agent-evaluation
🔌Pluginmuratcankoylan/Agent-Skills-for-Context-Engineering
|A comprehensive collection of agent skills focused on context engineering principles for building production-grade AI agent systems, covering context management, multi-agent architectures, memory systems, and evaluation frameworks.
Overview
Agent Skills for Context Engineering is an open collection of skills that teaches the discipline of context engineering — the art of managing a language model's context window to maximize agent effectiveness. Unlike simple prompt engineering, these skills address the holistic curation of all information entering the model's attention budget: system prompts, tool definitions, retrieved documents, message history, and tool outputs. The repository is cited in academic research from Peking University as foundational work on static skill architecture.
Key Features
- Foundational skills covering context fundamentals, degradation patterns (lost-in-middle, poisoning, distraction), and compression strategies for long-running sessions
- Architectural skills for multi-agent patterns (orchestrator, peer-to-peer, hierarchical), memory systems (short-term, long-term, graph-based), tool design, and filesystem-based context management
- Operational skills including context budgeting, agent evaluation with LLM-as-judge frameworks, planning strategies, and prompt self-optimization
- Advanced techniques for context routing, hosted background agents with sandboxed VMs, human-in-the-loop patterns, and production reliability patterns
- Platform-agnostic design — skills work across any agent platform, not tied to a specific framework
Who is this for?
Developers building AI agent systems who want to go beyond basic prompt engineering and master the science of context window management. Ideal for teams building production-grade multi-agent architectures, engineers dealing with context degradation in long-running agent sessions, and researchers studying agent skill frameworks and context engineering principles.
Part of
muratcankoylan-agent-skills-for-context-engineering
Installation
/plugin marketplace add muratcankoylan/Agent-Skills-for-Context-Engineering/plugin install agent-evaluation@context-engineering-marketplaceMore from this repository10
Context Engineering skills for building production-grade AI agent systems
A collection of agent skills focused on context engineering principles, teaching the art of curating the language model's context window for building production-grade AI agent systems.
Context engineering skills collection teaching the art of curating LLM context windows for production-grade AI agent systems, covering system prompts, tool definitions, and message history management
A context engineering skill that teaches agents how to compress and manage context windows efficiently, addressing attention mechanics, the lost-in-the-middle phenomenon, and token budget optimization for production AI systems.
A comprehensive collection of agent skills focused on context engineering principles for building production-grade AI agent systems. It covers managing context windows through attention mechanics, token budgeting, and structured information curation, and has been cited in academic research from Peking University and multiple US universities.
A comprehensive collection of agent skills focused on context engineering principles for building production-grade AI agent systems. Covers context fundamentals, degradation patterns, compression strategies, multi-agent architectures, memory systems, and tool design, cited in academic research from Peking University and CMU.
A comprehensive collection of agent skills focused on context engineering and harness engineering for building production-grade AI agent systems, covering context fundamentals, compression, multi-agent patterns, and memory system design. Cited in academic research from Peking University and CMU.
Part of Agent Skills for Context Engineering, a collection focused on context engineering and harness engineering principles for building production-grade AI agent systems, cited in academic research from Peking University and others.
A collection of agent skills focused on context engineering principles for building production-grade AI systems, covering context window management, attention mechanics, compression strategies, multi-agent patterns, and context degradation prevention.
A collection of agent skills focused on context engineering principles, teaching how to curate and manage the language model's context window for maximum effectiveness in production-grade AI agent systems.