system-prompt-engineering

# System Prompt Engineering Skill

Design effective system prompts for custom agents that establish identity, rules, and behavior.

## Purpose

Create system prompts that shape agent behavior across all conversations. System prompts are orders of magnitude more important than user prompts.

## When to Use

- Creating new custom agents
- Establishing agent expertise
- Defining persistent rules
- Building specialized assistants

## System Prompt vs User Prompt

| Aspect | System Prompt | User Prompt |
| --- | --- | --- |
| Scope | All conversations | Single task |
| Persistence | Affects everything | Per-request |
| Impact | Orders of magnitude higher | Lower blast radius |
| Sections | Purpose, Instructions, Examples | All sections |

## Key Sections

### Purpose (Required)

Define who the agent is and what it does.

```markdown
## Purpose

You are a security expert specializing in code review.
Your role is to identify vulnerabilities and suggest fixes.
You focus on OWASP Top 10 and secure coding practices.
```

**Guidelines:**

- Direct, clear identity statement
- Specific expertise area
- What the agent DOES

### Instructions (Recommended)

Establish rules, constraints, and boundaries.

```markdown
## Instructions

- Focus only on security concerns
- Always explain the reasoning behind findings
- Prioritize issues by severity (Critical, High, Medium, Low)
- Do not modify code without explicit permission
- When uncertain, ask clarifying questions
```

**Guidelines:**

- Bullet points for clarity
- Positive and negative rules
- Edge case handling
- Boundary definition

### Examples (Critical)

Shape behavior through concrete examples.

```markdown
## Examples

### Example 1: SQL Injection Finding
**Input:** "Review this login function"
**Output:** "Found SQL injection vulnerability at line 42. The user input is directly concatenated into the query string. Recommendation: Use parameterized queries instead."

### Example 2: Out of Scope Request
**Input:** "Fix this CSS