sw

**Usage**: `/sw:backlog <increment-id> --reason="<reason>"`

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.

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.

EMERGENCY ONLY - Manually cancel running auto session. Generates summary report and releases lock. Activates for: cancel auto, stop auto, emergency cancel.

Comprehensive health check for hooks - detects import errors, runtime failures, performance issues, and provides auto-fix suggestions

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.

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.

View and manage code-to-spec discrepancies. Detects API changes, function signature mismatches, and documentation gaps. Supports brownfield analysis and code-spec comparison.

Convert brownfield discrepancies into a new increment for systematic documentation improvement. Groups by module, generates spec with ACs, and tracks resolution.

Execute increment implementation following spec and plan - hooks run after EVERY task

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).

Close increment with PM validation - checks tasks, tests, and docs before closing

Auto-embed Acceptance Criteria from living docs into increment spec.md for hook compatibility

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.

View external items dashboard - open issues from GitHub, JIRA, and Azure DevOps

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.

Automatically detect and resolve duplicate increments with smart conflict resolution

Comprehensive implementation auditor - grills code quality, finds problems, and identifies improvements

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.

Import brownfield documentation from Notion exports, Confluence, GitHub Wiki, or any markdown folder. Automatically classifies files as specs, modules, team docs, or legacy.

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.

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.

AI-powered quality assessment using LLM-as-Judge pattern with BMAD risk scoring and formal gate decisions. Use for evaluating increment specs, assessing task completeness, or making quality gate decisions (PASS/CONCERNS/FAIL). Chain-of-thought reasoning ensures transparent evaluation.

Plan new Product Increment. Use when starting new features, hotfixes, or development work that needs specification.

**NOTE**: This command is normally intercepted by the UserPromptSubmit hook for instant execution (<100ms). If the hook output isn't displayed, execute the CLI fallback below.

Ultrathink LLM-as-Judge validation of completed work. Uses extended thinking by DEFAULT for thorough evaluation.

**Usage**: `/sw:living-docs [options]`

Migrate .env-only configuration to split secrets/config format

Smart increment transition - auto-close current if ready, intelligently suggest next work (backlog or new feature)

View and manage sync notifications - import completions, discrepancies, sync failures. Filter by type and severity, show details, dismiss notifications.

Full patch release with npm publish and GitHub Release. Flags: --quick (no GH release), --ci (Actions), --only (local).

**Usage**: `/sw:pause <increment-id> --reason="<reason>"`

Generate plan.md and tasks.md for PLANNING increment using Architect Agent

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.

Show detailed progress for active increments with task/AC completion, priority, and type

Run quality assessment on a SpecWeave increment with risk scoring and quality gate decisions

Reconcile increment ID collisions after multi-developer merge. Renumbers conflicting increments based on modification dates.

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.

**Usage**: `/sw:abandon <increment-id> --reason="<reason>"`

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.

**Usage**: `/sw:api-docs [options]`

Manually archive completed increments and sync living docs - NEVER auto-archives, explicit user action only

Enable parallel agent execution for multi-domain features with git worktree isolation

Show current auto session status, progress, and any pending gates. Activates for: auto status, auto status, session status, check auto.

Start autonomous execution with stop hook feedback loop. Works until all tasks complete or max iterations reached. Use when you want continuous unattended execution.

Clear specific learnings from CLAUDE.md Skill Memories section. Activates for reflect clear, clear learning, remove learning, delete memory.

Disable automatic reflection on session end. Manual reflection still works. Activates for reflect off, disable reflect, stop auto reflect.

Enable automatic reflection on session end. Stop hook will analyze session and extract learnings automatically. Activates for reflect on, enable reflect, auto reflect, automatic learning.

Show reflection configuration and learning statistics. Activates for reflect status, reflection status, memory status, learnings status.

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.

Reopen completed increments, tasks, or user stories when issues are discovered. Validates WIP limits, creates audit trail, and syncs to external tools. Use when recently completed work has issues that need fixing.

Restore archived increments back to active folder

Resume a paused or backlog increment

Revert WIP limit to original value after temporary adjustment

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.

SMART save - auto-generates commit messages, handles git pull/merge/rebase automatically, resolves divergent branches, stashes dirty work. Works for single repos and umbrella multi-repo setups. Run with no args for fully automatic save.

Create and validate Claude Code skills with proper YAML frontmatter, validation, and best practices.

Show increment status overview with rich details (active, backlog, paused, completed, abandoned)

Manually synchronize acceptance criteria (AC) checkbox status in spec.md based on task completion

Strategic documentation sync - review docs before implementation (pull context) OR export learnings after implementation (push to living docs). NOT bidirectional - two separate one-way operations at different phases.

Comprehensive progress sync - tasks.md → living docs → external tools (GitHub/JIRA/ADO). AUTO-CREATES missing external issues. Updates all systems with latest task completion status. TRUE single-button sync.

Sync ALL increment specifications to living docs structure by default. Creates FS-XXX folders for each increment. Use with increment ID to sync single increment.

Detect and fix status desyncs between metadata.json and spec.md

Sync tasks.md with actual completion status (GitHub issue or reality check)

Execute comprehensive TDD workflow with strict red-green-refactor discipline. Orchestrates test-first development with automated validation gates at each phase.

Implement minimal code to make failing tests pass in TDD green phase. Focuses on simplicity and making tests green without over-engineering.

Write comprehensive failing tests following TDD red phase principles. Generates failing tests that properly define expected behavior.

Refactor code with confidence using comprehensive test safety net. Applies design patterns, improves code quality, and optimizes performance while keeping all tests green.

Translate SpecWeave project content to target language using LLM-native zero-cost translation

Update living completion report with scope changes during increment execution

Validate feature folder consistency across project folders. Detects orphaned features, missing FEATURE.md, and auto-repairs discrepancies. Use for periodic health checks of living docs structure.

Validate SpecWeave increment with rule-based checks and optional AI quality assessment