Skip to content
Agentmart
Submit a tool

Prompt Engineer

Craft effective AI prompts for any model or use case

Skill by rar-file

IndexedMIT★ 38
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/rar-file-prompt-engineer

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Craft effective AI prompts for any model or use case

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/prompt-engineer

What's inside

Skill name
Prompt Engineer
Description
Craft effective AI prompts for any model or use case
License
MIT
Instructions
29 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • name: only lowercase letters, digits and single hyphens allowed
  • name: "Prompt Engineer" does not match folder "prompt_engineer"

Files (1)

  • SKILL.md

SKILL.md (first lines)

---
name: Prompt Engineer
description: Craft effective AI prompts for any model or use case
icon: 🧪
enabled: false
author: SURF
version: 1.0
---

# Prompt Engineer Skill

You help users write better prompts to get better results from AI models.

## When Active
When the user wants help crafting prompts:
1. Understand the desired output format and quality
2. Apply proven prompt engineering techniques
3. Structure the prompt with clear instructions
4. Add constraints, examples, and output format specs
5. Iterate based on what's not working

## Techniques
- **Role prompting** — "You are a [expert role]…"
- **Few-shot examples** — show 2-3 input/output pairs
- **Chain of thought** — "Think step by step…"
- **Output formatting** — specify JSON, markdown, lists, etc.
- **Constraints** — "Do NOT include…", "Keep it under…"
- **Self-consistency** — generate multiple answers and pick the best
- **ReAct** — Reasoning + Acting for tool-use agents

## Common Fixes
- Vague prompt → add specific constraints and examples
- Too verbose output → add length limits and format specs
- Wrong tone → add role and audience description
- Hallucination → add "only use information from…" constraints
- Inconsistent format → provide exact output template

From rar-file/surf, MIT.

More from rar-file/surf

Signals

Stars
38
Forks
1
Open issues
3
Last commit (this folder)
Mar 20, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from rar-file

Cite this page

Prompt Engineer skill. Agent Mart. https://agentmart.dev/skills/rar-file-prompt-engineer (last updated 2026-10-24)