prompt-engineering

Create, optimize, and compress prompts for Claude, GPT, and Gemini using the PRISM framework.

Updated Nov 20, 2025
One-click install
npx skills add https://github.com/wollfoo/codex-cli --skill prompt-engineering-wollfoo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prompt-engineering
Source: https://github.com/wollfoo/codex-cli/tree/main/skills/prompt-engineering
Command: npx skills add https://github.com/wollfoo/codex-cli --skill prompt-engineering-wollfoo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines the creation, refinement, and shortening of prompts for Large Language Models, ensuring clarity, effectiveness, and conciseness.

Core Features & Use Cases

  • Prompt Creation: Generates production-ready prompts using the PRISM framework.
  • Prompt Optimization: Analyzes and enhances existing prompts, offering multi-model variants.
  • Prompt Compression: Reduces verbose prompts to 1-2 clear sentences while preserving intent.
  • Use Case: You need to create a prompt for an LLM to summarize customer feedback. This Skill can generate a well-structured prompt, optimize an existing one for better results, or compress a lengthy prompt for efficiency.

Quick Start

Use the prompt-engineering skill to create a prompt for summarizing customer feedback.

Frequently Asked Questions about prompt-engineering

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a structured LLM prompt using the PRISM framework?

The PRISM framework structures prompt creation by generating production-ready prompts for LLMs like Claude, GPT, and Gemini. It provides a systematic approach to prompt design, ensuring clarity and effectiveness for your specific task.

Can I optimize an existing prompt for different models like Claude and Gemini?

Yes, prompt optimization analyzes and enhances existing prompts by offering multi-model variants. This feature tailors your prompt to achieve better results across different Large Language Models while maintaining the original intent.

What is the best way to compress a lengthy LLM prompt without losing intent?

Prompt compression reduces verbose prompts to one or two clear sentences while preserving the core intent. This shortening process maintains prompt effectiveness and improves processing efficiency for LLM interactions.

Does this prompt engineering approach work for both creating new prompts and refining old ones?

Yes, it supports three distinct modes: Create, Optimize, and Compress. You can generate new production-ready prompts from scratch, enhance existing ones, or shorten lengthy instructions while maintaining their original effectiveness.

When do I need prompt compression for my LLM interactions?

Prompt compression is needed when your existing prompts are verbose and inefficient. It shortens lengthy instructions to clear sentences, reducing token usage and latency while preserving the core intent for the LLM.