skills.rest
hackefeller
hackefellerOFFICIAL
Explore all skills by this author →
WebsiteGitHub

agent-native-architecture

Design agent-native applications using parity, granularity, and composability principles.

1|Updated Feb 23, 2026
Search Tags:#architecture#prompt engineering#design patterns#agent#LLM#autonomous systems
One-click install
npx skills add https://github.com/hackefeller/ghostwire --skill agent-native-architecture-hackefeller
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-native-architecture
Source: https://github.com/hackefeller/ghostwire/tree/main/src/plugin/skills/agent-native-architecture
Command: npx skills add https://github.com/hackefeller/ghostwire --skill agent-native-architecture-hackefeller

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the challenge of building applications where software agents are not just tools but fundamental components, enabling complex autonomous workflows and features defined by outcomes rather than code.

Core Features & Use Cases

  • Agent-Native Design: Architect applications where agents are first-class citizens, driving features and outcomes.
  • Core Principles: Understand and apply principles like Parity, Granularity, Composability, Emergent Capability, and Improvement Over Time.
  • Use Case: Design a personal assistant application where agents manage user workflows, organize files, and automate tasks based on natural language descriptions, rather than predefined commands.

Quick Start

Use this skill to design a new agent-native system from scratch.

Frequently Asked Questions about agent-native-architecture

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

FAQPage Schema
What is agent-native architecture and how does it differ from traditional application design?▼

Agent-native architecture builds applications where software agents are first-class citizens driving features through autonomous loops, rather than using predefined commands. It applies principles like parity, granularity, and composability to achieve outcomes defined by natural language.

How do I design an LLM application where agents manage user workflows autonomously?▼

You design autonomous LLM workflows by using a framework that emphasizes tool design, execution patterns, and context injection. This allows agents to manage user workflows, organize files, and automate tasks based on natural language descriptions of desired outcomes.

Can I use this agent design framework to build a personal assistant that organizes files and automates tasks?▼

Yes, you can build a personal assistant application using this framework. Agents act as fundamental components that manage user workflows, organize files, and automate tasks dynamically through loops and primitives instead of relying on hardcoded commands.

What are the core principles for building composable autonomous systems with LLMs?▼

The core principles for building composable autonomous systems include Parity, Granularity, Composability, Emergent Capability, and Improvement Over Time. These principles guide how agents use primitives and loops to achieve complex outcomes.

Do I need predefined commands to build an agent-native application?▼

No, you do not need predefined commands to build an agent-native application. Features are defined by outcomes rather than code, allowing agents to dynamically drive workflows and automate tasks based on natural language descriptions.

Related Skills

Explore More Software Engineering Skills→
ricardorochericardoroche
2

prompting-patterns

Automate prompt engineering with structured templates, few-shot examples, and injection prevention.

Community
Intermediate
i3ringiti3ringit
3

agent-native-architecture

Standardize agent-native architectures by separating prompts from atomic tools.

Community
Advanced
sammyjoycesammyjoyce

agent-native-architecture

Define core principles and tool design patterns for agent-native applications.

Community
Advanced
skogaiskogai

skogai-prompting

Defines prompt-native architectures for autonomous AI agents using outcome-based instructions instead of hard-coded workflows.

Official
Advanced