craftsman

Plugin craftsman from marketplace ai-craftsman-superpowers in BULDEE/ai-craftsman-superpowers. Commands read from the repo's manifest — 19 days ago.

Skills (28)

• craftsman-debug

  Systematic debugging using ReAct pattern. Use when encountering bugs, errors, unexpected behavior, test failures, or performance issues. Never guess - investigate methodically.

• craftsman-design

  Senior Domain-Driven Design methodology. Use for creating entities, value objects, aggregates, or designing domain models. Follows a 4-phase process (Understand, Challenge, Recommend, Implement).

• craftsman-legacy

  Legacy code rescue - audit hotspots, cover with characterization tests, break dependencies, and plan strangler-fig migrations. Use when inheriting, taming, testing, or refactoring an untested/undocumented codebase.

• craftsman-quality

  How to write code that passes the craftsman gate, and how to answer it when it refuses a turn. Load when coding in a repository where the craftsman plugin is enabled.

• craftsman-refactor

  Systematic refactoring with behavior preservation. Use when improving existing code structure, reducing technical debt, or when code smells are detected.

• craftsman-spec

  Specification-first development (BDD/TDD). Use when implementing new features, creating new components, or when requirements need clarification through tests.

• craftsman-test

  Pragmatic testing following Fowler/Martin principles. Use when writing or reviewing tests, deciding what to test, or improving test coverage strategically.

• agent-design

  Design AI agents using the 3P pattern (Perceive/Plan/Perform). Use when building autonomous AI agents or workflows.

• challenge

  Senior architecture review and code challenge. Use when reviewing code or PRs for quality, auditing architecture decisions, or responding to code review comments.

• ci

  CI/CD pipeline integration. Use when setting up or checking CI quality gates, exporting rules to GitHub Actions/GitLab CI/Bitbucket/Jenkins, or verifying pipeline alignment with local rules.

• debug

  Systematic debugging using ReAct pattern. Use when encountering bugs, errors, unexpected behavior, test failures, or performance issues. Never guess - investigate methodically.

• design

  Senior Domain-Driven Design methodology. Use for creating entities, value objects, aggregates, or designing domain models. Follows a 4-phase process (Understand, Challenge, Recommend, Implement).

• git

  Safe git workflow with destructive command protection. Use when committing changes, creating branches, managing git workflow, or handling merge conflicts.

• healthcheck

  Run a comprehensive diagnostic of your Craftsman plugin installation and runtime. Use when troubleshooting plugin issues, after setup, or when session-start reports warnings.

• legacy

  Legacy code rescue - audit hotspots, cover with characterization tests, break dependencies, and plan strangler-fig migrations. Use when inheriting, taming, testing, or refactoring an untested/undocumented codebase.

• loop

  Bounded goal-driven loop over the craftsman verify gate. Use for ratchet campaigns, red-to-green test runs, violation burn-down: any task shaped as act, verify, repeat until a Done-when condition holds. Every iteration re-verifies; the loop stops on green, on no-progress, or when the budget is spent

• metrics

  Quality metrics and local dashboard. Use when reviewing violation trends, session history, correction patterns, or rendering the aggregated multi-repository dashboard (--dashboard).

• mlops

  Audit ML projects for production readiness. Use when reviewing ML pipelines, deployments, or infrastructure against MLOps best practices.

• parallel

  Parallel agent orchestration for independent tasks. Use when facing 2+ independent tasks that operate on different files/domains and can be parallelized for efficiency.

• plan

  Structured planning for multi-step tasks. Use when starting features requiring 3+ steps, migrating or refactoring large codebases, or when task complexity clearly exceeds a single change.

• rag

  Design RAG (Retrieval-Augmented Generation) pipelines. Use when building knowledge bases, document Q&A, or semantic search systems.

• refactor

  Systematic refactoring with behavior preservation. Use when improving existing code structure, reducing technical debt, or when code smells are detected.

• scaffold

  Unified scaffolder for all pack types. Use when creating new entities, use cases, components, hooks, API resources, or custom packs. Types loaded from active packs.

• setup

  Interactive setup and onboarding. Use on first run, when changing stack/packs, or when healthcheck reports config issues.

• spec

  Specification-first development (BDD/TDD). Use when implementing new features, creating new components, or when requirements need clarification through tests.

• team

  Multi-agent orchestration with native Claude Code teams. Use when facing 2+ independent tasks needing parallel work, full-stack features requiring backend+frontend agents, code reviews needing multiple specialist perspectives, or security audits.

• verify

  Evidence-based verification before claiming completion. Use before committing, creating PRs, or claiming a task is done. Never claim success without proof.

• workflow

  Flexible development pipeline. Use when starting a new feature, fixing a complex bug, or when you want guided step-by-step methodology: design -> spec -> plan -> implement -> test -> verify -> commit.

