Create Skill Wizard

This skill helps you create new Agent Zero skills that follow the SKILL.md standard.

Quick Start

To create a new skill, I'll guide you through these steps:

1. Name & Purpose - What should this skill do?
2. Trigger Patterns - When should this skill activate?
3. Content Structure - What instructions should the agent follow?
4. Supporting Files - Any scripts or templates needed?

SKILL.md Format

Every skill needs a SKILL.md file with YAML frontmatter:

yaml
1---
2name: "skill-name"
3description: "Clear description of what this skill does and when to use it"
4version: "1.0.0"
5author: "Your Name"
6tags: ["category1", "category2"]
7trigger_patterns:
8  - "keyword1"
9  - "phrase that triggers this"
10---
11
12# Skill Title
13
14Your skill instructions go here...

Required Fields

Optional Fields

Skill Directory Structure

/a0/usr/skills/
└── my-skill/
   ├── SKILL.md           # Required: Main skill file
   ├── scripts/           # Optional: Helper scripts
   │   ├── helper.py
   │   └── process.sh
   ├── templates/         # Optional: Templates
   │   └── output.md
   └── docs/              # Optional: Additional docs
      └── examples.md

Writing Good Skill Instructions

Be Specific and Actionable

markdown
1# Good
2When reviewing code:
31. Check for security vulnerabilities
42. Verify error handling
53. Assess test coverage
6
7# Bad
8Review the code and make it better.

Include Examples

markdown
1## Example Usage
2
3**User**: "Review my Python function for issues"
4
5**Agent Response**:
6> I'll review your function using the code review checklist:
7>
8> 1. **Security**: No user input validation detected
9> 2. **Error Handling**: Missing try-catch for file operations
10> 3. **Testing**: Function is testable but no tests found

Provide Checklists

markdown
1## Review Checklist
2- [ ] Input validation present
3- [ ] Error handling complete
4- [ ] Tests included
5- [ ] Documentation updated

Creating Your Skill: Step by Step

Step 1: Define Purpose

Answer these questions:

• What problem does this skill solve?
• When should the agent use it?
• What's the expected output?

Step 2: Choose a Name

• Use lowercase letters and hyphens
• Be descriptive but concise
• Examples: code-review, data-analysis, deploy-helper

Step 3: Write Trigger Patterns

List words/phrases that should activate this skill:

yaml
1trigger_patterns:
2  - "review"
3  - "check code"
4  - "code quality"
5  - "pull request"

Step 4: Structure Your Content

Organize with clear sections:

markdown
1# Skill Title
2
3## When to Use
4Describe the trigger conditions
5
6## The Process
7Step-by-step instructions
8
9## Examples
10Show sample interactions
11
12## Tips
13Additional guidance

Step 5: Add Supporting Files (Optional)

If your skill needs scripts or templates:

bash
1# Create directory structure
2mkdir -p /a0/usr/skills/my-skill/{scripts,templates,docs}

Example: Complete Skill

yaml
1---
2name: "python-optimizer"
3description: "Optimize Python code for performance and readability. Use when asked to improve or optimize Python code."
4version: "1.0.0"
5author: "Agent Zero Team"
6tags: ["python", "optimization", "performance"]
7trigger_patterns:
8  - "optimize python"
9  - "improve performance"
10  - "make faster"
11  - "python optimization"
12---
13
14# Python Optimizer
15
16## When to Use
17Activate when user asks to optimize, improve, or speed up Python code.
18
19## Optimization Process
20
21### Step 1: Profile First
22Before optimizing, understand where time is spent:
23```python
24import cProfile
25cProfile.run('your_function()')

Step 2: Common Optimizations

1. Use List Comprehensions

   python
   1# Slow
   2result = []
   3for x in data:
   4    result.append(x * 2)
   5
   6# Fast
   7result = [x * 2 for x in data]

2. Use Sets for Lookups

   python
   1# Slow: O(n)
   2if item in large_list:
   3
   4# Fast: O(1)
   5if item in large_set:

3. Use Generators for Large Data

   python
   1# Memory-heavy
   2data = [process(x) for x in huge_list]
   3
   4# Memory-efficient
   5data = (process(x) for x in huge_list)

Step 3: Verify Improvement

Always measure before and after:

python
1import time
2start = time.perf_counter()
3# code to measure
4elapsed = time.perf_counter() - start
5print(f"Took {elapsed:.4f} seconds")

Anti-Patterns to Avoid

• Premature optimization
• Optimizing without profiling
• Sacrificing readability for tiny gains

## Skill Installation

### Local Installation

1. Create skill directory:
   ```bash
   mkdir -p /a0/usr/skills/my-skill

2. Create SKILL.md:

   bash
   1touch /a0/usr/skills/my-skill/SKILL.md

3. Add content and save

4. Skills are automatically loaded on next agent initialization

Sharing Skills

To share skills with others:

1. Create a GitHub repository
2. Include the skill directory structure
3. Add a README with installation instructions
4. Users can copy to their /a0/usr/skills/ directory

Testing Your Skill

After creating a skill:

1. Start a new conversation
2. Use one of your trigger patterns
3. Verify the agent follows your instructions
4. Iterate and improve based on results