The Playbook for AI Agent Skills

What is Agent Skills

Teach your agents new tricks.
Procedural knowledge, installed in one command.

What are
Agent Skills?

Think of Agent Skills as a "Skill Manual" or "Playbook" for AI.

They are structured documents (usually Markdown) combined with code, designed to teach AI how to complete specific tasks with high quality—whether it's building a website, creating a presentation, or writing a daily report. Skills act like plugins, granting AI professional capabilities instantly, eliminating the need for you to repeat lengthy, complex instructions.

The Evolution of Agent Skills

STAGE 01

The Problem: Repetition

Pain Point: Constantly repeating "Don't use blue, use SVG icons" for every request.

Solution: Writing requirements in a huge .md file.

Issue: Wastes tokens and context window by sending the entire manual for every interaction.

STAGE 02

Metadata Routing

Improvement: Adding Name and Description (Metadata).

Mechanism: The AI only sees the "Directory" initially. It selectively loads the full content only when it determines the user's request (e.g., "Build a website") requires that specific skill.

STAGE 03

Modularization

Scenario: Handling multiple styles (Minimalist, Tech, etc.) that don't fit in one file.

Mechanism: Progressive Loading. The AI reads the index file, realizes the user wants "Tech Style," and then loads the specific tech-style.md. Maximizes token efficiency.

STAGE 04

Code & Data

Scenario: Need for precise control (exact color codes, data lookups) that text struggles with.

Power: Incorporating CSVs and Python/JS scripts. Skill defines workflow → AI runs script → Data retrieved.

Technical Architecture

1. Metadata

System Prompt • Always Loaded

Contains Name and Description. Extremely lightweight. Allows the system to route requests without reading the full manual.

2. Instructions

Markdown • Load on Trigger

The core content. Essentially Structured Prompt Engineering. Loaded only when the AI decides it needs this specific know-how.

3. Resources & Code

Files/Scripts • Load on Demand

Auxiliary assets (CSVs, templates, Python scripts). Executed or read only during specific workflow steps to perform complex actions.

Where to Place Your Skills

Project Specific

Recommended for Teams

# Project Root
.
├── .claude/
└── skills/
├── my-skill-1/
├── SKILL.md
└── scripts/
└── src/
  • Automatically scanned by Claude Code, Cursor, etc.
  • Add .claude to .gitignore for private use, or commit to git to share with your team.

Global / Personal

Available Everywhere

# User Home Directory
~
├── .claude/
└── skills/
├── my-global-skill/
└── SKILL.md

Windows: C:\Users\Name\.claude\skills\

macOS/Linux: ~/.claude/skills/

Also Supported Directories

.gemini.cursor.trae.agent.agents.windsurf.kiro

Modern agentic tools typically check these locations for a skills subdirectory.

The Essence

Strip away the jargon, and Agent Skills are essentially Advanced Prompt Engineering wrapped in a modular architecture.

Why it matters:

It transforms generalist models (like Claude or GPT-4) into domain experts—instantly sharable and reusable.

Skills vs. MCP

Similar to the Model Context Protocol (MCP), Agent Skills aim to standardize how AI acquires context.

  • MCP connects AI to Live Data.
  • Skills provide Procedural Know-How.