context-engineering-collection

Organize context-engineering patterns for multi-agent system architectures.

4|Updated Dec 23, 2025
One-click install
npx skills add https://github.com/ken-cavanagh-glean/fieldkit --skill context-engineering-collection
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: context-engineering-collection
Source: https://github.com/ken-cavanagh-glean/fieldkit/tree/main/plugins/context-engineering/skills/context-engineering
Command: npx skills add https://github.com/ken-cavanagh-glean/fieldkit --skill context-engineering-collection

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a structured collection of agent context-engineering patterns and guidance to build scalable, multi-agent systems. It helps teams design, evaluate, and optimize how context is structured, shared, and remembered across agents, boosting reliability and performance.

Core Features & Use Cases

  • Foundational context patterns for system prompts, tool contracts, memory layers, and retrieved documents.
  • Architectural patterns for multi-agent coordination, memory graphs, and isolation strategies.
  • Integration guidance across context-fundamentals, context-optimization, context-degradation, and evaluation to support production-grade agents.

Quick Start

  1. Review the core concepts and core patterns in this collection.
  2. Identify the sub-skills you need (e.g., context-fundamentals, memory-systems, multi-agent-patterns) and read their SKILL.md.
  3. Start applying progressive context management concepts in a pilot project.

Frequently Asked Questions about context-engineering-collection

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

FAQPage Schema
How do I structure context for multi-agent systems at scale?

Multi-agent context engineering requires organizing system prompts, tool contracts, and memory layers across coordinated agents. This collection provides architectural patterns for memory graphs, isolation strategies, and cross-domain coordination to ensure reliable information flow and agent isolation in production systems.

What's the difference between memory management approaches for agent teams?

Memory systems range from simple retrieval to graph-based architectures that track relationships across agents. This collection compares foundational patterns, optimization techniques, and degradation strategies so teams can choose the right memory layer for their scale and consistency requirements.

How do I design context to prevent agent coordination failures?

Context degradation and isolation failures break multi-agent workflows. This collection documents patterns for tool contract definition, memory isolation, and evaluation methods to identify coordination gaps before production deployment.

Can I apply these context patterns incrementally to existing agent systems?

Yes. Start with core concepts and foundational patterns, then adopt sub-skills like context-fundamentals, memory-systems, or multi-agent-patterns based on your architecture. Progressive implementation lets teams pilot changes without redesigning entire systems.

What preparation is needed before implementing these context patterns?

Review your current system prompts, tool definitions, and memory structure. Understand your agent count, domain isolation needs, and retrieval data formats. The collection's core concepts guide you through assessment before selecting specific architectural patterns.

How do I evaluate whether my context design will scale?

Context engineering success depends on memory graph efficiency, agent isolation, and information retrieval latency. This collection provides integration guidance and evaluation criteria to test coordination reliability and identify bottlenecks before scaling production deployments.