write-a-skill

Name: write-a-skill
Availability: InStock
Author: Kartik

Create reusable agent skills with frontmatter, instructions, and bundled resources.

Updated Jul 17, 2026

Search Tags:#workflow #markdown #agent skills #prompt design #skill authoring

Ready to run

npx skills add https://github.com/kartikkabadi/skills --skill write-a-skill-kartikkabadi

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: write-a-skill
Source: https://github.com/kartikkabadi/skills/tree/main/write-a-skill
Command: npx skills add https://github.com/kartikkabadi/skills --skill write-a-skill-kartikkabadi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps create new agent skills with the right structure, clear triggers, and optional supporting resources so they are easy for an AI agent to load and use.

Core Features & Use Cases

Skill drafting: Defines a concise SKILL.md with frontmatter, instructions, and a practical workflow.
Resource planning: Explains when to add reference files or scripts for deeper knowledge and deterministic tasks.
Structure guidance: Provides a template for organizing a skill directory and deciding when to split content.
Use case: Use it when building a new skill for a specific domain, capability, or workflow that needs reusable agent instructions.

Quick Start

Ask the assistant to create a new skill for your target domain and include the use cases, trigger conditions, and any reference files or scripts it should contain.

Frequently Asked Questions about write-a-skill

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

FAQPage Schema

How do I create reusable agent skills with proper markdown structure?▼

To create reusable agent skills, draft a concise SKILL.md file containing frontmatter, core instructions, and a practical workflow to define the skill's behavior. This structure ensures the agent can easily load and trigger the instructions.

What is progressive disclosure in prompt design for skill authoring?▼

Progressive disclosure in skill authoring is an approach that keeps the main SKILL.md concise while moving deeper knowledge into optional reference files. Agents load primary instructions first and access bundled references only when deeper context is needed.

When should I add bundled resources or scripts to an agent skill directory?▼

You should add bundled reference files or scripts to an agent skill directory when the workflow requires deeper domain knowledge or deterministic task execution. This separates heavy content from core instructions, optimizing the agent's loading process.

How do I structure a skill directory to decide when to split content?▼

Structure a skill directory by keeping the core logic in a concise SKILL.md file and splitting content into separate reference files when the instructions become too extensive. This organization supports trigger-aware descriptions and clear content boundaries.

What is the best way to write trigger-aware descriptions for AI agent workflows?▼

The best way to write trigger-aware descriptions is to clearly define the use cases and trigger conditions within the SKILL.md frontmatter and instructions. This ensures the AI agent accurately identifies when to activate the specific workflow.