# Prompt Engineer

> Turn vague instructions into precision-crafted prompts and system messages that get the best out of any LLM

- **Type:** Skill
- **Install:** `agentstack add skill-furkangonel-cowrangler-prompt-engineer`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [furkangonel](https://agentstack.voostack.com/s/furkangonel)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [furkangonel](https://github.com/furkangonel)
- **Source:** https://github.com/furkangonel/cowrangler/tree/main/bundled_skills/prompt-engineer
- **Website:** https://cowrangler.com

## Install

```sh
agentstack add skill-furkangonel-cowrangler-prompt-engineer
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Prompt Engineer Skill

## Goal
Transform vague, incomplete, or underperforming prompts into precisely crafted instructions that reliably produce the intended output from an LLM.

## Prompt Engineering Fundamentals

### The Six Dimensions
Every strong prompt addresses:
1. **Role** — Who is the model? What expertise does it bring?
2. **Task** — What exactly should it do? (verb + noun: "analyze", "write", "classify")
3. **Context** — What background does the model need to succeed?
4. **Format** — What should the output look like? (length, structure, examples)
5. **Constraints** — What should it avoid? (tone, topics, length limits)
6. **Examples** — Few-shot examples for consistency (optional but powerful)

## Steps

### 1. Diagnose the existing prompt (if one exists)
If the user has a prompt that "doesn't work":
- What output is it producing?
- What output is desired?
- Which of the six dimensions is missing or weak?

Name the specific problem before prescribing a fix.

**Success criteria**: You can say "this prompt fails because [specific reason]."

### 2. Gather requirements
Ask (or infer from context):
- What model will this run on? (GPT-4, Claude, Gemini, Llama — each has different strengths)
- Is this a system prompt, user prompt, or both?
- Will it be used once or repeatedly at scale?
- What's the most common failure mode the user wants to prevent?

**Success criteria**: You know the model, use case, and primary failure mode.

### 3. Write the prompt
Apply these techniques based on the use case:

**For complex reasoning tasks:**
- Add "Think step by step before answering"
- Use XML tags to separate sections: ``, ``, ``
- Include a "before you respond, check:" section

**For consistent formatting:**
- Provide an exact output template with placeholders
- Add a negative example: "Do NOT format it like this: [bad example]"

**For role-playing/personas:**
- Define expertise: "You are a senior [role] with [X] years experience in [domain]"
- Define behavioral constraints: "You communicate in [style]. You never [bad behavior]."

**For classification/extraction:**
- Define every category with an example
- Handle edge cases explicitly: "If you can't determine X, output 'UNKNOWN'"

### 4. Stress-test the prompt
Mentally run through 3 edge cases:
- A minimal/ambiguous input
- An off-topic input
- A tricky input that could fail

Identify which edge cases need explicit handling in the prompt.

**Success criteria**: You've identified at least one way the prompt could fail and addressed it.

### 5. Deliver with explanation
Return:
1. The complete prompt (in a code block, ready to copy)
2. A **Why it works** section explaining the key design choices
3. Suggested variables/parameters if the prompt should be templated

**Success criteria**: User can copy-paste and get reliable results without further changes.

## Why/Failure Modes

[TODO: Explain the reasoning behind this skill's approach and common failure modes to avoid.]

## Standalone vs Supercharged

[TODO: Describe how this skill works on its own vs when combined with other tools/context.]

## Cross-References

[TODO: Link to other relevant skills or documentation.]

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [furkangonel](https://github.com/furkangonel)
- **Source:** [furkangonel/cowrangler](https://github.com/furkangonel/cowrangler)
- **License:** MIT
- **Homepage:** https://cowrangler.com

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-furkangonel-cowrangler-prompt-engineer
- Seller: https://agentstack.voostack.com/s/furkangonel
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.