expert-agent-writer

Guide users through authoring declarative agents in .agent.md files.

Updated Dec 20, 2025
One-click install
npx skills add https://github.com/ductrung-nguyen/Orca-vscode --skill expert-agent-writer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: expert-agent-writer
Source: https://github.com/ductrung-nguyen/Orca-vscode/tree/main/.github/skills/expert-agent-writer
Command: npx skills add https://github.com/ductrung-nguyen/Orca-vscode --skill expert-agent-writer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps users create and refine high-quality declarative agents (.agent.md files), streamlining the process of defining AI agent workflows.

Core Features & Use Cases

  • Agent Creation: Guides users through authoring new agents from scratch.
  • Agent Refinement: Assists in updating existing agents, ensuring adherence to best practices.
  • Guidance on Patterns: Provides advice on complex agent structures like loops and sub-agents.
  • Use Case: A user wants to build an agent that automatically reviews code pull requests. They can use this Skill to define the agent's purpose, inputs, outputs, and the step-by-step protocol it should follow, including calling other specialized agents.

Quick Start

Use the expert-agent-writer skill to create a new agent that summarizes meeting transcripts.

Frequently Asked Questions about expert-agent-writer

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

FAQPage Schema
How do I author a declarative agent from scratch?

To author a declarative agent, this skill guides you through a structured process for context gathering, drafting, and validation to define agent goals, inputs, outputs, and protocols in `.agent.md` files.

What is the best way to define agent workflows and sub-agent interactions?

The best way to define agent workflows is by using declarative patterns and best practices provided by this skill, which ensures conciseness, isolation, and proper tool usage for complex sub-agent interactions.

Can I use this skill to refine an existing agent?

Yes, you can refine an existing declarative agent. This skill assists in updating current agents by validating them against best practices for conciseness, isolation, and proper protocol definitions.

How do I structure loops and complex patterns when building LLM agents?

You structure loops and complex patterns by following the skill's guidance on declarative agent structures, leveraging templates to properly define step-by-step protocols and specialized sub-agent calls.

Do I need any specific frameworks to create declarative agents with this tool?

No specific frameworks are required as dependencies. You only need to define your agent workflows declaratively in markdown format, and the skill provides the necessary templates and validation for the `.agent.md` format.