context-engineering-collection

SKILL.md

This collection provides structured guidance for building production-grade AI agent systems through effective context engineering.

Context is not just prompt text—it is the complete state available to the language model at inference time, including system instructions, tool definitions, retrieved documents, message history, and tool outputs. Effective context engineering means understanding what information truly matters for the task at hand and curating that information for maximum signal-to-noise ratio.

Language models exhibit predictable degradation patterns as context grows: the "lost-in-middle" phenomenon where information in the center of context receives less attention; U-shaped attention curves that prioritize beginning and end; context poisoning when errors compound; and context distraction when irrelevant information overwhelms relevant content.

컨텍스트 엔지니어링, 멀티 에이전트 아키텍처 및 프로덕션 에이전트 시스템을 위한 포괄적인 에이전트 기술 컬렉션입니다. 효과적인 컨텍스트 관리가 필요한 에이전트 시스템을 구축, 최적화 또는 디버깅할 때 사용합니다. 출처: muratcankoylan/agent-skills-for-context-engineering.

원본 보기