specweave 1.0.229 → 1.0.230

package/CLAUDE.md

@@ -495,7 +495,8 @@ MCP supports lazy-loading (auto mode) - tools load on-demand when >10% context.
 | **Completion** | `/sw:done` only (NEVER edit metadata.json) |
 | **Protected dirs** | NEVER delete `.specweave/docs/`, `.specweave/increments/` |
 | **Token budget** | ~80k/increment, max 25 tasks, max 1500 lines/file |
-| **Marketplace** | Contributors: `scripts/refresh-marketplace.sh` | Users: `specweave refresh-marketplace` |
+| **Marketplace** | Contributors: `scripts/refresh-marketplace.sh` \| Users: `specweave refresh-marketplace` |
+| **No `name:` in frontmatter** | NEVER use `name:` in SKILL.md/command frontmatter - it strips plugin prefix (`/sw:grill` → `/grill`) |
 
 ## Plugin Naming
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "specweave",
-  "version": "1.0.229",
+  "version": "1.0.230",
   "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/commands/abandon.md

@@ -1,7 +1,7 @@
 ---
-name: abandon
 description: Abandon an incomplete increment (requirements changed, obsolete)
 argument-hint: [increment-id] --reason="reason"
+disable-model-invocation: true
 ---
 
 # Abandon Increment Command

package/plugins/specweave/commands/analytics.md

@@ -1,5 +1,4 @@
 ---
-name: analytics
 description: Show usage analytics dashboard - command invocations, skill activations, agent spawns. Supports --export json/csv and --since filtering. Activates for analytics, usage stats, command stats, what commands used, skill usage, agent usage.
 ---
 

package/plugins/specweave/commands/api-docs.md

@@ -1,5 +1,4 @@
 ---
-name: api-docs
 description: Generate and synchronize API documentation - OpenAPI spec, Postman collection with environments, and API client SDKs. Framework-aware with auto-detection. For API projects only.
 argument-hint: [--openapi] [--postman] [--all] [--validate]
 ---

package/plugins/specweave/commands/archive.md

@@ -1,6 +1,6 @@
 ---
-name: archive
 description: Manually archive completed increments and sync living docs - NEVER auto-archives, explicit user action only
+disable-model-invocation: true
 ---
 
 # Archive Increments (Manual Only)

package/plugins/specweave/commands/auto-parallel.md

@@ -1,8 +1,8 @@
 ---
-name: auto-parallel
 description: Enable parallel agent execution for multi-domain features with git worktree isolation
 argument-hint: "[INCREMENT_ID] --frontend --backend [OPTIONS]"
 allowed-tools: ["Bash(specweave auto *)"]
+disable-model-invocation: true
 ---
 
 # Parallel Execution Mode

package/plugins/specweave/commands/brownfield-analyzer.md

@@ -1,6 +1,6 @@
 ---
-name: brownfield-analyzer
 description: Analyzes existing brownfield projects to map documentation to SpecWeave's structure (PRD/HLD/Spec/Runbook). Use when migrating existing projects to SpecWeave, scanning legacy docs, or creating project context maps. Detects external tools (JIRA, ADO, GitHub) and supports incremental or comprehensive migration paths.
+disable-model-invocation: true
 ---
 
 # Brownfield Analyzer

package/plugins/specweave/commands/brownfield-onboarder.md

@@ -1,6 +1,6 @@
 ---
-name: brownfield-onboarder
 description: Intelligently onboards brownfield projects by merging existing CLAUDE.md backups into SpecWeave structure. Use when installing SpecWeave into existing projects with CLAUDE.md, merging documentation, or importing project knowledge. Distributes content to appropriate folders without bloating main CLAUDE.md.
+disable-model-invocation: true
 ---
 
 # Brownfield Onboarder - Intelligent CLAUDE.md Merger

package/plugins/specweave/commands/check-hooks.md

@@ -1,5 +1,4 @@
 ---
-name: check-hooks
 description: Comprehensive health check for hooks - detects import errors, runtime failures, performance issues, and provides auto-fix suggestions
 ---
 

package/plugins/specweave/commands/code-reviewer.md

@@ -1,5 +1,4 @@
 ---
-name: code-reviewer
 description: Elite multi-agent code review system with confidence-based scoring. Launches parallel review agents for CLAUDE.md compliance, bug detection, security analysis, and git history context. Filters false positives with 80+ confidence threshold. Use for PR reviews, security audits, or post-implementation self-reflection.
 model: opus
 allowed-tools: Read, Edit, Glob, Grep, Bash, Task

