Skill Authoring Guide

SkillAI & models

Guide for creating and maintaining user-facing agent skills

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the Skill Authoring Guide skill

What this skill tells your AI

The instructions your AI receives, as published by taurgis/has-marstek-local-api in .agents/skills/skill-authoring/SKILL.md and read by ahel’s review.

This skill guides you through creating user-facing agent skills. For the canonical reference, see agentskills.io.

Skill Structure

A skill is a folder containing a SKILL.md file with metadata and instructions:

my-skill/
├── SKILL.md          # Required: instructions + metadata
├── scripts/          # Optional: executable code
├── references/       # Optional: additional documentation
└── assets/           # Optional: templates, resources

SKILL.md Format

Required Frontmatter

---
name: skill-name
description: Brief description of what the skill does
---
  • name: Unique identifier (lowercase, hyphens)
  • description: One-line summary (loaded at startup for all skills - a maximum of 1000 characters)

Instructions Body

The body contains markdown instructions that tell the agent how to perform the task.

---
name: my-skill
description: Does something useful
---

# Skill Title

Brief overview of what this skill helps accomplish.

## When to Use

Describe scenarios when this skill applies.

## How to Use

Step-by-step instructions or patterns.

## Examples

Concrete examples demonstrating usage.

## Reference

- [Detailed Reference](references/REFERENCE.md) - Link to additional docs

Progressive Disclosure

Structure skills for efficient context usage:

LayerToken BudgetWhen Loaded
Metadata~100 tokensAt startup (all skills)
Instructions< 5000 tokensWhen skill activated
ReferencesAs neededOn demand

Guidelines

  1. Keep SKILL.md under 500 lines - Move detailed content to references
  2. Front-load key information - Put most important patterns first
  3. Use tables for quick reference - Easy to scan
  4. Link to references - Don't inline everything

Optional Directories

scripts/

Executable code that agents can run:

scripts/
├── validate.sh       # Validation script
├── generate.py       # Code generator
└── setup.js          # Setup helper

Scripts should:

  • Be self-contained or document dependencies
  • Include helpful error messages
  • Handle edge cases gracefully

references/

Additional documentation loaded on demand:

references/
├── PATTERNS.md       # Common patterns
├── API.md            # API reference
└── EXAMPLES.md       # Extended examples

Keep individual reference files focused. Smaller files = less context usage.

assets/

Static resources:

assets/
├── template.xml      # File templates
├── schema.json       # Schemas
└── diagram.png       # Visual aids

File References

Use relative paths from the skill root:

See [the reference guide](references/REFERENCE.md) for details.

Run the setup script:
scripts/setup.sh

Keep references one level deep. Avoid deeply nested chains.

Skill Categories

Developer Skills (.claude/skills/)

Skills for contributors working on this codebase:

  • Command development patterns
  • Testing approaches
  • API client patterns
  • Documentation standards

User-Facing Skills (plugins/*/skills/)

Skills for users of the tool:

  • CLI command usage
  • Platform-specific patterns (B2C Commerce)
  • Integration guides

Writing Effective Skills

1. Start with the User's Goal

## Overview

This skill helps you [accomplish X] by [doing Y].

2. Provide Quick Reference Tables

| Command | Description |
|---------|-------------|
| `cmd1`  | Does X      |
| `cmd2`  | Does Y      |

3. Show Concrete Examples

## Examples

### Basic Usage

\`\`\`bash
b2c command --flag value
\`\`\`

### Advanced Usage

\`\`\`bash
b2c command --complex-flag
\`\`\`

4. Explain When NOT to Use

## When NOT to Use

- Scenario A (use skill-x instead)
- Scenario B (manual approach better)

5. Link to Authoritative Sources

Reference official documentation rather than duplicating it:

## Reference

For complete API documentation, see [Official Docs](https://example.com/docs).

Validation Checklist

Before publishing a skill:

  • Frontmatter has name and description
  • SKILL.md under 400 lines
  • Key information appears early
  • Examples are concrete and runnable
  • Reference links are valid
  • No deeply nested reference chains
  • Tested with target agent

Detailed Reference

Signals

GitHub stars
35
Forks
5
Last commit
Sep 2026
Advanced
Item type
skill
Key
skill-authoring-taurgis
Source
github.com/taurgis/has-marstek-local-api