This repository provides a comprehensive set of Agent Skills focused on context engineering and harness engineering principles for building production-grade AI agent systems. It teaches how to curate context, design agent operating loops, and evaluate agent behavior across agent platforms. The work addresses challenges like the lost-in-the-middle phenomenon, U-shaped attention curves, and attention scarcity that arise as context length increases in LLM-based systems. It is cited in academic research on meta context engineering and agent harness engineering.