package/plugins/specweave/commands/code-standards-analyzer.md

@@ -1,5 +1,4 @@
 ---
-name: code-standards-analyzer
 description: Generate and maintain coding standards documentation from existing codebase patterns. Use when creating STANDARDS.md files, onboarding new developers, documenting team conventions, analyzing naming conventions, detecting anti-patterns, or discovering implicit code standards. Evidence-based approach - standards reflect reality, not aspirations.
 allowed-tools: Read, Grep, Glob, Bash, Write, Edit
 ---

package/plugins/specweave/commands/discrepancies.md

@@ -1,5 +1,4 @@
 ---
-name: discrepancies
 description: View and manage code-to-spec discrepancies. Detects API changes, function signature mismatches, and documentation gaps. Supports brownfield analysis and code-spec comparison.
 ---
 

package/plugins/specweave/commands/discrepancy-to-increment.md

@@ -1,5 +1,4 @@
 ---
-name: discrepancy-to-increment
 description: Convert brownfield discrepancies into a new increment for systematic documentation improvement. Groups by module, generates spec with ACs, and tracks resolution.
 ---
 

package/plugins/specweave/commands/docs-writer.md

@@ -1,5 +1,4 @@
 ---
-name: docs-writer
 description: Technical documentation writer for clear, comprehensive docs with incremental generation to prevent crashes. Use when creating API documentation, README files, user guides, or developer onboarding docs. Generates one section at a time (Installation → Usage → API → Configuration).
 allowed-tools: Read, Write, Edit
 ---

package/plugins/specweave/commands/embed-acs.md

@@ -1,5 +1,4 @@
 ---
-name: embed-acs
 description: Auto-embed Acceptance Criteria from living docs into increment spec.md for hook compatibility
 ---
 

package/plugins/specweave/commands/export-skills.md

@@ -1,8 +1,8 @@
 ---
-name: export-skills
 description: Export SpecWeave skills to Agent Skills open standard format (agentskills.io) for cross-platform portability. Use when converting skills to GitHub Copilot, VS Code, Gemini CLI, or Cursor format. Creates portable SKILL.md files compatible with any Agent Skills-supported tool.
 visibility: public
 allowed-tools: Read, Write, Glob, Bash
+disable-model-invocation: true
 ---
 
 # Export Skills to Agent Skills Standard

package/plugins/specweave/commands/external.md

@@ -1,5 +1,4 @@
 ---
-name: external
 description: View external items dashboard - open issues from GitHub, JIRA, and Azure DevOps
 argument-hint: [--refresh]
 ---

package/plugins/specweave/commands/feature-dev.md

@@ -1,5 +1,4 @@
 ---
-name: feature-dev
 description: Feature Development Workflow - 7-phase structured approach for building features. Based on Anthropic's official feature-dev plugin. Activates for build feature, implement feature, feature development, feature workflow, structured development.
 argument-hint: "[FEATURE_DESCRIPTION]"
 ---

package/plugins/specweave/commands/fix-duplicates.md

@@ -1,6 +1,6 @@
 ---
-name: fix-duplicates
 description: Automatically detect and resolve duplicate increments with smart conflict resolution
+disable-model-invocation: true
 ---
 
 # Fix Duplicate Increments

package/plugins/specweave/commands/image-generation.md

@@ -1,5 +1,4 @@
 ---
-name: image-generation
 description: AI image generation using Pollinations.ai with Stable Horde fallback - FREE with no API key required. Use when generating hero images, icons, logos, illustrations, mockups, or any visual assets for websites and apps. Covers product shots, avatars, placeholders, and social media images with professional quality.
 allowed-tools:
   - Read
@@ -8,6 +7,7 @@ allowed-tools:
   - Bash
 context: fork
 model: opus
+disable-model-invocation: true
 ---
 
 # AI Image Generation Skill

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

@@ -1,6 +1,6 @@
 ---
-name: import-docs
 description: Import brownfield documentation from Notion exports, Confluence, GitHub Wiki, or any markdown folder. Automatically classifies files as specs, modules, team docs, or legacy.
+disable-model-invocation: true
 ---
 
 # Import Brownfield Documentation

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

@@ -1,6 +1,6 @@
 ---
-name: import-external
 description: AUTO-EXECUTE import of external work items (GitHub/JIRA/ADO) since last import. NO PROMPTS - immediately runs with defaults. Creates READ-ONLY references in living docs. Options available but NOT required.
+disable-model-invocation: true
 ---
 
