create-system-prompt

Scaffold Copilot agent instruction samples with folder structure and metadata.

842|287|Updated Apr 25, 2024
One-click install
npx skills add https://github.com/pnp/copilot-prompts --skill create-system-prompt
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-system-prompt
Source: https://github.com/pnp/copilot-prompts/tree/main/.github/skills/create-system-prompt
Command: npx skills add https://github.com/pnp/copilot-prompts --skill create-system-prompt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The skill provides a guided scaffold to create new Copilot agent instruction samples, including the required file layout and metadata, so contributors can publish ready-to-use system prompts.

Core Features & Use Cases

  • Creates a standard folder structure under samples/agent-instructions/{agent-name}/ with readme.md and assets/sample.json
  • Validates naming, required sections, and metadata to ensure consistency with Copilot Studio workflows
  • Provides a repeatable template for agent instructions to accelerate contributor onboarding and collaboration

Quick Start

Create a new agent-instruction sample by following the scaffold steps in Copilot Studio to generate the required folder structure and metadata.

Frequently Asked Questions about create-system-prompt

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

FAQPage Schema
How do I create a Copilot agent instruction sample for the M365 Gallery?

To create a Copilot agent instruction sample, scaffold a standard folder structure under samples/agent-instructions/{agent-name}/ containing a readme.md with the full system prompt and an assets/sample.json file for required metadata.

What files are required for Copilot Studio agent instructions contributions?

Copilot Studio agent instructions contributions require a readme.md file containing the full system prompt and an assets/sample.json metadata file to ensure consistency and readiness for publishing.

How does scaffolding a system prompt template accelerate contributor onboarding?

Scaffolding a system prompt template provides a repeatable folder structure, enforces naming conventions, and validates required sections, which streamlines collaboration and accelerates contributor onboarding.

Can I use this scaffolding process to validate naming conventions for agent instructions?

Yes, the scaffolding process validates naming conventions and required sections for agent instructions, ensuring your generated system prompt meets the consistency standards required for the M365 Gallery.

What is the best way to structure a Copilot agent prompt folder for publication?

The best way to structure a Copilot agent prompt folder is to automate scaffolding under samples/agent-instructions/{agent-name}/, placing the system prompt in readme.md and contributor metadata in assets/sample.json.

Why does my Copilot agent instruction sample fail M365 Gallery validation?

Your Copilot agent instruction sample likely fails M365 Gallery validation due to missing required sections in readme.md, incorrect folder structure, or incomplete contributor metadata in the assets/sample.json file.