specweave 1.0.213 → 1.0.215

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "specweave",
-  "version": "1.0.213",
+  "version": "1.0.215",
   "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/.claude-plugin/plugin.json

@@ -18,7 +18,5 @@
     "pm",
     "architect",
     "living-docs"
-  ],
-  "commands": "./commands/",
-  "skills": "./skills/"
+  ]
 }

package/plugins/specweave/commands/abandon.md

@@ -1,7 +1,7 @@
 ---
 name: abandon
 description: Abandon an incomplete increment (requirements changed, obsolete)
-usage: /sw:abandon <increment-id> --reason="<reason>"
+argument-hint: [increment-id] --reason="reason"
 ---
 
 # Abandon Increment Command

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

@@ -1,7 +1,7 @@
 ---
 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.
-usage: /sw:api-docs [--openapi] [--postman] [--env] [--all] [--watch] [--validate] [--framework <name>]
+argument-hint: [--openapi] [--postman] [--all] [--validate]
 ---
 
 # API Documentation Generator

package/plugins/specweave/commands/backlog.md

@@ -1,7 +1,7 @@
 ---
 name: backlog
 description: Move an increment to backlog (planned but not ready to start)
-usage: /sw:backlog <increment-id> --reason="<reason>"
+argument-hint: [increment-id] --reason="reason"
 ---
 
 # Backlog Increment Command

package/plugins/specweave/commands/external.md

@@ -1,7 +1,7 @@
 ---
 name: external
 description: View external items dashboard - open issues from GitHub, JIRA, and Azure DevOps
-usage: /sw:external [--refresh]
+argument-hint: [--refresh]
 ---
 
 # External Items Dashboard

package/plugins/specweave/commands/jobs.md

@@ -1,7 +1,7 @@
 ---
 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.
-usage: /sw:jobs [--all] [--id <job-id>]
+argument-hint: [--all] [--id job-id]
 ---
 
 # Background Jobs Monitor

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

@@ -1,7 +1,7 @@
 ---
 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.
-usage: /sw:living-docs [--resume <jobId>] [--depth <level>] [--priority <modules>] [--sources <folders>] [--depends-on <jobIds>] [--foreground] [--full-scan] [--no-lsp]
+argument-hint: [--resume jobId] [--depth level] [--full-scan]
 ---
 
 # Living Docs Builder (Standalone)

package/plugins/specweave/commands/npm.md

@@ -1,6 +1,6 @@
 ---
 name: npm
-description: Full patch release - auto-commit, push, build, npm publish, AND GitHub Release creation. Use --quick for save+release (no GH release). Use --ci for GitHub Actions publish. Use --only for local publish without git push. Use --only --local for version bump only.
+description: Full patch release with npm publish and GitHub Release. Flags: --quick (no GH release), --ci (Actions), --only (local).
 ---
 
 # /sw:npm - NPM Release Automation

package/plugins/specweave/commands/pause.md

@@ -1,7 +1,7 @@
 ---
 name: pause
 description: Pause an active increment (blocked by external dependency, deprioritized)
-usage: /sw:pause <increment-id> --reason="<reason>"
+argument-hint: [increment-id] --reason="reason"
 ---
 
 # Pause Increment Command

package/plugins/specweave/commands/resume.md

@@ -1,7 +1,7 @@
 ---
 name: resume
 description: Resume a paused or backlog increment
-usage: /sw:resume <increment-id>
+argument-hint: [increment-id]
 ---
 
 # Resume Increment Command

package/plugins/specweave/commands/skill-match.md

@@ -1,13 +1,7 @@
 ---
 name: skill-match
 description: Test a prompt against skill triggers to see what would match
-trigger: /sw:skill-match
-category: debugging
-arguments:
-  - name: prompt
-    description: The prompt to test
-    required: true
-    type: string
+argument-hint: [prompt]
 ---
 
 # Skill Match Command

package/plugins/specweave/commands/skill.md

@@ -1,4 +1,10 @@
-# /sw:skill
+---
+name: skill
+description: Create Claude Code skills with proper YAML frontmatter, validation, and best practices
+argument-hint: [--name skill-name] [--type auto|command|knowledge]
+---
+
+# Skill Creator
 
 Create Claude Code skills with proper YAML frontmatter, validation, and best practices.
 

