Skills

Skill Authoring

Creates and structures SKILL.md files for AI coding agents, including YAML frontmatter...

Install

npx skills add rohitg00/skillkit --skill skill-authoring -g -a claude-code -y
Repository
rohitg00/skillkit1.6k
Category
AI and agents
Updated
5mo ago
License
Apache-2.0
Context cost
Lightabout 1,354 tokens
Runs scripts
No, instructions only

What it does

Creates and structures SKILL.md files for AI coding agents, including YAML frontmatter, trigger phrases, directive instructions, decision trees, code examples, and verification checklists. Use when the user asks to write a new skill, create a skill file, author agent capabilities, generate skill documentation, or define a skill template for Claude Code agents.

Skill Authoring Guide

You are authoring a SKILL.md for an AI coding agent. A well-written skill provides clear, actionable guidance that agents can follow consistently.

Core Principle

A skill's description triggers it; the body teaches it.

The description tells the agent WHEN to use the skill. The content tells the agent HOW to execute it.

Skill Anatomy

SKILL.md Structure

---
name: [lowercase-hyphenated-name]
description: [Concrete actions + "Use when..." clause]
version: [Semantic version]
triggers:
  - [keyword 1]
  - [keyword 2]
tags:
  - [tag 1]
---

# [Skill Title]

[Introduction paragraph explaining purpose]

## Core Principle

**[Single most important rule in bold]**

## [Main Content Sections]

## [Decision Points]

## [Verification Checklist]

Frontmatter Fields

FieldRequiredConstraints
nameYesLowercase alphanumeric + hyphens, 1, 64 chars
descriptionYesMust include "Use when..." clause; 1, 1024 chars
versionYesSemantic version (e.g. 1.0.0)
triggersRecommendedNatural-language phrases that activate the skill
tagsRecommendedCategorization tags

Writing Effective Triggers

Triggers should be phrases users naturally type.

Good triggers:

  • "write tests first"
  • "tdd"
  • "test driven development"

Bad triggers:

  • "testing methodology" (too vague)
  • "red-green-refactor-cycle-for-test-driven-development" (too specific)
  • "skill-123" (not natural language)

Trigger Guidelines

  1. Natural language, How would a human ask for this?
  2. Multiple variations, Different ways to say the same thing
  3. Specific enough, Don't trigger on too many queries
  4. Common terms, Use terms people actually use

Writing Skill Content

Voice and Tone

Use second person, present tense, active voice:

Read the whole SKILL.md on GitHub

More in AI and agents