muratcankoylan/agent-skills-for-context-engineering

context-engineering-collection skill from muratcankoylan/agent-skills-for-context-engineering

hosted-agents skill from muratcankoylan/agent-skills-for-context-engineering

Compresses and optimizes conversation context by strategically summarizing and preserving critical information while minimizing token usage across long-running agent sessions.

Optimizes context windows by strategically compressing, masking, caching, and partitioning to extend effective context capacity without increasing model size.

Enables persistent knowledge storage and retrieval across agent sessions through layered memory architectures, knowledge graphs, and temporal tracking.

Designs agent tools with clear contracts, unambiguous interfaces, and precise descriptions to enable effective agent-system interactions.

Skill

bdi-mental-states skill from muratcankoylan/agent-skills-for-context-engineering

Explains context engineering principles, architecture design, and optimization strategies for AI agent systems' context management and attention mechanics.

Designs and coordinates multi-agent systems by distributing complex tasks across specialized agents with isolated contexts for enhanced problem-solving.

Guides users through designing LLM project architectures, evaluating task-model fit, and selecting optimal agent-based development strategies.

filesystem-context skill from muratcankoylan/agent-skills-for-context-engineering

Develops robust LLM-as-a-judge evaluation techniques, mitigating biases and creating reliable automated quality assessment frameworks for comparing model outputs.

Systematically evaluates agent performance using multi-dimensional rubrics, LLM-as-judge techniques, and outcome-focused testing methodologies.

Conducts systematic, multi-source research by dynamically retrieving, synthesizing, and contextualizing information across diverse knowledge domains.

Evaluation frameworks and LLM-as-judge techniques for testing and validating AI agent systems

BDI mental state modeling and cognitive architecture patterns for building rational agents with formal belief-desire-intention representations

Multi-agent patterns, memory systems, tool design, filesystem-based context, and hosted agent infrastructure for building production AI agent architectures

Project development methodology for LLM-powered applications including pipeline architecture and batch processing

Core context engineering skills covering fundamentals, degradation patterns, compression strategies, and optimization techniques for AI agent systems

Context Engineering skills for building production-grade AI agent systems