Agent Skills for Context Engineering

Install

/plugin marketplace add muratcankoylan/Agent-Skills-for-Context-Engineering
/plugin install context-engineering@context-engineering-marketplace

This is third-party code. Review the repository files before installing.

What it does

The collection teaches the agent principles for building reliable agent systems. Foundational skills explain what context consists of and how it degrades as it grows: lost in the middle, poisoning, distraction. Architectural skills cover multi-agent patterns, prompts for long autonomous tasks, memory systems, tool design and hosted background agents. Operational skills address context compression and optimization, agent evaluation and LLM judges, harnesses with rollback and self-improvement loops.

Who it is for. For developers building their own agents and multi-agent systems.

Example request

My agent gets confused after a hundred steps; figure out which kind of context degradation this is and how to fix it

Limitations

Skills describe approaches with Python pseudocode examples; there is no production-ready code. Some topics, such as KV cache sharing between agents, apply only when you control the model runtime.

How to disable. Uninstall the context-engineering plugin via /plugin.

Security check

• The skills consist of instructions and reference material

README in short

The README defines context engineering and explains that the window is limited by attention mechanics rather than token count. Skills are grouped into foundational, architectural, operational, methodology and cognitive architecture, with a description table. It covers design principles: progressive disclosure, platform independence and pseudocode examples. Installation is via a Claude Code marketplace, MIT licensed.

SKILL.md

---
name: context-engineering-collection
description: "A comprehensive collection of Agent Skills for context engineering, harness engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, evaluating, or debugging agent systems that require effective context management and reliable operating loops."
---

# Agent Skills for Context Engineering

This collection provides structured guidance for building production-grade AI agent systems through effective context engineering.

## When to Activate

Activate these skills when:
- Building new agent systems from scratch
- Optimizing existing agent performance
- Debugging context-related failures
- Designing multi-agent architectures
- Creating or evaluating tools for agents
- Implementing memory and persistence layers
- Designing autonomous research or evaluation harnesses

## Skill Map

### Foundational Context Engineering

**Understanding Context Fundamentals**
Context is not just prompt text—it is the complete state available to the language model at inference time, including system instructions, tool definitions, retrieved documents, message history, and tool outputs. Effective context engineering means understanding what information truly matters for the task at hand and curating that information for maximum signal-to-noise ratio.

**Recognizing Context Degradation**
Language models exhibit predictable degradation patterns as context grows: the "lost-in-middle" phenomenon where information in the center of context receives less attention; U-shaped attention curves that prioritize beginning and end; context poisoning when errors compound; and context distraction when irrelevant information overwhelms relevant content.

### Architectural Patterns

**Multi-Agent Coordination**
Production multi-agent systems converge on three dominant patterns: supervisor/orchestrator architectures with centralized control, peer-to-peer swarm architectures for flexible handoffs, and hierarchical structures for complex task decomposition. The critical insight is that sub-agents exist primarily to isolate context rather than to simulate organizational roles.

Related