context-engineering-collection

Centralizes best practices for AI agent context engineering.

17.7k|1.5k|Updated Dec 21, 2025

Search Tags:#context #evaluation #multi-agent #agents #orchestration #memory

Ready to run

npx skills add https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering --skill context-engineering-collection-muratcankoylan

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: context-engineering-collection
Source: https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/tree/main
Command: npx skills add https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering --skill context-engineering-collection-muratcankoylan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of fragmented context management in AI agents by providing a centralized collection of best-practices for context engineering.

Core Features & Use Cases

Foundational, architectural, and operational patterns spanning context fundamentals, degradation, compression, multi-agent patterns, memory systems, tool design, and filesystem-based context
Progressive disclosure: metadata loads at startup; full instructions loaded on activation
Integration: cross-skill references, optional scripts/references/assets for on-demand use
Production-oriented guidance: evaluation frameworks, LLM-as-a-judge patterns, and project development guidance
Platform-agnostic applicability across Cursor, Claude Code, and other agent platforms

Quick Start

Begin by reading the collection overview and then explore foundational skills such as context-fundamentals.

Frequently Asked Questions about context-engineering-collection

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I manage context for AI agents to prevent fragmentation in production?▼

Context engineering standardizes AI agent context management by enforcing progressive disclosure, memory architectures, and disciplined tool integration to prevent fragmentation across platforms like Cursor and Claude Code.

What is progressive disclosure in multi-agent orchestration and how does it work?▼

Progressive disclosure in multi-agent orchestration loads metadata at startup and full instructions on activation, optimizing memory systems and preventing context degradation across distributed agent workflows.

How do I evaluate AI agent performance using LLM-as-a-judge patterns?▼

AI agent evaluation uses LLM-as-a-judge patterns and production-grade evaluation frameworks to assess context compression, multi-agent orchestration, and tool design effectiveness within development workflows.

Does this context engineering collection work with Cursor and Claude Code platforms?▼

This context engineering collection is platform-agnostic and supports Cursor, Claude Code, and other agent platforms by providing foundational patterns, filesystem-based context, and cross-skill references.

When should I use context compression for AI agents?▼

Context compression for AI agents should be used when managing large memory systems and multi-agent patterns, preventing context degradation and optimizing operational tool design in production environments.

What's the best way to structure filesystem-based context for AI agents?▼

Filesystem-based context for AI agents should follow architectural patterns with optional scripts, templates, and cross-skill references that standardize agent design and enforce progressive disclosure.