Systematic 3-phase Drupal development workflow with agents, skills, and commands. Implements Research → Architecture → Implementation phases with enforced SOLID, TDD, DRY, and security principles.
npx claudepluginhub camoa/claude-skills --plugin drupal-dev-frameworkMark a task as done and move to completed. Trigger: 'finish task', 'mark done', 'task complete', 'close task'. Runs ALL 5 quality gates before allowing completion.
Design architecture for a specific task. Trigger: 'architecture', 'design task', 'plan component', 'Phase 2'. REQUIRES completed research. Enforces Library-First, CLI-First, SOLID, DRY.
Load context and start implementing a task. Trigger: 'start coding', 'implement task', 'begin implementation', 'Phase 3', 'write code'. REQUIRES completed architecture. Enforces TDD (test-first).
Migrate v2.x single-file tasks to v3.0.0 folder structure. Trigger: 'upgrade tasks', 'convert task format', 'v2 to v3 migration'.
Start a new development project. Trigger: 'start project', 'new module', 'initialize project', 'begin development'. Creates project structure and gathers requirements BEFORE any coding.
Suggest next action based on project state. Trigger: 'what's next', 'continue working', 'resume', 'suggest action', 'what should I do'. ALWAYS use this when resuming work — it enforces phase order and quality gates.
Get pattern recommendations for a use case. Trigger: 'recommend pattern', 'which approach', 'Drupal pattern for', 'how should I implement'.
Research or investigate a task with competing agent team (3 perspectives + debate). Trigger: 'team research', 'debate', 'competing perspectives', 'deep research', '3 perspectives'. Better than /research for complex decisions.
Research a task topic and store findings in task file. Trigger: 'investigate', 'find patterns', 'research task', 'Phase 1', 'look into'. MUST be done before /design. Never skip research.
Show current project state and task progress. Trigger: 'show progress', 'where am I', 'project overview', 'task status'.
Validate implementation against architecture and standards. Trigger: 'check code', 'verify implementation', 'run validation', 'does this follow architecture'. Use proactively during Phase 3.
Compare rendered Drupal page against Figma design comp. Use when user says 'visual check', 'does it match the design', 'compare with figma', 'check against comp', 'visual parity', 'design match'. Requires Chrome (--chrome) for rendered page inspection. Optionally uses Figma MCP for automated design spec extraction.
Use when designing project architecture - creates architecture/main.md with component breakdown, service dependencies, and pattern references. Trigger: 'design module', 'plan architecture', 'create architecture document', 'component design', 'service design'. MUST enforce Library-First (services before forms/controllers), CLI-First (Drush commands for all features), SOLID principles, and DRY patterns. NEVER approve architecture that puts business logic in forms or controllers.
Use when validating implementation against architecture - checks approach matches documented patterns, dependencies, architecture principles (Library-First, CLI-First), and SOLID/DRY principles. Trigger: 'check my code', 'does this match the architecture', 'validate implementation', 'architecture review', 'code review against architecture'. MUST validate against ALL 5 quality gates: SOLID, Library-First/CLI-First, DRY, TDD, Security. BLOCK on violations — do not just warn. Use proactively after ANY code changes during Phase 3.
Use when researching Drupal contrib modules or existing solutions - analyzes drupal.org and contrib code to identify reusable patterns and integration points. Trigger: 'find existing module', 'is there a contrib for this', 'search drupal.org', 'existing solutions', 'before building'. Use proactively at the START of Phase 1 — ALWAYS check contrib before building custom. Never let user skip contrib research.
Use when choosing between Drupal patterns (FormBase vs ListBuilder, Entity vs Config) - recommends patterns with core/contrib references. Trigger: 'which pattern should I use', 'FormBase vs ConfigForm', 'entity type selection', 'best approach for', 'Drupal pattern for'. ALWAYS recommend patterns with core/contrib references. NEVER recommend a pattern without showing a core example.
Use when checking project status or deciding next steps - reads memory files, manages tasks, suggests actions, routes to appropriate agents/skills. Trigger: 'project status', 'what should I do next', 'which task', 'resume project', 'start working', 'continue'. ALWAYS route through 3-phase workflow (Research → Architecture → Implementation). NEVER skip phases. ALWAYS check quality gates before marking tasks complete.
Use before committing code - validates Drupal coding standards, SOLID/DRY principles, security practices, and CSS standards. Trigger: 'check code quality', 'pre-commit check', 'lint Drupal code', 'validate standards'. Use proactively before ANY commit. Checks SOLID, DRY, security, and Drupal coding standards.
Use when designing a specific module component - creates architecture/component_name.md with purpose, interface, dependencies, and pattern references
Use when needing Drupal core implementation examples - searches core modules for specific patterns and returns file path references
Use when visualizing architecture - generates Mermaid diagrams for data flow, service relationships, or entity structures. Trigger: 'draw diagram', 'visualize', 'show relationships', 'mermaid chart'.
Use when designing features - loads plugin methodology refs and delegates to dev-guides-navigator for online Drupal domain knowledge. Trigger: 'load guides', 'get reference docs', 'methodology references'. Use proactively during Phase 2 design — loads SOLID, Library-First, DRY, TDD, Security guides.
Use when needing specialized guide content - delegates to dev-guides-navigator plugin for online guide discovery with caching and disambiguation
Use when breaking down a component for implementation - creates task file in implementation_process/in_progress/ with TDD steps and acceptance criteria
Use after completing any phase activity - updates project_state.md, project registry, ensures files are in correct locations, maintains lean memory
Use when determining task phase - analyzes task file to identify Phase 1, 2, or 3 for a specific task
Use when starting a new development project - creates memory folder structure with project_state.md, architecture scaffolding, and registers project
Use when gathering project requirements - asks structured questions about project type, scope, integrations, and constraints to populate project_state.md
Use when resuming work on existing project - lists registered projects, reads project_state.md, summarizes current state, identifies where to continue. Trigger: 'pick up where I left off', 'continue project', 'what was I working on', 'resume session'.
Use when finishing a task - moves task to completed/, updates project_state.md, suggests next task. Trigger: 'finish task', 'done with task', 'move to completed'. MUST run ALL 5 quality gates. BLOCK completion if gates fail. Never skip gates.
Use when starting implementation of a task - loads architecture files, referenced patterns, relevant guides, and task file into context
Use when migrating existing single-file tasks to folder-based structure - preserves content, creates organized folders, backs up originals
Use during implementation to enforce TDD - reminds test-first, validates Red-Green-Refactor cycle, integrates with superpowers:test-driven-development. Trigger: 'test first', 'write tests', 'Red Green Refactor', 'TDD workflow'. MUST be active during all Phase 3 implementation. NEVER write implementation code before tests.
Battle-tested Claude Code plugin for engineering teams — 38 agents, 156 skills, 72 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.