 # Import External Work Items (Reference Import)

package/plugins/specweave/commands/increment-planner.md

@@ -1,5 +1,4 @@
 ---
-name: increment-planner
 description: Plan and create SpecWeave increments with PM and Architect agent collaboration. Use when starting new features, hotfixes, bugs, or any development work that needs specification and task breakdown. Creates spec.md, plan.md, tasks.md with proper AC-IDs and living docs integration.
 visibility: public
 context: fork

package/plugins/specweave/commands/jobs.md

@@ -1,5 +1,4 @@
 ---
-name: jobs
 description: Show current work status (active increments, progress) and background jobs (imports, cloning). Even with no jobs, shows increment summary and helpful context.
 argument-hint: [--all] [--id job-id]
 ---

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

@@ -1,5 +1,4 @@
 ---
-name: judge-llm
 description: Ultrathink LLM-as-Judge validation of completed work. Uses extended thinking by DEFAULT for thorough evaluation.
 ---
 
@@ -307,10 +306,12 @@ Claude will:
 | **Scope** | Increments only | Any files |
 | **Input** | Increment ID | Files, git diff, context |
 | **Default Mode** | Standard | **ULTRATHINK** |
-| **Pattern** | 7-dimension scoring | Judge LLM reasoning |
+| **Pattern** | 7-dimension scoring + BMAD risk | Judge LLM reasoning |
 | **Focus** | Spec quality, risks | Code correctness |
 | **When** | Before increment close | After any work |
 
+> **Note**: The `increment-quality-judge-v2` command has been retired. Its BMAD risk scoring and quality gate logic are available through `/sw:qa` which uses the v2 assessment internally.
+
 ## Best Practices
 
 1. **Use by default**: Ultrathink is worth the extra time for quality

package/plugins/specweave/commands/living-docs.md

@@ -1,5 +1,4 @@
 ---
-name: living-docs
 description: Launch or resume Living Docs Builder independently. Generates comprehensive enterprise documentation from codebase analysis with AI-powered insights. LSP-enhanced by default for accurate API extraction.
 argument-hint: [--resume jobId] [--depth level] [--full-scan]
 ---

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

@@ -1,6 +1,6 @@
 ---
-name: migrate-config
 description: Migrate .env-only configuration to split secrets/config format
+disable-model-invocation: true
 ---
 
 Migrate your project from the old .env-only format to the new split format where secrets stay in `.env` (gitignored) and configuration moves to `.specweave/config.json` (committed to git).

package/plugins/specweave/commands/notifications.md

@@ -1,5 +1,4 @@
 ---
-name: notifications
 description: View and manage sync notifications - import completions, discrepancies, sync failures. Filter by type and severity, show details, dismiss notifications.
 ---
 

package/plugins/specweave/commands/npm.md

@@ -1,6 +1,6 @@
 ---
-name: npm
 description: Full patch release with npm publish and GitHub Release. Flags: --quick (no GH release), --ci (Actions), --only (local).
+disable-model-invocation: true
 ---
 
 # /sw:npm - NPM Release Automation

package/plugins/specweave/commands/plugin-validator.md

@@ -1,5 +1,4 @@
 ---
-name: plugin-validator
 description: Validates SpecWeave plugin installation when EXPLICITLY requested by user. Use for checking if plugins are installed correctly, validating marketplace registration, or troubleshooting missing plugins. Only triggers on explicit requests to avoid false positives during normal workflow.
 allowed-tools: Read, Bash, Grep
 ---

package/plugins/specweave/commands/qa.md

@@ -1,5 +1,4 @@
 ---
-name: qa
 description: Run quality assessment on a SpecWeave increment with risk scoring and quality gate decisions
 ---
 

package/plugins/specweave/commands/reconcile.md

@@ -1,6 +1,6 @@
 ---
-name: reconcile
 description: Reconcile increment ID collisions after multi-developer merge. Renumbers conflicting increments based on modification dates.
+disable-model-invocation: true
 ---
 
 # Reconcile Increment IDs

package/plugins/specweave/commands/reflect-check.md

@@ -1,5 +1,4 @@
 ---
-name: reflect-check
 description: Diagnostic tool for validating SpecWeave reflection system health and troubleshooting issues. Use when reflection seems stuck, learnings aren't being captured, or CLAUDE.md Skill Memories aren't updating. Checks configuration, permissions, and system state.
 allowed-tools: Read, Bash
 user-invocable: false

package/plugins/specweave/commands/reflect.md

@@ -1,6 +1,6 @@
 ---
-name: reflect
-description: Analyze current session and extract learnings to CLAUDE.md Skill Memories. Enables self-improving AI that learns from corrections and patterns. Activates for reflect, remember, learn from session, extract learnings.
+description: Analyze session and extract learnings to CLAUDE.md Skill Memories. Supports subcommands --on, --off, --status, --clear. Activates for reflect, remember, learn from session, extract learnings.
+argument-hint: [--on | --off | --status | --clear [--skill name | --all]]
 ---
 
