Skill UI

Freezes PRD, technical design, and acceptance criteria before medium-to-large Codex work, then coordinates multiple agents with explicit file ownership and judges delivery from diffs, tests, and evidence-backed acceptance.

Diagnose slow SQL queries using execution plans, preserve results, and validate indexing or query modifications against representative data. This skill helps debug performance issues, design efficient schemas, reduce database load, and improve application scalability for growing datasets.

This skill provides comprehensive guidelines for optimizing Postgres database performance and security. It covers query optimization, schema design, connection management, Row-Level Security, and concurrency handling. Use it when writing SQL, reviewing database configurations, or implementing indexes. Based on Supabase best practices to ensure efficient and secure database operations for production environments.

LWC is a durable memory system for coding agents that preserves project decisions, code structure, and verified context across sessions. It utilizes a physical Wiki document graph and a CodeGraph index to enable source-grounded recall. This tool helps agents search, update, and maintain knowledge without losing critical information during future coding-agent interactions.

Expert in vector databases, embedding strategies, and semantic search implementation. Proficient with tools like Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similarity search. Optimizes index configuration, hybrid search, and performance tuning for scalable AI systems.

Deploy, configure, and optimize production vector databases such as Qdrant, Weaviate, pgvector, and Pinecone for RAG, semantic search, and recommendations, covering collection design, HNSW indexing, quantization, and multi-tenant filtering.

This comprehensive guide outlines best practices for optimizing vector indexes for production systems. It covers critical techniques such as tuning HNSW parameters, implementing quantization strategies, and optimizing memory usage. Use this when you need to balance search latency, recall, and scalability for large-scale vector databases.

Vexor is a command-line interface tool that utilizes vector embeddings to perform semantic file searches. It is designed to enhance workflow efficiency by allowing users to query files based on meaning rather than keywords, particularly when integrated with AI models like Claude or Codex. Ideal for developers needing context-aware file retrieval within codebases or documentation.

This comprehensive skill provides an index of official blueprints and implementation guides for building full-stack, AI-powered applications using Weaviate. It covers advanced patterns such as Retrieval-Augmented Generation (RAG), agentic workflows, data exploration, and multimodal document search, guiding users through best practices for setup, clients, and frontends.