agent-management

Manage creation, editing, and improvement of local agent configuration files.

Updated Aug 27, 2026

Search Tags:#hooks #skills #agents #conventions #prompts #instructions #agent-management

Ready to run

npx skills add https://github.com/zcawood-mie/agentz --skill agent-management-zcawood-mie

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: agent-management
Source: https://github.com/zcawood-mie/agentz/tree/main/skills/agent-management
Command: npx skills add https://github.com/zcawood-mie/agentz --skill agent-management-zcawood-mie

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides a single reference and methodology for creating, editing, and improving local agent ecosystem files so contributors follow consistent conventions and avoid damaging workspace state.

Core Features & Use Cases

Conventions & Locations: Specifies exact file locations and naming conventions for agents, skills, prompts, instructions, hooks, and toolsets.
Decision Guidance: Helps determine which primitive to use (agent, skill, prompt, instruction, or hook) and when to create new agents versus reuse existing ones.
Safety & Workflow Guidance: Recommends safe first steps (e.g., list_dir), clarifies that user-local config files should not be committed, and outlines the roles of each primitive for review and improvement workflows.

Quick Start

Ask the system to create a new agent by instructing it to create an agent named Implementation with a PascalCase filename and the appropriate tool access.

Frequently Asked Questions about agent-management

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

FAQPage Schema

How do I create and manage local agents and prompts?▼

To create agents, prompts, and skills, instruct the system to generate files with appropriate naming conventions like PascalCase filenames, placing them in the correct ~/.agents subdirectories to maintain local configuration safely.

What is the difference between an agent, a skill, a prompt, and a hook?▼

Agents perform tasks, skills define reusable capabilities, prompts provide specific instructions, and hooks trigger actions based on events. Decision guidance helps determine which primitive to use based on whether you need autonomous execution, reusable logic, or event-driven workflows.

Where should local agent configuration files be stored and should they be committed?▼

Agent, skill, prompt, and instruction files are stored in the ~/.agents directory and local configuration repositories. These user-local files should not be committed to version control to protect your workspace state.

How do I safely edit existing agents and instructions without breaking my workspace?▼

Safely edit agents and instructions by starting with read operations like list_dir to verify file locations, following naming conventions, and ensuring changes remain local within the ~/.agents subdirectories without committing user-local configuration files.

Can I review conversations to derive improvements for my prompts and skills?▼

Yes, you can review past conversations to derive improvements for prompts and skills. The workflow outlines roles for each primitive, allowing you to analyze interactions and update instruction files to refine agent behavior and capabilities.

When should I create a new agent versus reusing an existing one?▼

Create a new agent when existing primitives cannot accomplish the required task. Decision guidance helps determine if the needed functionality can be handled by updating prompts or skills instead of generating an entirely new agent configuration.