 # Reflect Command
@@ -10,18 +10,31 @@ description: Analyze current session and extract learnings to CLAUDE.md Skill Me
 ## Usage
 
 ```bash
-# Reflect on current session (analyzes all signals)
+# Manual reflection (analyzes session signals)
 /sw:reflect
-
-# Reflect with focus prompt
 /sw:reflect "Focus on the API patterns we discussed"
+
+# Enable auto-reflection on session end
+/sw:reflect --on
+
+# Disable auto-reflection
+/sw:reflect --off
+
+# Show reflection config and learning statistics
+/sw:reflect --status
+
+# Clear learnings
+/sw:reflect --clear --skill frontend
+/sw:reflect --clear --all
 ```
 
-## How It Works
+## Subcommands
+
+### Default (no flags) - Manual Reflection
 
-### Step 1: Signal Detection
+Scans conversation for learnable signals and extracts to CLAUDE.md.
 
-Scans conversation for learnable signals:
+**Signal Detection:**
 
 **Corrections (High Confidence)**
 ```
@@ -44,30 +57,97 @@ User: "Perfect! That's exactly how our API should look."
       → Skill: backend
 ```
 
-### Step 2: LLM Extraction
+**LLM Extraction** uses Claude Haiku to extract SpecWeave-specific learnings, then writes to the `## Skill Memories` section in CLAUDE.md.
 
-Uses Claude Haiku to extract SpecWeave-specific learnings:
+### `--on` - Enable Auto-Reflection
 
-```typescript
-interface SkillLearning {
-  skill: string;    // e.g., "frontend", "devops", "general"
-  learning: string; // The actual learning content
-}
+Enables automatic session analysis via the stop hook.
+
+**Execution:**
+1. Read existing config from `.specweave/config.json`
+2. Update config to set `reflect.enabled: true`
+3. Display confirmation
+
+**Output:**
+```
+Auto-reflection ENABLED
+
+Stop hook will analyze sessions on exit.
+Learnings saved to CLAUDE.md Skill Memories section.
+
+Disable with: /sw:reflect --off
+```
+
+### `--off` - Disable Auto-Reflection
+
+Disables automatic session analysis. Manual `/sw:reflect` still works.
+
+**CRITICAL: This is a SIMPLE operation. NO Glob, NO parallel tool calls needed.**
+
+**Execution:**
+1. Read existing config from `.specweave/state/reflect-config.json`
+   (If file doesn't exist, create with autoReflect: false)
+2. Write updated config: set `autoReflect` to `false`, preserve other fields
+3. Display confirmation
+
+**Output:**
+```
+Auto-reflection DISABLED
+
+Manual /sw:reflect still works.
+Existing learnings preserved.
+
+Re-enable with: /sw:reflect --on
 ```
 
-### Step 3: Write to CLAUDE.md
+**WARNING**: Do NOT use Glob to scan directories - this operation only writes ONE file.
 
-Updates the `## Skill Memories` section in CLAUDE.md:
+### `--status` - Show Config & Statistics
 
-```markdown
-## Skill Memories
+Shows reflection configuration and learning statistics.
 
-### Frontend
-- **2026-01-05**: Always use Button component with variant='primary' from design system
+**Execution:**
+1. Read config from `.specweave/config.json` for reflect settings
+2. Read CLAUDE.md to find Skill Memories section
+3. Parse learnings by skill category
+4. Display dashboard
 
-### Backend
-- **2026-01-05**: Return 404 for missing resources (not 500)
+**Output:**
 ```
+REFLECT: Status Dashboard
+
+CONFIGURATION
+  Reflection:      Enabled
+  Model:           haiku
+  Max/session:     3
+
+SKILL MEMORIES (CLAUDE.md)
+  Skill           Learnings
+  devops          1
+  frontend        2
+  backend         3
+  general         2
+  Total:          8
+
+RECENT LEARNINGS
+  - [devops] LSP requires ENABLE_LSP_TOOL=1 env var
+  - [frontend] Use shadcn/ui Button component
+  - [backend] Return 404 for missing resources
+```
+
+### `--clear` - Remove Learnings
+
+Remove specific learnings from CLAUDE.md Skill Memories section.
+
+```bash
+/sw:reflect --clear --skill frontend   # Clear all learnings for skill
+/sw:reflect --clear --all              # Clear ALL learnings (requires confirmation)
+```
+
+**Execution:**
+1. Read CLAUDE.md to find Skill Memories section
+2. Show confirmation with what will be deleted
+3. Edit CLAUDE.md to remove matching learnings on confirmation
 