package/plugins/specweave/commands/status.md

@@ -1,7 +1,7 @@
 ---
 name: status
 description: Show increment status overview with rich details (active, backlog, paused, completed, abandoned)
-usage: /sw:status [--active|--backlog|--paused|--completed|--abandoned|--stale]
+argument-hint: [--active|--backlog|--paused|--completed|--abandoned]
 ---
 
 # Increment Status

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

@@ -1,93 +0,0 @@
-# Skip Failed Increment in Auto Mode
-
-Skip a failed increment and move to the next one in queue. Use when an increment has exhausted retries and you want to continue with other work.
-
-## Usage
-
-```bash
-/sw:skip-increment [INCREMENT_ID]
-```
-
-## Arguments
-
-- `INCREMENT_ID`: Optional. If not provided, skips the current pending skip.
-
-## How It Works
-
-1. Marks the failed increment as "skipped" (not "completed" or "failed")
-2. Logs the skip with reason in the session state
-3. Moves to the next increment in queue
-4. Continues auto mode execution
-
-## When to Use
-
-- When an increment fails repeatedly and you want to move forward
-- When a blocking issue requires external resolution
-- When prioritizing other increments over the failed one
-
-## Session State
-
-The skip creates a `failedIncrements` entry with skip metadata:
-
-```json
-{
-  "incrementId": "0001-feature",
-  "skipReason": "test_failures",
-  "skippedAt": "2024-12-29T10:00:00Z",
-  "failureDetails": {
-    "file": "tests/auth.spec.ts",
-    "error": "timeout waiting for login"
-  }
-}
-```
-
-## Execution
-
-**When this command is invoked**, execute the following:
-
-```bash
-SESSION_FILE="$PROJECT_ROOT/.specweave/state/auto-session.json"
-
-if [ ! -f "$SESSION_FILE" ]; then
-    echo "No auto session active."
-    exit 1
-fi
-
-SESSION=$(cat "$SESSION_FILE")
-PENDING_SKIP=$(echo "$SESSION" | jq -r '.pendingSkip // null')
-
-if [ "$PENDING_SKIP" = "null" ]; then
-    echo "No increment pending skip. Run /sw:auto to continue."
-    exit 1
-fi
-
-SKIPPED_INCREMENT=$(echo "$PENDING_SKIP" | jq -r '.increment')
-SKIP_REASON=$(echo "$PENDING_SKIP" | jq -r '.reason')
-NEXT_INCREMENT=$(echo "$SESSION" | jq -r '.incrementQueue[1] // null')
-
-if [ "$NEXT_INCREMENT" = "null" ]; then
-    echo "No more increments in queue."
-    exit 1
-fi
-
-# Move skipped increment to failed list and advance queue
-jq --arg skipped "$SKIPPED_INCREMENT" --arg reason "$SKIP_REASON" \
-   --arg next "$NEXT_INCREMENT" --arg now "$(date -u +%Y-%m-%dT%H:%M:%SZ)" '
-   .failedIncrements += [{
-     "incrementId": $skipped,
-     "skipReason": $reason,
-     "skippedAt": $now,
-     "failureDetails": .pendingSkip
-   }] |
-   .currentIncrement = $next |
-   .incrementQueue = .incrementQueue[1:] |
-   .status = "running" |
-   del(.pendingSkip) |
-   del(.pauseTime) |
-   del(.pauseReason)
-' "$SESSION_FILE" > "$SESSION_FILE.tmp" && mv "$SESSION_FILE.tmp" "$SESSION_FILE"
-
-echo "Skipped increment $SKIPPED_INCREMENT, now working on $NEXT_INCREMENT"
-```
-
-Then continue with `/sw:do` to start working on the next increment.

