/commands/ui-inspect.md

@@ -1,3 +1,8 @@
+---
+name: ui-inspect
+description: Inspect web page elements using browser automation to identify selectors, attributes, and structure for testing and scraping.
+---
+
 # UI Inspect - Browser Element Inspection
 
 Inspect web page elements using browser automation tools. Helps identify selectors, attributes, and structure for automated testing and web scraping.