Agent Skills for Context Engineering
ActiveDescription
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems.
Key Features
- Covers 15 context engineering skills from foundational concepts to advanced cognitive architectures for systematic AI agent knowledge building
- Platform-agnostic design, applicable to Claude Code, Cursor, and any agent platform supporting custom instructions
- Progressive disclosure architecture: loads only skill names and descriptions at startup, activating full content on demand
- Covers context degradation pattern recognition, compression strategies, multi-agent coordination patterns, and memory system design
- Cited in academic research papers from Peking University, CMU, Yale, and other top institutions
- One-click installation via Claude Code plugin marketplace with automatic skill activation based on task context
Use Cases
💡 AI agent developers learning context management best practices to improve agent system performance
💡 Choosing appropriate coordination patterns and context isolation strategies when designing multi-agent architectures
💡 Diagnosing agent performance degradation in long sessions, such as the Lost-in-the-Middle phenomenon
💡 Building agent evaluation frameworks using LLM-as-a-Judge techniques for systematic assessment
💡 Guiding development teams to establish context engineering standards and improve AI project quality
Tags
Categories
Quick Start
In Claude Code, run /plugin marketplace add muratcankoylan/Agent-Skills-for-Context-Engineering to register the marketplace, then run /plugin install context-engineering@context-engineering-marketplace to install all 15 skills. Skills activate automatically based on your task context, or you can specify them manually.