package/plugins/specweave/lib/utils/validate-dev-setup.sh

@@ -1,133 +0,0 @@
-#!/bin/bash
-# Lightweight Developer Setup Validator for Hooks
-#
-# This script is sourced by hooks to validate that the marketplace symlink
-# is correctly configured for local development, preventing hook errors.
-#
-# Usage in hooks:
-#   source "$(dirname "$0")/../lib/utils/validate-dev-setup.sh"
-#   validate_marketplace_setup_quiet || exit 0  # Skip hook if setup invalid
-
-# Global variables set by validation
-MARKETPLACE_SETUP_VALID=0
-MARKETPLACE_SETUP_ERROR=""
-
-# Validate marketplace setup (quiet mode - for hooks)
-# Returns: 0 if valid, 1 if invalid
-# Sets: MARKETPLACE_SETUP_VALID, MARKETPLACE_SETUP_ERROR
-validate_marketplace_setup_quiet() {
-  # Only validate in development mode
-  if [[ ! -f "$(git rev-parse --show-toplevel 2>/dev/null)/package.json" ]]; then
-    MARKETPLACE_SETUP_VALID=1
-    return 0  # Not in a repo, assume valid
-  fi
-
-  # Check if we're in the SpecWeave repository
-  local repo_root
-  repo_root="$(git rev-parse --show-toplevel 2>/dev/null)" || {
-    MARKETPLACE_SETUP_VALID=1
-    return 0  # Not in git repo, assume valid
-  }
-
-  if [[ ! -f "$repo_root/package.json" ]]; then
-    MARKETPLACE_SETUP_VALID=1
-    return 0
-  fi
-
-  # Check if this is the SpecWeave repository
-  if ! grep -q '"name": "specweave"' "$repo_root/package.json" 2>/dev/null; then
-    MARKETPLACE_SETUP_VALID=1
-    return 0  # Not SpecWeave repo, assume valid (user project)
-  fi
-
-  # This IS the SpecWeave repository - validate marketplace setup
-  local marketplace_path="$HOME/.claude/plugins/marketplaces/specweave"
-
-  # Check if marketplace exists
-  if [[ ! -e "$marketplace_path" ]]; then
-    MARKETPLACE_SETUP_VALID=0
-    MARKETPLACE_SETUP_ERROR="Marketplace directory does not exist"
-    return 1
-  fi
-
-  # Check if it's a symlink
-  if [[ ! -L "$marketplace_path" ]]; then
-    MARKETPLACE_SETUP_VALID=0
-    MARKETPLACE_SETUP_ERROR="Marketplace is a regular directory, not a symlink"
-    return 1
-  fi
-
-  # Check if symlink points to this repository
-  local symlink_target
-  symlink_target="$(readlink "$marketplace_path")"
-
-  if [[ "$symlink_target" != "$repo_root" ]]; then
-    # Try resolving to absolute path in case symlink is relative
-    local resolved_target
-    resolved_target="$(cd "$(dirname "$marketplace_path")" && cd "$symlink_target" && pwd)" || {
-      MARKETPLACE_SETUP_VALID=0
-      MARKETPLACE_SETUP_ERROR="Symlink target cannot be resolved"
-      return 1
-    }
-
-    if [[ "$resolved_target" != "$repo_root" ]]; then
-      MARKETPLACE_SETUP_VALID=0
-      MARKETPLACE_SETUP_ERROR="Symlink points to wrong repository"
-      return 1
-    fi
-  fi
-
-  # All checks passed
-  MARKETPLACE_SETUP_VALID=1
-  return 0
-}
-
-# Validate marketplace setup (verbose mode - for scripts)
-# Prints detailed error messages
-# Returns: 0 if valid, 1 if invalid
-validate_marketplace_setup_verbose() {
-  if validate_marketplace_setup_quiet; then
-    return 0
-  fi
-
-  # Print error
-  echo "❌ Invalid marketplace setup: $MARKETPLACE_SETUP_ERROR" >&2
-  echo "" >&2
-  echo "Fix by running:" >&2
-  echo "  ./scripts/setup-dev-plugins.sh" >&2
-  echo "" >&2
-  echo "Or manually:" >&2
-  echo "  rm -rf ~/.claude/plugins/marketplaces/specweave" >&2
-  echo "  ln -s \$(pwd) ~/.claude/plugins/marketplaces/specweave" >&2
-  echo "" >&2
-
-  return 1
-}
-
-# Quick check for hooks - returns true if running in user project
-is_user_project() {
-  local repo_root
-  repo_root="$(git rev-parse --show-toplevel 2>/dev/null)" || return 0
-
-  if [[ ! -f "$repo_root/package.json" ]]; then
-    return 0  # No package.json, assume user project
-  fi
-
-  # Check if this is NOT the SpecWeave repository
-  if ! grep -q '"name": "specweave"' "$repo_root/package.json" 2>/dev/null; then
-    return 0  # User project
-  fi
-
-  return 1  # SpecWeave repository
-}
-
-# Print warning about marketplace setup (for hooks)
-warn_marketplace_setup() {
-  if [[ "${SPECWEAVE_SUPPRESS_WARNINGS:-}" == "true" ]]; then
-    return 0
-  fi
-
-  echo "⚠️  Warning: Marketplace setup issue detected" >&2
-  echo "   Run: ./scripts/validate-local-dev-setup.sh" >&2
-  echo "" >&2
-}

