agent-authoring

Author agents, tools, and runtime skills for the Nixopus system.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/nixopus/agent --skill agent-authoring-nixopus
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-authoring
Source: https://github.com/nixopus/agent/tree/main/.cursor/skills/agent-authoring
Command: npx skills add https://github.com/nixopus/agent --skill agent-authoring-nixopus

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides a structured, repeatable workflow to author and integrate new agents, tools, and runtime skills within the Nixopus system, reducing manual setup and inconsistencies.

Core Features & Use Cases

  • Step-by-step guidance for agent composition, tool creation, tool wrappers, and runtime skill authoring.
  • Clear engine integration steps: registering agents, configuring step limits, and optional memory for continuity.
  • Practical examples: creating a new agent with id, name, description, instructions, and linking it to engine maps.

Quick Start

Create a new agent by adding src/engine/agents/<name>-agent.ts and registering it in src/engine/index.ts.

Frequently Asked Questions about agent-authoring

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

FAQPage Schema
How do I create a new agent in the Nixopus system?

To create a new agent, add a new file at src/engine/agents/<name>-agent.ts defining its id, name, description, and instructions, then register the agent in src/engine/index.ts to integrate it with the engine maps.

What is the process for authoring runtime skills and tool wrappers?

Authoring runtime skills and tool wrappers involves composing agents, creating modular tools, and integrating optional memory for continuity, following the structured workflows described in the Skill unit to ensure consistency.

How does engine registration work when adding new agents?

Engine registration links your new agent to the system by updating engine maps in src/engine/index.ts, allowing you to configure step limits and optional memory for continuity within the Nixopus runtime.

Can I integrate memory into my custom agents for conversation continuity?

Yes, you can integrate optional memory into your custom agents during the engine registration step, enabling continuity across interactions within the modular tooling and runtime skill workflows.

Do I need any external dependencies to author agents and tools?

No external dependencies are required to author agents and tools, as the workflow relies on the existing Nixopus codebase structure and engine registration system to implement modular tooling.

Why should I use a structured workflow for agent composition and tool creation?

A structured workflow for agent composition and tool creation reduces manual setup errors and inconsistencies, providing repeatable steps for engine integration, wrapper usage, and meeting documentation standards.