Subagents (12)

• ai-engineer

  Senior AI/ML engineer - deep expertise in RAG pipelines (pgvector, embeddings, chunking), LLM integration (Claude, OpenAI), prompt engineering, AI agents (Symfony AI, LangChain), and MLOps practices. Use for AI feature reviews, RAG audits, or AI system design. - Read - Glob - Grep - Bash - Agent - E

• api-craftsman

  Senior API architect - deep expertise in API Platform 4, REST/HATEOAS standards, OpenAPI specification, JSON-LD/Hydra, and API security (OAuth2, JWT). Use for API design reviews, API Platform configuration, or RESTful architecture decisions. - Read - Glob - Grep - Bash - Agent - Edit - Write - craft

• architect

  Senior software architect - deep expertise in DDD (strategic + tactical), CQRS, Clean Architecture, Event-Driven Architecture, and system design. Validates dependency direction, bounded contexts, aggregate boundaries, and design decisions. Use for architecture reviews, design validation, or system d

• backend-craftsman

  Senior PHP/Symfony craftsman - deep expertise in Symfony 7/8, API Platform 4, Doctrine ORM, messaging (RabbitMQ/Redis), and DDD tactical patterns. Use for backend code reviews, refactoring, performance audits, or feature implementation. - Read - Glob - Grep - Bash - Agent - Edit - Write - craftsman:

• doc-writer

  Senior technical writer - generates and reviews API docs (OpenAPI), ADRs, READMEs, runbooks, and user guides. Verifies documentation accuracy against code. Use for documentation audits, API doc generation, or technical writing tasks. - Read - Glob - Grep - Edit - Write

• frontend-craftsman

  Senior React/TypeScript craftsman - deep expertise in React 19, TypeScript 5, TanStack Query, Tailwind, shadcn/ui, Recharts, and component architecture. Use for frontend reviews, component refactoring, or feature implementation. - Read - Glob - Grep - Bash - Agent - Edit - Write - craftsman:test

• legacy-surgeon

  Legacy code surgeon - brings untested, tangled, inherited code under control without breaking it. Characterizes behavior first, breaks dependencies with seams, refactors under a net, and migrates with strangler-fig. Never rewrites from scratch. Use for legacy rescue, taming a god class, or getting c

• react-reviewer

  React/TypeScript specialist for reviewing frontend applications. Use when reviewing React components, hooks, or TypeScript code. - Read - Glob - Grep - Bash - Edit - craftsman:challenge

• security-pentester

  Security specialist for finding vulnerabilities in code. Use when auditing security, reviewing authentication, or checking for OWASP issues. - Read - Glob - Grep - Bash - Write

• symfony-reviewer

  Symfony/PHP specialist for reviewing Symfony applications. Use when reviewing PHP/Symfony code, Doctrine entities, or Symfony services. - Read - Glob - Grep - Bash - Edit - craftsman:challenge

• team-lead

  CTO & Tech Lead clone - orchestrates specialized teams across all projects. Use as team lead for any multi-agent task: reviews, implementations, audits. Proactively delegates, challenges decisions, and consolidates deliverables. - Read - Glob - Grep - Bash - Agent - TaskCreate - TaskList - TaskUpdat

• ui-ux-director

  UI/UX director and design system guardian - deep expertise in SaaS dashboard UX, data visualization, accessibility WCAG 2.1 AA, and design token systems. Use for design reviews, a11y audits, or UX improvements. - Read - Glob - Grep - Write

Hooks (22)

• SessionStart

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/session-start.sh"

• PreToolUse

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/config-protection.sh"

• PreToolUse

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/pre-write-check.sh"

• PreToolUse

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/git-bypass-guard.sh"

• PreToolUse

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/pre-push-verify.sh"

• PostToolUse

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/post-write-check.sh"

• PostToolUse

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/agent-ddd-verifier.sh"

• PostToolUse

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/post-write-check.sh"

• PostToolUse

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/post-bash-test-verify.sh"

• TaskCompleted

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/task-completed-verify.sh"

• PostToolUseFailure

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/tool-failure-tracker.sh"

• PostToolUseFailure

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/post-bash-test-verify.sh"

• UserPromptSubmit

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/bias-detector.sh"

• UserPromptSubmit

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/post-bash-test-verify.sh"

• FileChanged

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/file-changed.sh"

• SubagentStop

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/subagent-quality-gate.sh"

• PreCompact

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/pre-compact-save.sh"

• PostCompact

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/post-compact-verify.sh"

• Stop

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/test-dismissal-guard.sh"

• Stop

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/agent-sentry-context.sh"

• Stop

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/agent-final-review.sh"

• SessionEnd

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/session-metrics.sh"

Similar plugins