Claude Skills

High-performance computing patterns for C++20 including cache-friendly data structures, SIMD vectorization, memory management, thread parallelism, lock-free data structures, and NUMA-aware allocation.

CWF knowledge repository providing plan structure, tasklist format, checkpoint definitions, amendment rules, and validation requirements. Load this skill when: (1) executing CWF commands like /write-plan, /implement-plan, /amend-plan, (2) answering questions about CWF workflow or plan/tasklist format, (3) validating plan or tasklist documents, (4) understanding phase structure or task conventions. This is KNOWLEDGE context, not an action - do NOT confuse with the /write-plan, /implement-plan, /amend-plan, or /brainstorm commands which are user-invoked.

Deep reasoning with Claude's extended thinking feature for complex multi-step problems. Use when implementing think-aloud reasoning, complex analysis, or debugging difficult issues.

Validates Claude Agent SDK configuration files, environment setup, dependencies, and project structure

API authentication patterns, SDK installation scripts, environment variable management, and connection testing for ElevenLabs. Use when setting up ElevenLabs authentication, installing ElevenLabs SDK, configuring API keys, testing ElevenLabs connection, or when user mentions ElevenLabs authentication, xi-api-key, ELEVENLABS_API_KEY, or ElevenLabs setup.

Production deployment patterns for ElevenLabs API including rate limiting, error handling, monitoring, and testing. Use when deploying to production, implementing rate limiting, setting up monitoring, handling errors, testing concurrency, or when user mentions production deployment, rate limits, error handling, monitoring, ElevenLabs production.

Document chunking implementations and benchmarking tools for RAG pipelines including fixed-size, semantic, recursive, and sentence-based strategies. Use when implementing document processing, optimizing chunk sizes, comparing chunking approaches, benchmarking retrieval performance, or when user mentions chunking, text splitting, document segmentation, RAG optimization, or chunk evaluation.

Multi-format document parsing tools for PDF, DOCX, HTML, and Markdown with support for LlamaParse, Unstructured.io, PyPDF2, PDFPlumber, and python-docx. Use when parsing documents, extracting text from PDFs, processing Word documents, converting HTML to text, extracting tables from documents, building RAG pipelines, chunking documents, or when user mentions document parsing, PDF extraction, DOCX processing, table extraction, OCR, LlamaParse, Unstructured.io, or document ingestion.

Google File Search API patterns for managed RAG with Gemini. Covers both TypeScript (@google/genai) and Python (google-genai) SDKs. Use when building File Search integrations, implementing RAG with Google AI, or when user mentions Google File Search, Gemini RAG, document indexing, or semantic search.

Agentic Platform Contract tables for AI agent applications - runs, events, artifacts, and tool calls tracking. Use when building AI agent backends that need structured run/event storage.

Configure Supabase authentication providers (OAuth, JWT, email). Use when setting up authentication, configuring OAuth providers (Google/GitHub/Discord), implementing auth flows, configuring JWT settings, or when user mentions Supabase auth, social login, authentication setup, or auth configuration.

End-to-end testing scenarios for Supabase - complete workflow tests from project creation to AI features, validation scripts, and comprehensive test suites. Use when testing Supabase integrations, validating AI workflows, running E2E tests, verifying production readiness, or when user mentions Supabase testing, E2E tests, integration testing, pgvector testing, auth testing, or test automation.

Configure pgvector extension for vector search in Supabase - includes embedding storage, HNSW/IVFFlat indexes, hybrid search setup, and AI-optimized query patterns. Use when setting up vector search, building RAG systems, configuring semantic search, creating embedding storage, or when user mentions pgvector, vector database, embeddings, semantic search, or hybrid search.

Row Level Security policy templates for Supabase - multi-tenant patterns, user isolation, role-based access, and secure-by-default configurations. Use when securing Supabase tables, implementing RLS policies, building multi-tenant AI apps, protecting user data, creating chat/RAG systems, or when user mentions row level security, RLS, Supabase security, tenant isolation, or data access policies.

RLS policy testing patterns for Supabase - automated test cases for Row Level Security enforcement, user isolation verification, multi-tenant security, and comprehensive security audit scripts. Use when testing RLS policies, validating user isolation, auditing Supabase security, verifying tenant isolation, testing row level security, running security tests, or when user mentions RLS testing, security validation, policy testing, or data leak prevention.

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.

Production-ready database schema patterns for AI applications including chat/conversation schemas, RAG document storage with pgvector, multi-tenant organization models, user management, and AI usage tracking. Use when building AI applications, creating database schemas, setting up chat systems, implementing RAG, designing multi-tenant databases, or when user mentions supabase schemas, chat database, RAG storage, pgvector, embeddings, conversation history, or AI application database.

Database schema validation tools - SQL syntax checking, constraint validation, naming convention enforcement, and schema integrity verification. Use when validating database schemas, checking migrations, enforcing naming conventions, verifying constraints, or when user mentions schema validation, migration checks, database best practices, or PostgreSQL validation.

The EXPLORING phase gathers context about the project and forms an initial understanding