Prompt Engineer

Takes your messy prompts and restructures them using 11 established frameworks like RTF, RISEN, Chain of Thought, and RODES. It analyzes what you're actually trying to do, asks up to three clarifying questions if needed, then silently picks the best framework or combination without explaining its choices. Works across any context, handles both English and Portuguese, and outputs ready-to-use prompts in code blocks. The "magic mode" approach is smart: you get structured prompts without framework jargon or meta-commentary. Most useful when you know what you want but can't articulate it clearly, or when tackling complex tasks that benefit from systematic reasoning.

skills.sh installs: 1.4K
GitHub stars: 43.1K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add sickn33/antigravity-awesome-skills --skill prompt-engineer --agent claude-code

Installs into .claude/skills of the current project.

Files

Purpose

This skill transforms raw, unstructured user prompts into highly optimized prompts using established prompting frameworks. It analyzes user intent, identifies task complexity, and intelligently selects the most appropriate framework(s) to improve clarity. Output quality depends on the model and task and requires evaluation.

The skill operates in "magic mode" - it works silently behind the scenes, only interacting with users when clarification is critically needed. Users receive polished, ready-to-use prompts without technical explanations or framework jargon.

This is a universal skill that works in any terminal context, not limited to Obsidian vaults or specific project structures.