arcanea

Classify, author, and validate Arcanean spells on the four canon axes (element, discipline, tier, gate/rank). Use when adding or reviewing spells, building the magic encyclopedia, or generating spell media. Canon-faithful — never contradicts CANON_LOCKED.md.

Frameworks for productive human-AI co-creation - the orchestra model, creative partnerships, and symbiotic workflows

Anti-trope and naming protocol - banned AI cliches, forbidden words, and better alternatives for authentic Arcanean prose

The Seven Luminors - aspects of creative consciousness providing guidance through archetypical wisdom for any creative challenge

Character development through psychological depth - wounds, desires, contradictions, and authentic character voices

Navigate creative blocks using the taxonomy of psychological obstacles - naming rituals and protocols for each creature type

Master narrative craft - story structure, scene design, dramatic tension, and meaning-making through storytelling

Universe creation and world-building - geography, history, belief systems, cultures, and living ecologies of meaning

Guide for building MCP (Model Context Protocol) servers for the Arcanea ecosystem. Use when creating new MCP tools, extending packages/arcanea-mcp, adding Arcanea-branded tools, integrating external APIs as MCP endpoints, or building new MCP servers for the Arcanea AI toolkit. Triggers on: MCP server, MCP tool, model context protocol, mcp-builder, create tool, arcanea-mcp, new MCP. Sourced from Anthropic's official mcp-builder skill, adapted for Arcanea's TypeScript + Bun stack.

Next.js 16 App Router best practices for Arcanea. Use when writing or reviewing Next.js page files, layouts, route handlers, middleware, metadata, image/font optimization, RSC boundaries, async params/cookies, or any App Router pattern. Triggers on: layout.tsx, page.tsx, route.ts, loading.tsx, error.tsx, generateMetadata, Server Actions, 'use client', 'use server', next/image, next/font. Sourced from Vercel's official next-skills repository.

Playwright E2E testing for the Arcanea web app. Use when writing, running, or debugging Playwright tests, automating browser interactions on the Arcanea platform, capturing screenshots for QA, testing UI flows (academy gate quizzes, lore pages, prompt books, auth), or setting up the test infrastructure. Triggers on: Playwright, E2E test, end-to-end, browser test, UI test, automation, screenshot, test the page. Sourced from Anthropic's official webapp-testing skill and adapted for Arcanea's Next.js 16 stack.

React 19 and Next.js 16 performance optimization for the Arcanea platform. Use when writing, reviewing, or refactoring React components, data fetching logic, bundle optimization, or any frontend performance work. Triggers on: React components, Next.js pages, hooks, data fetching, bundle size, re-renders, Server Components, Client Components, hydration. Sourced from Vercel Engineering's official React best practices (57 rules, 8 categories) and adapted for the Arcanea stack.

Supabase + PostgreSQL patterns for Arcanea. Use when writing SQL queries, designing database schemas, implementing Row Level Security, managing connections, optimizing Supabase queries, or working with Supabase Auth, Realtime, or Storage. Triggers on: supabase, postgres, SQL, RLS, row level security, schema, migration, database, auth, realtime, storage. Sourced from Supabase Engineering's official postgres-best-practices skill.

TypeScript strict mode expert patterns for the Arcanea stack. Use when writing TypeScript types, resolving type errors, designing type-safe APIs, working with generics, discriminated unions, Zod validation, or any TypeScript-heavy work. Triggers on: TypeScript, type error, any, generic, interface, type, discriminated union, Zod, type safety, strict mode, infer. Stack: TypeScript 5.5+ strict mode, Next.js 16, Supabase typed client, Vercel AI SDK 6, Zod.

Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications.

Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.

Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.

Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.

Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Comprehensive GitHub code review with AI-powered swarm coordination

Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration

Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning

Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management

Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management

Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows.

Leverage Claude Opus 4.5's extended thinking capabilities for deep reasoning, complex analysis, and multi-step synthesis. Use when problems require thorough deliberation before response.

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks

Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.

Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workflows, or implementing meta-cognitive systems.

Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.

Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows

Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows

Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

CLI modernization and hooks system enhancement for claude-flow v3. Implements interactive prompts, command decomposition, enhanced hooks integration, and intelligent workflow automation.