One-click install
npx skills add https://github.com/mattbutlerengineering/mattbutlerengineering --skill write-a-skill-mattbutlerengineering
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: write-a-skill
Source: https://github.com/mattbutlerengineering/mattbutlerengineering/tree/main/.agents/skills/write-a-skill
Command: npx skills add https://github.com/mattbutlerengineering/mattbutlerengineering --skill write-a-skill-mattbutlerengineering

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps authors produce new agent skills with a consistent, discovery-friendly layout and operational content. It prevents missing metadata, unclear instructions, and poorly organized resources that make skills hard to reuse and reliable to activate.

Core Features & Use Cases

  • Requirement gathering: Prompts for domain, intended use cases, and whether the skill needs scripts or only instructions.
  • Structured skill authoring: Guides the creation of a root SKILL.md with concise operational guidance and an optional reference/extras layout for larger content.
  • Progressive disclosure: Encourages splitting advanced details into linked files like REFERENCE.md to keep SKILL.md focused for quick loading.
  • Deterministic resource bundling: Advises adding scripts only when tasks are deterministic and benefit from validation and explicit error handling.

Quick Start

Use the write-a-skill skill when you want to create a new agent capability and ask it to draft the SKILL.md plus any needed reference files following the prescribed structure.

Frequently Asked Questions about write-a-skill

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

FAQPage Schema
How do I structure agent skills for reliable activation and discovery?

Structure agent skills by creating a root SKILL.md with YAML frontmatter containing name and description, then split advanced details into linked files like REFERENCE.md and EXAMPLES.md to enable progressive disclosure and quick loading.

What is progressive disclosure in skill authoring and when should I use it?

Progressive disclosure in skill authoring is the practice of splitting advanced operational details into linked files like REFERENCE.md, keeping the root SKILL.md focused. Use it when skills contain large content or deeper references that would slow down quick loading.

How do I create deterministic scripts for an agent skill?

Create deterministic scripts by bundling them into a scripts directory only when tasks require validation and explicit error handling. This ensures the agent skill produces consistent, reliable outputs for predictable operations.

Do I need YAML frontmatter in SKILL.md for agent skill discovery?

Yes, YAML frontmatter in SKILL.md is required for agent skill discovery. It must include the name and description fields, which allow the skill to be found and reliably activated by users and systems.

What's the best way to organize reference documentation for a new skill?

Organize reference documentation by placing concise operational guidance in SKILL.md, then moving deeper references and examples into separate REFERENCE.md and EXAMPLES.md files. This structure prevents missing metadata and poorly organized resources.

When should I not use deterministic scripts in an agent skill?

Avoid using deterministic scripts in an agent skill when tasks are not predictable or do not benefit from validation and explicit error handling. In these cases, rely on structured instructions within SKILL.md instead of bundled scripts.