Agent Skills Hub

screenshot-capture

Automated screenshot-to-knowledge workflow for Enzo. Captures, categorizes, extracts content, and logs patterns from screenshots to build a structured reference library.

query-sub-agent

Specialized IDF (Information Display Frame) sub-agent for generating and reviewing CQRS Query Side implementations across Java, TypeScript, and Go.

plantuml-manipulator

Structured batch manipulation, validation, and reporting for PlantUML sequence diagrams across multiple files.

data-engineer

Specialized data engineering agent for designing ETL/ELT pipelines, defining data schemas, managing data quality, and implementing robust ingestion workflows.

cohort-analysis

Perform cohort analysis on user engagement data. Identify retention trends, feature adoption rates, churn patterns, and generate actionable research recommendations through quantitative data analysis.

claude-code-guide

An advanced development guide for Claude Code, covering REPL environments, MCP integration, development workflows, and best practices for AI-assisted coding.

postgresql-table-design

A comprehensive guide for designing high-performance, maintainable PostgreSQL database schemas, covering best practices, data types, indexing, and advanced features.

database-driver-design

Expert guidance for building production-ready Swift database client libraries, covering wire protocols, connection pooling, state machines, and NIO integration.

session-logs

Search, analyze, and audit GeminiClaw session logs and memory. Use to investigate past interactions, track token usage, debug tool calls, and monitor agent performance.

qras

A local RAG semantic memory system using Qdrant and Ollama. Ideal for recalling workspace files, notes, project decisions, and user preferences with high-relevance vector search.

web-search

Autonomous research specialist for verified information gathering, source evaluation, and structured synthesis.

kreuzberg

High-performance document intelligence library for extracting text, tables, code, and metadata from 91+ file formats, with OCR and LLM-ready output.