Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By camoa
Execute a structured 3-phase Drupal development workflow—Research patterns and requirements, Architecture design with SOLID/DRY enforcement and Mermaid diagrams, Implementation via TDD cycles—using agents, skills, and commands that validate code standards, security gates, and task progress before completion.
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.
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.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Complete guide for creating Claude Code plugins - skills, commands, agents, hooks, MCP servers, and configuration. Supersedes skill-creation-tools.
Drupal development workflow with live autopilot: 19 skills, 4 agents, 10 commands, behavioral evals, session analysis, and Magic Loop Autopilot for task classification and drift detection.
PHP and WordPress development capabilities
Automate 7-phase feature development with specialized agents (code-explorer, code-architect, code-reviewer). Use for multi-file features, architectural decisions, or encountering ambiguous requirements, integration patterns, design approach errors.
Agent Skills and specialist agents for Drupal and WordPress. PR workflows, accessibility / performance / security / quality audits, design-to-code (Figma → blocks/paragraphs), FRD generation with story points, CSV export, strategist UX audits, PM workflows (triage, meeting prep, heartbeats, QA), Drupal.org contribution, and Drupal/Pantheon DevOps. Skills use MCP servers (Teamwork, Slack, Gmail, Fathom, CoWork, GitHub) directly from the main session.
Expert agents for software architecture, backend development, and system design
Systematic testing through mental execution - trace code, skills, commands, and configs line-by-line with concrete values to find bugs, missing logic, edge cases, and AI hallucinations
Smart guide discovery and routing for dev-guides. Uses hash-based caching and KG metadata (concepts, disambiguation, relationships) to route AI to the correct guide. All fetches use curl (never WebFetch) to preserve raw structured content.
Complete guide for creating Claude Code plugins - skills, commands, agents, hooks, MCP servers, and configuration. Supersedes skill-creation-tools.
Create branded visual content (presentations, carousels, infographics, HTML pages) with Aaker personality-driven design, style recommendation engine, visual components, 26 visual styles, design systems, and Presentation Zen principles
HTMX development guidance and AJAX-to-HTMX migration tools for Drupal 11.3+. Includes analyzers, pattern recommendations, and validation.
Custom plugins and tools for Claude Code.
I started building what I called "frameworks" over a year before Claude officially released Skills. Same concept, different name.
The idea came from frustration. I was tired of repeating the same instructions every conversation. Instead of starting fresh each time, I asked AI to analyze our successful interactions and create frameworks capturing recurring requirements and preferences. These became reusable project knowledge.
This approach produced results: 3 published Drupal contrib modules, 17+ blog articles, automated social media campaigns, and phase-based editorial workflows.
When Claude released Skills officially, I recognized what I'd been building. This repository translates those frameworks into proper Skills with tooling.
I wrote more about this methodology in My Journey with AI Tools.
# Add the marketplace
/plugin marketplace add https://github.com/camoa/claude-skills
# Install individual plugins
/plugin install dev-guides-navigator@camoa-skills
/plugin install drupal-dev-framework@camoa-skills
/plugin install plugin-creation-tools@camoa-skills
/plugin install brand-content-design@camoa-skills
/plugin install code-quality-tools@camoa-skills
/plugin install drupal-htmx@camoa-skills
/plugin install code-paper-test@camoa-skills
There's a known bug in Claude Code affecting git-based marketplaces. Skills may fail to load during initialization with "no such file or directory" errors because Claude Code looks for skill files in the wrong location.
Workaround: Skills still work when invoked via the Skill tool (slash commands). The issue only affects automatic discovery at startup.
Status: Awaiting fix from Anthropic.
Smart guide discovery and routing for the dev-guides site. Routes AI to the correct guide using hash-based caching and KG metadata for disambiguation.
llms.txt with hash-based freshness check — no redundant fetchesconcepts/not fields) prevents wrong-guide selection (e.g., "story.yml" routes to UI Patterns, not Storybook)llms.txt → topic index.md → specific guide# Invoked automatically before design/dev tasks, or manually:
/dev-guides-navigator style guide
Systematic 3-phase Drupal development workflow: Research → Architecture → Implementation. Enforces SOLID, TDD, DRY, security, and code purposefulness through 5 quality gates. Requires dev-guides-navigator — loads Drupal domain guides proactively at every phase.
/plugin install dev-guides-navigator@camoa-skills # Required dependency
/plugin install drupal-dev-framework@camoa-skills
/drupal-dev-framework:new my_module # Create project
/drupal-dev-framework:next # Continue work (main entry point)
| Component | Contents |
|---|---|
| Commands | 11 (/new, /next, /research, /research-team, /design, /implement, /complete, /status, /validate, /pattern, /migrate-tasks) |
| Agents | 5 with cost control (maxTurns) — project-orchestrator, architecture-drafter, architecture-validator (isolated worktree), pattern-recommender, contrib-researcher |
| Skills | 16 (phase management, TDD companion, guide integration, context loading) |
| References | 6 methodology docs (SOLID, TDD, DRY, Library-First, Quality Gates, Purposeful Code) |
| Hooks | SessionStart (dependency check + project context), PreCompact (context preservation) |
Features competing agent research (/research-team) with Build/Use/Extend debate for features and competing hypothesis investigation for bugs.
See drupal-dev-framework/README.md for full documentation.
Complete guide for creating Claude Code plugins — skills, commands, agents, hooks, MCP servers, and configuration. Covers 18 hook events, 4 hook types (command/prompt/agent/HTTP), agent isolation and cost control, marketplace distribution with 6 source types, and pushy description optimization.
# Just describe what you want:
Create a plugin called "my-tools" with a deploy command
# Or use specific commands:
/plugin-creation-tools:create my-tools --skill --agent --hook
/plugin-creation-tools:validate ./my-tools
| Component | Contents |
|---|---|
| Skills | 1 (plugin-creation — 30+ reference docs, templates, examples) |
| Commands | 3 (/create, /add-component, /validate) |
| Agents | 2 (skill-quality-reviewer, plugin-structure-auditor) |