muratcankoylan/Agent-Skills-for-Context-Engineering: Trending on GitHub

muratcankoylan/Agent-Skills-for-Context-Engineering: Trending on GitHub

In the rapidly evolving landscape of artificial intelligence (AI), context engineering has emerged as a crucial discipline for building production-grade AI agent systems. The muratcankoylan/Agent-Skills-for-Context-Engineering repository on GitHub is a comprehensive, open collection of Agent Skills focused on context engineering principles. These skills teach the art and science of curating context to maximize agent effectiveness across any agent platform.

What is Context Engineering?

Context engineering is the discipline of managing the language model's context window. Unlike prompt engineering, which focuses on crafting effective instructions, context engineering addresses the holistic curation of all information that enters the model's limited attention budget: system prompts, tool definitions, retrieved documents, message history, and tool outputs. The fundamental challenge is that context windows are constrained not by raw token capacity but by attention mechanics. As context length increases, models exhibit predictable degradation patterns: the "lost-in-the-middle" phenomenon, U-shaped attention curves, and attention scarcity. Effective context engineering means finding the smallest possible set of high-signal tokens that maximize the likelihood of desired outcomes.

Recognition

This repository is cited in academic research as foundational work on static skill architecture:

"While static skills are well-recognized [Anthropic, 2025b; Muratcan Koylan, 2025], MCE is among the first to dynamically evolve them, bridging manual skill engineering and autonomous self-improvement."

— Meta Context Engineering via Agentic Skill Evolution, Peking University State Key Laboratory of General Artificial Intelligence (2026)

Skills Overview

The repository contains a comprehensive set of skills, categorized into five areas: Foundational Skills, Architectural Skills, Operational Skills, Development Methodology, and Cognitive Architecture Skills.

Foundational Skills

These skills establish the foundational understanding required for all subsequent context engineering work.

• context-fundamentals: Understand what context is, why it matters, and the anatomy of context in agent systems.
• context-degradation: Recognize patterns of context failure: lost-in-middle, poisoning, distraction, and clash.
• context-compression: Design and evaluate compression strategies for long-running sessions.

Architectural Skills

These skills cover the patterns and structures for building effective agent systems.

• multi-agent-patterns: Master orchestrator, peer-to-peer, and hierarchical multi-agent architectures.
• memory-systems: Design short-term, long-term, and graph-based memory architectures.
• tool-design: Build tools that agents can use effectively.
• filesystem-context: Use filesystems for dynamic context discovery, tool output offloading, and plan persistence.
• hosted-agents: Build background coding agents with sandboxed VMs, pre-built images, multiplayer support, and multi-client interfaces.

Operational Skills

These skills address the ongoing operation and optimization of agent systems.

• context-optimization: Apply compaction, masking, and caching strategies.
• evaluation: Build evaluation frameworks for agent systems.
• advanced-evaluation: Master LLM-as-a-Judge techniques: direct scoring, pairwise comparison, rubric generation, and bias mitigation.

Development Methodology

These skills cover the meta-level practices for building LLM-powered projects.

• project-development: Design and build LLM projects from ideation through deployment, including task-model fit analysis, pipeline architecture, and structured output design.

Cognitive Architecture Skills

These skills cover formal cognitive modeling for rational agent systems.

• bdi-mental-states: Transform external RDF context into agent mental states (beliefs, desires, intentions) using formal BDI ontology patterns for deliberative reasoning and explainability.

Design Philosophy

The repository follows a design philosophy that emphasizes progressive disclosure, platform agnosticism, and conceptual foundation with practical examples.

• Progressive Disclosure: Each skill is structured for efficient context use. At startup, agents load only skill names and descriptions. Full content loads only when a skill is activated for relevant tasks.
• Platform Agnosticism: These skills focus on transferable principles rather than vendor-specific implementations. The patterns work across Claude Code, Cursor, and any agent platform that supports skills or allows custom instructions.
• Conceptual Foundation with Practical Examples: Scripts and examples demonstrate concepts using Python pseudocode that works across environments without requiring specific dependency installations.

Usage

The repository provides a comprehensive set of skills that can be used with Claude Code, Cursor, and other agent platforms.

• Installation: To install the skills, run the following command in Claude Code: /plugin marketplace add muratcankoylan/Agent-Skills-for-Context-Engineering
• Usage: Once installed, the skills can be used by selecting the relevant skill and following the instructions provided.

Examples

The repository includes a set of examples that demonstrate the usage of the skills in real-world scenarios.

• digital-brain-skill: A personal operating system for founders and creators that uses a combination of skills to provide a comprehensive set of features.
• x-to-book-system: A multi-agent system that monitors X accounts and generates daily synthesized books using a combination of skills.
• llm-as-judge-skills: A production-ready LLM evaluation tool that uses a combination of skills to provide a comprehensive set of features.
• book-sft-pipeline: A system that trains models to write in any author's style using a combination of skills.

Star History

The repository has a star history that reflects its popularity and usage in the community.

• Structure: The repository follows a standard structure that includes a set of skills, each with its own documentation and examples.
• Contributing: The repository is open to contributions from the community, and contributors are encouraged to follow a set of guidelines to ensure that their contributions are consistent with the rest of the repository.

License

The repository is licensed under the MIT License, which allows for free use, modification, and distribution of the code.

• Requirements: The repository has a set of requirements that must be met in order to use the skills, including a minimum of 800 words of documentation and a clear structure.
• References: The repository includes a set of references that provide additional information and context for the skills.

Overall, the muratcankoylan/Agent-Skills-for-Context-Engineering repository provides a comprehensive set of skills that can be used to build production-grade AI agent systems. The repository is well-structured, well-documented, and widely used in the community, making it a valuable resource for anyone interested in building AI systems.

Source: https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering