> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/Shubhamsaboo/awesome-llm-apps/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent Skills Overview

> Learn about Agent Skills - packaged instructions that extend AI agent capabilities

# Agent Skills Overview

Agent Skills are packaged instructions and scripts that extend AI agent capabilities. They follow the [Agent Skills specification](https://agentskills.io/specification) - a simple, open format for giving agents new capabilities and expertise.

## What Are Agent Skills?

Agent Skills are modular, reusable packages that give AI agents specialized expertise. Think of them as "skill packages" that transform a general-purpose agent into a domain expert.

Each skill contains:

* **SKILL.md** - Instructions for the agent (required)
* **scripts/** - Helper scripts for automation (optional)
* **references/** - Supporting documentation (optional)
* **assets/** - Images, templates, etc. (optional)

## Why Use Agent Skills?

<CardGroup cols={2}>
  <Card title="Consistent Expertise" icon="award">
    Package best practices and domain knowledge into reusable skills that work across different agents
  </Card>

  <Card title="Easy to Share" icon="share-nodes">
    Simple markdown format makes skills easy to create, share, and maintain
  </Card>

  <Card title="Automatic Activation" icon="bolt">
    Skills activate automatically based on triggers and context - no manual selection needed
  </Card>

  <Card title="Open Standard" icon="code">
    Built on an open specification supported by multiple agent platforms
  </Card>
</CardGroup>

## How Skills Work

1. **Installation**: Add skills to your agent's knowledge base
2. **Trigger Detection**: Agent detects when a skill is relevant based on the description and triggers
3. **Skill Activation**: Agent loads the skill's instructions and follows them
4. **Enhanced Response**: Agent responds with specialized expertise from the skill

## Skill Structure

Every skill follows this directory structure:

```
skill-name/
├── SKILL.md          # Required: Instructions for the agent
├── AGENTS.md         # Optional: Compiled rules and guidelines
├── scripts/          # Optional: Helper scripts
│   ├── script1.sh
│   └── script2.py
├── references/       # Optional: Supporting docs
│   ├── doc1.md
│   └── doc2.md
└── assets/          # Optional: Images, templates
    └── template.txt
```

## SKILL.md Format

The core of every skill is a `SKILL.md` file with YAML frontmatter:

```yaml theme={null}
---
name: skill-name
description: |
  What the skill does and when to use it.
  Include triggers like "use when debugging" or "when user mentions code review".
license: MIT
metadata:
  author: awesome-llm-apps
  version: "1.0.0"
---

# Skill Name

You are [role description]. Instructions for the agent to follow...

## When to Apply

Use this skill when:
- [Trigger condition 1]
- [Trigger condition 2]
- [Trigger phrase or keyword]

## [Sections with instructions]

[Detailed guidance, checklists, examples, etc.]
```

## Key Components

### Description Field

The description tells the agent when to use this skill. Include:

* What the skill does
* When to activate it
* Trigger phrases ("use when", "when user mentions")
* Common keywords that should activate it

**Example:**

```yaml theme={null}
description: |
  Thorough code review with focus on security, performance, and best practices.
  Use when: reviewing code, performing security audits, checking code quality,
  or when user mentions code review, PR review, security vulnerabilities.
```

### Instructions Section

Provide clear, actionable instructions:

* Use imperative voice ("Check for X", "Ensure Y")
* Include checklists for systematic workflows
* Provide examples of good and bad patterns
* Define priority levels (CRITICAL, HIGH, MEDIUM, LOW)
* Show expected output formats

### Supporting Files

**AGENTS.md**: Compiled reference with all rules and examples
**scripts/**: Automation scripts the agent can run
**references/**: Deep-dive documentation on specific topics
**assets/**: Templates, diagrams, or other resources

## Installation Methods

<Tabs>
  <Tab title="Using npx">
    ```bash theme={null}
    npx skills add shubhamsaboo/awesome-agent-skills
    ```
  </Tab>

  <Tab title="Manual Install">
    1. Clone or download the skill directory
    2. Copy to your agent's skills folder
    3. Reference in agent configuration
  </Tab>

  <Tab title="Direct Reference">
    Upload SKILL.md to your agent's knowledge base or custom instructions
  </Tab>
</Tabs>

## Platform Compatibility

Agent Skills work with any skills-compatible agent platform:

* **Claude Desktop / claude.ai** - Upload SKILL.md to project knowledge
* **Cursor / VSCode** - Reference skills in `.cursorrules` or instructions
* **Custom agents** - Load SKILL.md as system prompts
* **AI frameworks** - Use with LangChain, AutoGen, or custom frameworks

## Skill Categories

Skills are organized into categories by domain:

<CardGroup cols={2}>
  <Card title="Coding Skills" icon="code" href="/agent-skills/coding-skills">
    Python expert, code reviewer, debugger, fullstack developer
  </Card>

  <Card title="Research Skills" icon="magnifying-glass" href="/agent-skills/research-skills">
    Deep research, fact checker, academic researcher
  </Card>

  <Card title="Writing Skills" icon="pen" href="/agent-skills/writing-skills">
    Technical writer, content creator, editor
  </Card>

  <Card title="Planning Skills" icon="list-check" href="/agent-skills/planning-skills">
    Project planner, sprint planner, strategy advisor
  </Card>
</CardGroup>

## Example: Python Expert Skill

Here's how a typical skill works in practice:

**User:** "Write a function to find duplicates in a list"

**Agent detects:** Keywords "write a function" + "Python" context → Loads `python-expert` skill

**Agent follows skill:**

* Uses type hints
* Includes comprehensive docstring
* Follows PEP 8 style
* Provides examples and explanation
* Uses efficient implementation

**Result:** Production-ready Python code following best practices

## Next Steps

<CardGroup cols={2}>
  <Card title="Browse Coding Skills" icon="laptop-code" href="/agent-skills/coding-skills">
    Explore coding and development skills
  </Card>

  <Card title="Browse Research Skills" icon="flask" href="/agent-skills/research-skills">
    Discover research and analysis skills
  </Card>

  <Card title="Browse Writing Skills" icon="pen-fancy" href="/agent-skills/writing-skills">
    Find writing and documentation skills
  </Card>

  <Card title="Create Your Own" icon="plus" href="/agent-skills/creating-skills">
    Learn to create custom agent skills
  </Card>
</CardGroup>

## Resources

* [Agent Skills Specification](https://agentskills.io/specification)
* [Agent Skills Documentation](https://agentskills.io)
* [Vercel Agent Skills](https://github.com/vercel-labs/agent-skills) - Official examples
* [Anthropic Skills](https://github.com/anthropics/skills) - More examples