 ## Configuration
 
@@ -103,15 +183,6 @@ Learnings are routed to these skills:
 | `architect` | System design, ADRs, patterns |
 | `general` | Fallback for general SpecWeave learnings |
 
-## Related Commands
-
-| Command | Purpose |
-|---------|---------|
-| `/sw:reflect-on` | Enable automatic reflection on session end |
-| `/sw:reflect-off` | Disable automatic reflection |
-| `/sw:reflect-status` | Show reflection configuration |
-| `/sw:reflect-clear` | Remove specific learnings |
-
 ## Quality Rules
 
 **NEVER store user input verbatim. ALWAYS synthesize into actionable rules.**

package/plugins/specweave/commands/restore.md

@@ -1,6 +1,6 @@
 ---
-name: restore
 description: Restore archived increments back to active folder
+disable-model-invocation: true
 ---
 
 # Restore Increment from Archive

package/plugins/specweave/commands/revert-wip-limit.md

@@ -1,6 +1,6 @@
 ---
-name: revert-wip-limit
 description: Revert WIP limit to original value after temporary adjustment
+disable-model-invocation: true
 ---
 
 # Revert WIP Limit Command

package/plugins/specweave/commands/role-orchestrator.md

@@ -1,5 +1,4 @@
 ---
-name: role-orchestrator
 description: Multi-agent orchestration system that coordinates PM, Architect, DevOps, QA, Tech Lead, and Security agents for complex tasks. Use when building full products, creating SaaS applications, or any end-to-end implementation requiring multiple specialized roles. Implements hierarchical orchestrator-worker pattern.
 ---
 

package/plugins/specweave/commands/skill.md

@@ -1,7 +1,7 @@
 ---
-name: skill
 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]
+disable-model-invocation: true
 ---
 
 # Skill Creator & Validator
@@ -44,17 +44,14 @@ Run these checks on every SKILL.md:
 
 #### 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)
-```
+> **WARNING**: Do NOT use `name:` in SKILL.md frontmatter for plugin-based skills.
+> It causes Claude Code to strip the plugin namespace prefix (e.g., `/sw:grill` becomes `/grill`).
+> The skill name is derived from the directory name automatically.
+
+#### 3. Description Quality (moved up - name validation removed)
 
 #### 4. Description Quality
 ```
@@ -172,7 +169,7 @@ Comprehensive audit of ALL skills across project.
 
 | Issue | Auto-Fix |
 |-------|----------|
-| Missing frontmatter | Add minimal `---\nname: {from-filename}\ndescription: TODO\n---` |
+| Missing frontmatter | Add minimal `---\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 |
@@ -314,7 +311,6 @@ mkdir -p .claude/skills/{skill-name}
 **Auto-activating skill**:
 ```yaml
 ---
-name: {skill-name}
 description: {description with "Activates for:" keywords}
 ---
 
@@ -355,7 +351,6 @@ Ask me about:
 **Command skill** (add frontmatter):
 ```yaml
 ---
-name: {skill-name}
 description: {description}
 disable-model-invocation: true
 ---
@@ -364,7 +359,6 @@ disable-model-invocation: true
 **Knowledge skill** (add frontmatter):
 ```yaml
 ---
-name: {skill-name}
 description: {description}
 user-invocable: false
 ---
@@ -373,7 +367,6 @@ user-invocable: false
 **With tool restrictions** (add frontmatter):
 ```yaml
 ---
-name: {skill-name}
 description: {description}
 allowed-tools: Read, Grep, Glob, WebSearch
 ---
@@ -383,11 +376,10 @@ allowed-tools: Read, Grep, Glob, WebSearch
 
 Check these before finishing:
 - [ ] SKILL.md starts with `---` on line 1
-- [ ] Has `name:` field (matches directory name)
 - [ ] Has `description:` field (includes "Activates for:")
 - [ ] Closing `---` present before markdown content
 - [ ] Description under 1024 characters
-- [ ] Name matches `^[a-z0-9]([a-z0-9-]*[a-z0-9])?$`
+- [ ] Does NOT have `name:` field (causes prefix stripping in plugins)
 
 ### Step 4: Show Next Steps
 
@@ -596,7 +588,7 @@ From https://code.claude.com/docs/en/skills:
 
 | Field | Required | Type | Description |
 |-------|----------|------|-------------|
-| `name` | Recommended | string | Identifier (kebab-case, max 64 chars) |
+| `name` | **AVOID for plugins** | string | Strips plugin prefix! Only for standalone `~/.claude/skills/` |
 | `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) |