Commands Reference
Complete reference for the AI Craftsman Superpowers skills: usage, effort, and examples.
Overview
AI Craftsman Superpowers ships 19 skills, invoked with /craftsman:<name> inside a Claude Code session. Version 4.7.0 removed agent-design, mlops and rag, and added loop.
Commands became skills in v4
v4.0.0 deleted commands/ and moved every workflow to skills/<name>/SKILL.md, gaining forked execution, agent binding and live context injection. Your invocations did not change: /craftsman:design still works exactly as before.
| Category | Skills |
|---|---|
| Design & Architecture | design, challenge, spec |
| Implementation | scaffold, refactor, parallel |
| Quality & Testing | test, verify, debug |
| Planning | plan |
| Legacy | legacy |
| AI/ML engineering | rag, mlops, agent-design |
| Operations | git, metrics, ci, team |
| Utility | setup, healthcheck, workflow |
Effort levels
Each command has an effort level - Quick (<5 min), Medium (5-20 min), Heavy (20+ min). Heavy commands orchestrate multiple agents and produce comprehensive outputs.
/craftsman:design - Senior DDD Methodology
Effort: Heavy | Model: Sonnet
Four mandatory phases before any code is written. Violating phase order is blocked.
/craftsman:design Create a User aggregate with subscription managementPhases:
- Understand - Map domain, identify entities, bounded contexts
- Challenge - Question assumptions, explore alternatives, find simpler solutions
- Recommend - Select approach with explicit trade-offs
- Implement - Write code following DDD tactical patterns
NO CODE WITHOUT PHASES 1-3 COMPLETE
The design command enforces a strict gate: no implementation until phases 1-3 are documented. This prevents the most common DDD mistake - jumping to code before understanding the domain.
/craftsman:challenge - Architecture Review
Effort: Medium | Model: Sonnet
3-level severity review for code and architecture decisions.
/craftsman:challenge Review the current authentication implementationSeverity levels:
BLOCKING- Must fix before proceeding (security, data corruption risk)MUST FIX- Fix before PR merge (architecture violations)IMPROVE- Suggestion for better design (non-blocking)
/craftsman:spec - Specification-First Development
Effort: Medium | Model: Sonnet
BDD/TDD specification before implementation. The Iron Law: no production code without a failing test first.
/craftsman:spec UserRepository should find users by emailOutput: Gherkin scenarios → failing test → implementation plan
/craftsman:debug - Systematic ReAct Debugging
Effort: Medium | Model: Sonnet
6-phase systematic investigation. No guessing allowed.
/craftsman:debug The user authentication fails intermittently in productionPhases: Observe → Hypothesize → Experiment → Analyze → Root Cause → Fix
NO FIXES WITHOUT ROOT CAUSE
The debug command blocks jumping to fixes. You must complete the investigation phases and identify the root cause before proposing solutions.
/craftsman:plan - Structured Planning
Effort: Heavy | Model: Sonnet
Three modes for different planning needs:
/craftsman:plan create "Migrate authentication to JWT" # Create plan
/craftsman:plan execute # Execute current plan
/craftsman:plan execute-with-agents # Execute with agent teamProduces a structured markdown plan with phases, dependencies, and success criteria.
/craftsman:scaffold - Unified Code Scaffolder
Effort: Quick | Model: Haiku
Generates code from canonical examples (Iron Law pattern). Supports multiple scaffold types:
/craftsman:scaffold entity # DDD Entity with Value Objects + Domain Events
/craftsman:scaffold usecase # Use Case with Command/Handler (CQRS)
/craftsman:scaffold component # React component with TypeScript + tests
/craftsman:scaffold hook # React hook with TanStack Query
/craftsman:scaffold api-resource # API Platform 4 Resource
/craftsman:scaffold pack # Community pack skeletonEach scaffold loads the canonical example first, then adapts it to your context.
/craftsman:refactor - Systematic Refactoring
Effort: Medium | Model: Sonnet
Safe refactoring with behavior preservation. Detects and addresses code smells.
/craftsman:refactor The UserService class has grown to 800 linesCode smell catalog: Long method, large class, feature envy, primitive obsession, shotgun surgery, data clumps, parallel inheritance hierarchies.
/craftsman:test - Pragmatic Testing
Effort: Medium | Model: Sonnet
Testing pyramid: 80% unit, 15% integration, 5% E2E. Focuses on behavior, not implementation.
/craftsman:test Write tests for the OrderService use caseRules:
- AAA structure (Arrange, Act, Assert)
- One concept per test
- No testing implementation details
- Mock only at system boundaries
/craftsman:verify - Evidence-Based Verification
Effort: Quick | Model: Haiku
Runs verification before claiming completion. The Golden Rule: no completion claims without fresh verification evidence.
/craftsman:verifyRuns: TypeScript compilation → linting → tests → architecture check. Produces a pass/fail report with evidence.
NO COMPLETION CLAIMS WITHOUT PROOF
Never run /craftsman:verify and ignore its output. If it fails, fix the issues before closing the task.
/craftsman:git - Safe Git Workflow
Effort: Quick | Model: Haiku
Conventional Commits enforcement with destructive command protection.
/craftsman:gitStages files, drafts a conventional commit message, checks for >15 files (atomic commit warning), and creates the commit.
Protected commands (require explicit confirmation): git push --force, git reset --hard, git clean -f, git branch -D.
/craftsman:metrics - Quality Dashboard
Effort: Quick | Model: Haiku
SQLite-backed quality metrics from your sessions.
/craftsman:metricsOutput:
- Total violations this week / month
- Corrections made (learning feedback loop)
- Session history (last 10 sessions)
- 7-day and 30-day trend charts
- Top violated rules
/craftsman:ci - CI/CD Integration
Effort: Quick | Model: Haiku
Generates CI configuration and shows CI status.
/craftsman:ci export # Generate CI config for your provider
/craftsman:ci status # Show last CI run statusDetects your provider from .craft-config.yml and generates the appropriate workflow file. See CI Integration for full details.
/craftsman:team - Agent Team Manager
Effort: Heavy | Model: Sonnet
Orchestrates multiple agents for complex tasks. Three built-in templates:
/craftsman:team code-review # Architect + Security + Doc reviewer in parallel
/craftsman:team feature # Team-Lead orchestrates Frontend + Backend + Tests
/craftsman:team security-audit # Security specialist deep dive/craftsman:setup - Interactive Configuration Wizard
Effort: Quick | Model: Haiku
Runs the DISC mini-assessment, detects your stack, and generates ~/.claude/.craft-config.yml. See Getting Started.
/craftsman:healthcheck - Diagnose the Install
Effort: Low | Model: Haiku
Reports what the plugin actually loaded: active packs, resolved rules, which gate levels are live on this machine, and which language servers were detected.
/craftsman:healthcheckThere is no session-start command. Config, packs and rules load automatically on SessionStart, so healthcheck is for inspecting that result, not for triggering it.
/craftsman:parallel - Multi-Agent Orchestration
Effort: Heavy | Model: Sonnet
Identifies independent tasks and runs them in parallel with separate agents.
/craftsman:parallel Implement the user registration featureProduces a dependency matrix, spawns parallel agents for independent tasks, then merges results.