package/plugins/specweave-ado/skills/ado-manager/SKILL.md

@@ -1,16 +0,0 @@
----
-name: ado-manager
-description: Azure DevOps integration specialist for SpecWeave increments with epic/feature/story management and bidirectional sync. Use when creating ADO work items, syncing task completion, or troubleshooting ADO API issues. Covers rate limiting, WIQL queries, and area path configuration.
-role: Azure DevOps Integration Specialist
-context: |
-  You are an expert in Azure DevOps (ADO) REST API integration, work item management, and SpecWeave increment synchronization.
-
-  Your responsibilities:
-  - Create and manage ADO work items (Epics, Features, User Stories)
-  - Sync SpecWeave increment progress to ADO
-  - Handle bidirectional sync (ADO ↔ SpecWeave)
-  - Troubleshoot ADO API issues
-  - Optimize sync performance and rate limiting
-model: opus
-context: fork
----

package/plugins/specweave-infrastructure/skills/network-engineer/SKILL.md

@@ -1,12 +0,0 @@
----
-name: network-engineer
-description: Cloud network architect for VPC design, service mesh, zero-trust networking, load balancers, and CDN optimization. Use for network troubleshooting or connectivity issues.
-model: opus
-context: fork
----
-
-## ⚠️ Chunking for Large Network Architectures
-
-When generating comprehensive network architectures that exceed 1000 lines (e.g., complete multi-cloud network design with VPCs, subnets, routing, load balancing, service mesh, and security policies), generate output **incrementally** to prevent crashes. Break large network implementations into logical layers (e.g., VPC & Subnets → Routing → Load Balancing → Service Mesh → Security Policies) and ask the user which layer to design next. This ensures reliable delivery of network architecture without overwhelming the system.
-
-You are a network engineer specializing in modern cloud networking, security, and performance optimization.

package/plugins/specweave-infrastructure/skills/performance-engineer/SKILL.md

@@ -1,12 +0,0 @@
----
-name: performance-engineer
-description: Performance engineering - OpenTelemetry, distributed tracing, load testing (k6, JMeter), multi-tier caching, Core Web Vitals. Use for slow apps or latency issues.
-model: opus
-context: fork
----
-
-## ⚠️ Chunking for Large Performance Optimization Plans
-
-When generating comprehensive performance optimization implementations that exceed 1000 lines (e.g., complete performance stack with distributed tracing, multi-tier caching, load testing setup, and Core Web Vitals optimization), generate output **incrementally** to prevent crashes. Break large performance projects into logical components (e.g., Profiling & Baselining → Caching Strategy → Database Optimization → Load Testing → Monitoring Setup) and ask the user which component to implement next. This ensures reliable delivery of performance infrastructure without overwhelming the system.
-
-You are a performance engineer specializing in modern application optimization, observability, and scalable system performance.

package/plugins/specweave-infrastructure/skills/sre/SKILL.md

@@ -1,13 +0,0 @@
----
-name: sre
-description: SRE expert for incident response, production troubleshooting, root cause analysis, post-mortems, and runbooks. Use for outages, performance issues, or SEV incidents.
-allowed-tools: Read, Bash, Grep
-model: opus
-context: fork
----
-
-# SRE Agent - Site Reliability Engineering Expert
-
-## ⚠️ Chunking for Large Incident Reports
-
-When generating comprehensive incident reports that exceed 1000 lines (e.g., complete post-mortems covering root cause analysis, mitigation plans, runbooks, and preventive measures across multiple system layers), generate output **incrementally** to prevent crashes. Break large incident reports into logical phases (e.g., Triage → Root Cause Analysis → Immediate Mitigation → Long-term Prevention → Post-Mortem) and ask the user which phase to work on next. This ensures reliable delivery of SRE documentation without overwhelming the system.