context-engineering

Curate minimal high-signal token sets for LLM reasoning tasks.

Updated Jan 31, 2026

Search Tags:#llm #evaluation #multi-agent #compression #token-optimization #context-engineering #memory-systems

Ready to run

npx skills add https://github.com/luan-thnh/hrm-auto-extension --skill context-engineering-luan-thnh

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: context-engineering
Source: https://github.com/luan-thnh/hrm-auto-extension/tree/main/.opencode/skills/context-engineering
Command: npx skills add https://github.com/luan-thnh/hrm-auto-extension --skill context-engineering-luan-thnh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Context engineering curates the smallest high-signal token set for LLM tasks to maximize reasoning quality while minimizing token usage.

Core Features & Use Cases

Reduces context bloat by selecting high-signal tokens for reasoning tasks.
Guides design of agent architectures, memory systems, and multi-agent coordination in LL-powered workflows.
Provides practical patterns, metrics, and references to improve efficiency and evaluation.

Quick Start

Analyze a conversation context and output a compact, high-signal token plan preserving essential goals.

Frequently Asked Questions about context-engineering

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

FAQPage Schema

What is context engineering for LLM pipelines and when do I need it?▼

Context engineering curates the smallest high-signal token set for LLM tasks to maximize reasoning quality while minimizing token usage. You need it when reducing context bloat in multi-agent and memory-driven workflows.

How do I optimize token usage without losing essential reasoning goals?▼

Analyze a conversation context and output a compact, high-signal token plan preserving essential goals. This approach reduces token usage by selecting only the highest-value tokens needed for the specific reasoning task.

How does context engineering help debug context failures in multi-agent systems?▼

Context engineering helps debug multi-agent failures by providing practical patterns and metrics to evaluate token selection. It identifies where low-signal tokens degrade coordination and curates inputs to restore pipeline efficiency.

Can I use this to design memory systems for multi-agent coordination?▼

Yes, context engineering guides the design of agent architectures, memory systems, and multi-agent coordination in LLM-powered workflows. It provides reference patterns to structure memory efficiently across coordinated pipelines.

What are the limitations of relying on high-signal token selection for agent architectures?▼

High-signal token selection requires accurate evaluation metrics to avoid dropping critical context. If the compact token plan fails to preserve essential goals, agent architectures may experience reasoning failures or degraded multi-agent coordination.